Intent analysis for call center response generation
24 claims: 3 independent, 21 dependent
- 1コンピュータ によって実行される 方法であって、 履歴 データを取得することと、前記 履歴 データは、顧客とクライアントのエージェントとの間の 以前の対話 に対応し、 前記以前の対話に関連付けられた顧客応答内の 明示的要素及び暗示的要素を識別することと、 前記明示的要素、前記暗示的要素、及び前記顧客と前記エージェントとの間の前記以前の対話 から文脈のセットを決定することと、機械学習アルゴリズムをトレーニングすることと、前記機械学習アルゴリズムは、前記文脈のセット、前記明示的要素、前記暗示的要素、及び前記顧客と前記エージェントとの間の 前記以前の対話 を使用してトレーニングされ、前記機械学習アルゴリズムは、 異なる顧客応答 に対するエージェント応答を向上するために実行可能なアクションのセットを生成するようにトレーニングされ、新しい会話に対応する新しい会話データを受信することと、前記新しい会話に関係付けられた 新しい顧客応答内の 新しい 明示的要素及び新しい暗示的要素 へのエージェント応答を向上するために実行可能なアクションを識別することと、前記アクションは、前記新しい会話データ及び前記機械学習アルゴリズムを使用して識別され、前記アクションに対応する1つ以上の推奨を生成することと、前記1つ以上の推奨は、 前記新しい顧客応答へのエージェント応答を向上する ために提示され、前記1つ以上の推奨への準拠をリアルタイムで動的に監視することとを含む 、方 法。
- 2前記1つ以上の推奨は条件付き論理を含み、前記条件付き論理は、 前記新しい顧客応答への前記エージェント応答を向上する ために、 前記 新しい明示的要素及び 前記 新しい暗示的要素を文脈化するように実行可能である、請求項1に記載 の方 法。
- 3前記1つ以上の推奨への準拠を動的に監視することは、顧客とエージェントとの間の新しい会話のデータストリームを処理することを含み、前記データストリームは、前記新しい会話中にリアルタイムで処理され、前記データストリームからの前記エージェント応答は、前記エージェントが前記1つ以上の推奨に準拠しているかどうかを決定するためにリアルタイムで評価される、請求項1に記載 の方 法。
- 4前記1つ以上の推奨への準拠を動的に監視することは、前記エージェントにフィードバックを提供することを含み、前記フィードバックは、前記1つ以上の推奨にしたがう 前記 エージェント応答の評価に基づいて提供される、請求項1に記載 の方 法。
- 5前記1つ以上の推奨への準拠を動的に監視することは、新しい会話から感情を決定することを含み、前記感情は、前記新しい会話における 前記 エージェント応答が前記1つ以上の推奨に準拠するかどうかを決定するために評価される、請求項1に記載 の方 法。
- 6前記エージェントに対応する性能メトリックのセットを生成することをさらに含み、前記性能メトリックのセットは、 前記新しい顧客応答内の感情的要素 に対処する際の前記エージェントの性能に対応する、請求項1に記載 の方 法。
- 7前記会話に対応するフィードバックを取得することをさらに含み、前記フィードバックは、前記新しい 顧客応答 に対する前記エージェント応答を向上するために実行可能な前記アクションのセットを識別するように処理される、請求項1に記載 の方 法。
- 8前記機械学習アルゴリズムをさらにトレーニングするために、 前記 文脈の新しいセット、 前記 新しい明示的要素、 前記 新しい暗示的要素、前記新しい会話、及び前記1つ以上の推奨への準拠に対応するデータを使用することをさらに含む、請求項1に記載 の方 法。
- 9システムであって、1つ以上のプロセッサと、命令を記憶しているメモリとを備え、前記命令は、前記1つ以上のプロセッサによって実行された結果として、前記システムに、 履歴 データを取得させ、前記 履歴 データは、顧客とクライアントのエージェントとの間の 以前の対話 に対応し、 前記以前の対話に関連付けられた顧客応答内の 明示的要素及び暗示的要素を識別させ、 前記明示的要素、前記暗示的要素、及び前記顧客と前記エージェントとの間の前記以前の対話 から文脈のセットを決定させ、機械学習アルゴリズムをトレーニングさせ、前記機械学習アルゴリズムは、前記文脈のセット、前記明示的要素、前記暗示的要素、及び前記顧客と前記エージェントとの間の 前記以前の対話 を使用してトレーニングされ、前記機械学習アルゴリズムは、 異なる顧客応答 に対するエージェント応答を向上するために実行可能なアクションのセットを生成するようにトレーニングされ、新しい会話に対応する新しい会話データを受信させ、前記新しい会話に関係付けられた 新しい顧客応答内の新しい明示的要素及び新しい暗示的要素 に対するエージェント応答を向上するために実行可能なアクションを識別させ、前記アクションは、前記新しい会話データ及び前記機械学習アルゴリズムを使用して識別され、前記アクションに対応する1つ以上の推奨を生成させ、前記1つ以上の推奨は、 前記新しい顧客応答へのエージェント応答を向上する ために提示され、前記1つ以上の推奨への準拠をリアルタイムで動的に監視させる、システム。
- 10前記1つ以上の推奨は条件付き論理を含み、前記条件付き論理は、 前記新しい顧客応答への前記エージェント応答を向上する ために 前記 新しい明示的要素及び 前記 新しい暗示的要素を文脈化するように実行可能である、請求項9に記載のシステム。
- 11前記システムに前記1つ以上の推奨への準拠を動的に監視させる前記命令はさらに、前記システムに、顧客とエージェントとの間の新しい会話のデータストリームを処理させ、前記データストリームは、前記新しい会話中にリアルタイムで処理され、前記データストリームからの前記エージェント応答は、前記エージェントが前記1つ以上の推奨に準拠しているかどうかを決定するためにリアルタイムで評価される、請求項9に記載のシステム。
- 12前記システムに前記1つ以上の推奨の準拠を動的に監視させる前記命令はさらに、前記システムに、前記エージェントへのフィードバックを提供させ、前記フィードバックは、前記1つ以上の推奨にしたがう 前記 エージェント応答の評価に基づいて提供される、請求項9に記載のシステム。
- 13前記システムに前記1つ以上の推奨への準拠を動的に監視させる前記命令はさらに、前記システムに、新しい会話からの感情を決定させ、前記感情は、前記新しい会話における 前記 エージェント応答が前記1つ以上の推奨に準拠するかどうかを決定するために評価される、請求項9に記載のシステム。
- 14前記命令はさらに、前記システムに、前記エージェントに対応する性能メトリックのセットを生成させ、前記性能メトリックのセットは、 前記新しい顧客応答内の感情的要素 に対処する際の前記エージェントの性能に対応する、請求項9に記載のシステム。
- 15前記命令はさらに、前記システムに、前記会話に対応するフィードバックを取得させ、前記フィードバックは、前記新しい 顧客応答 に対する前記エージェント応答を向上するために実行可能な前記アクションのセットを識別するように処理される、請求項9に記載のシステム。
- 16前記命令はさらに、前記システムに、 前記 文脈の新しいセット、前記新しい明示的要素、前記新しい暗示的要素、前記新しい会話、及び前記1つ以上の推奨への準拠に対応するデータを使用させて、前記機械学習アルゴリズムをさらにトレーニングさせる、請求項9に記載のシステム。
- 17実行可能な命令を記憶している非一時的コンピュータ読取可能記憶媒体であって、前記実行可能な命令は、コンピュータシステムの1つ以上のプロセッサによって実行される結果として、前記コンピュータシステムに、 履歴 データを取得させ、前記 履歴 データは、顧客とクライアントのエージェントとの間の 以前の対話 に対応し、 前記以前の対話に関連付けられた顧客応答内の 明示的要素及び暗示的要素を識別させ、 前記明示的要素、前記暗示的要素、及び前記顧客と前記エージェントとの間の前記以前の対話 から文脈のセットを決定させ、機械学習アルゴリズムをトレーニングさせ、前記機械学習アルゴリズムは、前記文脈のセット、前記明示的要素、前記暗示的要素、及び前記顧客と前記エージェントとの間の 前記以前の対話 を使用してトレーニングされ、前記機械学習アルゴリズムは、 異なる顧客応答 に対するエージェント応答を向上するために実行可能なアクションのセットを生成するようにトレーニングされ、新しい会話に対応する新しい会話データを受信させ、前記新しい会話に関係付けられた 新しい顧客応答内の新しい明示的要素及び新しい暗示的要素 に対するエージェント応答を向上するために実行可能なアクションを識別させ、前記アクションは、前記新しい会話データ及び前記機械学習アルゴリズムを使用して識別され、前記アクションに対応する1つ以上の推奨を生成させ、前記1つ以上の推奨は、 前記新しい顧客応答へのエージェント応答を向上する ために提示され、前記1つ以上の推奨への準拠をリアルタイムで動的に監視させる、非一時的コンピュータ読取可能記憶媒体。
- 18前記1つ以上の推奨は条件付き論理を含み、前記条件付き論理は、 前記新しい顧客応答への前記エージェント応答を向上する ために、 前記 新しい明示的要素及び 前記 新しい暗示的要素を文脈化するように実行可能である、請求項17に記載の非一時的コンピュータ読取可能記憶媒体。
- 19前記コンピュータシステムに、前記1つ以上の推奨への準拠を動的に監視させる前記実行可能な命令はさらに、前記コンピュータシステムに、顧客とエージェントとの間の新しい会話のデータストリームを処理させ、前記データストリームは、前記新しい会話中にリアルタイムで処理され、前記データストリームからの前記エージェント応答は、前記エージェントが前記1つ以上の推奨に準拠しているかどうかを決定するためにリアルタイムで評価される、請求項17に記載の非一時的コンピュータ読取可能記憶媒体。
- 20前記コンピュータシステムに、前記1つ以上の推奨の準拠を動的に監視させる前記実行可能な命令はさらに、前記コンピュータシステムに、前記エージェントへのフィードバックを提供させ、前記フィードバックは、前記1つ以上の推奨にしたがう 前記 エージェント応答の評価に基づいて提供される、請求項17に記載の非一時的コンピュータ読取可能記憶媒体。
- 21前記コンピュータシステムに前記1つ以上の推奨への準拠を動的に監視させる前記実行可能な命令はさらに、前記コンピュータシステムに、新しい会話から感情を決定させ、前記感情は、前記新しい会話内の 前記 エージェント応答が前記1つ以上の推奨に準拠するかどうかを決定するために評価される、請求項17に記載の非一時的コンピュータ読取可能記憶媒体。
- 22前記実行可能な命令はさらに、前記コンピュータシステムに、前記エージェントに対応する性能メトリックのセットを生成させ、前記性能メトリックのセットは、 前記新しい顧客応答内の感情的要素 に対処する際の前記エージェントの性能に対応する、請求項17に記載の非一時的コンピュータ読取可能記憶媒体。
- 23前記実行可能な命令はさらに、前記コンピュータシステムに、前記会話に対応するフィードバックを取得させ、前記フィードバックは、 前記新しい顧客応答 に対する前記エージェント応答を向上するために実行可能な前記アクションのセットを識別するように処理される、請求項17に記載の非一時的コンピュータ読取可能記憶媒体。
- 24前記実行可能な命令はさらに、前記コンピュータシステムに、 前記 文脈の新しいセット、 前記 新しい明示的要素、 前記 新しい暗示的要素、前記新しい会話、及び前記1つ以上の推奨への準拠に対応するデータを使用させて、前記機械学習アルゴリズムをさらにトレーニングさせる、請求項17に記載の非一時的コンピュータ読取可能記憶媒体。
Independent claims24
163 paragraphs, as filed
CROSS-REFERENCE TO RELATED APPLICATIONS [0001] This application claims the benefit of U.S. Provisional Patent Application No. 62/981,466, filed February 25, 2020, entitled "INTENT ANALYSIS FOR CALL CENTER RESPONSE GENERATION," which is incorporated herein by reference in its entirety.
[0002] The present disclosure relates generally to communication processing using a structured framework for delivering preferred conversational responses. More specifically, techniques are provided for developing a framework that assists virtual and/or human agents in providing conversational responses to customers based on intent communicated by those customers.
[0003] Various embodiments of the present disclosure are described in detail below. Although specific implementations are described, it should be understood that this is done for illustrative purposes only. Those skilled in the art will recognize that other components and configurations can be used without departing from the spirit and scope of the present disclosure. Thus, the following description and drawings are illustrative and should not be construed as limiting. Numerous specific details are described to provide a thorough understanding of the present disclosure. However, in certain instances, well-known or conventional details are not described in order to avoid obscuring the description. References to one or an embodiment in the present disclosure may be references to the same embodiment or any embodiment, and such references mean at least one of the embodiments.
[0004] A reference to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the disclosure. The appearance of the phrases "one embodiment" and "an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment, nor are they separate or alternative embodiments mutually exclusive of other embodiments. Furthermore, various features are described that may be exhibited by some embodiments and not by other embodiments.
[0005] The terms used herein generally have their ordinary meaning in the art, within the context of this disclosure and in the specific context in which each term is used. Alternative language and synonyms may be used for any one or more of the terms discussed herein, and no special importance should be placed on whether a term is recited or discussed herein. In some cases, synonyms of a particular term are provided. The recitation of one or more synonyms does not preclude the use of other synonyms. The use of examples anywhere in this specification, including examples of any term discussed herein, is illustrative only and is not intended to further limit the scope and meaning of the disclosure or any exemplary term. Similarly, the disclosure is not limited to the various embodiments provided herein.
[0006] Without intending to limit the scope of the present disclosure, examples of instruments, devices, methods, and their related results according to the embodiments of the present disclosure are given below. Please note that titles or subtitles can be used in the examples for the convenience of the reader and do not limit the scope of the present disclosure. Unless otherwise defined, all technical and scientific terms used herein have the meanings as commonly understood by those skilled in the art to which the present disclosure belongs. In case of conflict, the present document, including definitions, will control.
[0007] Additional features and advantages of the present disclosure will be set forth hereinafter and in part will be apparent from the description or may be learned by practice of the principles disclosed herein. The features and advantages of the present disclosure may be realized and obtained by means of the orders and combinations particularly pointed out in the appended claims. These and other features of the present disclosure will become more fully apparent from the following description and the appended claims or may be learned by practice of the principles described herein.
[0008] The present disclosure is described in conjunction with the accompanying drawings.
<figref num="1">[0009] FIG. 1 illustrates an illustrative example of an environment in which intent from a customer is evaluated to determine a solution to the intent and generate a response that can be provided by an agent, according to at least one embodiment.</figref><figref num="2">[0010] FIG. 2 illustrates an illustrative example of an environment in which intent, responses, and feedback obtained during a communication session between a customer and an agent are evaluated to determine the agent's performance, according to at least one embodiment.</figref><figref num="3">[0011] FIG. 3 illustrates an illustrative example of an environment in which a performance monitoring service measures and manages the performance of an organization's conversational operations, according to at least one embodiment.</figref><figref num="4">[0012] FIG. 4 shows an illustrative example of a process 400 for implementing a framework to assist an agent in responding to customer utterances during a conversation, according to at least one embodiment.</figref><figref num="5">[0013] FIG. 5 shows an illustrative example of a process 500 for generating a set of performance metrics and recommendations for improving or enhancing the set of performance metrics for a client, according to at least one embodiment.</figref><figref num="6">[0014] FIG. 6 shows an illustrative example of a process 600 for benchmarking client performance by comparing these performance metrics to targets and/or industry associations across various performance metrics, according to at least one embodiment.</figref><figref num="7">[0015] FIG. 7 illustrates an illustrative example of a user interface for presenting a performance summary for a client based on one or more metrics according to at least one embodiment.</figref><figref num="8">[0016] FIG. 8 illustrates an illustrative example of a user interface for presenting calculated scores corresponding to different performance metrics, according to at least one embodiment.</figref><figref num="9">[0017] FIG. 9 illustrates an illustrative example of a user interface for presenting insight into conversation volume framed by possible entry points according to at least one embodiment.</figref><figref num="10">[0018] FIG. 10 illustrates an illustrative example of a user interface for presenting various performance metrics for a particular line of business, according to at least one embodiment.</figref><figref num="11">[0019] FIG. 11 illustrates an illustrative example of a user interface for providing information usable to compare key performance indicators (KPIs) to industry benchmarks, according to at least one embodiment.</figref><figref num="12">[0020] FIG. 12 illustrates an illustrative example of a user interface for presenting recommendations or enhancements for improving one or more performance metrics according to at least one embodiment.</figref><figref num="13">[0021] FIG. 13 illustrates an illustrative example of a user interface for presenting data corresponding to closed conversations and agent login times over a specified date range according to at least one embodiment.</figref><figref num="14">[0022] FIG. 14 illustrates an illustrative example of a user interface for displaying configuration settings that may drive client performance, according to at least one embodiment.</figref><figref num="15">[0023] Figure 15 illustrates an illustrative example of a computing system architecture including various components in electrical communication with each other using connections such as a bus, according to various embodiments.</figref><figref num="16">[0024] Figure 16 illustrates an illustrative example of an environment in which various embodiments may be implemented.</figref>
[0025] In the accompanying drawings, similar components and/or features may have the same reference label. Furthermore, various components of the same type may be distinguished by following the reference label with a dash and a second label that distinguishes between the similar components. If only a first reference label is used in this specification, the description is applicable to any one of the similar components having the same first reference label, regardless of the second reference label.
[0026] The following description provides only preferred examples of embodiments and is not intended to limit the scope, applicability, or configuration of the present disclosure. Rather, the following description of preferred examples of embodiments provides those skilled in the art with an enabling description for implementing the preferred examples of embodiments. It is understood that various changes can be made in the configuration and function of elements without departing from the spirit and scope as set forth in the appended claims.
1 illustrates an illustrative example of an environment 100 in which intent from a customer 108 is evaluated to determine a solution to the intent and generate a response that can be provided by an agent 112, according to at least one embodiment. Particular embodiments relate to establishing a connection between a network device 110 (which may be operated by the customer 108) and a terminal device 114 (which may be operated by the agent 112) to enable the customer 108 and the agent 112 to engage in a communication session, such as a customer service messaging session. The network device 110 may include a mobile device (e.g., a smartphone, a tablet computer, etc.), a computing device (e.g., a laptop, a personal computer, a server, etc.), and the like.
In some embodiments, a customer 108 may be a person who accesses the customer service call center 102 to present a problem or request that can be resolved or otherwise handled by an agent 112 at the customer service call center 102. For example, a customer 108 may be a person expecting a service to be performed on their behalf. Such services may include questions that are answered, getting assistance from an agent 112 with a task or service, conducting a transaction, etc.
[0029] The customer service call center 102 may be an entity that provides, operates, or executes an online service to provide assistance to customers of a client or other organization that provides services and/or goods to that customer, such as customer 108. For example, the customer service call center 102 may provide customer support on behalf of the client or other organization. In some embodiments, the customer service call center 102 is provided by a client or other organization to handle requests and/or problems submitted by the client's customers.
[0030] The customer service call center 102 may employ one or more agents 112. The agents 112 may be people, such as support agents or salespeople, tasked with providing the customers 108 with support or information regarding the online service (e.g., information about products available at an online store) and/or handling any issues or requests submitted by the customers 108 (e.g., refund requests, troubleshooting requests, etc.). The agents 112 may or may not be affiliated with a client. Each agent may be associated with one or more clients. In some non-limiting examples, the customers 108 may be people who shop at an online store from a personal computing device, the clients may be businesses that sell products online, and the agents 112 may be salespeople employed by the businesses. In various embodiments, the customers 108, clients, and agents 112 may be other individuals or entities.
In one embodiment, the customer service call center 102 implements an intent processing system 104 configured to process incoming intent from customers 108. The intent processing system 104 may access (e.g., extracted or received) messages from customers 108 to the customer service call center 102 and engage agents 112 to resolve requests or issues. Examples of intent may include (for example) topic, sentiment, complexity, and urgency. Topics may include, but are not limited to, subjects, products, services, technical issues, usage questions, complaints, refund requests, or purchase requests, etc. Intent may be determined based on, for example, a semantic analysis of the message (e.g., by identifying keywords, sentence structure, repeated words, punctuation characters, and/or non-article words), user input (e.g., with one or more categories selected), and/or statistics associated with the message (e.g., typing speed and/or response wait time).
In one embodiment, the intent processing system 104 analyzes incoming messages from the customer 108 to determine the context in which the request or problem is shared. Additionally, the intent processing system 104 determines what the level of urgency is, how stressed the customer 108 is, whether there is a time constraint in handling the request or problem, and the like. For example, if the message includes a request to address a problem related to the customer's television and the customer 108 indicates that a big game that the customer 108 wants to watch is about to start, the intent processing system 104 can determine that there is a time constraint in handling this problem and that the customer 108 may be exhibiting a level of stress or anxiety.
In one embodiment, the intent processing system 104 retrieves a customer profile from the customer profile repository 116 in response to retrieving a new message or customer utterance. The customer profile repository 116 may be maintained by the customer service call center 102 or may be maintained remotely by a client. The customer profile may include historical information and other data about the customer 108, including, but not limited to, past interactions between the customer 108 and agents of the customer service call center 102 to address other requests or issues the customer 108 may have had. The customer profile may be used by the intent processing system 104 to better determine characteristics of messages retrieved from the customer 108.
In one embodiment, the intent processing system 104 provides the agent 112 with the intent along with other information that can be used by the agent 112 to construct a response to the intent or customer utterance. In some examples, the intent processing system 104 can provide the agent 112 with a baseline response that incorporates elements that can generate a positive response from the customer 108. For example, the intent processing system 104 can indicate that the response from the agent 112 will include a particular basis (e.g., the message to be communicated), end (e.g., the outcome of the message, such as a timeline for resolution to the problem/request), and/or other positive elements that provide flair to the response that can appeal to the customer 108 or that can alleviate the customer's concerns and reduce the customer's stress level. The information provided by the intent processing system 104 can guide the agent 112 in preparing a response tailored to the customer's known or perceived preferences while addressing the received intent.
In one embodiment, once the agent 112 engages with the customer 108, the customer 108 may provide additional utterances or responses via the communication session established between the customer 108 and the agent 112. These additional utterances may be processed by the intent processing system 104 to further generate recommendations and parameters for responses to these utterances. Thus, during the communication session, the intent processing system 104 may evaluate the new utterance and determine how the agent 112 should respond to the customer 108 based on an analysis of the customer profile, the context in which the new utterance was made, the original intent presented by the customer 108, and other features of the conversation. In some embodiments, the intent processing system 104 includes a machine learning model or artificial intelligence (AI) that may be used to process the intent and other customer utterances as inputs, along with the customer profile, to generate a response. This response may be provided to the agent 112, who may provide this tailored response to the customer 108.
In one embodiment, the agents 112 are trained using a framework designed to assist virtual and/or human agents in delivering a positive conversational experience to customers of the customer service call center 102. For example, the customer service call center 102 may include an agent training system 118 that defines a sequence of actions to be performed to accurately capture key elements expressed by customers of the customer service call center 102 in conversations with the agent and identify how to best respond appropriately to the customers. The agent training system 118 may be implemented using computing devices associated with the customer service call center 102 (e.g., provided by the customer service call center 102, provided by a third-party service associated with the customer service call center 102, etc.). The agent training system 118 may be configured to address situational and emotional elements (whether explicit or implicit) to enable the agent to meet the customer's intent and expectations while maintaining a fluid and natural conversation.
[0037] The agent training system 118 can operate under an "analyze, identify, respond" framework, through which the agent training system 118 can identify any improvements that can be made by the agent 112 to better respond to customers of the customer service call center 102. For example, in one embodiment, the agent training system 118 processes historical data corresponding to previous interactions between the agent 112 and customers of the customer service call center 102. This historical data may be obtained from a customer relationship management (CRM) system (not shown) maintained by the customer service call center 102 or from a historical conversation data store maintained by the agent training system 118. The agent training system 118 can process the historical conversation data corresponding to conversations between the agent 112 and customers of the customer service call center 102, as well as corresponding customer profiles of the customers from the customer profile repository 116, to identify explicit and implicit elements in the customer responses and contextualize these responses.
In one embodiment, the agent training system 118 uses a machine learning algorithm or artificial intelligence to identify actions that the agent 112 can take to improve its ability to recognize explicit and implicit elements in customer responses and contextualize these elements to determine what they may be related to (e.g., associated intent, etc.). The machine learning algorithm or artificial intelligence may be trained using supervised training techniques. For example, the machine learning algorithm or artificial intelligence may be trained using sample conversations and corresponding feedback provided regarding recommendations generated by the machine learning algorithm or artificial intelligence based on the sample conversations to identify explicit and implicit elements and contextualize these elements. As an illustrative example, an evaluator of the machine learning algorithm or artificial intelligence (e.g., an administrator of the agent training system 118, an agent at the customer service call center 102, an independent party introduced to perform such evaluation, etc.) may review the provided recommendations and determine whether the recommendations lead to improved agent responses to customers. In some examples, the evaluator may play the role of a customer, who may send new messages to the sample agent to determine whether the sample agent's performance with respect to responding to these messages improved as a result of the provided recommendations. For example, the evaluator may determine, based on the recommendations provided, whether the agent was able to quickly identify the evaluator's intent and provide a response that was advantageous to the evaluator in addressing the intent in a positive manner. Based on this feedback, the machine learning algorithm or artificial intelligence may be retrained to provide more accurate or improved recommendations to the agent based on past conversation data available to the agent.
In one embodiment, the output of the machine learning algorithm or artificial intelligence provides a conditional logic that may be used by the agent once the agent identifies what the detected implicit and explicit elements of the customer's message pertain to. This conditional logic may introduce different elements to address the intent identified based on the detected implicit and explicit elements of the customer's message. For example, the conditional logic may include a component that serves to address the customer's intent (e.g., what the customer requests or wants when the customer initiates messaging the customer service call center 102) and a component that constitutes another section that corresponds to the next question or action that may be taken by the customer. In addition to these elements, the machine learning algorithm or artificial intelligence may provide recommendations to appropriately respond to positive or negative emotional elements in the conversation, such as frustration, disappointment, stress, joy, happiness, satisfaction, etc.
In addition to identifying and determining the implicit and explicit elements of the customer's message, identifying intent based on these elements, and providing recommendations for responding to the emotional elements in the conversation, the machine learning algorithm or artificial intelligence can further assess qualitative and quantitative aspects of the agent response before the agent response is presented. For example, when the agent 112 generates a response to a customer message to be presented, the agent training system 118 (using the machine learning algorithm or artificial intelligence) can evaluate the response in real time to determine whether all identified elements have been addressed in the response proposed by the agent 112. Additionally, the agent training system 118 may provide any feedback deemed necessary to improve the response according to the identified elements and the likelihood of a positive perception of the effort by the customer 108.
[0041] The agent training system 118 may determine, based on the incoming data stream of the communication session and/or the transcript of the conversation, whether the agent 112 followed the suggestions or responses prepared by the agent training system 118. If the agent training system 118 determines that the agent 112 did not follow the suggestions or responses prepared by the agent training system 118, the agent training system 118 may implement one or more corrective actions, such as sending a notification to the agent 112 or the agent's 112's supervisor indicating necessary steps to be taken to improve the agent's 112's performance.
[0042] In one embodiment, the aforementioned machine learning algorithm is retrained based on the messages exchanged during these new conversations along with the context, explicit elements, and implicit elements from these new conversations, data corresponding to the recommendations provided to the agent during these new conversations (e.g., compliance with the recommendations, etc.), and metrics corresponding to the agent performance for these new conversations. For example, if the machine learning algorithm has generated recommendations that are not complied with and the agent performance shows improvement, the machine learning algorithm may be retrained to generate more accurate or appropriate recommendations corresponding to actions taken by the agent that result in improved performance. Alternatively, if the agent complies with the recommendations provided and the agent performance shows improvement for these conversations, the machine learning algorithm may be trained to enhance the generation of similar recommendations.
[0043] In one embodiment, the customer service call center 102 includes a performance monitoring system 106 configured to determine the performance of the agents 112 based on the customers 108's feedback regarding the agent's responses during a communication session between the customers 108 and the agents 112. For example, the performance monitoring system 106 may process an incoming data stream of the communication session and/or a transcript of the conversation between the customers 108 and the agents 112 to determine how the customers 108 responded to each agent 112's utterances.
In one embodiment, the performance monitoring system 106 provides feedback to the agent training system 118 regarding the agent's consistency with the suggestions or responses prepared by the intent processing system 104 and/or the agent training system 118. Additionally, the performance monitoring system 106 can provide to the agent training system 118 any feedback provided by the customer 108 regarding the communication session between the customer 108 and the agent 112. For example, at the end of the communication session or at any time during the communication session, the performance monitoring system 106 can send a request to the customer 108 to evaluate the agent 112's performance in addressing the customer's intent or other issues. The performance monitoring system 106 can prompt the customer 108 to indicate whether the agent 112 was able to effectively respond in a positive manner to the customer's intent or other issues. Additionally, the performance monitoring system 106 can prompt the customer 108 to indicate its sentiment regarding the communication session. For example, if the customer 108 has a negative experience with the agent 112 over a communication session, the customer 108 may provide feedback to improve the agent and/or to address the customer's intent or other issues. Alternatively, if the customer 108 has a positive experience with the agent 112 over a communication session, the customer 108 may provide feedback to identify the customer's intent or other issues and indicate what the agent 112 did correctly in addressing the intent or other issues.
In some embodiments, the performance monitoring system 106 updates a customer profile of the customer 108 based on how the customer 108 responded to the agent's utterances during the communication session. For example, the performance monitoring system 106 can evaluate the incoming data stream and/or conversation transcript of the communication session to determine whether the customer's stress or anxiety level decreased as a result of the agent's response to the intent. This can include a semantic analysis of the customer's utterances compared to known semantic patterns of the customer 108 that are classified as relating to customer stress or anxiety. If such a change in the customer's emotion is detected, the performance monitoring system 106 can update the customer profile of the customer 108 to indicate that the agent's utterances were effective in calming or otherwise soothing the customer 108.
In one embodiment, the performance monitoring system 106 also evaluates the incoming data stream and/or conversation transcript of the communication session to determine whether the intent was fulfilled by the agent 112. For example, the performance monitoring system 106 may determine whether the customer 108 provided an evaluation or other acknowledgment that their request or problem was successfully resolved by the agent 112. If so, the performance monitoring system 106 may indicate that the response generated by the intent processing system 104 was effective in resolving the problem or request. However, if the performance monitoring system 106 determines that the intent was not fulfilled, the performance monitoring system 106 may update the intent processing system 104 to cause the intent processing system 104 to generate an alternative response that may be used to fulfill the intent. This may include updating training data that may be used to train a machine learning model or AI utilized by the intent processing system 104 to generate a response to the customer intent.
[0047] The performance monitoring system 106 can obtain customer feedback through other mechanisms. For example, at the end of a communication session, the customer 108 may be provided with a form or survey that may be completed by the customer 108 to provide feedback on the performance of the agent 112. The customer 108 may be prompted to indicate whether the agent 112 was able to effectively use conversation guilding and respond to the emotional aspects of the conversation. Additionally, the customer 108 may be prompted to determine whether the agent 112 was able to successfully fulfill the customer's intent. The performance monitoring system 106 can use this feedback from the customer 108 to evaluate the agent 112 as described above.
In one embodiment, in order to accurately identify training and coaching opportunities for agents or groups of individuals, how they impact the overall performance of client operations, and prioritize corrective actions, the performance monitoring system 106 tracks the performance of each agent 112 and correlates this performance with existing performance metrics of the customer service call center 102. For example, in one embodiment, the performance monitoring system 106 provides detailed metrics corresponding to the performance of each agent 112 to the agent training system 118 to identify a course of action that may be taken to improve the performance of these agents in responding to customer messages. As an illustrative example, the agent training system 118 may use the detailed metrics corresponding to the agent's 112 performance for one or more conversations, along with transcripts or exchanged messages corresponding to these one or more conversations, as inputs to a machine learning algorithm or artificial intelligence to generate performance improvement recommendations that may be implemented by the agent 112 to improve his or her ability to identify customer intents and respond to these intents in a manner that is more likely to generate a positive response from the customer. In some cases, the performance monitoring system 106 may track compliance by the agents 112 with the recommendations and training provided by the agent training system 118, thereby enabling the performance monitoring system 106 to correlate compliance with these recommendations and training to the performance of the agents 112 in providing a positive customer experience to customers associated with the customer service call center 102.
[0049] In one embodiment, the performance monitoring system 106 provides clients with a portal that can be used to track various performance metrics of the client and compare the client's performance to that of competitors. Through the portal or other interface, the performance monitoring system 106 may present metric-driven best practices that balance efficiency and effectiveness. For example, the performance monitoring system 106 may provide a user interface that provides a set of interactive dashboards aligned to different measurement pillars (e.g., operational, automation, intent, sales, etc.). Each of these measurement pillars may include dashboard modules and enablement frameworks that are used to articulate how primary and secondary KPIs impact success and client performance. The user interface may provide a consolidated view of different client metrics with associated context such as industry benchmarks, account settings, and metric correlations.
[0050] The framework utilized by the performance monitoring system 106 to provide insight into the performance of agents associated with the customer service call center 102 may rely on metrics generated based on effort, sentiment, efficiency, and effectiveness. For example, the effort-related metrics may correspond to the amount of effort required by agents of the customer service call center 102 or other clients involved with the customer service call center 102 to address customer intent. For example, based on the agent's performance in addressing customer intent and issues, the performance monitoring system 106 may determine the amount of effort required by the agent to address the customer intent and issues and calculate one or more metrics corresponding to this amount of effort. As an illustrative example, if customers 108 required repeated contact with the customer service call center 102 to address their issues, experienced multiple transfers between agents to address their issues, and/or experienced significant wait times to address their issues, the performance monitoring system 106 may assign a score corresponding to a large amount of effort required to address the customer intent and other issues. For example, the performance monitoring system 106 may assign a high score corresponding to a high amount of effort required, while a low score may correspond to a low amount of effort required by the agent to address the customer's intent or problem.
Similarly, the performance monitoring system 106 can determine the level of emotion among customers of the customer service call center 102 or other clients associated with the customer service call center 102 to calculate an emotion score for an agent. For example, if a significant number of conversations are related to cancellations and billing disputes, which tend to be emotionally charged and result in a higher number of complaints or escalations for the agent, the performance monitoring system 106 can calculate an emotion score corresponding to a negative emotional load for the customer. Alternatively, if a significant number of conversations are resolved positively, thereby causing the customer to be satisfied with the resolution, the performance monitoring system 106 can calculate an emotion score corresponding to a positive emotional load for the customer.
[0052] The performance monitoring system 106 may further determine the level of an agent's efficiency in handling customer intent or issues over time to calculate an efficiency score for the customer service call center 102 or other clients associated with the customer service call center 102. The performance monitoring system 106 may, for example, weight the balance between available resources (e.g., agent availability, etc.) and demands (e.g., customer contacts with the customer service call center 102, etc.). For example, if an agent has a low online rate, such that the agent is only able to receive new conversations during a limited period of time during a day/shift, the performance monitoring system 106 may assign an efficiency score corresponding to a low level of efficiency among the agent. Alternatively, if an agent has a high online rate and is able to receive new conversations during a wider range of times during a day/shift, the performance monitoring system 106 may assign an efficiency score corresponding to a higher level of efficiency among the agent.
[0053] The framework utilized by the performance monitoring system 106 can further provide for a determination of an agent's level of effectiveness in addressing customer intent and problems leveraging available capabilities and tools. For example, if the performance monitoring system 106 determines, based on an evaluation of an agent's performance, that an agent is not leveraging automated tools for completing conversations or distributing conversations among agents, the performance monitoring system 106 can assign an effectiveness score corresponding to a low level of effectiveness among the agents. Similarly, if the performance monitoring system 106 determines that an agent is sending multiple messages at an above average rapid rate, leaving little or no time for engineering a solution to the customer intent or problem, the performance monitoring system 106 may assign an effectiveness score corresponding to a low level of effectiveness among the agents.
[0054] As mentioned above, the performance monitoring system 106 can provide the above-mentioned scores and other metrics to the management of the customer service call center 102 or other clients associated with the customer service call center 102 via a portal or other interface. In one embodiment, in addition to these scores and other metrics, the performance monitoring system 106 utilizes machine learning algorithms or artificial intelligence to automatically provide an assessment of all conversational behavior, which can lead to data-driven decision-making for improving agent performance. For example, the performance monitoring system 106 can provide metrics and characteristics corresponding to conversations between agents and customers (e.g., conversation topics or intents, customer surveys or feedback, messaging rate metrics, agent availability metrics, metrics related to the use of automation tools or capabilities, etc.), actual conversation transcripts, and the like, as inputs to the machine learning algorithms or artificial intelligence to obtain an assessment of agent performance and identify possible solutions or recommendations for improvement. For example, the output of the machine learning algorithms or artificial intelligence can provide a description of what has happened or is happening between the agents and customers, resulting in the current performance levels of these agents. Additionally, the output of the machine learning algorithm or artificial intelligence can provide diagnostic information corresponding to the rationale for what happened or is happening. For example, the output can indicate that the customer is not satisfied with the response provided by the agent because the agent took too long to respond and generally is unable to identify or otherwise address the customer issue in a timely manner.
In some instances, the machine learning algorithms utilized by the performance monitoring system 106 to provide an assessment of agent performance and identify solutions and recommendations for improvement may be retrained based on updated performance metrics for the agent resulting from compliance or disregard of the provided solutions and recommendations. For example, a client may provide feedback regarding the agent performance resulting from the implementation of the provided solutions and recommendations. This feedback may be used to retrain the machine learning algorithm to strengthen the algorithm (e.g., compliance with the solutions and recommendations led to a significant improvement in agent performance) or to retrain the algorithm to provide more accurate or appropriate solutions and recommendations (e.g., compliance with the solutions and recommendations led to no change in agent performance or to a significant deterioration). In some instances, the performance monitoring system 106 may evaluate compliance with the provided solutions and recommendations along with agent performance over time to determine if there is a correlation between agent performance and compliance with the provided solutions and recommendations. Based on this evaluation, the performance monitoring system 106 may retrain the machine learning algorithm to provide better solutions and recommendations based on the agent performance.
[0056] In addition to providing an explanation of the problems faced by the customer-agent conversation and the reasons behind these problems, the machine learning algorithm or artificial intelligence can provide one or more recommendations on how to correct these problems to improve the customer experience. For example, using the above example where the agent takes too long to respond to the customer and the customer is dissatisfied because the agent is unable to identify the customer's problem in a timely manner, the machine learning algorithm or artificial intelligence can recommend remedial training for the agent to better identify these problems using automated tools, such as tools configured to process customer messages to identify problems or intent. If such tools are already implemented and the agent is not using these tools effectively, the machine learning algorithm or artificial intelligence may recommend that the agent be trained on how to effectively utilize these tools to provide the agent with appropriate recommendations for identifying and addressing customer intent and problems, or alternatively, have all messages processed using these tools automatically.
In one embodiment, the performance monitoring system 106 may further provide, via a portal or other interface, using machine learning algorithms or artificial intelligence, a prediction regarding the improvement of an agent's performance if the aforementioned recommendations are implemented. For example, the machine learning algorithm or artificial intelligence may indicate that metrics corresponding to effort, emotion, efficiency, and effectiveness can be improved by a certain margin if the provided recommendations are implemented. The machine learning algorithm or artificial intelligence may provide this prediction using numerical metric values (e.g., "efficiency will improve by 56%") and/or descriptive narratives (e.g., "agent efficiency should increase dramatically"), which may be presented via the portal or other interface in conjunction with a description of the identified issues, diagnostic information explaining why these issues are occurring or have occurred, and recommendations to address these issues.
[0058] The machine learning algorithm or artificial intelligence may be dynamically trained using supervised training techniques. For example, a data set of input conversations, feedback, agent performance metrics, known improvement procedures, and results of applying or ignoring the improvement procedures and resulting outcomes may be selected for training the machine learning model. The machine learning model may be evaluated to determine whether the machine learning model extracts the expected recommendations and predictions based on the agent's performance in dealing with the customer intent or problem based on the sample inputs provided to the machine learning model. Based on this evaluation, the machine learning model may be modified to increase the likelihood that the machine learning model produces the desired results. The machine learning model may further be dynamically trained by soliciting feedback from clients, including clients associated with the customer service call center 102 or agents 112, regarding the assessments, recommendations, and predictions provided by the machine learning algorithm or artificial intelligence to improve agent performance. For example, when the customer service call center 102 implements one or more recommendations provided by the machine learning algorithm or artificial intelligence, the performance monitoring system 106 may obtain new performance metrics corresponding to the agents 112 based on their performance in dealing with customer conversations. The performance monitoring system 106 can determine what steps have been taken by the customer service call center 102 and the agents 112 to address issues identified by the performance monitoring system 106, and can determine whether the new performance metrics correspond to the predicted performance improvements indicated by the machine learning algorithm or artificial intelligence. This determination (including variance, etc.) can be used to further train the machine learning algorithm or artificial intelligence to provide more accurate predictions of performance improvements and to better generate recommendations for performance improvements.
In one embodiment, the performance monitoring system 106 further provides a benchmarking dashboard or other interface through which managers may compare agents' performance against targets and/or industry associations across various KPIs, such as those described above. For example, managers and other entities may select one or more targets and/or industry associations for which the performance monitoring service 106 may generate comparisons across various KPIs via a benchmarking dashboard. These one or more targets and/or industry associations may also utilize the performance monitoring system 106 to evaluate their agents and organizations with respect to their performance in conversations with customers. Additionally or alternatively, the performance monitoring system 106 may obtain various performance metrics for these one or more targets and/or industry associations through other sources (e.g., publications, third-party performance evaluators, etc.).
[0060] The performance monitoring system 106, via the benchmarking dashboard, may show any insights related to the actions taken by one or more targets and/or industry associations selected by the administrator to achieve their performance metrics. For example, the performance monitoring system 106 may provide, for a particular target, performance metrics before the execution of one or more actions (e.g., implementing an automated capability to identify customer intent and train agents to comply with recommendations from the agent training system 118) and performance metrics after the execution of the one or more actions. This allows the administrator to easily determine the impact of these actions and whether similar actions can be implemented for the agent. In some examples, the performance monitoring system 106 may provide insights regarding problems encountered by one or more targets and/or industry associations, why these problems were encountered, what actions were taken or recommended to address these problems, and the consequences resulting from the execution or omission of these actions.
In some cases, the performance monitoring system 106 may provide, via a benchmarking dashboard, a comparison of KPIs for an organization (e.g., customer service call center 102, etc.) with KPIs for one or more targets and/or industry associations by intent and/or business. For example, the performance monitoring system 106 may aggregate performance metrics for various agents 112 according to specific intents, intent categories, and/or business as determined by the performance monitoring system 106 via evaluation of conversation transcripts and any information provided regarding the organization's operations (e.g., business units, problems typically addressed by the organization, etc.). The performance monitoring system 106 may generate a comparison between performance metrics for the organization and one or more targets and/or industry associations according to specific intents, categories, and/or business selected by management utilizing the benchmarking dashboard. This may provide more granular details regarding the performance of agents 112 in addressing different intents or in addressing problems related to different business.
[0062] The performance monitoring system 106 may include a configuration engine that allows clients (e.g., customer service call center 102, etc.) to define reporting units and store the data in associated segmentations. These segmentations may persist over time, eliminating time spent defining filters and thus reducing the time to generate insights. Clients may also label reporting units via a user interface with descriptive data such as 24/7 operations, dedicated messaging agents, program goals, and the like.
2 illustrates an illustrative example of an environment 200 in which intent 214, responses 216, and feedback obtained during a communication session between a customer 206 and an agent 210 are evaluated to determine the performance of the agent 210, according to at least one embodiment. The customer 206 and the agent 210 can participate in the communication session established via a network device 208 and a terminal device 212, respectively.
In the environment 200, the customer 206 can submit an intent 214 to the intent processing system 202 via a communication session. For example, as illustrated in FIG. 2, the customer 206 indicates that he is looking to move money between his main account and a new flex account that he opened. The intent processing system 202 can evaluate this intent 214 to determine the problem the customer 206 wants to address. In this particular case, the customer 206 may be having trouble transferring funds from one online account to another. Based on the provided intent 214, the intent processing system 202 can determine the context in which the request or problem is shared, the level of urgency, the customer's 206's stress or anxiety level, whether there is a time constraint, and the like. Furthermore, the intent processing system 202 can identify what the customer 206 wants to solve based on the intent 214.
In one embodiment, based on the identified intent 214, the intent processing system 202 identifies a process required to resolve the problem or request provided by the customer 206. For example, based on the intent 214 provided by the customer 206, the intent processing system 202 may determine that the account must be authenticated before the customer can transfer funds to the account. Further, the intent processing system 202 may determine that authenticating the account can be performed online. Based on the identified process, the intent processing system 202 may develop a strategy to respond to the customer intent 214 in a manner that not only resolves the intent but also leads to a positive customer experience. This may include developing a basis for the response, a desired outcome of the response, and/or any positive additions to give the response distinctiveness. The content of the suggested response may be generated based on customer preferences as identified in a customer profile via analysis of past customer interactions with agents.
[0066] The intent processing system 202 can provide suggested response strategies and prepared responses to the agent 210, which the agent 210 can use to prepare a response to the customer intent 214. As illustrated in Figure 2, the agent 210 can provide an acknowledgment indicating that it understands the problem ("I see the problem") and provide a solution to the intent 214 using language that may be appealing to the customer 206.
In one embodiment, the agent training system 204 monitors the interaction between the customer 206 and the agent 210 to determine whether the agent 210 complies with the suggested response strategies generated by the intent processing system 202 in addressing the intent 214. For example, the agent training system 204 can evaluate any customer utterances to determine whether the intent 214 is being met. Additionally, the performance monitoring system 204 can evaluate the agent's utterances to determine whether they conform to the suggested responses and strategies provided by the intent processing system 202. As an illustrative example, the agent training system 204 can determine that the customer 206 has accepted the agent's instructions and was able to successfully perform the action according to these instructions when the customer 206 responds with "I did it." Additionally, the agent training system 204 can determine that the customer 206 is grateful for the assistance provided by the agent 210 and had a positive experience when the customer 206 responds with "Thanks! That worked!" This information may be used to gauge the agent's 210 performance, as well as input that may be used to update the customer profile to provide additional data points for determining how to best respond to customer intent.
In one embodiment, if the agent training system 204 determines that the agent 210 is not complying with the suggested response strategies and prepared responses provided by the intent processing system 202 or is not complying with the recommendations provided by the agent training system 204, the agent training system 204 may communicate with the agent 210 to reinforce the suggested response strategies and further encourage the agent 210 to incorporate the suggested response strategies and prepared responses when communicating with customers regarding specific and/or similar intents. Additionally or alternatively, the agent training system 204 may send a notification to the agent's 210's manager or other supervisor indicating any necessary steps to be taken to encourage the agent 210 to comply with the recommendations provided by the agent training system 204 and/or the suggested response strategies and prepared responses provided by the intent processing system 202.
[0069] As described above, the agent training system 204 provides a framework designed to assist virtual and/or human agents in delivering a positive conversational experience to customers. The agent training system 204 may operate under an "analyze, identify, respond" framework, through which the agent training system 204 may identify any improvements that can be made by the agent 210 to better respond to customers. The agent training system 204 may process historical data corresponding to previous interactions between the agent and the customer to identify explicit and implicit elements in customer responses and contextualize these responses. This process may result in the creation of conditional logic that may be used by the agent once the agent identifies what the detected implicit and explicit elements of the customer's message pertain to. In some embodiments, this conditional logic and the identified improvements can be used to further improve the intent processing system 202 to better identify explicit and implicit elements in a customer response in real time and dynamically generate recommended responses that may be provided to the agent 210 to better guide the agent 210 in providing a response to the customer that is likely to generate a positive resolution to the customer's intent. Additionally, the agent training system 204 can assess qualitative and quantitative aspects of the agent response before the agent response is presented. The agent training system 204 can evaluate the response in real time to determine whether all identified elements have been addressed in the response proposed by the agent 210.
3 illustrates an illustrative example of an environment 300 in which a performance monitoring service 302 measures and manages the performance of an organization's conversational operations, according to at least one embodiment. In the environment 300, the performance monitoring system 302 can process conversation data 318 generated based on conversations between customers 314 and agents 316 associated with a customer service call center to generate performance metrics for the agents 316 and provide various insights related to the performance of these agents 316. In one embodiment, the performance monitoring system 302 includes a performance evaluation subsystem 304 configured to process the conversation data 318 to generate performance metrics for the agents 316. The performance evaluation subsystem 304 can be implemented using a computing device associated with the performance monitoring system 302.
[0071] The performance evaluation subsystem 304 may periodically retrieve conversation data 318. For example, the performance evaluation subsystem 304 may access a conversation data repository or data store maintained by a customer service call center or other entity tasked with maintaining records associated with existing conversations between customers 314 and agents 316. The conversation data repository or data store may include a conversation transcript or record corresponding to each conversation handled by the customer service call center. A conversation transcript or record may include various messages exchanged between a particular customer and one or more agents during the course of a conversation to address a particular intent or problem. Thus, a conversation transcript or record may be associated with a particular customer and a particular intent or problem that the customer was attempting to solve. Additionally, a conversation transcript or record may include identification information associated with an agent or set of agents (e.g., virtual and/or human) that engaged the customer to address a particular intent or problem. Thus, the performance evaluation subsystem 304 may process existing conversations, generate performance metrics associated with an agent or set of agents for the existing conversations, and relate these performance metrics to particular intents, customers, and/or tasks to create correlations between agent performance and particular intents/types of intent, customers, and/or tasks.
In one embodiment, the performance evaluation subsystem 304 can process conversation data 318 of a conversation in real time to determine real-time performance of an agent or set of agents with respect to a particular conversation. For example, the performance evaluation subsystem 304 can be configured to evaluate an incoming data stream of messages corresponding to existing conversations between customers 314 and agents 316 to determine a dynamic set of performance metrics for these agents 316 in real time. As an illustrative example, when a new message is exchanged between a particular customer and agent, the performance evaluation subsystem 304 can calculate one or more performance metrics for the agent. When the performance evaluation subsystem 304 detects that a new message has been exchanged, the performance evaluation subsystem 304 can dynamically recalculate one or more performance metrics for the agent in real time, thus providing updated performance metrics for the agent.
As discussed above, these performance metrics may correspond to a framework built on customer and client interests tied to effort, emotion, efficiency, and effectiveness. For example, a metric related to effort may correspond to the amount of effort required by the agent 316 to address customer intent. For example, based on the agent 316's performance in addressing customer intent and issues, the performance evaluation subsystem 304 may determine the amount of effort required by the agent 316 to address customer intent and issues and calculate one or more metrics corresponding to this amount of effort. Similarly, the performance evaluation subsystem 304 may determine the level of emotion among the customers 314 while engaged in a conversation with the agent 316 to calculate an emotion score for the agent. The performance evaluation subsystem 304 may further determine the level of efficiency of the agent 316 in handling customer intent or issues over time to calculate an efficiency score for each agent by weighting the balance between available resources (e.g., agent availability, etc.) and demands (e.g., customer contacts with clients, etc.). The performance evaluation subsystem 304 may further provide a determination of the customer's intent to utilize available capabilities and tools and the level of effectiveness of the agent 316 in addressing the problem.
In one embodiment, the performance evaluation subsystem 304 presents the calculated performance metrics for each agent or set of agents 316 to the client 312 through a dashboard 310 provided by the performance monitoring system 302. The performance evaluation subsystem 304 may present the calculated performance metrics according to one or more configuration settings provided by the client 312. For example, if the client 312 indicates that it would like to see aggregated performance metrics for agents according to business or other classification of agents, the performance evaluation subsystem 304 may aggregate these performance metrics according to business or other classification of agents (as indicated by the client 312) and present the aggregated performance metrics to the client 312 via the dashboard 310. In some instances, the client 312 may submit a query via the dashboard 310 to obtain performance metrics for a particular agent or set of agents. In response to the query, the performance evaluation subsystem 304 may aggregate performance metrics for the particular agent or set of agents and update the dashboard 310 to provide the aggregated performance metrics. In one embodiment, the performance evaluation subsystem 304 can dynamically update the dashboard 310 in real-time to provide up-to-date performance metrics for the agents 316 as messages are exchanged in real-time between the customers 314 and the agents 316. This allows the client 312 to track the performance of any agent in real-time and potentially identify any agent problems as they occur.
In one embodiment, in addition to these performance metrics, the performance monitoring system 302 may generate various insights into agent performance that may be used to identify areas of improvement or enhancement for the agent 316 associated with the client 312. For example, as illustrated in FIG. 3, the performance evaluation subsystem 304 may transmit the calculated performance metrics for the agent 316 along with the conversation data 318 to a performance insight generator 308 to identify these areas of improvement or enhancement and provide any valuable insight into the conversational behavior of the client 312. The performance insight generator 308 may be implemented using a computing device associated with the performance monitoring system 302.
In one embodiment, the performance insight generator 308 utilizes machine learning algorithms or artificial intelligence to automatically provide an assessment of a client's conversational behavior, which can lead to data-driven decision making for the improvement of agent performance. For example, the performance insight generator 308 can provide metrics and characteristics corresponding to conversations between agents and customers (e.g., conversation topics or intents, customer surveys or feedback, messaging rate metrics, agent availability metrics, metrics related to the use of automation tools or capabilities, etc.), actual conversation transcripts, and the like (such as provided by the performance evaluation subsystem 304, obtained directly from the client 312, etc.) as inputs to the machine learning algorithm or artificial intelligence to obtain an assessment of agent performance and identify possible solutions or recommendations for improvement. The output of the machine learning algorithm or artificial intelligence can provide a description of what has occurred or is occurring between the agents 316 and the customers 314 that has resulted in the current performance level for these agents 316. Additionally, the output of the machine learning algorithm or artificial intelligence can provide diagnostic information corresponding to the rationale for what has occurred or is occurring. For example, the output may indicate that the customer 314 is not satisfied with the response provided by the agent 316 because the agent 316 took too long to respond, typically because the customer problem was not identified or otherwise addressed in a timely manner.
[0077] The performance insight generator 308 may further provide one or more recommendations on how to correct these issues to improve the customer experience. For example, using the above example where the agent takes too long to respond to the customer and is not able to identify the customer issue in a timely manner, the machine learning algorithm or artificial intelligence utilized by the performance insight generator 308 may recommend corrective training for the agent to use automated tools to better identify these issues. If such tools are already implemented and the agent 316 is not using these tools effectively, the machine learning algorithm or artificial intelligence may recommend that the agent 316 be trained on how to effectively utilize these tools, or alternatively, have all messages processed using these tools automatically, in order to provide the agent with appropriate recommendations for identifying and addressing the customer intent and issue.
In addition to providing one or more recommendations for improving or enhancing agent performance, the performance insight generator 308 can provide a prediction as to how the performance of the agent 316 may be affected by implementing one or more recommendations. For example, the performance insight generator 308 may indicate that metrics corresponding to effort, emotion, efficiency, and effectiveness can be improved by a certain margin if the provided recommendation is implemented. The performance insight generator 308 can provide this prediction using numerical metric values (e.g., efficiency will improve by 56%) and/or descriptive narratives (e.g., agent efficiency should increase dramatically), which can be presented via the dashboard 310 along with descriptions of identified problems, diagnostic information explaining why these problems are occurring or have occurred, and recommendations for addressing these problems.
[0079] As described above, the performance monitoring system 302 can provide a dashboard 310 through which a client 312 can compare the performance of its agents 316 against targets and/or industry associations across various performance metrics (e.g., KPIs). For example, the client 312 can select one or more targets and/or industry associations for which the performance monitoring service 302 can generate a comparison across various performance metrics via the dashboard 310. These one or more targets and/or industry associations can also utilize the performance monitoring system 302 to evaluate their agents and organizations with respect to their performance in conversations with customers. Additionally or alternatively, the performance monitoring system 302 may obtain various performance metrics for these one or more targets and/or industry associations through other sources (e.g., publications, third-party performance evaluators, etc.).
In one embodiment, the performance monitoring system 302 stores performance data associated with the clients 312 as well as other targets and/or industry associations in the comparative data store 306. For example, when the performance evaluation subsystem 304 calculates performance metrics for a set of agents associated with the clients 312, the performance evaluation subsystem 304 may store the performance metrics associated with the clients 312 in the comparative data store 306. Additionally, insights, recommendations, and predictions generated by the performance insight generator 308 based on performance metrics of the agents 316 associated with the clients 312 may be stored in the comparative data store 306 in association with the performance metrics calculated by the performance evaluation subsystem 304 for the agents 316. This process may be performed for each client associated with the performance monitoring system 302, such that the comparative data store 306 may store comparable performance metrics and insights for each client.
Additionally, the comparison data store 306 may store data for other targets and/or industry associations that may not be serviced by the performance monitoring system 302, but that may provide a benchmark for determining the relative performance of clients otherwise associated with the performance monitoring system 302. For example, the performance monitoring system 302 may obtain various performance metrics for these one or more targets and/or industry associations through other sources (e.g., publications, third-party performance evaluators, etc.). For example, the performance monitoring system 302 may subscribe to one or more data streams associated with the other sources of performance metrics to obtain performance metrics for these one or more targets and/or industry associations. In some examples, if the obtained performance metrics or other data associated with one or more targets and/or industry associations is not in a format conducive to providing a benchmarking comparison with the performance metrics of the client 312, the performance monitoring system 302 may use the performance evaluation subsystem 304 to process the obtained performance metrics or other data to generate a new set of performance metrics for the one or more targets and/or industry associations that can be used for benchmarking purposes as described herein.
[0082] Through the dashboard 310, the performance monitoring system 302 can show any insights related to the actions taken by one or more targets and/or industry associations selected by the client 312 to achieve their corresponding performance metrics along different classifications (e.g., by business, type of agent, etc.). For example, the performance monitoring system 302 can provide, for a particular target, via the dashboard 310, performance metrics for the particular target before the execution of one or more actions (e.g., implementing an automated ability to identify customer intent, training an agent to comply with recommendations from an agent training system, etc.) and performance metrics for the particular target after the execution of the one or more actions. This may enable the client 312 to easily determine the impact of these actions and whether similar actions may be implemented for its agents 316. In some examples, the performance monitoring system 302 can provide, via the performance insight generator 308, insights regarding issues encountered by one or more targets and/or industry associations, why these issues were encountered, what actions were taken or recommended to address these issues, and the results resulting from the performance or omission of these actions.
In some cases, based on the insights and recommendations provided by the performance insights generator 308 and presented via the dashboard 310, the client 312 may request that the provided insights and recommendations be used by the agent training system to define a course of action to be performed to accurately capture the key elements expressed by the customer 314 in the conversation with the agent 316 and identify the best way to respond appropriately to the customer 314. As described above, the agent training system may be configured to address situational and emotional elements (whether explicit or implicit) to enable the agent 316 to meet the customer's intent and expectations while maintaining a fluid and natural conversation. Based on the insights and recommendations provided by the performance insights generator 308, the agent training system may identify what actions can be taken to address these elements to enable the agent 316 to meet the customer's intent and expectations according to the generated insights and recommendations.
[0084] Figure 4 illustrates an illustrative example of a process 400 for implementing a framework for assisting an agent in response to customer utterances during a conversation, according to at least one embodiment. Process 400 may be performed by an agent training system of a customer service call center. The agent training system may be configured to accurately capture key elements expressed by a customer in a conversation with an agent, as described above, and define a course of actions to be performed to identify the best way to respond appropriately to the customer. Additionally, the agent training system may be configured to address situational and emotional elements (whether explicit or implicit) to enable the agent to meet the customer's intent and expectations while maintaining a fluid and natural conversation.
In step 402, the agent training system processes historical data corresponding to previous interactions between agents and customers associated with the client. This historical data may be obtained from a CRM system maintained by the client or from a historical conversation data store maintained by the agent training system. The agent training system 118 may process the historical conversation data corresponding to conversations between agents and the client's customers as well as corresponding customer profiles of the customers to identify explicit and implicit elements in customer responses and contextualize these responses. In some cases, the agent training system may obtain performance metrics associated with the client from a performance monitoring system. For example, the agent training system may query the performance monitoring system to obtain performance metrics for each agent associated with the client as well as any insights or recommendations generated by the performance monitoring system for the improvement of these performance metrics.
[0086] In step 404, the agent training system identifies explicit and implicit elements in the previous interactions specified in the historical data. The agent training system may process these previous interactions using machine learning algorithms or artificial intelligence trained to extract explicit and implicit elements in these previous interactions and identify any intent and/or problems presented by the corresponding customers during these interactions. Further, in one embodiment, the agent training system may evaluate these interactions to measure the agent's performance in identifying explicit and implicit elements in customer utterances during these previous interactions. This agent's performance in identifying explicit and implicit elements may be evaluated against performance metrics obtained from a performance monitoring system for the corresponding agent, thereby creating a correlation between the agent's performance in identifying explicit and implicit elements in a conversation and the performance metrics calculated by the performance monitoring system for the agent.
[0087] In step 406, the agent training system can use key information in the historical data to contextualize the identified explicit and implicit elements of the previous interactions. For example, the agent training system can obtain data corresponding to previous evaluations of past communication sessions provided by customers associated with previous interactions recorded in the historical data. Data corresponding to these previous evaluations may indicate certain elements of the customer's communications that may indicate certain emotions, pressures, intent, and the like. Thus, based on these history and elements identified from the customer utterances, the agent training system can determine what the identified elements in the customer utterances relate to in the context of the previous interactions.
[0088] In step 408, the agent training system generates conditional logic that can be used by the agent to address intent based on the explicit and implicit elements of the customer's utterance. For example, the output of the machine learning algorithm or artificial intelligence described above can provide a conditional logic that can be used by the agent once the agent identifies what the detected implicit and explicit elements of the customer's message relate to. This conditional logic can introduce different elements to address the identified intent based on the detected implicit and explicit elements of the customer's message. For example, the conditional logic can include a component that serves to address the customer's intent (e.g., what the customer requests or wants when the customer starts messaging the client) and a component that constitutes another section corresponding to a likely next question or action to be taken by the customer.
In step 410, the agent training system can provide recommendations for appropriately responding to these elements as well as positive or negative emotional elements in the conversation, such as frustration, disappointment, stress, joy, happiness, satisfaction, etc. For example, the agent training system can provide, as recommendations, sample responses to customer utterances that correspond to different emotional elements in the conversation. These sample responses may be generated to provide more positive emotional responses from the customer, which in turn may lead to improved customer feedback regarding the conversation. One or more recommendations can further provide instructions to the agent to utilize one or more automated tools to more efficiently handle a particular intent or issue. For example, if the customer intent is related to billing, the agent training system can recommend that the agent utilize an automated billing system to automatically address the customer intent.
[0090] In step 412, the agent training system can monitor the agent's compliance with the conditional logic and recommendations provided by the agent training system to the agent associated with the client. For example, the agent training system may assess the qualitative and quantitative aspects of the agent response before the agent response is presented. When the agent generates a response to a customer message to be presented, the agent training system (using machine learning algorithms or artificial intelligence) can evaluate the response in real time to determine whether all identified elements have been addressed in the response proposed by the agent. Furthermore, the agent training system may provide any feedback deemed necessary to improve the response according to the identified elements and the likelihood of a positive perception of the effort by the customer. Furthermore, the agent training system can evaluate the incoming data stream and/or conversation transcript of the communication session to determine whether the agent is following the recommendations and conditional logic provided by the agent training system. If the agent training system determines that the agent is not following the recommendations and conditional logic prepared by the agent training system, the agent training system can execute one or more corrective actions, such as sending a notification to the agent or the agent's supervisor indicating any necessary steps to be taken to improve the agent's performance.
FIG. 5 illustrates an illustrative example of a process 500 for generating a set of performance metrics and recommendations for improving or enhancing the set of performance metrics for a client, according to at least one embodiment. The process 500 may be performed by a performance monitoring system that may generate insights and recommendations for improving performance metrics associated with the client's agents. In step 502, the performance monitoring system obtains conversation data generated based on conversations between a customer and an agent associated with the client. The conversation data may include transcripts or other data corresponding to messages exchanged between the customer and the agent associated with the client over a period of time. For example, the conversation data for a particular conversation may include messages exchanged between the customer and one or more agents for resolution of an intent or other problem presented by the customer. Additionally, the conversation data may include any feedback provided by the customer regarding the performance of one or more agents with whom the customer may have interacted. The performance monitoring system may obtain the conversation data by accessing a conversation data repository or data store maintained by the client or other entity tasked with maintaining records associated with existing conversations between the customer and agents.
[0092] In step 504, the performance monitoring system may calculate one or more performance metrics (eg, KPIs) for the agents based on the evaluation of the conversation data.
As mentioned above, these performance metrics may correspond to a framework built on customer and client interests linked to effort, emotion, efficiency, and effectiveness. The performance metrics related to effort may correspond to the amount of effort required to address customer intent by an agent. Similarly, the performance monitoring system may determine the level of emotion among customers while engaged in a conversation with an agent to calculate an agent's emotion score. The performance monitoring system may further determine the agent's level of efficiency in handling customer intent or issues over time to calculate each agent's efficiency score by weighting the balance between available resources (e.g., agent availability, etc.) and demands (e.g., customer contacts with clients, etc.). The performance monitoring system may further provide a determination of the agent's level of effectiveness in addressing customer intent and issues utilizing available capabilities and tools.
[0093] In step 506, the performance monitoring system may generate one or more insights and/or recommendations based on the calculated performance metrics. For example, in one embodiment, the performance monitoring system may use a machine learning algorithm or artificial intelligence to automatically provide an assessment of all conversational behavior, which may lead to data-driven decision-making for improving agent performance. For example, the performance monitoring system may provide metrics and characteristics corresponding to conversations between agents and customers (e.g., conversation topics or intents, customer surveys or feedback, messaging rate metrics, agent availability metrics, metrics associated with the use of automation tools or capabilities, etc.), actual conversation transcripts, and the like, as inputs to the machine learning algorithm or artificial intelligence to obtain an assessment of agent performance and identify possible solutions or recommendations for improvement. The output of the machine learning algorithm or artificial intelligence may provide diagnostic information corresponding to a rationale for what happened or is happening. Additionally, the output may provide one or more recommendations on how to fix these issues to improve customer experience.
[0094] At step 508, the performance monitoring system generates one or more predictions corresponding to compliance with the insights and/or recommendations generated by the performance monitoring system. For example, using the machine learning algorithms or artificial intelligence described above, the performance monitoring system can provide one or more predictions regarding improvements in the agent's performance if the insights and/or recommendations described above are implemented. For example, the machine learning algorithms or artificial intelligence may indicate that metrics corresponding to effort, emotion, efficiency, and effectiveness could be improved by a certain margin if the provided recommendations are implemented. The machine learning algorithms or artificial intelligence may provide this prediction using numerical metric values (e.g., "efficiency will improve by 56%") and/or descriptive narratives (e.g., "agent efficiency should increase dramatically").
[0095] At step 510, the performance monitoring system may present the calculated performance metrics, insights and/or recommendations, and predictions via a dashboard or other interface accessible by the client. For example, via the dashboard, the client may be presented with such predictions along with descriptions of identified problems, diagnostic information explaining why those problems are occurring or have occurred, and recommendations for addressing those problems. Additionally, via the dashboard, the client may be presented with performance metrics across various intents, agent types, and/or business operations based on the client's desired presentation of the data.
[0096] Figure 6 illustrates an illustrative example of a process 600 for benchmarking a client's performance by comparing these performance metrics to targets and/or industry associations across various performance metrics, according to at least one embodiment. Process 600 can be performed by the performance monitoring system described above, which can obtain and process performance data corresponding to one or more targets and/or industry associations to provide additional insights and recommendations regarding the performance of an agent associated with the client. In step 602, the performance monitoring system can receive a request from a client to compare the client's performance across various performance metrics (e.g., KPIs) to one or more targets and/or industry associations. For example, via a dashboard or other interface provided by the performance monitoring system, the client can select one or more targets and/or industry associations for which the client would like to obtain a benchmark for its agent across one or more performance metrics. The one or more targets and/or industry associations may correspond to other clients of the performance monitoring system, as described herein, and other entities for which performance data may be available via one or more remote sources.
In step 604, the performance monitoring system may determine whether performance metrics for the selected targets and/or industry associations are available in a comparative data store of the performance monitoring system. For example, if the selected targets and/or industry associations are clients of the performance monitoring system, the performance monitoring system may retrieve performance metrics for these targets and/or industry associations from the comparative data store in step 610. Alternatively, if performance metrics for the selected targets and/or industry associations are not available via the comparative data store, the performance monitoring system may retrieve performance data associated with the selected targets and/or industry associations from one or more remote sources in step 606. These remote sources may include publications, third-party performance evaluators, or any other source to which the performance monitoring system may subscribe to retrieve performance data.
[0098] In step 608, the performance monitoring system may use the data obtained from the remote source to generate performance metrics for the selected targets and/or industry associations. For example, if the obtained performance metrics or other data associated with one or more targets and/or industry associations are not in a format conducive to providing benchmarking comparisons with the client's performance metrics, the performance monitoring system may use the performance evaluation subsystem to process the obtained performance metrics or other data to generate a new set of performance metrics for the one or more targets and/or industry associations that can be used for benchmarking purposes. In some examples, the performance monitoring system may anonymize the performance metrics of the selected targets and/or industry associations to obscure the source of these performance metrics.
[0099] In step 612, the performance monitoring system can compare the client's performance metrics with performance metrics of one or more targets and/or industry associations selected by the client according to one or more classifications. The one or more classifications can correspond to a particular intent, type of intent, and/or business, and the like. Furthermore, in step 614, the performance monitoring system can generate insights and/or recommendations based on the comparison of the aforementioned performance metrics. For example, the performance monitoring system can generate insights related to actions taken by one or more targets and/or industry associations selected by the client to achieve their corresponding performance metrics along different classifications. For example, the performance monitoring system can determine performance metrics for a particular target before execution of one or more actions (e.g., realizing an automated capability to identify customer intent and train agents to comply with recommendations from an agent training system) and performance metrics for the particular target after execution of the one or more actions for the particular target. In some examples, the performance monitoring system may generate insights regarding problems encountered by one or more targets and/or industry groups, why those problems were encountered, what actions were taken or recommended to address those problems, and the consequences resulting from the performance or omission of those actions.
At step 616, the performance monitoring system may present the comparison and any insights and/or recommendations generated by the performance monitoring system to the client via a dashboard or other interface. For example, the performance monitoring system may provide a comparison of the client's performance metrics to the performance metrics of the selected targets and/or industry associations via the dashboard. Similarly, the performance monitoring system may update the dashboard to provide insight into actions taken by one or more targets and/or industry associations to improve their performance metrics. As discussed above, information corresponding to the selected one or more targets and/or industry associations may be anonymized to ensure the privacy of the entities from whom the performance metrics were obtained and the known actions taken to improve the performance metrics.
[0101] Figure 7 illustrates an illustrative example of a user interface 700 for presenting a performance summary for a client based on one or more metrics, according to at least one embodiment. Through the user interface 700, a client can be presented with various performance metrics via a set of charts, graphs, or other graphical representations. In addition, these performance metrics may be categorized based on a behavioral model. For example, as illustrated in Figure 7, various performance metrics for a client may be categorized as part of an efficiency pillar, an effectiveness pillar, an effort pillar, and an emotion pillar. It should be noted that the categories presented in Figure 7 are for illustrative purposes, and that additional, fewer, or alternative categories may be implemented and presented via the user interface 700.
7, the performance monitoring system may provide a client, via a user interface 700, with one or more options for defining what data is presented to the client as well as the level of granularity for the presentation of the data. For example, the performance monitoring system may allow a client to select, via the user interface 700, business operations for which the client may want to obtain performance metrics, select a date range for the data to be presented via the user interface 700, and the level of granularity of the data to be presented within the specified date range (e.g., weekly or monthly, as illustrated in FIG. 7, or any other level of granularity).
[0103] The performance monitoring system may provide an overview of KPIs corresponding to the effort, sentiment, efficiency, and effectiveness pillars, as well as indicate (via graphs, tables, etc.) any changes to these KPIs over a specified date range indicated by the client. For example, as illustrated in FIG. 7, for the efficiency pillar, the performance monitoring system may indicate the current closed conversations by logged in hours (CCPLH) for a selected job. Additionally, the performance monitoring system may indicate any changes to the CCPLH over a specified date range to provide the client with an indication of any changes to the efficiency of the selected job over this specified date range. As another illustrative example, for the effectiveness pillar, the performance monitoring system may indicate the current recurring contact rate 3 days (RCR 3D) for a selected job. The RCR for the job may be The 3D may correspond to the percentage of closed conversations where the same customer identifier initiated a subsequent conversation between days 1 and 3. Similar to the graphical representation of CCPLH changes over a specified date range, the performance monitoring system may show any changes to the RCR 3D over a specified date range to provide the client with an indication of any changes to the effectiveness of the selected business in addressing customer intent or issues over this specified date range.
[0104] With respect to the effort pillar, the performance monitoring system may indicate the current recurring contact rate 1 hour (RCR 1 HR) for a selected job. The RCR 1 HR for a job may correspond to the percentage of closed conversations where the same customer identifier initiates a subsequent conversation within an hour. In contrast to the RCR 3D, the RCR 1 HR may serve as an indication of an agent's effort to address a customer's intent or problem in an appropriate manner to generate a positive resolution. As an illustrative example, if an agent terminates a conversation with a particular customer with little or no effort to resolve the customer's intent or problem, the likelihood that the customer will initiate a subsequent conversation within a short period of time for the same or similar intent or problem may be increased.
[0105] The sentiment pillars may be represented via the user interface 700 using Meaningful Conversation Scores (MCS), where the MCS represents an automated, real-time measurement of customer sentiment for closed conversations, including any unassigned conversations. In some examples, the MCS is attributed only to the last assigned agent in the conversation. In one embodiment, the performance monitoring system utilizes a machine learning algorithm or other artificial intelligence to determine the MCS for agents associated with the selected assignment. For example, the machine learning algorithm or other artificial intelligence may process conversation data corresponding to conversations between customers and agents to analyze the tone, content, and sentiment of the customers' actual conversations with these agents in real time. For example, the machine learning algorithm or other artificial intelligence may utilize natural language processing (NLP) to evaluate the conversations in real time and identify the tone, content, and sentiment behind each message exchanged during these conversations. Each message may be assigned an MCS, and the conversation MCS may be determined based on a combination of all message MCSs for the conversation. These scores may be aggregated to form the MCS for the selected assignment, which may be represented via the user interface 700.
In addition to providing performance metrics corresponding to the different performance pillars described above, the performance monitoring system may further provide, via the user interface 700, an opportunity panel. Through the opportunity panel, the performance monitoring system may rank primary and secondary performance metrics across different performance pillars based on deviation from an industry benchmark or target value (as defined by the client) and as determined by the metric configuration (benchmark or numerical target). In some instances, the performance metrics represented within the opportunity panel may be color coded by their respective performance pillar and then ranked based on which performance metric has the greatest deviation from a selected benchmark or numerical target. This may enable clients to focus on the most impactful performance metrics that will improve overall client performance in customer conversations.
[0107] In some instances, the performance monitoring system may allow clients to filter various performance metrics according to their corresponding performance pillars. For example, the performance monitoring system may provide a filter drop-down menu that may display multiple selection options that allow clients to choose which performance pillars to display in the opportunity panel. Additionally, the performance monitoring system may allow clients to select an individual bar that corresponds to a particular performance metric and automatically navigate to that performance metric within the performance pillar details section of the interface, as described in more detail herein.
[0108] The performance monitoring system may further provide, via the user interface 700, a controlled delivery panel through which each selected task is represented by a dot on a two-axis chart. The chart represented in the controlled delivery panel may compare overall scores for efficiency (e.g., performing in the best way with the least waste of resources) and effectiveness (e.g., ability to achieve the intended result that solves the customer's intent or problem) for each task. The overall score may be determined by a weighted score of all primary and secondary performance metrics within the performance metric categories for efficiency and effectiveness. Through the controlled delivery panel, the client may assess tasks on which to focus based on the location of those tasks in the chart. For example, tasks located in the upper right corner of the chart (e.g., high effectiveness and efficiency) may be very effective and efficient, while tasks located in the lower left corner of the chart may be very ineffective and inefficient. In some examples, if the client uses a cursor to hover over a particular data point in the chart, the performance monitoring system may present, via the user interface 700, the name of the task and the overall performance score for the task. Additionally, selection of a data point in the chart may cause the performance monitoring system to update the user interface 700 to present a performance summary details panel, as described in more detail herein.
FIG. 8 illustrates an illustrative example of a user interface 800 for presenting calculated scores corresponding to different performance metrics, according to at least one embodiment. Through the user interface 800, the performance monitoring system may provide a summary of performance metrics according to each of the performance pillars mentioned above (e.g., efficiency, effectiveness, effort, and emotion). For example, through the user interface 800, the performance monitoring system can generate a composite performance score for each of the performance pillars to provide the client with a summary regarding performance for each of the performance pillars. For each performance pillar, the performance monitoring system can incorporate all primary and secondary performance metrics associated with the performance pillar. Furthermore, the performance monitoring system can weight each of these performance metrics based on the impact level identified for each performance metric.
In one embodiment, the performance monitoring system provides, via the user interface 800, the client's performance relative to industry benchmarks for each of the performance pillars described above. For example, the performance monitoring system may display industry benchmarks in 25 percentile increments, thereby quantifying the client's performance relative to each performance pillar according to a particular industry benchmark quartile. In some cases, these percentile increments may be color coded, whereby red may be used to indicate quartiles below the 50th percentile and green may be used to indicate quartiles above the 50th percentile. Thus, the performance scores for each of the performance pillars may be adjusted or scaled according to the industry benchmarks to determine the client's performance relative to the industry benchmark. As an illustrative example, the client's performance score for the efficiency pillar may be assigned a value of 55% (as shown in FIG. 8), which may serve as an indication that the client is performing within the 50th to 75th percentile (third quartile) within a particular industry.
In addition to providing a performance score for each of the performance pillars, the performance monitoring system can provide any additional insight into the client's performance within each of the performance pillars. As described above, the performance monitoring system can generate various insights into agent performance that may be used to identify areas of improvement or enhancement for the agent associated with the client. For example, the performance monitoring system can utilize performance metrics calculated for the agent along with the conversation data to identify these areas of improvement or enhancement and provide any valuable insight into the client's conversational behavior. These areas of improvement/enhancement and insights may be generated according to each of the performance pillars represented in the user interface 800. Thus, the performance monitoring system can qualify the client's performance within the user interface 800 in addition to quantifying the client's performance along the various performance pillars against industry benchmarks.
[0112] Figure 9 illustrates an illustrative example of a user interface 900 for presenting insight into conversation volume closed by possible entry points, according to at least one embodiment. The user interface 900 can provide channel-specific views that enable clients to understand activity across various entry points (e.g., social media platforms, applications across different operating systems, etc.). For example, as illustrated in Figure 9, the performance monitoring system can provide a bar graph that displays the distribution of closed conversations across various entry points utilized by clients for conversations between customers and agents.
[0113] In addition to the bar graphs discussed above, the performance monitoring system can present to the client, via the user interface 900, a graphical representation of the amount of conversation closed over time for each of the entry points. For example, as illustrated in Figure 9, the performance monitoring system can generate a line graph that displays entry point volume over time according to each possible entry point utilized by the client.
FIG. 10 illustrates an illustrative example of a user interface 1000 for presenting various performance metrics for a particular job, according to at least one embodiment. The performance monitoring system can display various performance metrics corresponding to the aforementioned performance pillars via the user interface 1000. For example, the performance monitoring system can provide primary and secondary performance metrics corresponding to efficiency, effectiveness, effort, and emotion pillars. In some instances, the performance monitoring system can provide the client, via the user interface 1000, with one or more options for filtering the provided performance metrics. For example, the client can select to view performance metrics tied to a particular performance pillar. Alternatively, the client may select a particular performance metric to be displayed via the user interface 1000.
In one embodiment, the performance monitoring system can provide data corresponding to the performance of a particular client business against various benchmarks (e.g., performance against an industry benchmark), targets (e.g., target values, if defined by the client), and trends (e.g., upward or downward trends). The client can toggle through the user interface 1000 between selections corresponding to various options for displaying performance metrics against the benchmarks, targets, and/or trends. In some examples, the performance monitoring system can provide various default options for the presentation of performance metrics of a particular business. For example, the performance monitoring system can provide benchmark, actual, trend, and deviation values for each performance metric based on a filtered date range entered by the client (e.g., such as the date range defined and illustrated in FIG. 7 ).
[0116] FIG. 11 illustrates an illustrative example of a user interface 1100 for providing information usable to compare KPIs to industry benchmarks, according to at least one embodiment. Through the user interface 1100, the performance monitoring system can provide a vast amount of information to clients to enable them to compare performance metrics for each of the performance pillars described above. Through the user interface 1100, clients can compare the primary and secondary performance metrics for each of these performance pillars to industry benchmarks and/or targets. For example, as illustrated in FIG. 11, clients may be presented with the actual performance metric values for each performance pillar (presented using white numbers), how the client trended compared to the industry benchmarks (e.g., smaller values with upward or downward trend indicators), along with the variance of the client's performance against the industry benchmarks (expressed via percentages, showing the gap between what was expected and what occurred). Additionally, clients may be presented with minimum, maximum, and average values for their performance according to the corresponding performance metric, along with detailed trend lines for each performance metric, via the user interface 1100.
In one embodiment, the performance monitoring system further provides a diagnostic section via the user interface 1100. The diagnostic section of the user interface 1100 can provide a detailed description of the performance of the client's business. As described above, the performance monitoring system may use machine learning algorithms or artificial intelligence to automatically provide an assessment of the client's conversational behavior, which can lead to data-driven decision-making for the improvement of agent performance. For example, the performance monitoring system may provide metrics and characteristics corresponding to conversations between agents and customers (e.g., conversation topics or intents, customer surveys or feedback, messaging rate metrics, agent availability metrics, metrics associated with the use of automation tools or capabilities, etc.), actual conversation transcripts, and the like, as inputs to the machine learning algorithm or artificial intelligence to obtain an assessment of client performance and identify possible solutions or recommendations for improvement. The output of the machine learning algorithm or artificial intelligence can provide a description of what happened or is happening during the client's business that resulted in the current performance level. Additionally, the output of the machine learning algorithm or artificial intelligence can provide diagnostic information corresponding to the rationale for what happened or is happening.
[0118] The performance monitoring system, via the diagnostics section of user interface 1100, can contextualize a client's performance metric data according to various performance pillars and account configuration settings selected by the client to provide automated, customized recommendations to the client to improve performance based on a selected business and date range. In some examples, the performance monitoring system may provide diagnostic playbooks or other resources that include action steps that may be taken to improve client performance.
12 illustrates an illustrative example of a user interface 1200 for presenting recommendations and insights for one or more performance metrics, according to at least one embodiment. User interface 1200 may be accessed via a client interaction with user interface 1100 described above. For example, in one embodiment, the performance monitoring system may provide, via a diagnostic section of user interface 1100, an indication as to whether a particular performance metric may need improvement (e.g., the performance metric does not meet an acceptable threshold), is within acceptable parameters (e.g., the performance metric is within a range believed to correspond to an acceptable state), or is believed to be in a favorable state (e.g., the performance metric is within a range believed to correspond to a favorable state). In addition, the performance monitoring system may provide a header for each performance metric that may correspond to recommendations and insights for improvement of the performance metric.
[0120] In one embodiment, selection of the header causes the performance monitoring system to provide a user interface 1200 for the selected performance metric. For example, as shown in FIG. 12, the user interface 1200 may correspond to CCPLH performance metrics for a transaction selected by a client. Through the user interface 1200, the performance monitoring system can provide context regarding the selected performance metric. For example, the performance monitoring system can provide a definition for the selected performance metric and can provide insight into how the performance metric may impact the client's overall performance. For example, as shown in FIG. 12, the performance monitoring system can
[0121] Additionally, the performance monitoring system may provide one or more recommendations to improve metric performance. For example, as illustrated in FIG. 12 for the CCPLH metric, the performance monitoring system may indicate that the client should ensure that agents have sufficient volume to remain at a constant capacity, configure automation and processes to remove unnecessary management from agents, review conversation transcripts of higher performing agents to identify opportunities for improvement, and ensure that any system tools used by agents are optimized for asynchronous work. In addition to these recommendations, the performance monitoring system may provide additional insights regarding these recommendations. For example, as illustrated in FIG. 12, the performance monitoring system may indicate that agents should focus on providing holistic solutions with as few messages as possible, and that processes should be designed to allow as little reliance as possible on other departments or individuals to fully empower agents to resolve customer inquiries. Thus, the performance monitoring system may provide reinforcement regarding the provided recommendations to encourage compliance with these recommendations.
[0122] As described above, based on the insights and recommendations provided by the performance monitoring system and presented via user interface 1200, the client may request that the provided insights and recommendations be used by the agent training system to define a course of actions to be performed to accurately capture key elements expressed by customers in conversations with agents and identify the best way to respond appropriately to the customers. Based on the insights and recommendations provided by the performance monitoring system, the agent training system may identify what actions can be taken to address these elements to enable agents to meet customer intents and expectations according to the generated insights and recommendations.
[0123] Figure 13 shows an illustrative example of a user interface 1300 for presenting data corresponding to closed conversations and agent login times over a specified date range, according to at least one embodiment. Through the user interface 1300, the performance monitoring system may present trends related to available client resources (e.g., agent availability, etc.) and demand for clients (e.g., volume of closed conversations, etc.). Through the user interface 1300, a client may view the volume of closed conversations (e.g., by agent, customer, or auto-closure) and agent login times over a date range specified by the client (such as through the user interface 700 described above). Correlations between agent login times and volume of closed conversations over the same period can be used by the client to optimize the client's agent staffing and/or implement automated tools (e.g., bots, etc.) to address spikes in demand over time.
[0124] Figure 14 shows an illustrative example of a user interface 1400 for displaying configuration settings that can drive client performance, according to at least one embodiment. As illustrated in Figure 14, the account configurations may include auto-terminate time, inactivity time, smart capacity min, and smart capacity max. Values for each of these settings may be defined by the client via the user interface 1400. These settings may be used to determine the impact of agent performance on each of the performance pillars. For example, the auto-terminate time setting may potentially impact performance metrics associated with the effort pillars measured in a conversation. In addition to these account configurations, the performance monitoring system may provide a chart or other graphical representation of the distribution of agent max slots.
FIG. 15 illustrates a computing system architecture 1500 including various components that communicate electrically with each other using a connection 1506, such as a bus, according to some implementations. The exemplary system architecture 1500 includes a processing unit (CPU or processor) 1504 and a system connection 1506 that couples various system components, including a system memory 1520, such as a ROM 1518 and a RAM 1516, to the processor 1504. The system architecture 1500 may include a cache 1502 of high-speed memory that is directly connected to, adjacent to, or integrated as part of the processor 1504. The system architecture 1500 may copy data from the memory 1520 and/or storage device 1508 to the cache 1502 for quick access by the processor 1504. In this manner, the cache provides a performance boost that avoids the processor 1504 being delayed while waiting for data. These and other modules can control or be configured to control the processor 1504 to perform various actions.
[0126] Other system memory 1520 may also be available for use. Memory 1520 may include multiple different types of memory with different performance characteristics. Processor 1504 may include any general purpose processor, as well as hardware or software services, such as service 1 1510, service 2 1512, and service 3 1514, stored in storage device 1508 and configured to control processor 1504, as well as special purpose processors where software instructions are embedded in the actual processor design. Processor 1504 may be a completely self-contained computing system, including multiple cores or processors, buses, memory controllers, caches, etc. Multi-core processors may be symmetric or asymmetric.
[0127] To enable user interaction with the computing device 1500, the input device 1522 may represent any number of input mechanisms, such as a microphone for speech, a touch-sensitive screen for gesture or graphic input, a keyboard, a mouse, motion input, speech, and the like. The output device 1524 may also be one or more of several output mechanisms known to those skilled in the art. In some cases, a multimodal system may enable a user to provide multiple types of input to communicate with the computing system architecture 1500. The communication interface 1526 may generally govern and manage user input and system output. There is no restriction to operating on any particular hardware configuration, and thus the basic functions herein may be easily replaced with improved hardware or firmware configurations as they are deployed.
[0128] The storage device 1508 is a non-volatile memory and may be a hard disk or other type of computer-readable medium capable of storing data that is accessible by a computer, such as a magnetic cassette, a flash memory card, a solid-state memory device, a digital versatile disk, a cartridge, RAM 1516, ROM 1518, and hybrids thereof.
[0129] The storage device 1508 can include services 1510, 1512, 1514 for controlling the processor 1504. Other hardware or software modules are contemplated. The storage device 1508 can be connected to a system connection 1506. In one aspect, a hardware module that performs a particular function can include a software component stored in a computer readable medium in association with the necessary hardware components, such as the processor 1504, the connection 1506, the output device 1524, etc., to perform that function.
FIG. 16 illustrates an illustrative example of an environment 1600 in which various embodiments can be contemplated. In the environment 1600, an analyze-identify-respond (AIR) framework is presented that incorporates the intent processing system and the performance monitoring system described above in connection with FIGs. 1 and 2. Through the AIR framework, responses to customer intents can be generated and the performance of agents responding to the intents can be evaluated to determine their effectiveness in providing a positive customer experience. As described above, the performance monitoring system can provide feedback on agent performance to different entities within the customer service call center (e.g., trainers, team managers, quality assurance teams, leadership personnel, etc.), which allows these entities to coach agents on how to best respond to customers or perform other corrective tasks.
[0131] The evaluations performed through the AIR framework may be used to generate a set of metrics and other performance data for the client that can be compiled within a 4E (Effectiveness, Effort, Emotion, Efficiency) framework. Through the 4E framework, the client may be presented with a user interface, such as that described above in connection with Figures 7 through 14, through which the client may obtain these various metrics and other performance data about the client and other clients. This allows the client to determine how its agent is performing overall and compare its performance to that of other clients. This can help the client define possible avenues for improvement.
[0132] The disclosed methods can be performed using a computing system. An example computing system can include a processor (e.g., a central processing unit), a memory, a non-volatile memory, and an interface device. The memory may store data and/or one or more sets of code, software, scripts, etc. The components of the computer system can be coupled to each other via a bus or through some other known or convenient device. The processor may be configured to perform all or part of the methods described herein, for example, by executing code stored in the memory. One or more of the user device or computer, the provider server or system, or the suspended database update system may include components of a computing system or variations of such systems.
[0133] The present disclosure contemplates a computer system taking any suitable physical form, including, but not limited to, a point-of-sale system ("POS"). By way of example and not limitation, a computer system may be an embedded computer system, a system-on-chip (SOC), a single-board computer system (SBC) (e.g., a computer-on-module (COM) or system-on-module (SOM)), a desktop computer system, a laptop or notebook computer system, an interactive kiosk, a mainframe, a mesh of computer systems, a mobile phone, a personal digital assistant (PDA), a server, or a combination of two or more of these. Where appropriate, a computer system may include one or more computer systems; may be single or distributed; may span multiple locations; may span multiple machines; and/or may reside in a cloud that may include one or more cloud components in one or more networks. Where appropriate, one or more computer systems may perform one or more steps of one or more methods described or illustrated herein without substantial spatial or temporal limitations. By way of example, and not limitation, one or more computer systems may perform one or more steps of one or more methods described or illustrated herein in real time or in batch mode. One or more computer systems may, where appropriate, perform one or more steps of one or more methods described or illustrated herein at different times or in different locations.
[0134] The processor may be, for example, a conventional microprocessor such as an Intel Pentium microprocessor or a Motorola Power PC microprocessor. Those skilled in the art will recognize that the terms "machine-readable (storage) medium" or "computer-readable (storage) medium" include any type of device that can be accessed by a processor.
[0135] The memory may be coupled to the processor by, for example, a bus. The memory may include, by way of example and not limitation, random access memory (RAM), such as dynamic RAM (DRAM) and static RAM (SRAM). The memory may be local, remote, or distributed.
[0136] The bus may also couple the processor to non-volatile memory and drive units. Non-volatile memory is often a magnetic floppy or hard disk, a magneto-optical disk, an optical disk, a CD-ROM, a read-only memory (ROM) such as an EPROM or EEPROM, a magnetic or optical card, or another form of storage for large amounts of data. Some of this data is often written to the memory by a direct memory access process during the execution of software in the computer. Non-volatile storage may be local, remote, or distributed. Non-volatile memory is optional, since the system can be created with all applicable data available in memory. A typical computer system will usually include at least a processor, a memory, and a device (e.g., a bus) that couples the memory to the processor.
[0137] The software can be stored in a non-volatile memory and/or a drive unit. In fact, for large programs, it may not even be possible to store the entire program in memory. It should be understood, however, that in order to execute the software, it is moved, if necessary, to a computer-readable location suitable for processing, and for purposes of illustration, that location is referred to herein as memory. Even when the software is moved to memory for execution, the processor can utilize hardware registers to store values associated with the software, and ideally a local cache, which serves to speed up execution. As used herein, a software program is assumed to be stored in any known or convenient location (from non-volatile storage to hardware registers) when the software program is referred to as being "embodied in a computer-readable medium." A processor is considered to be "configured to execute a program" when at least one value associated with the program is stored in a register readable by the processor.
[0138] The bus may also couple the processor to a network interface device. The interface may include one or more of a modem or a network interface. It will be understood that the modem or network interface may be considered to be part of the computer system. The interface may include an analog modem, an integrated services digital network (ISDN0 modem, a cable modem, a token ring interface, a satellite transmission interface (e.g., "Direct PC"), or other interface for coupling the computer system to other computer systems. The interface may include one or more input and/or output (I/O) devices. The I/O devices may include, by way of example and not limitation, a keyboard, a mouse or other pointing device, disk drives, printers, scanners, and other input and/or output devices including display devices. The display devices may include, by way of example and not limitation, a cathode ray tube (CRT), a liquid crystal display (LCD), or any other applicable known or convenient display device.
[0139] In operation, a computer system may be controlled by operating system software, including a file management system, such as a disk operating system. One example of operating system software having associated file management system software is the family of operating systems known as Windows® from Microsoft Corporation of Redmond, Washington, and their associated file management systems. Another example of operating system software having associated file management system software is the Linux® operating system and its associated file management system. The file management system may be stored in non-volatile memory and/or drive units and may cause a processor to perform various operations required by the operating system to input and output data and store data in memory, including storing files in the non-volatile memory and/or drive units.
[0140] Some portions of the detailed descriptions which follow may be presented in terms of algorithms and symbolic representations of operations on data bits within a computer memory. These algorithmic descriptions and representations are the means used by those skilled in the data processing arts to most effectively convey the substance of their work to others skilled in the art. An algorithm is here, and generally, conceived to be a self-consistent sequence of operations leading to a desired result. The operations require physical manipulations of physical quantities. Usually, though not necessarily, these quantities take the form of electrical or magnetic signals capable of being stored, transferred, combined, compared, or otherwise manipulated. It has proven convenient at times, principally for reasons of common usage, to refer to these signals as bits, values, elements, symbols, characters, terms, numbers, or the like.
[0141] It should be noted, however, that all of these and similar terms are to be associated with the appropriate physical quantities and are merely convenient labels applied to these quantities. As will be apparent from the discussion below, unless specifically stated otherwise, throughout this application, discussions utilizing terms such as "processing," or "calculating," or "determining," or "displaying," or "generating," or the like, are understood to refer to the actions and processing of a computer system or similar electronic computing device that manipulates and converts data, represented as physical (electronic) quantities in the computer system's registers and memory, into other data, similarly represented as physical quantities in the computer system's memory or registers, or other such information storage, transmission, or display device.
[0142] The algorithms and displays presented herein are not inherently related to any particular computer or other apparatus. Various general-purpose systems may be used with programs in accordance with the teachings herein, or it may prove convenient to construct a more specialized apparatus to perform some of the example methods. The required structure for a variety of these systems will appear from the description below. In addition, the technology is not described with reference to any particular programming language, and thus the various examples may be implemented using a variety of programming languages.
[0143] In various implementations, the system may operate as a stand-alone device or may be connected (e.g., networked) to other systems. In a networked deployment, the system may operate in the capacity of a server or a client system in a client-server network environment, or as a peer system in a peer-to-peer (or distributed) network environment.
[0144] The system may be a server computer, a client computer, a personal computer (PC), a tablet PC, a laptop computer, a set-top box (STB), a personal digital assistant (PDA), a cellular telephone, an iPhone®, a Blackberry®, a processor, a telephone, a web appliance, a network router, switch or bridge, or any system capable of executing a set of instructions (sequential or otherwise) that specify actions to be taken by the system.
[0145] Although a machine-readable medium or machine-readable storage medium is shown as being a single medium by way of example, the terms "machine-readable medium" and "machine-readable storage medium" should be interpreted to include a single medium or multiple media (e.g., a centralized or distributed database and/or associated caches and servers) that store one or more sets of instructions. The terms "machine-readable medium" and "machine-readable storage medium" should also be interpreted to include any medium capable of storing, encoding, or carrying a set of instructions for execution by a system, causing the system to perform any one or more of the methodologies or modules disclosed herein.
[0146] In general, the routines executed to realize an implementation of the present disclosure may be realized as part of an operating system or a specific application, component, program, object, module, or sequence of instructions referred to as a "computer program." A computer program is typically stored at various times in various memory and storage devices within a computer, and includes one or more instructions that, when read and executed by one or more processing units or processors within the computer, cause the computer to perform operations to implement elements including various aspects of the present disclosure.
[0147] Moreover, while the examples have been described in the context of fully functional computers and computer systems, those skilled in the art will appreciate that the various examples may be distributed as program objects in a variety of forms, and that the present disclosure applies equally regardless of the particular type of machine or computer-readable medium used to actually affect the distribution.
[0148] Further examples of machine-readable storage media, machine-readable media, or computer-readable (storage) media include, but are not limited to, recordable-type media such as volatile and non-volatile memory devices, floppy and other removable disks, hard disk drives, optical disks (e.g., Compact Disk Read Only Memory (CD ROM), Digital Versatile Disks (DVD), etc.), and transmission-type media such as digital and analog communications links, among others.
[0149] In some circumstances, an operation of a memory device, such as a change in state from a binary 1 to a binary 0 or vice versa, may comprise a transformation, such as, for example, a physical transformation. In certain types of memory devices, such a physical transformation may comprise a physical transformation of an article to a different state or thing. For example, but not by way of limitation, for some types of memory devices, a change in state may involve the accumulation and storage of an electric charge, or the release of a stored electric charge. Similarly, in other memory devices, a change in state may comprise a physical change, or a change in magnetic orientation, or a physical change or transformation of a molecular structure, such as from crystalline to amorphous, or vice versa. The foregoing is not intended to be an exhaustive list of all examples in which a change in state from a binary 1 to a binary 0, or vice versa, in a memory device may comprise a transformation, such as a physical transformation. Rather, the foregoing is intended as an illustrative example.
[0150] A storage medium may typically be non-transient or may comprise a non-transient device. In this context, a non-transient storage medium may include a device that is tangible, meaning that the device has a tangible physical form, although the device can change its physical state. Thus, for example, non-transient refers to a device that remains tangible despite this change in state.
[0151] The above description and drawings are illustrative and should not be construed as limiting the subject matter to the precise form disclosed. Those skilled in the art may appreciate that many modifications and variations are possible in light of the above disclosure. Many specific details are described to provide a thorough understanding of the present disclosure. However, in certain instances, well-known or conventional details are not described in order to avoid obscuring the description.
[0152] As used herein, the terms "connected," "coupled," or any variation thereof, when applied to modules of a system, means any direct or indirect connection or coupling between two or more elements, where the coupling of connections between elements may be physical, logical, or any combination thereof. In addition, the terms "herein," "above," "below," and terms of similar import, when used in this application, shall refer to this application as a whole and not to any particular portions of this application. Where the context permits, terms in the above Detailed Description using singular or plural numbers may also include plural or singular numbers, respectively. The term "or" in reference to a list of two or more items encompasses all of the following interpretations of that term: any of the items in the list, all of the items in the list, or any combination of the items in the list.
[0153] Those skilled in the art will appreciate that the disclosed subject matter may be embodied in other forms and manners not set forth below. It will be understood that the use of related terminology, if any, such as first, second, top and bottom, and the like, is only used to distinguish one entity or action from another, without necessarily requiring or implying any such actual relationship or order between such entities or actions.
[0154] Although processes or blocks are presented in a given order, alternative implementations may perform routines having steps or use systems having blocks in a different order, and some processes or blocks may be deleted, moved, added, sub-divided, substituted, combined, and/or modified to provide alternatives or sub-combinations. Each of these processes or blocks may be implemented in a variety of different ways. Also, while processes or blocks are at times shown as being performed sequentially, these processes or blocks may instead be performed in parallel or at different times. Additionally, any specific numbers referred to herein are examples only, and alternative implementations may employ different values or ranges.
[0155] The teachings of the disclosure provided herein may be applied to other systems, not necessarily the system described above. Elements and operations of the various examples described above may be combined to provide further examples.
[0156] Any of the above patents and applications and other references, including any that may be listed in accompanying application documents, are incorporated herein by reference. Aspects of the present disclosure can be modified, if necessary, to employ the systems, functions, and concepts of the various references described above to provide still further examples of the present disclosure.
[0157] These and other changes can be made to the present disclosure in light of the above detailed description. Although the above description describes certain examples and describes the best mode contemplated, no matter how detailed the above may be in the text, the present teachings may be practiced in many ways. The details of the system may vary widely in their implementation details while still being encompassed by the subject matter disclosed herein. As also noted above, it should be noted that a particular term used when describing a particular feature or aspect of the present invention should not be taken to imply that the term is redefined herein to be limited to any particular characteristic, feature, or aspect of the present disclosure with which the term is associated. In general, the terms used in the following claims should not be construed to limit the disclosure to the particular implementations disclosed herein, unless the detailed description section above explicitly defines such terms. Thus, the actual scope of the present disclosure encompasses not only the disclosed implementations, but also all equivalent ways of practicing or implementing the present disclosure under the scope of the claims.
[0158] Although some aspects of the disclosure are presented below in some claim form, the inventors contemplate various aspects of the disclosure in any number of claim forms. Any claim intended to be treated under 35 U.S.C. § 142(f) will be prefaced with the words "means for." Accordingly, the applicants reserve the right to add additional claims after filing to pursue such additional claim forms for other aspects of the disclosure.
[0159] The terms used herein generally have their ordinary meaning in the art, within the context of this disclosure and in the specific context in which each term is used. Certain terms used to describe this disclosure have been explained above or elsewhere in this specification to provide additional guidance to the practitioner regarding the description of this disclosure. For convenience, certain terms may be highlighted, for example, using capital letters, italics, and/or quotation marks. The use of highlighting does not affect the scope and meaning of the term, which is the same in the same context whether or not it is highlighted. It will be understood that the same element can be described in more than one way.
[0160] Thus, alternative language and synonyms may be used for any one or more of the terms discussed herein, and no special importance is placed on whether a term is recited or discussed herein. Synonyms of certain terms are provided. The recitation of one or more synonyms does not preclude the use of other synonyms. The use of examples anywhere in this specification, including examples of any term described herein, is merely illustrative and is not intended to further limit the scope and meaning of the disclosure or of any exemplified term. Similarly, the disclosure is not limited to the various examples provided herein.
[0161] Without intending to further limit the scope of the present disclosure, examples of instruments, devices, methods, and their related results according to the examples of the present disclosure are given below. Please note that titles or subtitles may be used in the examples for the convenience of the reader, but this should not limit the scope of the present disclosure in any way. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this disclosure pertains. In the event of any conflict, the present document, including definitions, shall prevail.
[0162] Some portions of this description describe examples in terms of algorithms and symbolic representations of operations on information. These algorithmic descriptions and representations are commonly used by those skilled in the data processing arts to most effectively convey the substance of their work to others skilled in the art. While these operations have been described in functional, computational, or logical terms, it will be understood that they may be implemented by computer programs or equivalent electrical circuits, microcode, or the like. Further, it has been found convenient at times to refer to these arrangements of operations as modules, without loss of generality. The described operations and their associated modules may be embodied in software, firmware, hardware, or any combination thereof.
[0163] Any of the steps, operations, or processes described herein may be performed or realized using one or more hardware or software modules, alone or in combination with other devices. In some examples, software modules are realized using computer program objects comprising a computer-readable medium containing computer program code that can be executed by a computer processor to perform any or all of the described steps, operations, or processes.
[0164] Examples may also relate to an apparatus for performing the operations herein. This apparatus may be specially constructed for the required purposes and/or may comprise a general-purpose computing device selectively activated or reconfigured by a computer program stored in the computer. Such computer programs may be stored in a non-transitory, tangible computer-readable storage medium, which may be coupled to a computer system bus, or in any type of medium suitable for storing electronic instructions. Furthermore, any computing system referred to herein may include a single processor or may be an architecture employing a multiple processor design to increase computing power.
[0165] Examples may also relate to objects generated by the computing processes described herein. Such objects may comprise information resulting from the computing processes, where the information is stored on a non-transitory, tangible computer-readable storage medium, and may include any implementation of a computer program object or other data combination described herein.
[0166] The language used herein has been selected primarily for ease of reading and instructional purposes, and not to specifically delineate or limit the subject matter. Accordingly, the scope of the disclosure is intended to be limited not by this detailed description, but by any claims issued on an application based hereon. Accordingly, the disclosure of the examples is intended to be illustrative, but not limiting, of the scope of the subject matter described in the following claims.
[0167] Specific details have been provided in the above description to provide a thorough understanding of various implementations of systems and components for the context-connected system. However, it should be understood by those skilled in the art that these implementations may be practiced without these specific details. For example, circuits, systems, networks, processes, and other components may be shown as components in block diagram form so as not to obscure the embodiments with unnecessary detail. In other examples, well-known circuits, processes, algorithms, structures, and techniques may be shown without unnecessary detail so as to avoid obscuring the embodiments.
[0168] It should also be noted that the individual implementations may be described as a process that is depicted as a flowchart, a flow diagram, a data flow diagram, a structure diagram, or a block diagram. Although a flowchart may describe operations as a sequential process, many of the operations may be performed in parallel or simultaneously. Additionally, the order of operations may be rearranged. A process terminates when its operations are completed, but may have additional steps not included in the drawings. A process may correspond to a method, a function, a procedure, a subroutine, a subprogram, etc. When a process corresponds to a function, its termination may correspond to the invocation of the function or a return of the function to the main function.
[0169] Client devices, network devices, and other devices may be computing systems that include, among other things, one or more integrated circuits, input devices, output devices, data storage devices, and/or network interfaces. Integrated circuits may include, for example, one or more processors, volatile memory, and/or non-volatile memory, among other things. Input devices may include, for example, keyboards, mice, keypads, touch interfaces, microphones, cameras, and/or other types of input devices. Output devices may include, for example, display screens, speakers, haptic feedback systems, printers, and/or other types of output devices. Data storage devices, such as hard drives or flash memory, may enable computing devices to store data temporarily or permanently. Network interfaces, such as wireless or wired interfaces, may enable computing devices to communicate with a network. Examples of computing devices include desktop computers, laptop computers, server computers, handheld computers, tablets, smartphones, personal digital assistants, digital home assistants, as well as machines and equipment in which computing devices are embedded.
[0170] The term "computer-readable medium" includes, but is not limited to, portable or non-portable storage devices, optical storage devices, and various other media capable of storing, containing, or transporting instructions and/or data. Computer-readable media may also include non-transitory media on which data may be stored and does not include carrier waves and/or transitory electronic signals propagating wirelessly or over wired connections. Examples of non-transitory media may include, but are not limited to, magnetic disks or tapes, optical storage media such as compact disks (CDs) or digital versatile disks (DVDs), flash memory, memory or memory devices. A computer-readable medium may store code and/or machine-executable instructions, which may represent a procedure, a function, a subprogram, a program, a routine, a subroutine, a module, a software package, a class, or any combination of instructions, data structures, or program statements. A code segment may be coupled to another code segment or a hardware circuit by passing and/or receiving information, data, arguments, parameters, or memory contents. Information, arguments, parameters, data, etc. may be passed, forwarded, or transmitted via any suitable means including memory sharing, message passing, token passing, network transmission, or the like.
[0171] Furthermore, the various examples described above may be implemented by hardware, software, firmware, middleware, microcode, hardware description languages, or any combination thereof. When implemented in software, firmware, middleware, or microcode, the program code or code segments (e.g., computer program product) to perform the necessary tasks may be stored in a computer-readable or machine-readable medium (e.g., a medium for storing program code or code segments). A processor implemented in an integrated circuit may perform the necessary tasks.
[0172] When a component is described as being "configured to" perform a particular operation, such configuration may be achieved, for example, by designing electronic circuitry or other hardware to perform the operation, by programming a programmable electronic circuitry (e.g., a microprocessor or other suitable electronic circuitry) to perform the operation, or any combination thereof.
[0173] The various example logic blocks, modules, circuits, and algorithm steps described in connection with the implementations disclosed herein may be implemented as electronic hardware, computer software, firmware, or combinations thereof. To clearly illustrate this interchangeability of hardware and software, the various example components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the particular application and design constraints imposed on the overall system. Those skilled in the art may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.
[0174] The techniques described herein may also be implemented in electronic hardware, computer software, firmware, or any combination thereof. Such techniques may be implemented in any of a variety of devices, such as a general purpose computer, a wireless communication device handset, or an integrated circuit device having multiple uses, including applications in wireless communication device handsets and other devices. Any features described as modules or components may be implemented together in an integrated logic device, or separately as discrete but interoperable logic devices. If implemented in software, the techniques may be realized at least in part by a computer-readable data storage medium comprising program code including instructions that, when executed, perform one or more of the methods described above. The computer-readable data storage medium may form part of a computer program product, which may include packaging materials. The computer readable medium may comprise a memory or data storage medium such as random access memory (RAM), such as synchronous dynamic random access memory (SDRAM), read only memory (ROM), non-volatile random access memory (NVRAM), electrically erasable programmable read only memory (EEPROM), FLASH memory, magnetic or optical data storage media, and the like. The technology may additionally or alternatively be embodied at least in part by a computer readable communications medium that carries or communicates program code in the form of instructions or data structures and that can be accessed, read, and/or executed by a computer, such as a propagated signal or wave.
[0175] The program code may be executed by a processor, which may include one or more processors, such as one or more digital signal processors (DSPs), general purpose microprocessors, application specific integrated circuits (ASICs), field programmable logic arrays (FPGAs), or other equivalent integrated circuits or discrete logic circuits. Such a processor may be configured to perform any of the techniques described in this disclosure. A general purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration. Thus, as used herein, the term "processor" may refer to any of the foregoing structures, any combination of the foregoing structures, or any other structure or device suitable for implementing the techniques described herein. Additionally, in some aspects, the functionality described herein may be provided within dedicated software or hardware modules configured for implementation of a suspended database update system.
[0176] The foregoing detailed description of the technology has been presented for purposes of illustration and description. It is not intended to be exhaustive or to limit the technology to the precise form disclosed. Many modifications and variations are possible in light of the above teachings. The described embodiments were chosen to best explain the principles of the technology, its practical application, and to enable others skilled in the art to utilize the technology in various embodiments and with various modifications suitable to the particular uses contemplated. It is intended that the scope of the technology be defined by the claims.
<u style="Single"> The following is a summary of the claims as originally filed:</u><u style="Single">[C1]</u><u style="Single"> 1. A computer-implemented method comprising:</u><u style="Single"> acquiring conversation data, the conversation data corresponding to one or more conversations between a customer and a client agent, the one or more conversations corresponding to a set of intents;</u><u style="Single"> identifying explicit and implicit elements of said set of intents;</u><u style="Single"> determining a set of contexts from the set of intents, the set of contexts being determined based on the explicit elements, the implicit elements, and the one or more conversations between the customer and the agent;</u><u style="Single"> training a machine learning algorithm, the machine learning algorithm being trained using the set of contexts, the explicit elements, the implicit elements, and the one or more conversations between the customer and the agent, the machine learning algorithm being trained to generate a set of executable actions to improve agent response to new intents;</u><u style="Single"> receiving new conversation data corresponding to the new conversation;</u><u style="Single"> identifying actions that can be taken to improve agent response to new intents associated with the new conversation, the actions being identified using the new conversation data and the machine learning algorithm;</u><u style="Single"> generating one or more recommendations corresponding to the action, the one or more recommendations being presented to address the new intent associated with the new conversation;</u><u style="Single"> and dynamically monitoring compliance with the one or more recommendations in real time.</u><u style="Single">[C2]</u><u style="Single"> The computer-implemented method of C1, wherein the one or more recommendations include conditional logic, the conditional logic being executable to contextualize new explicit elements and new implicit elements to address the new intent associated with the new conversation.</u><u style="Single">[C3]</u><u style="Single"> 2. The computer-implemented method of claim 1, wherein dynamically monitoring compliance with the one or more recommendations includes processing a data stream of a new conversation between a customer and an agent, the data stream being processed in real time during the new conversation, and the agent responses from the data stream being evaluated in real time to determine whether the agent is in compliance with the one or more recommendations.</u><u style="Single">[C4]</u><u style="Single"> 2. The computer-implemented method of claim 1, wherein dynamically monitoring compliance with the one or more recommendations includes providing feedback to the agent, the feedback being provided based on an evaluation of an agent's response in accordance with the one or more recommendations.</u><u style="Single">[C5]</u><u style="Single"> The computer-implemented method of C1, wherein dynamically monitoring compliance with the one or more recommendations includes determining emotions from new conversations, the emotions being evaluated to determine whether agent responses in the new conversation comply with the one or more recommendations.</u><u style="Single">[C6]</u><u style="Single"> 3. The computer-implemented method of claim 1, further comprising generating a set of performance metrics corresponding to the agent, the set of performance metrics corresponding to a performance of the agent in addressing the set of intents and emotions of the customer.</u><u style="Single">[C7]</u><u style="Single"> 3. The computer-implemented method of claim 1, further comprising obtaining feedback corresponding to the conversation, the feedback being processed to identify the set of actions that can be taken to improve the agent response to the new intent.</u><u style="Single">[C8]</u><u style="Single"> 2. The computer-implemented method of claim 1, further comprising using data corresponding to a new set of context, new explicit elements, new implicit elements, the new conversation, and compliance with the one or more recommendations to further train the machine learning algorithm.</u><u style="Single">[C9]</u><u style="Single"> 1. A system comprising:</u><u style="Single"> one or more processors;</u><u style="Single"> and a memory storing instructions that, when executed by the one or more processors, cause the system to:</u><u style="Single"> acquiring conversation data corresponding to one or more conversations between a customer and a client agent, the one or more conversations corresponding to a set of intents;</u><u style="Single"> identifying explicit and implicit elements of said set of intents;</u><u style="Single"> determining a set of contexts from the set of intents, the set of contexts being determined based on the explicit elements, the implicit elements, and the one or more conversations between the customer and the agent;</u><u style="Single"> training a machine learning algorithm, the machine learning algorithm being trained using the set of context, the explicit elements, the implicit elements, and the one or more conversations between the customer and the agent, the machine learning algorithm being trained to generate a set of executable actions to improve agent response to new intent;</u><u style="Single"> receiving new conversation data corresponding to the new conversation;</u><u style="Single"> identifying actions that can be taken to improve an agent response to new intent associated with the new conversation, the actions being identified using the new conversation data and the machine learning algorithm;</u><u style="Single"> generating one or more recommendations corresponding to the action, the one or more recommendations being presented to address the new intent associated with the new conversation;</u><u style="Single"> The system dynamically monitors compliance with the one or more recommendations in real time.</u><u style="Single">[C10]</u><u style="Single"> The system of C9, wherein the one or more recommendations include conditional logic, the conditional logic being executable to contextualize new explicit elements and new implicit elements to address the new intent associated with the new conversation.</u><u style="Single">[C11]</u><u style="Single"> The system of claim 9, wherein the instructions for causing the system to dynamically monitor compliance with the one or more recommendations further cause the system to process a data stream of a new conversation between a customer and an agent, the data stream being processed in real time during the new conversation, and the agent responses from the data stream being evaluated in real time to determine whether the agent is in compliance with the one or more recommendations.</u><u style="Single">[C12]</u><u style="Single"> The system of C9, wherein the instructions for causing the system to dynamically monitor compliance with the one or more recommendations further cause the system to provide feedback to the agent, the feedback being provided based on an evaluation of an agent's response in accordance with the one or more recommendations.</u><u style="Single">[C13]</u><u style="Single"> The system of C9, wherein the instructions for causing the system to dynamically monitor compliance with the one or more recommendations further cause the system to determine a sentiment from a new conversation, the sentiment being evaluated to determine whether an agent response in the new conversation complies with the one or more recommendations.</u><u style="Single">[C14]</u><u style="Single"> 9. The system of claim 8, wherein the instructions further cause the system to generate a set of performance metrics corresponding to the agent, the set of performance metrics corresponding to a performance of the agent in addressing the set of intents and emotions of the customer.</u><u style="Single">[C15]</u><u style="Single"> 9. The system of claim 8, wherein the instructions further cause the system to obtain feedback corresponding to the conversation, the feedback being processed to identify the set of actions that can be taken to improve the agent response to the new intent.</u><u style="Single">[C16]</u><u style="Single"> 9. The system of claim 8, wherein the instructions further cause the system to use data corresponding to a new set of context, new explicit elements, new implicit elements, the new conversation, and compliance with the one or more recommendations to further train the machine learning algorithm.</u><u style="Single">[C17]</u><u style="Single"> A non-transitory computer-readable storage medium having executable instructions stored thereon,</u><u style="Single"> The executable instructions, when executed by one or more processors of a computer system, cause the computer system to:</u><u style="Single"> acquiring conversation data corresponding to one or more conversations between a customer and a client agent, the one or more conversations corresponding to a set of intents;</u><u style="Single"> identifying explicit and implicit elements of said set of intents;</u><u style="Single"> determining a set of contexts from the set of intents, the set of contexts being determined based on the explicit elements, the implicit elements, and the one or more conversations between the customer and the agent;</u><u style="Single"> training a machine learning algorithm, the machine learning algorithm being trained using the set of context, the explicit elements, the implicit elements, and the one or more conversations between the customer and the agent, the machine learning algorithm being trained to generate a set of executable actions to improve agent response to new intent;</u><u style="Single"> receiving new conversation data corresponding to the new conversation;</u><u style="Single"> identifying actions that can be taken to improve an agent response to new intent associated with the new conversation, the actions being identified using the new conversation data and the machine learning algorithm;</u><u style="Single"> generating one or more recommendations corresponding to the action, the one or more recommendations being presented to address the new intent associated with the new conversation;</u><u style="Single"> A non-transitory computer-readable storage medium that causes compliance with the one or more recommendations to be dynamically monitored in real time.</u><u style="Single">[C18]</u><u style="Single"> The one or more recommendations include conditional logic, the conditional logic being executable to contextualize new explicit elements and new implicit elements to address the new intent associated with the new conversation.</u><u style="Single">[C19]</u><u style="Single"> The non-transitory computer-readable storage medium of C17, wherein the executable instructions that cause the computer system to dynamically monitor compliance with the one or more recommendations further cause the computer system to process a data stream of a new conversation between a customer and an agent, the data stream being processed in real time during the new conversation, and the agent responses from the data stream being evaluated in real time to determine whether the agent is in compliance with the one or more recommendations.</u><u style="Single">[C20]</u><u style="Single"> The non-transitory computer-readable storage medium of C17, wherein the executable instructions that cause the computer system to dynamically monitor compliance with the one or more recommendations further cause the computer system to provide feedback to the agent, the feedback being provided based on an evaluation of an agent's response in accordance with the one or more recommendations.</u><u style="Single">[C21]</u><u style="Single"> The non-transitory computer-readable storage medium of C17, wherein the executable instructions for causing the computer system to dynamically monitor compliance with the one or more recommendations further cause the computer system to determine emotions from a new conversation, the emotions being evaluated to determine whether an agent response in the new conversation complies with the one or more recommendations.</u><u style="Single">[C22]</u><u style="Single"> The non-transitory computer-readable storage medium of C17, wherein the executable instructions further cause the computer system to generate a set of performance metrics corresponding to the agent, the set of performance metrics corresponding to the agent's performance in addressing the set of intents and emotions of the customer.</u><u style="Single">[C23]</u><u style="Single"> The non-transitory computer-readable storage medium of C17, wherein the executable instructions further cause the computer system to obtain feedback corresponding to the conversation, the feedback being processed to identify the set of actions that can be taken to improve the agent response to the new intent.</u><u style="Single">[C24]</u><u style="Single"> The non-transitory computer-readable storage medium of C17, wherein the executable instructions further cause the computer system to use data corresponding to a new set of context, new explicit elements, new implicit elements, the new conversation, and compliance with the one or more recommendations to further train the machine learning algorithm.</u>
16 sheets
Sheet 1 Sheet 2 Sheet 3 Sheet 4 Sheet 5 Sheet 6 Sheet 7 Sheet 8 Sheet 9 Sheet 10 Sheet 11 Sheet 12 Sheet 13 Sheet 14 Sheet 15 Sheet 16
Every citation, both ways
| Document | Relation | Office |
|---|---|---|
| JP2018081444A | Cites | Japan |
| US20150189088A1 | Cites | United States of America |
| US20150178371A1 | Cites | United States of America |
| JP2019530050A | Cites | Japan |
| JP2014512046A | Cites | Japan |
19 members in 8 offices
Priority claims3
| Document | Office | Kind | Date |
|---|---|---|---|
| 62981466 | United States of America | – | |
| 202062981466 | United States of America | P | |
| 2021019327 | United States of America | W |
Members19
| Document | Office | Kind | |
|---|---|---|---|
| US11076047B1 | United States of America | B1 | |
| CA3167955A1 | Canada | A1 | |
| WO2021173611A1 | World Intellectual Property Organization (WIPO) | A1 | |
| US2022046129A1 | United States of America | A1 | |
| AU2021226758A1 | Australia | A1 | |
| IL295410A | Israel | A | |
| CN115151936A | China | A | |
| US11516343B2 | United States of America | B2 | |
| EP4111401A1 | European Patent Office (EPO) | A1 | |
| US2023123022A1 | United States of America | A1 | |
| JP2023523678A | Japan | A | |
| AU2021226758B2 | Australia | B2 | |
| US11770476B2 | United States of America | B2 | |
| US2024137444A1 | United States of America | A1 | |
| US2024236235A9 | United States of America | A9 | |
| US12081700B2 | United States of America | B2 | |
| IL295410B1 | Israel | B1 | |
| JP7654681B2This record | Japan | B2 | |
| IL295410B2 | Israel | B2 |
12 legal events, as the office reported them to INPADOC
Over the term
Point at a mark for the eventEvents
| Event | Code | |
|---|---|---|
| Certificate of patent or registration of utility modelJAPANESE INTERMEDIATE CODE: R150R150 | R150 | |
| First payment of annual fees (during grant procedure)JAPANESE INTERMEDIATE CODE: A61A61 | A61 | |
| Written decision to grant a patent or to grant a registration (utility model)JAPANESE INTERMEDIATE CODE: A01A01 | A01 | |
| Decision of grant or rejection writtenTRDD | TRDD | |
| Written request for extension of timeJAPANESE INTERMEDIATE CODE: A601A601 | A601 | |
| Notification of reasons for refusalJAPANESE INTERMEDIATE CODE: A131A131 | A131 | |
| Request for written amendment filedJAPANESE INTERMEDIATE CODE: A523A521 | A521 | |
| Written request for extension of timeJAPANESE INTERMEDIATE CODE: A601A601 | A601 | |
| Notification of reasons for refusalJAPANESE INTERMEDIATE CODE: A131A131 | A131 | |
| Report on retrievalJAPANESE INTERMEDIATE CODE: A971007A977 | A977 | |
| Notification of acceptance of power of attorneyJAPANESE INTERMEDIATE CODE: A7422RD02 | RD02 | |
| Written request for application examinationJAPANESE INTERMEDIATE CODE: A621A621 | A621 |
Numbers
- Publication
- 7654681
- Application
- 2022550907
Titles2
- Japanese
- コールセンター応答生成のための意図分析
- English
- Intention Analysis for Call Center Response Generation
Classification
- CPC, 11
- H04M3/42221
- G06Q10/0639
- G06Q10/20
- G06Q30/016
- H04L51/02
- H04L51/04
- H04L51/216
- H04M2203/403
- H04M2203/401
- H04M3/5175
- H04M3/42
- IPC, 1
- G06Q30 015
