Conversation controller, and conversation control method

【0001】

[Technical field to which the invention belongs]

The present invention relates to a conversation control device and a conversation control method.

【0002】

[Conventional technology]

In the conventional conversation control device, it is possible to output a pre-stored answer sentence corresponding to the utterance content based on the utterance content from the user (for example, Patent Document 1).

【0003】

[Patent Document 1]

JP-A-2002-169804 (pages 6-15, Fig. 16) [0004]

[Problems to be Solved by the Invention]

However, when the user's utterance content is perceived as having multiple meanings and there are multiple answer sentences corresponding to the utterance content, the conversation control device generally outputs the first searched answer sentence. It was. For this reason, when the user's utterance content is captured in multiple meanings, the conversation control device selects and selects the meaning of the utterance content related to the specific topic to be developed in advance from each of the meanings. The answer sentence corresponding to the meaning of the utterance content could not be output.

【0005】

For example, if the content of the utterance from the user is {Please tell me the IR}, the content of the utterance can be understood as the meaning of IR (Investor Relations) of the production image on the game machine or IR (Investor Relations) of the company. Sometimes. In this case, when the conversation control device first searches for the answer sentence corresponding to the IR (Inazuma Rush) of the production image in the game machine from each answer sentence, the conversation control device outputs the first searched answer sentence. ..

【0006】

That is, even when the conversation control device wants to output the answer sentence corresponding to the IR of the company, when the answer sentence corresponding to the IR (Inazuma Rush) of the production image is first searched, the first searched answer is obtained. The statement was output automatically. For this reason, it has been desired to develop a system that can output an answer sentence related to a specific topic to be developed in advance when the content of the utterance from the user can be grasped in a plurality of meanings.

【0007】

Therefore, the present invention has been made in view of the above points, and when the content of the user's utterance is understood to have a plurality of meanings, by outputting an answer sentence related to a specific topic to be developed in advance, the present invention is made. An object of the present invention is to provide a conversation control device and a conversation control method capable of guiding a current topic to a specific topic.

【0008】

[Means for solving problems]

The present invention has been made to solve the above problems, and is input by the user when searching for a response sentence corresponding to the input information based on the input information including the utterance content input by the user. Search each phrase including the input information from multiple phrases stored in advance based on the input information, and select a phrase related to the topic you want to develop in advance from each phrase based on each searched phrase. It is characterized by searching for the answer sentence corresponding to the selected phrase.

【0009】

That is, in the present invention, the above phrase includes second morpheme information indicating a morpheme composed of one character, a plurality of character strings, or a combination thereof, and the plurality of second morpheme information includes a response sentence to the user. And the priority for being selected as the answer sentence are associated with each other, and each second morpheme information and each answer sentence are stored in advance, and characters are stored based on the character string included in the input information input from the user. At least one morpheme constituting the smallest unit of the column is extracted as the first morpheme information, and based on the extracted first morpheme information, the first morpheme information is included from each of the second morpheme information stored in advance. When the second morpheme information is searched and a plurality of second morpheme information is searched, each of the searched first morphemes according to the magnitude of each priority associated with each searched second morpheme information. It is characterized in that one second morpheme information is selected from the two morpheme information, and the answer sentence associated with the second morpheme information is searched based on the selected second morpheme information.

【0010】

According to the invention according to the present application, when the second morpheme information 1 and the second morpheme information 2 are searched as the second morpheme information including the extracted first morpheme information, the conversation control device: From the searched second morpheme information 1 and second morpheme information 2, for example, the second morpheme information 1 associated with a high priority is selected, and the answer sentence associated with the selected second morpheme information 1 is selected. Can be output. Here, the fact that each phrase including the input information is searched for a plurality of times, or that the second morpheme information including the first morpheme information constituting the input information is searched for a plurality of times means that the input information is regarded as having a plurality of meanings. Means that.

【0011】

That is, when the input information is captured in a plurality of meanings, and when a plurality of second morpheme information (or phrases) are searched, the conversation control device expands in advance from each second morpheme information by the conversation control device. It is possible to select the second morpheme information (second morpheme information to which a high priority is associated) related to the topic to be desired.

【0012】

As a result, the conversation control device does not output a passive answer sentence based on the content of the utterance from the user (for example, faithfully answering the content of the question from the user), but voluntarily from the conversation control device. It is possible to output an active answer sentence that expands to a specific topic, in other words, an answer sentence that guides the current topic to a specific topic.

【0013】

In the above invention, when each second morpheme information searched this time is searched more than a predetermined reference number of times, the second morpheme information different from the previously selected second morpheme information is searched this time. It may be selected from each second morpheme information. As a result, when the second morpheme information selected last time is included in each second morpheme information searched this time, and each second morpheme information searched this time is searched more than a predetermined reference number of times, a conversation is made. The control device can select the second morpheme information different from the second morpheme information selected last time from each of the second morpheme information searched this time.

【0014】

That is, when the same utterance content is repeatedly uttered by the user, the conversation control device can sequentially change the second morpheme information according to the number of times the utterance is repeated. As a result, the conversation control device can change the answer sentence that guides the current topic to a specific topic one by one according to the number of repeated utterance contents.

【0015】

In the above invention, the answer sentence may include contents for guiding to a specific topic. In this case, since the answer sentence includes the content for guiding to a specific topic, the conversation control device outputs the answer sentence to more accurately develop the current topic into the topic to be developed in advance. Can be induced. That is, the conversation control device can internally take the initiative on the current topic and guide the current topic more accurately by a specific story.

【0016】

In the above invention, when the previously searched second morpheme information is included in each of the second morpheme information searched this time, the second morpheme previously searched from each of the second morpheme information searched this time. It is preferable to specify the next priority of the priority associated with the information and select the second morpheme information associated with the specified priority.

【0017】

BEST MODE FOR CARRYING OUT THE INVENTION

[First Embodiment]

(Basic Configuration of Conversation Control System) The conversation control system according to the present invention will be described with reference to the drawings. FIG. 1 is a schematic configuration diagram of a conversation control system having a conversation control device 1 according to the present embodiment.

【0018】

As shown in the figure, the conversation control device 1 includes an input unit 100, a voice recognition unit 200, a conversation control unit 300, a sentence analysis unit 400, a conversation database 500, an output unit 600, and a voice recognition dictionary storage. It has a part 700.

【0019】

In the present embodiment, for convenience of explanation, the description is limited to the utterance content of the user (this utterance content is a kind of input information), but the description is not limited to the utterance content of the user, and the keyboard. It may be the input information input from the above. Therefore, the "utterance content" shown below can be explained by replacing the "utterance content" with the "input information".

【0020】

Similarly, in the explanation described later, for convenience of explanation, the description will be limited to the "utterance sentence type" (utterance type), but the description is not limited to this "utterance sentence type" and is input from a keyboard or the like. It may be an "input type" indicating the type of input information. Therefore, the "utterance type" (utterance type) shown below can be explained by replacing the "utterance type" with the "input type".

【0021】

The input unit 100 is an acquisition means for acquiring input information from the user, and in the present embodiment, a microphone, a keyboard, and the like can be mentioned. The input unit 100 is also a character recognition means for specifying a character string indicating the input information based on the input information input from the user.

【0022】

Here, the input information means characters, symbols, voices, etc. input through a keyboard or the like. Specifically, the input unit 100 acquires the user's input information (other than voice) and outputs the acquired input information to the conversation control unit 300. In addition, the input unit 100, which has acquired the utterance content from the user (this utterance content is composed of voice and is a kind of input information) with a microphone or the like, outputs the voice constituting the acquired utterance content as a voice signal. Is output to the voice recognition unit 200.

【0023】

The voice recognition unit 200 is a character recognition means for identifying a character string included in the utterance content based on the utterance content acquired by the input unit 100. Specifically, the voice recognition unit 200 in which the voice signal is input from the input unit 100 analyzes the input voice signal, and the character string included in the analyzed voice signal is stored in the voice recognition dictionary storage unit 700. It is specified using the dictionary, and the specified character string is output to the conversation control unit 300 as a character string signal. The voice recognition dictionary storage unit 700 stores a dictionary corresponding to a standard voice signal.

【0024】

The sentence analysis unit 400 analyzes the character string specified by the input unit 100 or the voice recognition unit 200. In the present embodiment, as shown in FIG. 2, the morpheme extraction unit 410 and the phrase analysis unit 420 It has a sentence structure analysis unit 430, a speech type determination unit 440, a morpheme database 450, and a speech type database 460.

【0025】

The morpheme extraction unit 410 is a morpheme extraction means that extracts at least one morpheme constituting the minimum unit of the character string as the first morpheme information based on the character string specified by the input unit 100 or the voice recognition unit 200.

【0026】

Specifically, the morpheme extraction unit 410 in which the character string signal is input from the management unit 310 extracts each morpheme from the character string corresponding to the input character string signal. Here, the morpheme means, in the present embodiment, the smallest unit of the word structure expressed in the character string. As shown in FIG. 3, as the minimum unit of this word structure, for example, part of speech such as a noun, an adjective, and a verb can be mentioned. In this embodiment, each morpheme is expressed as m1, m2, ..., Mill.

【0027】

That is, the morpheme extraction unit 410 collates the character string corresponding to the input character string signal with the morpheme group such as nouns, adjectives, and verbs stored in advance in the morpheme database 450, and morpheme elements from the character string. Each morpheme (m1, m2, ...) That matches the group is extracted, and each extracted morpheme is output to the clause analysis unit 420 as an extraction signal.

【0028】

The phrase analysis unit 420 is a conversion means for converting each morpheme into a phrase format based on each morpheme extracted by the morpheme extraction unit 410. Specifically, the phrase analysis unit 420 in which the extraction signal is input from the morpheme extraction unit 410 organizes the phrase format using each morpheme corresponding to the input extraction signal.

【0029】

Here, the phrase format is, in the present embodiment, an independent word or a sentence in which an independent word has one or more attached words, or a character string to the extent that the meaning of the Japanese grammar is not destroyed. It means a single sentence that is divided as finely as possible. In this embodiment, this phrase is expressed as p1, p2, ... Pk.

【0030】

That is, as shown in FIG. 4, the phrase analysis unit 420 sets the dependent elements (for example, (m2), ha (m4), and (m5) of each morpheme based on each morpheme corresponding to the input extraction signal. ) ) Is extracted, and each morpheme is put together in each clause based on the extracted dependency element. The "t" shown in the figure means transposition.

【0031】

The phrase analysis unit 420, which summarizes each morpheme into each phrase, uses sentence pattern information including each phrase that summarizes each morpheme and each morpheme that constitutes each phrase as a sentence pattern signal, and the sentence structure analysis unit 430 and the utterance type determination unit 440. Output to.

【0032】

The sentence structure analysis unit 430 is a classification means for classifying each morpheme of the first morpheme information segmented by the sentence analysis unit 420 into each attribute such as the accusative case and the accusative case. Specifically, the sentence structure analysis unit 430 in which the sentence pattern signal is input from the phrase analysis unit 420 is based on each morpheme corresponding to the input sentence pattern signal and a phrase composed of each morpheme, and the sentence structure analysis unit 430 contains each morpheme included in the phrase. Determine the "case composition".

【0033】

Here, the "case structure" means a case (attribute) indicating a substantive concept in a clause, and in the present embodiment, for example, a subject (subject case) meaning a subject / nominative case and an object are used. Examples include an object (nominative case) that means, an action that means an action, a time (tense, aspect) that means time, and a location that means a place. In the present embodiment, each morpheme associated with the "case" (case structure) of the three elements of subject, object, and action is used as the first morpheme information.

【0034】

That is, as shown in FIG. 5, in the sentence structure analysis unit 430, for example, when the dependent element of each morpheme is "ga" or "ha", the morpheme in front of the dependent element is the subject (subject). Or it is judged to be the subject). Further, the sentence structure analysis unit 430 determines that, for example, when the dependency element of each morpheme is "" or "", the morpheme in front of the dependency element is an object (object).

【0035】

Further, in the sentence structure analysis unit 430, for example, when the dependency element of each morpheme is "do", the morpheme in front of the dependency element is composed of an action (predicate; this predicate is a verb, an adjective, etc.). It is judged that it is.

【0036】

The sentence structure analysis unit 430, which has determined the "case structure" of each morpheme constituting each clause, sets the range of topics to be described later based on the first morpheme information associated with the determined "case structure". The topic search command signal for identification is output to the reflexive determination unit 320.

【0037】

The utterance type determination unit 440 is a type identification means for specifying the utterance type (input type) indicating the type of the utterance content (input information) based on the phrase specified by the phrase analysis unit 420. Specifically, the "utterance sentence type" (utterance type) is determined based on each morpheme corresponding to the sentence pattern signal input from the phrase analysis unit 420 and the phrase composed of each morpheme.

【0038】

Here, in the present embodiment, the "type of utterance sentence" is a statement sentence (D; Declaration), an impression sentence (I; Impression), a conditional sentence (C; Condition), and a result sentence (as shown in FIG. It is composed of E; Effect), time sentence (T; Time), place sentence (L; Location), repulsion sentence (N; Negation), and so on. Each of these sentences is represented by an affirmative sentence (A; Answer) or a question sentence (Q; Question), as shown in FIG.

【0039】

The statement sentence means a sentence consisting of the opinions or thoughts of the user, and in the present embodiment, as shown in FIG. 6, for example, a sentence such as "I like Sato" can be mentioned. The impression sentence means a sentence consisting of the impression that the user has. A place sentence means a sentence consisting of a place element.

【0040】

A result sentence means that the sentence is composed of sentences containing the element of the result for the topic. A time sentence means a sentence composed of a sentence containing a temporal element related to a topic.

【0041】

A conditional sentence means a sentence that includes elements such as the premise of the topic and the conditions and reasons that the topic is established when one utterance is regarded as a topic. A repulsive sentence means a sentence composed of a sentence containing an element that repels the utterance partner. An example sentence for each "type of utterance sentence" is as shown in FIG.

【0042】

That is, the utterance type determination unit 440 collates each phrase with each dictionary stored in the utterance type database 460 based on each phrase corresponding to the input sentence pattern signal, and each of the phrases is selected. Extract sentence elements related to the dictionary. The utterance type determination unit 440, which extracts sentence elements related to each dictionary from each phrase, determines the "type of utterance sentence" based on the extracted sentence elements. The sentence element means a type of a minute for specifying the type of a character string, and in the present embodiment, the sentence element includes a definition phrase (which is) described above.

【0043】

Here, as shown in FIG. 7, the utterance type database 460 is a definition expression case dictionary including a dictionary related to a definition phrase (for example, ~), and an affirmative phrase (for example, agree, agree, ping pong). positive cases dictionary with a dictionary related to, a result clause (for example, so, so) the results representation case dictionary with a dictionary related to, greeting clause (for example, Hello) greeting case dictionary with a dictionary related to, It consists of a negative case dictionary with dictionaries related to negative phrases (for example, don't be stupid, the opposite), and each dictionary is associated with a "spoken sentence type".

【0044】

As a result, the utterance type determination unit 440 collates the phrase with each dictionary stored in the utterance type database 460, extracts sentence elements related to each dictionary from the phrase, and associates them with the extracted sentence elements. The "type of utterance sentence" can be determined by referring to the type of determination.

【0045】

The utterance type determination unit 440 outputs an answer search command signal for causing the corresponding user to search for a specific answer sentence to the answer sentence search unit 370 based on an instruction from the topic search unit 360 described later.

【0046】

The conversation database 500 stores a plurality of answers in which a second morpheme information indicating each morpheme composed of one character, a plurality of character strings, or a combination thereof and a response sentence to a user for the uttered content are associated with each other in advance. It is a memory means (discourse memory means; morpheme memory means). The conversation database 500 is also an answer storage means (discourse storage means) that stores a plurality of answer types indicating the types of each answer sentence associated with the plurality of answer sentences in advance in association with the second morpheme information.

【0047】

Further, the conversation database 500 is a morpheme storage means for storing a plurality of discourse ranges (keywords) indicating morphemes constituting a range related to the input contents to be input by the user or the answer sentence to the user in advance. But also. A plurality of second morpheme information indicating a morpheme consisting of one character, a plurality of character strings, or a combination thereof is associated with this discourse range (keyword), and each second morpheme information contains a response sentence to the user. Associated with each.

【0048】

Furthermore, the conversation database 500 is also an answer storage means (discourse storage means) that classifies and stores each element constituting the second morpheme information into attributes such as each subject consisting of the nominative case and the target case consisting of the object case. ..

【0049】

As shown in FIG. 8, this conversation database 500 can be broadly divided into discourses that mean a relevant range of utterance contents or response sentences to the user that will be uttered by the user in the present embodiment. It is composed of a range (discourse) and a topic (topic) that means the range most closely related to the content spoken by the user. As shown in the figure, the "discourse range" is positioned as a superordinate concept of the "topic" in the present embodiment.

【0050】

As shown in FIG. 9, each discourse range can be configured to have a hierarchical structure. As shown in the figure, for example, the discourse range (entertainment) of the superordinate concept for a certain discourse range (movie) is located in the upper hierarchical structure, and the discourse range (movie) of the subordinate concept with respect to the discourse range (movie). Attributes, showing movies) can be located in the lower hierarchical structure. That is, in the present embodiment, each discourse range can be arranged at a hierarchical position where the relationship between the superordinate concept, the subordinate concept, the synonym, and the antonym is clear with the other discourse range.

【0051】

As described above, the discourse range is composed of each topic, and in the present embodiment, for example, if the discourse range is the A movie name, a plurality of topics related to the A movie name are included.

【0052】

This topic means a morpheme consisting of one character, a plurality of character strings, or a combination thereof, that is, each morpheme constituting the utterance content that will be uttered by the user. It consists of each morpheme associated with a subject (subject case), an object (target case), and an action "case" (attribute). In this embodiment, each morpheme associated with these three elements is expressed as a topic title (this topic title corresponds to a subordinate concept of "topic") (second morpheme information). ..

【0053】

The topic title is not limited to each morpheme associated with the above three elements, but is not limited to other "cases", that is, time (tense, aspect) meaning time, location meaning place, and so on. It may have each morpheme associated with a condition meaning a condition, an impression meaning an impression, an effect meaning a result, and the like.

【0054】

In this embodiment, this topic title (second morpheme information) is stored in advance in the conversation database 500, and is the first morpheme information (derived from the utterance content uttered by the user). It is something that can be distinguished.

【0055】

For example, the topic title is subject (A movie name), object (director), action (great) {this is "A movie name", as shown in Fig. 10, when the discourse range is "A movie name". The director of the name is made up of} which means "great".

【0056】

If there is no morpheme associated with the "case structure" (subject, object, action, etc.) in the topic title, that part will be indicated by "*" in this embodiment.

【0057】

For example, if you convert the sentence {A movie name?} To a topic title (subject; object; action), the "A movie name" in the sentence {A movie name?} Will be specified as the subject. However, since other "objects" and "actions" are not elements of sentences, the topic titles are "subject" (A movie name); "object" none (*); "action" none (*). (See Figure 10).

【0058】

In this embodiment, the answer text is associated with each topic title (second morpheme information) (see FIG. 8). In the present embodiment, as shown in FIG. 11, the answer sentence is a statement (D; Declaration) and an impression sentence in order to give an answer corresponding to the type of the utterance sentence uttered by the user. Types (answers) such as (I; Impression), conditional (C; Condition), result (E; Effect), time (T; Time), location (L; Location), negative (N; Negation), etc. It is classified into (type).

【0059】

That is, as shown in FIG. 12, each answer sentence is associated with, for example, the discourse range (Sato) {subordinate concept; home run, superordinate concept; grass baseball, synonym; panda Sato / Sato player / panda} and each topic title. Has been done.

【0060】

As shown in the figure, for example, topic title 1-1 is {(Sato; *; I like): This consists of the order (subject; object; action) as described above. If the order is the same as below}, the answer sentence 1-1 corresponding to the topic title 1-1 is (DA; statement affirmative sentence "I like Sato"), (IA; impression affirmative sentence. "I like Sato very much"), (CA; Condition affirmative sentence "Because Sato's home run is very impressive"), (EA; Result affirmative sentence "I always watch Sato's game on TV"), (TA; Time affirmative sentence "Actually, I like it since I've been away from five at-bats in a row at Koshien"), (LA; Place affirmative sentence "I like the serious face when standing on the batting"), (NA ; Repulsion affirmative sentence "I don't want to talk to people who don't like Sato, goodbye").

【0061】

In the present embodiment, the conversation control unit 300 includes a management unit 310, a reflexive determination unit 320, an echolalia determination unit 330, a discourse range determination unit 340, and an abbreviation completion unit 350, as shown in FIG. , It has a topic search unit 360 and an answer text search unit 370.

【0062】

The management unit 310 controls the entire conversation control unit 300. Specifically, the management unit 310 in which a character string is input from the input unit 100 or the voice recognition unit 200 outputs the input character string as a character string signal to the morpheme extraction unit 410. Further, the management unit 310 outputs the answer sentence acquired by the answer sentence search unit 370 to the output unit 600.

【0063】

The reflexive determination unit 320 is a standard acquisition means for collating the first morpheme information extracted by the morpheme extraction unit 410 with each standard content and searching for the standard content including the first morpheme information from each standard content. ..

【0064】

Here, the standard content means the reflective element information for answering the standard content to the utterance content from the user, and this reflective element information is stored in the reflective element database 801 (standard storage means) in advance. Multiple are stored. As the reflective element information, in the present embodiment, as shown in FIG. 13, for example, "Good morning", "Hello", "Good evening", "greeting elements" such as "Hey", "I see", "Really?" "Standard elements" such as.

【0065】

Specifically, the reflexive determination unit 320 in which the topic search command signal is input from the sentence structure analysis unit 430 is stored in the first form element information and the reflective element database 801 included in the input topic search command signal. The reflection element information is collated with each other, the reflection element information including the first morphological element information is searched from each reflection element information, and the searched reflection element information is output to the management unit 310.

【0066】

That is, assuming that the reflection element information is D1 and the first morpheme information is W, the reflection determination unit 320 determines that the relationship of W D1 φ (φ; empty set) is established, and the above reflection Perform processing to give a specific answer.

【0067】

For example, when the user utters the utterance content of "good morning", the reflex determination unit 320 collates the utterance content "good morning" with each reflex element information, and the utterance content is selected from each reflex element information. The reflective element information "good morning" including (matching) "good morning" is searched, and the searched reflective element information "good morning" is output to the management unit 310.

【0068】

When the reflexive determination unit 320 cannot search the reflex element information including the utterance content from each reflex element information, the reflexive determination unit 320 returns the topic search command signal input from the sentence structure analysis unit 430 to the reflex determination unit 330. Output to.

【0069】

The Echolalia determination unit 330 collates the current first morpheme information extracted by the morpheme extraction unit 410 with the past answer sentences stored in the Echolalia element database 802, and the current first morpheme information is the past answer. When it is included in the sentence, it is a standard acquisition means to acquire the contents of the agreement.

【0070】

Here, "echolalia" means, in the present embodiment, to return the utterance content of the user as it is (or a content close to it). In the present embodiment, the Echolalia element is also composed of the first morpheme information constituting the answer sentence output from the conversation control device 1 immediately before, and as shown in FIG. 14, for example, "horse is beautiful". (Horse; *; beautiful), "I like Sato" (Sato; *; I like) and so on.

【0071】

In addition, the Echolalia element database 802 is also an agreement storage means for storing in advance the contents of the agreement for agreeing with the input information input from the user. The content of the agreement includes, for example, the input information previously input by the user (if the previous input information by the user is "Is the director of the A movie name Mr. S?", The content of the agreement is ". A The director of the movie name is Mr. S "), or" yes "," true ", etc.

【0072】

Specifically, the Echolalia determination unit 330 in which the topic search command signal is input from the reflexive determination unit 320 constitutes the first morpheme information and the Echolalia element included in the input topic search command signal for each Echolalia element. By collating each morpheme, it is determined whether the first morpheme information is included in the Echolalia element (see Fig. 14).

【0073】

When the Echolalia determination unit 330 determines that the first morpheme information is included in each Echolalia element, it acquires the agreement content and outputs the response text consisting of the acquired agreement content to the management unit 310 (Echolalia). Process). That is, assuming that the Echolalia element (previous answer sentence, etc.) is S and the first morpheme information is W, the Echolalia determination unit 330 shows the above when the relationship of W S and W φ is established. Performs Echolalia processing.

【0074】

For example, the conversation control device 1 responds with "The director of the A movie name is Mr. S" (Director of the A movie name; Mr. S; *) (This order is subject; object; action order, and so on. ) Is output, and then, if the user utters "Is the director of the A movie name Mr. S?" (Director of the A movie name; Mr. S; *) in response to the output sentence, it will be returned. Since the judgment unit 330 matches the first form element information of the user (Director of A movie name; Mr. S; *) and each form element of the answer sentence (Director of A movie name; Mr. S; *), The user concludes that he / she is returning to the reply, acquires the memorized agreement content "That's right", etc., and outputs the acquired agreement content.

【0075】

Further, the Echolalia determination unit 330 collates the current first morpheme information extracted by the morpheme extraction unit 410 with the past first morpheme information stored in the Echolalia element database 802, and the current first morpheme information. Is also a standard acquisition means for acquiring the content of repulsion when is included in the past first morpheme information.

【0076】

Specifically, when the user utters the utterance content of "horse is beautiful" and the conversation control device 1 outputs the content of "horse is good with a sense of dynamism" as an answer sentence, it is used later. When a person repeats the utterance content of "horse is beautiful", the parrot return judgment unit 330 tells each morphological element (first morphological element information) {horse; *; beautiful} that constitutes the current utterance content "horse is beautiful". Since each morphological element (first morphological element information) {horse; *; beautiful} that composes the previous utterance "horse is beautiful" matches, the user can answer the answer from conversation control device 1 "horse is dynamic". It can be concluded that "it's okay to have a feeling" has not been heard at all.

【0077】

In this case, the Echolalia determination unit 330 acquires the memorized repulsion content (for example, do not repeat the same content) because the user has not heard the response sentence from the conversation control device 1, and the acquired repulsion. The contents can be output.

【0078】

On the other hand, when the first morpheme information is the same as the content of the previous answer sentence or the first morpheme information is not the same as the previous first morpheme information, the Echolalia determination unit 330 is transmitted from the reflexive determination unit 320. The input topic search command signal is output to the discourse range determination unit 340.

【0079】

The above-mentioned Echolalia determination unit 330 has shown the processing when the user makes an Echolalia in response to the "answer sentence of the conversation control device 1", but the following processing can also be performed. For example, when the output unit 600 outputs the answer sentence "horse is beautiful", the user asks "why horse is beautiful?", "Why is it beautiful?", Or "why?" This is the processing of the Echolalia determination unit 330 that is performed when an utterance is made.

【0080】

In this case, the Echolalia judgment unit 330 outputs the answer sentence S "the horse is beautiful" and the utterance content W from the user ("why the horse is beautiful? (Question sentence)" or "why is it beautiful? (Question sentence)". When collated with "), (Wc) S, S φ, c φ (this c means the utterance type of W, and this utterance type is determined by the utterance type determination unit 440 described later. As will be described later, the utterance type includes, for example, an interrogative sentence. Therefore, a "conditional" echo-return process (the user attaches an interrogative sentence to the answer sentence). (Processing when the utterance is returned) is performed.

【0081】

As the "conditional" echolalia processing, for example, when the conversation control device 1 outputs the answer sentence "horse is beautiful", the above user utters "why horse is beautiful?" At that time, in order to solve the user's doubts, the Echolalia judgment unit 330 acquires an answer sentence such as "Because the horse is not beautiful" from the Echolalia element database 802, and the acquired answer sentence is sent to the management unit 310. Performs output processing.

【0082】

The discourse range determination unit 340 collates the first morpheme information extracted by the phrase analysis unit 420 with each discourse range stored in advance, and matches the morpheme included in the first morpheme information from each discourse range. It is a discourse range search means for searching a discourse range.

【0083】

Specifically, the discourse range determination unit 340 in which the topic search command signal is input from the echolalia determination unit 330 determines the discourse range of the user based on the input discourse search command signal. That is, the discourse range determination unit 340 searches the conversation database 500 for a range (discourse range) related to the content spoken by the user based on the input search command signal.

【0084】

For example, the discourse range determination unit 340 determines this first morpheme information when the first morpheme information included in the input topic search command signal is (interesting movie; *; is) {is there an interesting movie?}. And the discourse range group are collated, and when the discourse range group contains a morpheme (for example, "movie") that constitutes the first morpheme information, the "movie" included in the first morpheme information is determined as the discourse range. To do. In this case, since the discourse range determination unit 340 includes the discourse range "movie" in the first morpheme information, the input first morpheme information is included in the topic search command signal and output to the topic search unit 360.

【0085】

On the other hand, when the discourse range determination unit 340 does not include the discourse range group in the first morpheme information, the discourse range determination unit 340 includes the input first morpheme information in the topic search command signal and outputs it to the abbreviation completion unit 350.

【0086】

As a result, the topic search unit 360, which will be described later, collates each "topic title" belonging to the "discourse range" determined by the discourse range determination unit 340 with the first morpheme information specified by the sentence structure analysis unit 430. Therefore, it is not necessary to collate the "topic title" (second morpheme information) of "all" with the first morpheme information, and the answer sentence search unit 370, which will be described later, searches for the final answer sentence. Time can be shortened.

【0087】

As described above, the discourse range determination unit 340 collates the first morpheme information with the discourse range group, and if the discourse range group contains the morpheme of the first morpheme information, determines the morpheme as the discourse range. However, the discourse range is not limited to this, and the morpheme of the utterance return element searched immediately before by the information return determination unit 330 or the morpheme constituting the utterance content uttered by the user may be determined as the discourse range. .. The abbreviated sentence complementing unit 350, which will be described later, can add the discourse range to the first morpheme information in which the morpheme is omitted by using the discourse range determined by the discourse range determining unit 340.

【0088】

The abbreviation completion unit 350 searches for attributes that do not include morphemes from each attribute (subject, object, action, etc.) that constitutes the first morpheme information based on the first morpheme information extracted by the clause analysis unit 420. It is an attribute search means to be performed. Further, the abbreviation completion unit 350 is also a morpheme addition means for adding a morpheme constituting the discourse range searched by the discourse range determination unit 340 to the attribute based on the searched attribute.

【0089】

Specifically, the abbreviated sentence complementing unit 350 in which the topic search command signal is input from the discourse range determination unit 340 is an utterance composed of the first morpheme information based on the first morpheme information included in the input discourse search command signal. It is determined whether the content is an abbreviated sentence, and if the utterance content consisting of the first morpheme information is an abbreviated sentence, the morpheme of the discourse range to which the first morpheme information belongs is added to the first morpheme information.

【0090】

For example, in the abbreviated sentence completion unit 350, the morpheme constituting the first morpheme information included in the input topic search command signal is (director; *; *) (director?) (This sentence is "what" director. (It means an abbreviation because it is unknown whether it is), the discourse range determined by the discourse range determination unit 340 (A movie name; this A movie name indicates the title of the movie. If it is the first morpheme information belonging to (a), the determined discourse range (A movie name) is added to the first morpheme information (director of "A movie name"; *; *)

【0091】

That is, assuming that the first morpheme information is W and the determined discourse range is D, the abbreviation completion unit 350 adds the discourse range D to W and includes the added first morpheme information in the topic search command signal. Output to the topic search unit 360.

【0092】

As a result, even if the first morpheme information is an abbreviated sentence and is not clear as Japanese, the abbreviation complementing unit 350 can be used, for example, if the first morpheme information belongs to a certain discourse range. The discourse range D (A movie name) is added to the first morpheme information W (director; *; *), and the first morpheme information is added to W'(A movie name director; *; *) {A movie name director Since it can be treated as?}, Even if the user's utterance is an abbreviated sentence, the abbreviated sentence can be complemented based on the previously determined discourse range, and the abbreviated sentence is clarified. be able to.

【0093】

Therefore, even if the utterance content constituting the first morpheme information is an abbreviated sentence, the abbreviation sentence complementing unit 350 uses the first morpheme information so that the utterance content constituting the first morpheme information is in proper Japanese. Since a specific morpheme can be complemented to, the topic search unit 360 acquires the optimum "topic title" (second morpheme information) related to the first morpheme information based on the complemented first morpheme information. The answer sentence search unit 370 can output an answer sentence more suitable for the content of the user's speech based on the "topic title" acquired by the topic search unit 360.

【0094】

The topic search unit 360 collates the first morpheme information extracted by the phrase analysis unit 420 or the first morpheme information complemented by the abbreviation completion unit 350 with each second morpheme information, and of each second morpheme information. It is a search means for searching the second morpheme information including the morpheme constituting the first morpheme information.

【0095】

Specifically, the topic search unit 360 in which the topic search command signal is input from the discourse range determination unit 340 or the abbreviation complement unit 350 has a discourse range based on the first form element information included in the input topic search command signal. From each "topic title" (second form element information) belonging to the discourse range determined by the determination unit 340, the "topic title" including the form element of the first form element information is searched, and this search result is used as a search result signal. It is output to the answer sentence search unit 370 and the utterance type determination unit 440.

【0096】

For example, if the "case structure" that constitutes the first morpheme information is (Sato; *; like) {I like Sato}, the topic search unit 360 will perform the above "case structure" as shown in FIG. Collate each morpheme belonging to "Composition" (Sato; *; I like) with each topic title 1-1 ~ 1-4 belonging to the utterance range (Sato), and from each topic title 1-1 ~ 1-4 Search for topic title 1-1 (Sato; *; like) that matches (or approximates) each morpheme (Sato; *; likes) belonging to "case composition", and use this search result as a search result signal. Output to the search unit 370 and the utterance type determination unit 440.

【0097】

The utterance type determination unit 440 in which the search result signal is input from the topic search unit 360 is an answer search command for searching a specific answer sentence to be answered to the corresponding user based on the input search result signal. A signal (this answer search command signal also includes the determined "utterance sentence type") is output to the answer sentence search unit 370.

【0098】

The answer sentence search unit 370 is an answer search means for searching the answer sentence associated with the second morpheme information based on the second morpheme information (topic title) searched by the topic search unit 360. In addition, the answer sentence search unit 370 collates the utterance type of the specified user with each answer type associated with the second morpheme information based on the second morpheme information searched by the topic search unit 360. It is also a second search method for acquiring an answer type that matches the utterance type of the user from each answer type.

【0099】

Specifically, the answer sentence search unit 370 in which the search result signal from the topic search unit 360 and the answer search command signal from the utterance type determination unit 440 is input is the topic title (search result) corresponding to the input search result signal. Based on the "speech type" (speech type) corresponding to the answer search command signal, "speech" from the answer sentence group associated with the "topic title". Search for an answer sentence consisting of an answer type that matches the sentence type (DA, IA, CA, etc.) (this answer type means the "answer sentence type" shown in FIG. 11).

【0100】

For example, if the topic title corresponding to the search result is the topic title 1-1 (Sato; *; likes) shown in FIG. 12, the answer sentence search unit 370 is associated with the topic title 1-1. Answers consisting of answer types (DA) that match the "utterance type" (for example, DA; utterance type) determined by the utterance type determination unit 440 from the answer sentences 1-1 (DA, IA, CA, etc.) Search sentence 1-1 (DA; (I also like Sato)) and output this searched answer sentence to the management unit 310 as an answer sentence signal.

【0101】

The management unit 310, in which the answer sentence signal is input from the answer sentence search unit 370, outputs the input answer sentence signal to the output unit 600. In addition, the management unit 310 in which the reflection element information from the reflexive determination unit 320 or the content of the echolalia processing is input from the echolalia determination unit 330 is the response sentence corresponding to the input reflection element information and the content of the input echolalia processing. The answer sentence corresponding to is output to the output unit 600.

【0102】

The output unit 600 is an output means for outputting the answer sentence acquired by the answer sentence search unit 370, and in the present embodiment, for example, a speaker, a display, and the like can be mentioned. Specifically, the output unit 600 in which the answer sentence is input from the management unit 310 outputs the input answer sentence {for example, I also like Sato}.

【0103】

(Conversation Control Method Using Conversation Control Device) The conversation control method by the conversation control device 1 having the above configuration can be implemented by the following procedure. FIG. 15 is a flow chart showing the procedure of the conversation control method according to the present embodiment.

【0104】

First, the input unit 100 performs a step of acquiring the utterance content from the user (S101). Specifically, the input unit 100 acquires the voice constituting the utterance content of the user, and outputs the acquired voice as a voice signal to the voice recognition unit 200. Further, the input unit 100 identifies a character string included in the input information (other than voice) based on the input information (other than voice) input from the user, and uses the specified character string as a character string signal as a conversation control unit. Output to 300.

【0105】

Next, the voice recognition unit 200 performs a step of specifying the character string included in the utterance content based on the utterance content acquired by the input unit 100 (S102). Specifically, the voice recognition unit 200 in which the voice signal is input from the input unit 100 analyzes the input voice signal, and the character string included in the analyzed voice signal is stored in the voice recognition dictionary storage unit 700. It is specified using the dictionary, and the specified character string is output to the conversation control unit 300 as a character string signal.

【0106】

Then, the morpheme extraction unit 410 performs a step of extracting each morpheme constituting the minimum unit of the character string as the first morpheme information based on the character string specified by the voice recognition unit 200 (S103).

【0107】

Specifically, the morpheme extraction unit 410 in which the character string signal is input from the management unit 310 contains the character string corresponding to the input character string signal and the nouns, adjectives, verbs, etc. stored in advance in the morpheme database 450. It collates with the morpheme group, extracts each morpheme (m1, m2, ...) That matches the morpheme group from the character string, and outputs each extracted morpheme as an extraction signal to the clause analysis unit 420.

【0108】

Then, the phrase analysis unit 420 performs a step of grouping each morpheme into a phrase format based on each morpheme extracted by the morpheme extraction unit 410 (S104). Specifically, the phrase analysis unit 420 in which the extraction signal is input from the morpheme extraction unit 410 organizes the phrase format using each morpheme corresponding to the input extraction signal.

【0109】

That is, as shown in FIG. 4, the phrase analysis unit 420 extracts and extracts the dependency elements (for example, ga ha o ) of each morpheme based on each morpheme corresponding to the input extraction signal. Each morpheme is grouped into each clause based on the dependent elements. The phrase analysis unit 420, which summarizes each morpheme into each phrase, uses sentence pattern information including each phrase that summarizes each morpheme and each morpheme that constitutes each phrase as a sentence pattern signal, and the sentence structure analysis unit 430 and the utterance type determination unit 440. Output to.

【0110】

After that, the sentence structure analysis unit 430 performs a step of classifying each morpheme of the first morpheme information segmented by the sentence analysis unit 420 into each attribute such as the accusative case and the accusative case (S105). Specifically, the sentence structure analysis unit 430 in which the sentence pattern signal is input from the phrase analysis unit 420 is based on each morpheme corresponding to the input sentence pattern signal and a phrase composed of each morpheme, and the sentence structure analysis unit 430 contains each morpheme included in the phrase. Determine the "case composition".

【0111】

That is, as shown in FIG. 5, in the sentence structure analysis unit 430, for example, when the dependent element of each morpheme is "ga" or "ha", the morpheme in front of the dependent element is the subject (subject). Or it is judged to be the subject). Further, the sentence structure analysis unit 430 determines that, for example, when the dependency element of each morpheme is "" or "", the morpheme in front of the dependency element is an object (object).

【0112】

Further, in the sentence structure analysis unit 430, for example, when the dependency element of each morpheme is "do", the morpheme in front of the dependency element is composed of an action (predicate; this predicate is a verb, an adjective, etc.). It is judged that it is.

【0113】

The sentence structure analysis unit 430, which has determined the "case structure" of each morpheme constituting each clause, sets the range of topics to be described later based on the first morpheme information associated with the determined "case structure". The topic search command signal for identification is output to the topic search unit 360.

【0114】

Next, the utterance type determination unit 440 performs a step of specifying the utterance type indicating the type of the utterance content based on the phrase specified by the phrase analysis unit 420 (S106). Specifically, the "utterance sentence type" (utterance type) is determined based on each morpheme corresponding to the sentence pattern signal input from the phrase analysis unit 420 and the phrase composed of each morpheme.

【0115】

That is, the utterance type determination unit 440 collates each phrase with each dictionary stored in the utterance type database 460 based on each phrase corresponding to the input sentence pattern signal, and each of the phrases is selected. Extract sentence elements related to the dictionary. The utterance type determination unit 440, which extracts sentence elements related to each dictionary from each phrase, determines the "type of utterance sentence" based on the extracted sentence elements.

【0116】

The utterance type determination unit 440 outputs an answer search command signal for causing the corresponding user to search for a specific answer sentence to the answer sentence search unit 370 based on an instruction from the topic search unit 360 described later.

【0117】

Next, the reflexive determination unit 320 collates the first morpheme information extracted by the morpheme extraction unit 410 with each standard content, and performs a step of searching for the standard content including the first morpheme information from each standard content. (S107; reflexive processing).

【0118】

Specifically, the reflexive determination unit 320 in which the topic search command signal is input from the sentence structure analysis unit 430 is stored in the first form element information and the reflective element database 801 included in the input topic search command signal. The reflection element information (standard content) is collated, the reflection element information including the first form element information is searched from each reflection element information, and the searched reflection element information is output to the management unit 310.

【0119】

When the reflexive determination unit 320 cannot search the reflective element information including the first morpheme information from each reflective element information, the reflexive determination unit 320 makes a return determination of the topic search command signal input from the sentence structure analysis unit 430. Output to unit 330.

【0120】

Next, the Echolalia determination unit 330 collates the first morpheme information extracted by the morpheme extraction unit 410 with each Echolalia element, and performs a step of searching for an Echolalia element including the first morpheme information from each Echolalia element ( S108; Echolalia processing).

【0121】

When the Echolalia determination unit 330 determines that the first morpheme information is included in each Echolalia element, it acquires the Echolalia element including the first morpheme information and manages the answer sentence consisting of the acquired Echolalia element. Output to unit 310 (echolalia processing). That is, assuming that the Echolalia element (the answer sentence output last time, the utterance content spoken by the user last time, etc.) is S and the first morpheme information is W, the Echolalia determination unit 330 has a relationship of W S and W φ. If it is satisfied, the above-mentioned Echolalia processing is performed.

【0122】

On the other hand, when the Echolalia determination unit 330 determines that the first morpheme information is not included in each Echolalia element, the topic search command signal input from the reflexive determination unit 320 is sent to the discourse range determination unit 340. Output.

【0123】

Then, the discourse range determination unit 340 collates the first morpheme extracted by the phrase analysis unit 420 with each discourse range, and searches (determines) the discourse range including the first morpheme information from each discourse range. Take steps (S109).

【0124】

Specifically, the discourse range determination unit 340 in which the topic search command signal is input from the Echolalia determination unit 330 describes the content spoken by the user from the conversation database 500 based on the input search command signal. Search for a relevant range (discourse range).

【0125】

For example, the discourse range determination unit 340 determines this first morpheme information when the first morpheme information included in the input topic search command signal is (interesting movie; *; is) {is there an interesting movie?}. And the discourse range group are collated, and when the discourse range group contains a morpheme (for example, "movie") that constitutes the first morpheme information, the "movie" included in the first morpheme information is determined as the discourse range. To do. In this case, since the discourse range determination unit 340 includes the discourse range "movie" in the first morpheme information, the input first morpheme information is included in the topic search command signal and output to the topic search unit 360.

【0126】

On the other hand, when the discourse range determination unit 340 does not include the discourse range group in the first morpheme information, the discourse range determination unit 340 includes the input first morpheme information in the topic search command signal and outputs it to the abbreviation completion unit 350.

【0127】

Next, the abbreviation completion unit 350 selects an attribute that does not include a morpheme from among the attributes (subject, object, action, etc.) that compose the first morpheme information based on the first morpheme information extracted by the phrase analysis unit 420. Take the steps to search for. After that, the abbreviation completion unit 350 performs a step of adding the morphemes constituting the discourse range searched by the discourse range determination unit 340 to the attribute based on the attribute that does not include the searched morpheme (S110; abbreviation). Complement).

【0128】

Specifically, the abbreviated sentence complementing unit 350 in which the topic search command signal is input from the discourse range determination unit 340 is an utterance composed of the first morpheme information based on the first morpheme information included in the input discourse search command signal. It is determined whether the content is an abbreviated sentence, and if the utterance content consisting of the first morpheme information is an abbreviated sentence, the morpheme of the discourse range to which the first morpheme information belongs is added to the first morpheme information.

【0129】

For example, in the abbreviated sentence completion unit 350, the morpheme constituting the first morpheme information included in the input topic search command signal is (director; *; *) (director?) (This sentence is "what" director. If it is (meaning an abbreviation), the discourse range (A movie name; this A movie name is the title of the movie) previously determined by the discourse range determination unit 340. If it is the first morpheme information belonging to (shown), the morpheme (A movie name) of the determined discourse range is added to the first morpheme information ("A movie name") to the morpheme constituting the first morpheme information. Supervision; *; *).

【0130】

That is, assuming that the first morpheme information is W and the determined discourse range is D, the abbreviation completion unit 350 adds the discourse range D to the first morpheme information W and uses the added first morpheme information as a topic search command. Included in the signal and output to the topic search unit 360.

【0131】

Next, the topic search unit 360 collates the first morpheme information extracted by the phrase analysis unit 420 or the first morpheme information complemented by the abbreviation completion unit 350 with each second morpheme information, and each second morpheme element. From the information, a step of searching the second morpheme information including the morpheme constituting the first morpheme information is performed (S111).

【0132】

Specifically, the topic search unit 360 in which the topic search command signal is input from the discourse range determination unit 340 or the abbreviation complement unit 350 has a discourse range based on the first form element information included in the input topic search command signal. From each "topic title" (second form element information) belonging to the discourse range determined by the determination unit 340, the "topic title" including the form element of the first form element information is searched, and this search result is used as a search result signal. It is output to the answer sentence search unit 370 and the utterance type determination unit 440.

【0133】

For example, if the "case structure" that constitutes the first morpheme information is (Sato; *; like) {I like Sato}, the topic search unit 360 will perform the above "case structure" as shown in FIG. Collate each morpheme belonging to "Composition" (Sato; *; I like) with each topic title 1-1 ~ 1-4 belonging to the utterance range (Sato), and from each topic title 1-1 ~ 1-4 Search for topic title 1-1 (Sato; *; like) that matches (or approximates) each morpheme (Sato; *; likes) belonging to "case composition", and use this search result as a search result signal. Output to the search unit 370 and the utterance type determination unit 440.

【0134】

The utterance type determination unit 440 in which the search result signal is input from the topic search unit 360 is an answer search command for searching a specific answer sentence to be answered to the corresponding user based on the input search result signal. A signal (this answer search command signal also includes the determined "utterance sentence type") is output to the answer sentence search unit 370.

【0135】

Then, the answer sentence search unit 370 collates the utterance type of the specified user with each answer type associated with the second morpheme information based on the second morpheme information searched by the topic search unit 360. From each answer type, the answer type that matches the utterance type of the user is searched, and the answer sentence associated with the answer type is searched based on the searched answer type (S112).

【0136】

Specifically, the answer sentence search unit 370 in which the search result signal from the topic search unit 360 and the answer search command signal from the utterance type determination unit 440 is input is the topic title (search result) corresponding to the input search result signal. Based on the "speech type" (speech type) corresponding to the answer search command signal, "speech" from the answer sentence group associated with the "topic title". Search for an answer sentence consisting of an answer type that matches the sentence type (DA, IA, CA, etc.) (this answer type means the "answer sentence type" shown in FIG. 11).

【0137】

For example, if the topic title corresponding to the search result is the topic title 1-1 (Sato; *; likes) shown in FIG. 12, the answer sentence search unit 370 is associated with the topic title 1-1. Answers consisting of answer types (DA) that match the "utterance type" (for example, DA; utterance type) determined by the utterance type determination unit 440 from the answer sentences 1-1 (DA, IA, CA, etc.) Search sentence 1-1 (DA; (I also like Sato)) and output this searched answer sentence to the management unit 310 as an answer sentence signal.

【0138】

Next, the management unit 310 in which the answer sentence signal is input from the answer sentence search unit 370 outputs the input answer sentence signal to the output unit 600. In addition, the management unit 310 in which the reflection element information from the reflexive determination unit 320 or the content of the echolalia processing is input from the echolalia determination unit 330 is the response sentence corresponding to the input reflection element information and the content of the input echolalia processing. The answer sentence corresponding to is output to the output unit 600 (S113). The output unit 600, in which the answer text is input from the management unit 310, outputs the input response text {for example, I also like Sato}.

【0139】

(Actions and Effects of Conversation Control Device and Conversation Control Method) According to the invention according to the present application having the above configuration, the reflexive determination unit 320 stores in advance the first morpheme information constituting the utterance content uttered by the user. have been collated with each standard content, from among the standard content, it is possible to find the standard content including a first morpheme information, reflexive determination unit 320, for example, first morpheme information is "Hello", etc. in the case of a fixed content of, it is possible to answer this routine contents same boilerplate content and "Hello" or the like.

【0140】

Further, when the user's utterance content is a standard content, the reflexive determination unit 320 replies the standard content (greeting, etc.), so that the user first communicates with the conversation control device 1. You can experience the feeling of communicating.

【0141】

In addition, the input return determination unit 330 collates the current first form element information with the past answer sentence, and if the current first form element information is not included in the past answer sentence, the agreement stored in advance is stored. Since the content can be acquired, the user returns the memory (use) to the past answer if the input information currently input by the user matches the past answer. It can be concluded that the person has entered the input information (that the person is re-listening to the answer text).

【0142】

In this case, the Echolalia determination unit 330 acquires the memorized consensus content because the user has echoed the past response text, and the acquired consensus content (for example, "That's right"). Can be output. As a result, if the user does not understand the meaning of the answer sentence output from the conversation control device 1, he / she can listen again and listen to the answer sentence again, so that he / she is talking with another user. You can experience the feeling.

【0143】

In addition, the input return determination unit 330 collates the current first form element information with the past first form element information, and if the current first form element information is included in the past first form element information, acquires the repulsion content. Therefore, when the input information input last time is included in the input information input this time, the user repeatedly inputs the same contents as the previous input information. It can be determined that the user has not responded appropriately to the response text from the conversation control device.

【0144】

In this case, the Echolalia determination unit 330 acquires the memorized repulsion content and acquires the repulsion content in order to repel the user because the user does not properly respond to the previous response sentence. Is output. As a result, if the user does not input appropriate input information for the response text from the conversation control device 1, the conversation control device 1 outputs the repulsive content, so that the user can talk with other users. You can experience the feeling of being there.

【0145】

Further, in order to search for the second morpheme information that is similar to the first morpheme information, the topic search unit 360 may collate each second morpheme information belonging to the "discourse range" with the first morpheme information. Since it is not necessary to collate the second morpheme information of "" with the first morpheme information, it is possible to shorten the time required to search for the second morpheme information that is close to the first morpheme information.

【0146】

As a result, the topic search unit 360 can search (pinpoint search) the second morpheme information that is similar to the first morpheme information in a short time, so that the answer sentence search unit 370 can be used by the topic search unit 360. The answer sentence associated with the second morpheme information can be acquired in a short time based on the searched second morpheme information, and the conversation control device 1 promptly responds to the utterance content from the user. be able to.

【0147】

In addition, the topic search unit 360 searches for the second form element information including the form elements (elements constituting the utterance content of the user) constituting the first form element information from each second form element information, and the answer sentence search unit. Since the answer sentence search unit 370 can search the answer sentence associated with the second form element information based on the second form element information searched by the topic search unit 360, the answer sentence search unit 370 can search the utterance content of the user. Based on each morphological element (first morphological element information) that composes, considering the semantic space (subject, object, etc.) constructed by each morphological element, it is possible to search for a pre-created answer sentence based on such semantic space. Therefore, it is possible to search for an answer sentence that is more suitable for the utterance content, rather than simply searching for the answer sentence associated with the keyword using the entire utterance content as a keyword.

【0148】

Further, since the topic search unit 360 searches for the second morpheme information including the first morpheme information, it is not necessary to search for the second morpheme information that completely matches the utterance content of the user, and the conversation control device 1 is developed. It is not necessary for the developer to store a huge amount of answer sentences corresponding to the utterance contents that will be uttered by the user in advance, and the capacity of the storage unit can be reduced.

【0149】

Furthermore, the answer sentence search unit 370 selects the answer type that matches the user's utterance type from the answer types (statement, affirmation, place, repulsion, etc.) associated with each second form element information belonging to the "discourse range". Since it is possible to search for the answer sentence associated with the answer type based on the searched answer type, the conversation control device 1 can be used by the utterance type that constitutes the conversation content of the user, for example, the user. Based on what the user simply expressed his / her opinion, what the user had, and what the user stated the locational element, the answer sentence that matched the user's utterance type was selected from multiple answer sentences. It will be possible to search, and it will be possible to give a more optimal answer to the relevant user.

【0150】

Furthermore, the answer sentence search unit 370 is an answer that matches the utterance type of the user from among the answer types associated with each second morpheme information belonging only to the "discourse range" searched by the utterance range determination unit 340. Since it is only necessary to search for the type (pinpoint search is possible), it is not necessary to search for the answer type associated with the second morpheme information of "all" and the utterance type of the user one by one, and the utterance type of the user is not required. It is possible to obtain the optimum answer sentence corresponding to the above in a short time.

【0151】

Finally, the abbreviated sentence completion unit 350 belongs to the discourse range in which the first morpheme information is present even if the first morpheme information constituting the utterance content of the user is an abbreviated sentence and is not clear in Japanese. If so, the discourse range can be added to the first morpheme information to complement the first morpheme information consisting of abbreviated sentences.

【0152】

As a result, the abbreviated sentence complement unit 350 can use the first morpheme information so that the utterance content constituting the first morpheme information is in proper Japanese even if the utterance content constituting the first morpheme information is an abbreviated sentence. Since it is possible to complement a specific morpheme (such as a morpheme that constitutes a discourse range), the topic search unit 360 is based on the complemented first morpheme information complemented by the abbreviation completion unit 350. The optimum second morpheme information related to the information can be acquired, and the answer sentence search unit 370 obtains an answer sentence more suitable for the user's utterance content based on the second morpheme information acquired by the topic search unit 360. Can be output.

【0153】

As a result, even if the input information from the user is an abbreviated sentence, the conversation control device 1 does not use functions such as neuronetwork and AI intelligence, and what the abbreviated sentence means through the past search results. Since it is possible to infer whether or not the conversation control device 1 is installed, the developer of the conversation control device 1 does not need to be equipped with a neuro-network or AI intelligence, so that the system of the conversation control device 1 can be constructed more easily.

【0154】

[Change example]

The present invention is not limited to the above embodiment, and the following modifications can be made.

【0155】

(First modification example) In this modification example, the conversation database 500 may be an element storage means for storing a plurality of element information indicating the entire set group consisting of a set of a plurality of morphemes in association with the set group. .. Further, the morpheme extraction unit 410 collates the morpheme extracted from the character string with each set group, selects the set group including the extracted morpheme from each set group, and the element associated with the selected set group. The information may be extracted as the first morpheme information.

【0156】

As shown in FIG. 16, some morphemes included in the character string spoken by the user are similar. For example, as shown in FIG. 16, if the element information indicating the entire set group is "gift", the "gift" is similar to presents, gifts, year-end gifts, middle yuan, celebrations, etc. (group group). Therefore, if there is a morpheme similar to the "gift" (such as the above present), the morpheme extraction unit 410 can handle the similar morpheme as a "gift".

【0157】

That is, in the morpheme extraction unit 410, for example, when the morpheme extracted from the character string is a "gift", as shown in FIG. 16, the element information representing the "gift" is a "gift". "Present" can be replaced with "gift".

【0158】

As a result, the morpheme extraction unit 410 can sort out morphemes that are similar to each other, so that the developer who develops the conversation control device corresponds to the semantic space grasped from each of the first morpheme information that is similar to each other. It is not necessary to create the answer sentences related to the two morpheme information and the second morpheme information one by one, and as a result, the amount of data to be stored in the storage unit can be reduced.

【0159】

(Second Change Example) As shown in FIG. 17, in this change example, the ratio calculation unit 361 and the selection unit 362 may be provided in the topic search unit 360.

【0160】

The ratio calculation unit 361 collates the first morpheme information extracted by the morpheme extraction unit 410 with each second information, and for each second morpheme information, the ratio of the first morpheme information to the second morpheme information. It is a calculation means to calculate.

【0161】

Specifically, as shown in FIG. 17, the ratio calculation unit 361 in which the topic search command signal is input from the sentence structure analysis unit 430 is the first morpheme information included in the input topic search command signal. The first morpheme information is collated with each topic title (second morpheme information) belonging to the discourse range stored in the conversation database 500, and the first morpheme information occupies each topic title in each topic title. Calculate the percentage.

【0162】

For example, as shown in FIG. 18, when the first morpheme information constituting the utterance sentence uttered by the user is (Sato; *; I like) {I like Sato}, the ratio calculation unit 361 Each morpheme belonging to "case composition" (Sato; *; likes) is compared with each morpheme included in the topic title (Sato; *; likes), and each morpheme belonging to "case composition" is added to the above topic title. Calculate the percentage that includes (Sato; *; I like) as 100%. The ratio calculation unit 361 performs these calculations for each topic title, and outputs each calculated ratio as a ratio signal to the selection unit 362.

【0163】

The selection unit 362 is a selection means for selecting one second morpheme information from each second morpheme information according to the magnitude of each ratio calculated for each second morpheme information by the ratio calculation unit 361. is there.

【0164】

Specifically, the selection unit 362 in which the ratio signal is input from the ratio calculation unit 361 is selected from each ratio (element of "case composition" / element of "topic title" x 100) included in the input ratio signal. For example, select a topic title with a high percentage (see Figure 18). The selection unit 362 that selects a topic title with a high ratio outputs the selected topic title as a search result signal to the answer sentence search unit 370 and the utterance type determination unit 440. The answer sentence search unit 370 searches for the answer sentence associated with the topic title based on the topic title selected by the selection unit 362.

【0165】

As a result, the selection unit 362 calculates the ratio of the first morpheme information to the second morpheme information for each second morpheme information, and the magnitude of each ratio calculated for each second morpheme information. Since one second morpheme information can be selected from each second morpheme information according to the above, the selection unit 362 can use, for example, the first morpheme information (which constitutes the content of the user's speech). If the second morpheme information, which accounts for a large proportion of the second morpheme information, can be obtained from a plurality of second morpheme information groups, the second morpheme information that follows the semantic space grasped from the first morpheme information can be obtained. As a result, the answer sentence search unit 370 can give an optimum answer to the content of the user's speech.

【0166】

Further, since the selection unit 362 can select a topic title with a high ratio calculated by the ratio calculation unit 361 from a plurality of topic titles, it belongs to the "case structure" included in the utterance sentence of the user. Even if each morpheme and each topic title stored in the conversation database 500 do not completely match, it is possible to acquire a topic title closely related to each morpheme belonging to the "case structure".

【0167】

As a result, the selection unit 362 can acquire a topic title closely related to the "case structure" that constitutes the first morpheme information, so that the developer who develops the conversation control device 1 can obtain the "case structure" that constitutes the first morpheme information. Since it is not necessary to store the topic titles that completely match the "case structure" in the conversation database 500 one by one, the capacity of the conversation database 500 can be reduced.

【0168】

Further, the ratio calculation unit 361 calculates the ratio of the first morpheme information to the second morpheme information for each second morpheme information belonging only to the "discourse range" searched by the discourse range determination unit 340. Therefore, it is no longer necessary to calculate the ratio of the first morpheme information to the "all" second morpheme information, and the second morpheme information that follows the semantic space composed of the first morpheme information can be acquired in a shorter time. As a result, the optimum answer sentence to the utterance content from the user can be quickly output based on the acquired second morpheme information.

【0169】

The ratio calculation unit 361 collates each morpheme of the first morpheme information belonging to each classified attribute with each morpheme of each second morpheme information belonging to each attribute stored in advance for each attribute. It may be the first search means for searching the second morpheme information including each morpheme of the first morpheme information in at least one attribute from the second morpheme information.

【0170】

Specifically, the ratio calculation unit 361 in which the topic search command signal is input is used for each "case" (subject; object; action) of the "case structure" included in the input topic search command signal. The morphemes belonging to "case" are compared with each morpheme belonging to "case" of the topic title consisting of the same "case", and it is determined whether or not the morphemes constituting each other "case" are the same.

【0171】

For example, as shown in FIG. 19, the ratio calculation unit 361 determines that if the morpheme of the "case" of the "case composition" is (dog; person; bite) {dog bites a person}, those morphemes. Match "dog", "person", "bite" with the morpheme "dog", "person", "bite" of the topic title consisting of the same "case" as the "case" that composes those morphemes. However, among the morphemes "dog", "person", and "bite" that make up the topic title, the morpheme "dog" of the "case composition" consisting of the same "case" as the "case" corresponding to each morpheme, Calculate (100%) the percentage that matches "person" and "bite".

【0172】

If the element that constitutes the topic title is (person; dog; bite) {person bites a dog}, the ratio calculation unit 361 uses the same procedure as above to form a morpheme belonging to two cases. Is different, so the degree of agreement between the morphemes that make up the "case composition" and the "topic title" for each "case" is calculated to be 33% (see Fig. 19).

【0173】

The ratio calculation unit 361 that calculated the ratio selects a topic title with a high ratio from each ratio, and outputs the selected topic title as a search result signal to the answer sentence search unit 370 and the utterance type determination unit 440.

【0174】

As a result, the ratio calculation unit 361 sets each morpheme of the first morpheme information belonging to each classified "case structure" (subject case, target case, etc.) and a topic title stored in advance for each "case". Since it is possible to search the second morpheme information including each morpheme of the first morpheme information in at least one "case" from each topic title by collation, the ratio calculation unit 361 is different from the normal word order. When the content of the speech is composed of things, for example, "a person bites a dog", the morpheme of the subject is "person" and the morpheme of the target is "dog". You can search for matching second morpheme information and get the answer text {"really?" Or "I don't understand the meaning"} associated with that second morpheme information (person; dog; chew). can do.

【0175】

That is, the ratio calculation unit 361 can identify utterance contents that are difficult to identify, for example, "a person bites a dog" and "a dog bites a person". For the former, for example, "really?", For the latter, for example, "is it okay?"

【0176】

Further, since the ratio calculation unit 361 may search for the second morpheme information including the morpheme of the first morpheme information in at least one attribute from each second morpheme information belonging to the "discourse range", "all". It is no longer necessary to acquire one second morpheme information from the second morpheme information of, and the second morpheme information that follows the semantic space composed of the first morpheme information can be acquired in a shorter time. As a result, the conversation control device 1 can quickly output the optimum answer sentence to the content of the utterance from the user based on the acquired second morpheme information.

【0177】

The selection unit 362 may select one topic title from each topic title according to a predetermined priority. This priority means the priority for being selected as a topic title. This priority is predetermined by the developer at the development stage.

【0178】

(Third modification example) As shown in FIG. 20, the modification example is not limited to the above embodiment and each modification example, and the communication unit 800 in the conversation control devices 1a and 1b and the communication network 1000. A communication unit 900 for transmitting and receiving data via the communication unit 900, each conversation database 500b to 500d connected to the communication unit 900, and servers 2a to 2c may be provided (conversation control system).

【0179】

Here, the communication network 1000 means a communication network for transmitting and receiving data, and in the present embodiment, for example, the Internet and the like can be mentioned. In this modification, the conversation databases 500b to 500d and the servers 2a to 2c are limited for convenience, but the present invention is not limited to these, and other conversation databases may be provided.

【0180】

As a result, the conversation control unit 300 refers not only to the conversation database 500a arranged inside the conversation control device 1a, but also to other conversation control devices 1b, other conversation databases 500b to 500d, and servers 2a to 2c. Therefore, for example, there is a case where it is not possible to search the conversation range, etc. related to each morphological element (first morphological element information) belonging to the "case structure" included in the topic search command signal from the conversation database 500a. However, by referring to other conversation control devices 1b, conversation databases 500b to 500d, and servers 2a to 2c, it is possible to search for the discourse range related to the above "case structure", depending on the spoken text of the user. You can search for suitable answer sentences.

【0181】

(Fourth modification example) The sentence structure analysis unit 430 stores each "case structure" constituting the specified first morpheme information and each morpheme associated with each "case structure" in the conversation database 500. You may. The answer sentence search unit 370 may store each "case structure" constituting the acquired answer sentence and each morpheme associated with each "case structure" in the conversation database 500.

【0182】

The discourse range determination unit 340 may store the searched discourse range in the conversation database 500. The topic search unit 360 may store the searched second morpheme information in the conversation database 500.

【0183】

The first morpheme information, the second morpheme information, each "case structure" constituting the first morpheme information or the second morpheme information, each morpheme associated with each "case structure", and the searched answer text are displayed. Each of the constituent "case configurations" and each morpheme associated with each "case configuration" and the searched discourse range are stored in the conversation database 500 or the parrot return element database 802 as historical morpheme information by associating them with each other. be able to.

【0184】

The abbreviation completion unit 350 does not include morphemes from each attribute (subject, object, action, etc .; case configuration) that constitutes the first morpheme information based on the first morpheme information extracted by the phrase analysis unit 420. The attribute is searched, and the history morpheme information stored in the conversation database 500 or the parrot return element database 802 is added to the attribute based on the searched attribute.

【0185】

Specifically, the abbreviated sentence complementing unit 350 in which the topic search command signal is input from the discourse range determination unit 340 is an utterance composed of the first form element information based on the first form element information included in the input discourse search command signal. It is determined whether the content is an abbreviated sentence, and if the utterance content consisting of the first form element information is an abbreviated sentence (for example, the subject, object, or action does not have a predetermined form element), the conversation database 500 or The history form information stored in the sentence return element database 802 is added to the first form element information.

【0186】

That is, if the subject included in the history form information is S1, the object is O1, the action A1, the discourse range is D1, and the omitted first morpheme information is W, the complemented first morpheme information W1 is S1W. , O1W, A1W, or D1W.

【0187】

The topic search unit 360 collates the first morpheme information W1 complemented by the abbreviation completion unit 350 with each second morpheme information, and from each "topic title" (second morpheme information), the first morpheme information. The second morpheme information including W1 is searched, and the searched topic title is output as a search result signal to the answer sentence search unit 370 and the utterance type determination unit 440.

【0188】

As a result, even if the utterance content consisting of the first form element information is an abbreviated sentence and is not clear as Japanese, the abbreviated sentence completion unit 350 uses the history form information stored in the conversation database 500 to use the history form information. Since the morphological elements of the omitted first morphological element information can be complemented, the utterance content consisting of the omitted first morphological element information can be clarified.

【0189】

Therefore, when the abbreviated sentence completion unit 350 indicates that the utterance content constituting the first morpheme information is an abbreviated sentence, the first morpheme information so that the utterance content consisting of the first morpheme information becomes appropriate Japanese. Since the morphemes omitted in can be complemented, the topic search unit 360 can use the optimal "topic title" (second morpheme) associated with the first morpheme information based on the first morpheme information complemented by the morpheme. Information) can be acquired, and the answer sentence search unit 370 can output an answer sentence more suitable for the content of the user's speech based on the optimum "topic title" searched by the topic search unit 360. ..

【0190】

(Fifth modification example) As shown in FIG. 21, the topic search unit 360 may include a deletion unit 363 and a discourse addition unit 364. The deletion unit 363 collates the second morpheme information with the discourse range searched by the discourse range determination unit 340 based on the searched second morpheme information, and discourses from each morpheme constituting the second morpheme information. It is a deletion means that deletes morphemes that match the range.

【0191】

Specifically, the topic search unit 360 in which the topic search command signal is input from the abbreviation complement unit 350 contains the first morpheme information included in the input topic search command signal and the discourse determined by the discourse range determination unit 340. The second morpheme information belonging to the range is collated, and the second morpheme information matching the first morpheme information is searched from each second morpheme information.

【0192】

Then, the deletion unit 363 collates the second morpheme information with the morpheme constituting the discourse range determined by the discourse range determination unit 340 based on the searched second morpheme information, and contains the second morpheme information. Therefore, the morpheme that matches the morpheme constituting the discourse range is deleted, and the second morpheme information from which the morpheme is deleted is output to the discourse addition unit 364 as a deletion signal.

【0193】

That is, the deletion unit 363 removes (removes) the current morpheme range D2 (this D2 is composed of morphemes) determined by the discourse range determination unit 340 from each morpheme t1 constituting the second morpheme information. If the result is t2, then t2 = t1-D2).

【0194】

The discourse addition unit 364 acquires another discourse range associated with the discourse range searched by the discourse range determination unit 340 based on the second morpheme information from which the morpheme is deleted by the deletion unit 363, and obtains another discourse range. It is a discourse adding means for adding a morpheme constituting a discourse range to the second morpheme information.

【0195】

Specifically, if the discourse range in which the current discourse range D2 is related to the answer sentence K1 is DK, then the answer sentence K1 or another discourse related to the current discourse range D2 (those having a sibling relationship) Since the range D3 can be expressed as D3 = D2DK, the second morpheme information W2 after adding the morphemes constituting the other discourse range D3 can be W2 = t2D3.

【0196】

For example, each morpheme t1 constituting the second morpheme information is (A movie name; *; interesting) {A movie name is interesting?}, And the current discourse range D2 determined by the discourse range determination unit 340 is (A). In the case of (movie name), the deletion unit 363 first deletes the discourse range D2 (A movie name) from each morpheme t1 (A movie name; *; interesting), and the deleted result is t2 (*; *). ; Interesting) (t2 = t1-D2).

【0197】

If the other morpheme D3 related to the current discourse range D2 (A movie name) is "B movie name", the second morpheme information after adding the morphemes that make up the other discourse range D3. Since W2 is t2D3, it can be (B movie name; *; funny) {B movie name is funny?}.

【0198】

As a result, when the user's utterance content is "A movie name is interesting?", The discourse addition unit 364 matches each morpheme (A movie name; *; interesting) that constitutes the user's utterance content. You can change the second morpheme information (A movie name; *; interesting) to another second morpheme information (B movie name; *; interesting) {B movie name is interesting?} The part 370 can acquire the answer sentence (for example, "B movie name is interesting") associated with the second morpheme information changed in the utterance addition part 364, and can output the acquired answer sentence.

【0199】

As a result, the answer sentence search unit 370 does not directly output the answer sentence to the utterance content of the user, but the utterance content is based on the second morpheme information including the morpheme added by the discourse addition unit 364. Since the answer sentence related to can be output, the output unit 600 can output a more humane answer sentence based on the answer sentence searched by the answer sentence search unit 370.

【0200】

The discourse addition unit 364 is not limited to adding another discourse range to the second morpheme information from which the morpheme has been deleted, and the history morpheme information (conversation) to the second morpheme information from which the morpheme has been deleted. It may be the one that adds (stored in database 500).

【0201】

(Sixth change example) When the topic search unit 360 cannot search the second morpheme information including the first morpheme information from each second morpheme information, the first morpheme information and each answer sentence are selected. When the answer sentence including the first morpheme information can be searched from each answer sentence by collation, it is the first search means for acquiring the second morpheme information associated with the searched answer sentence. You may.

【0202】

Specifically, the topic search unit 360 in which the topic search command signal is input from the abbreviation complement unit 350 uses the first morpheme information and each second morpheme information based on the first morpheme information included in the input topic search command signal. When the morpheme information is collated and the second morpheme information matching the first morpheme information cannot be obtained from each second morpheme information, as shown in FIG. 22, the first morpheme information and the first morpheme information are displayed. Match with the answer text associated with the second morpheme information.

【0203】

By this collation, when the topic search unit 360 determines that the answer sentence contains a morpheme (morpheme or morpheme associated with the action) that constitutes the first morpheme information, the answer sentence includes the morpheme. Search for the associated second morpheme information.

【0204】

As a result, even if the topic search unit 360 cannot search for the second morpheme information that matches the first morpheme information from each second morpheme information, the first morpheme information from each answer sentence. Since the answer sentence including the morpheme (the action or the morpheme associated with the action) that constitutes the above can be specified and the second morpheme information associated with the specified answer sentence can be searched, the content of the user's speech can be searched. The second morpheme information corresponding to the first morpheme information constituting the above can be appropriately searched.

【0205】

As a result, the topic search unit 360 can search for the optimum second morpheme information corresponding to the first morpheme information, so that the answer sentence search unit 370 can search for the optimum second morpheme information searched by the topic search unit 360. Based on, it is possible to search for an appropriate answer sentence to the content of the user's utterance.

【0206】

[program]

The contents described in the conversation control system and the conversation control method can be realized by executing a dedicated program for using a predetermined program language on a general-purpose computer such as a personal computer.

【0207】

Here, as the program language, the topic requested by the user, the degree of emotion of the user for a certain matter, or the types of statements, affirmative sentences, question sentences, repulsive sentences, etc. are associated with morphemes according to their meanings and hierarchies. Languages for storing in a database, for example, DKML (Discourse Knowledge Markup Language), XML (eXtensible Markup Language), C language, etc. developed by the inventors in this embodiment.

【0208】

That is, the conversation control device 1 is used to store data (second form element information, standard contents, answer sentences, answer types, sets, discourse range, element information, and other stored information) stored in each conversation database 500a to 500d, and others. Each part of is constructed by DKML (Discourse Knowledge Markup Language), XML (eXtensible Markup Language), etc., and can be realized by executing a program for using the constructed stored information.

【0209】

According to such a program according to the present embodiment, each morpheme constituting the utterance content of the user is specified, the meaning content grasped from each specified morpheme is analyzed, and the meaning content is associated with the analyzed meaning content. In general, a conversation control device, a conversation control system, and a conversation control method that have the effect of being able to output the optimum answer sentence corresponding to the utterance content of the user by outputting the pre-created answer sentence. It can be easily realized with a general-purpose computer.

【0210】

In addition, the developer who develops the conversation control device 1 can hierarchically construct the second form element information or the like for searching the answer sentence for the utterance content of the user in the database using the language. The conversation control device 1 can acquire an answer sentence to the utterance content based on the utterance content of the user from the database through a hierarchical procedure.

【0211】

That is, the conversation control device 1 has determined and determined the hierarchy of the user's utterance content (for example, whether it is in the upper concept or the lower concept with respect to the second morpheme information stored in the database). An appropriate answer sentence can be searched from each answer sentence accumulated in advance based on the hierarchy.

【0212】

Therefore, the conversation control device 1 does not collate the first morpheme information consisting of the user's uttered content with the "all" second morpheme information stored in advance, and each belongs to a specific hierarchy. Since the second morpheme information and the first morpheme information may be collated, the second morpheme information similar to the first morpheme information can be acquired in a short time.

【0213】

Further, in the communication between the communication unit 800 and the communication unit 900, data may be transmitted / received via a communication network 1000 by a protocol including DKML or the like. As a result, for example, when the conversation control device 1 does not have an answer sentence suitable for the user's utterance content, the conversation control device 1 is suitable for the user's utterance content through the communication network 1000 in accordance with a convention such as DKML. You can search for the answer text (written in DKML etc.) and search for the searched answer text (see Fig. 20).

【0214】

The program can be recorded on a recording medium. As shown in FIG. 23, examples of this recording medium include a hard disk 1100, a flexible disk 1200, a compact disk 1300, an IC chip 1400, and a cassette tape 1500. According to the recording medium on which such a program is recorded, the program can be easily stored, transported, sold, and the like.

【0215】

[Second Embodiment]

(Basic Configuration of Conversation Control Device) The second embodiment of the present invention will be described with reference to the drawings. As shown in FIG. 24, the conversation control device 1 in the present embodiment has substantially the same internal structure as the conversation control device 1 in the first embodiment, but has a selection unit 380 (second search means; selection means). It differs in that. Further, unlike the first embodiment, the conversation control device 1 partially differs in the functions of the topic search unit 360 (first search means) and the answer sentence search unit 370 (second search means; answer sentence search means). ..

【0216】

Except for this difference, the structure is the same as that of the first embodiment and the modified example. Therefore, the description of the structure other than the difference will be omitted. It should be noted that the present embodiment naturally has various functions in the first embodiment, such as a reflexive treatment and a reflexive treatment, and naturally also exerts an effect corresponding to those functions.

【0217】

In this embodiment, the first morpheme information and the topic title, which will be described later, are different from the first embodiment, and each morpheme belonging to the first morpheme information and the topic title is a case such as a subject, an object, or an action. It will be described as being included regardless of the configuration.

【0218】

In the first embodiment, the process in which the conversation control device 1 outputs an answer sentence corresponding to the utterance content based on the utterance content from the user has been described. In the present embodiment, when the meaning of the utterance content from the user can be grasped by a plurality of meanings, the conversation control device 1 utters a topic close to the topic to be developed by the conversation control device 1 from among the meanings. The process of selecting the meaning of the content and outputting the answer sentence corresponding to the selected meaning will be described.

【0219】

Specifically, the conversation control device 1 in the present embodiment is a passive answer process based on the content of the utterance from the user (for example, a process of faithfully answering the question content from the user) as in the first embodiment. Is not an execution, but an active answer processing that voluntarily guides the current topic to a specific topic from the conversation control device 1. The structure of the conversation control device 1 in this embodiment is as follows. The conversation control method and program in the present embodiment can be executed with the same processing content as the processing content in the conversation control device 1.

【0220】

As shown in FIG. 25, in the present embodiment, the phrase includes a topic title indicating a morpheme consisting of one character, a plurality of character strings, or a combination thereof, and the topic title includes a response sentence to the user. It is associated. This phrase may include, for example, an utterance content or a topic title. In this embodiment, this phrase corresponds to a topic title as shown in FIG.

【0221】

For example, as shown in Fig. 25, if the topic title 1 is (A device; IR (Inazuma rush); Tell me) {Tell me the IR (Inazuma rush) of A device}, the topic title 1 is Topic titles 2 (Company A; IR (Investor Relations); Tell me) {Tell me IR (Investor Relations) of Company A} are listed as topic titles that include some of the constituent morphemes (IR; tell me). Be done. Each of the above phrases, each topic title, and each answer sentence is stored in the conversation database 500 (morpheme storage means).

【0222】

In addition, the common topic titles are associated with priorities for being selected as answer sentences. In addition, it is desirable that the answer sentence includes the content for guiding to a specific topic or the content related to the associated topic title.

【0223】

The topic search unit 360 (first search means) searches for each phrase including the utterance content from a plurality of phrases stored in advance in the conversation database (morpheme memory means) based on the utterance content input from the user. Is what you do. That is, in the present embodiment, the topic search unit 360 uses the topic titles including the first morpheme information from the pre-stored topic titles based on the first morpheme information extracted by the sentence structure analysis unit 430. To search for.

【0224】

Specifically, as shown in FIG. 25, when the first morpheme information (IR; tell), the topic search unit 360 includes the topic title 1 including the first morpheme information (IR; tell). Search for (A device; IR; Tell me) and topic title 2 (A company; IR; Tell me).

【0225】

The selection unit 380 (selection means) selects a phrase related to the topic to be developed in advance from each phrase based on each phrase searched by the topic search unit 360. That is, in the present embodiment, when a plurality of topic titles are searched by the topic search unit 360, the selection unit 380 determines the size of each priority associated with each of the plurality of searched topic titles. Select one topic title.

【0226】

Here, the fact that a plurality of topic titles including the utterance content or the first morpheme information constituting the utterance content are searched means that the utterance content is captured in a plurality of meanings in the present embodiment. As a result, when the utterance content is captured in a plurality of meanings, that is, when a plurality of topic titles are searched, the selection unit 380 selects the topic to be developed in advance by the conversation control device 1 from the searched topic titles. Select topic titles related to (topic titles associated with high priority).

【0227】

Specifically, as shown in FIG. 25, when the sentence structure analysis unit 430 extracts the first morpheme information (IR; teach), the topic search unit 360 uses the first morpheme information (IR; teach). Search for topic title 1 and topic title 2 including. As shown in FIG. 25, since the priority associated with the searched topic title 1 is 2 and the priority associated with the topic title 2 is 1, the selection unit 380 has the topic title 1 and From the topic titles 2, the topic title 2 associated with the priority 1 is selected.

【0228】

That is, when a plurality of topic titles are searched by the topic search unit 360, the selection unit 380 identifies the highest priority from each priority associated with each searched topic title. , Select topic titles associated with the specified priority. The selection unit 380 may specify the lowest priority from each of the above priorities and select a topic title associated with the specified priority.

【0229】

The answer sentence search unit 370 (answer sentence search means) searches for the answer sentence corresponding to the phrase selected by the selection unit 380. That is, in the present embodiment, the answer sentence search unit 370 searches for the answer sentence associated with the topic title based on the topic title selected by the selection unit 380.

【0230】

Specifically, as shown in FIG. 25, the answer sentence search unit 370 corresponds to the topic title 2 when the topic title 2 (Company A; IR; tell me) is selected by the selection unit 380, for example. Get the attached answer sentence 2 (IR of company A is ~). The output unit 600 outputs the answer sentence 2 (IR of company A is ~) acquired by the answer sentence search unit 370.

【0231】

If the topic title searched last time is included in each topic title searched this time, the selection unit 380 will select a topic title different from the topic title searched last time from among the topic titles searched this time. May be elected. That is, when the topic title searched last time is included in each topic title searched this time, the selection unit 380 is associated with the topic title searched last time from each topic title searched this time. The next priority of the priority may be specified, and the topic title associated with the specified priority may be selected.

【0232】

Specifically, as shown in FIG. 25, for example, in the selection unit 380, the topic title 2 (Company A; IR; tell) searched last time is the topic title 1 or the topic title searched this time. If it is included in 2, specify the priority 1 associated with the topic title 2 (Company A; IR; Tell me) that was searched (or selected) last time. This selection unit 380 selects the topic title 1 (A device; IR; tell me) associated with the priority 2 next to the specified priority 1 from the topic title 1 or the topic title 2 searched this time. elect.

【0233】

(Conversation Control Method Using Conversation Control Device) The conversation control method by the conversation control device 1 having the above configuration can be implemented by the following procedure. FIG. 26 is a flow chart showing the procedure of the conversation control method according to the present embodiment. Since the processes (S201) to (S204) shown in FIG. 26 are the same as the processes (S101) to (S104) in the first embodiment, detailed description thereof will be omitted.

【0234】

As shown in FIG. 26, the topic search unit 360 selects each topic title including the first morpheme information from each topic title stored in advance based on the first morpheme information extracted by the sentence structure analysis unit 430. Take steps to search for (S205). Specifically, as shown in FIG. 25, when the first morpheme information (IR; tell), the topic search unit 360 includes the topic title 1 including the first morpheme information (IR; tell). Search for (A device; IR; Tell me) and topic title 2 (A company; IR; Tell me).

【0235】

After that, when each topic title is searched by the topic search unit 360, the selection unit 380 selects one topic title according to the size of each priority associated with each searched topic title. Take the step to do (S206). Specifically, as shown in FIG. 25, when the sentence structure analysis unit 430 extracts the first morpheme information (IR; teach), the topic search unit 360 uses the first morpheme information (IR; teach). Search for topic title 1 and topic title 2 including.

【0236】

Since the priority associated with the searched topic title 1 is 2 and the priority associated with the topic title 2 is 1, the selection unit 380 is selected from the topic title 1 and the topic title 2. Select topic title 2 associated with priority 1.

【0237】

On the other hand, when the topic title searched last time is included in each topic title searched this time, the selection unit 380 is associated with the topic title searched last time from each topic title searched this time. The next priority of the priority is specified, and the topic title associated with the specified priority is selected.

【0238】

Specifically, as shown in FIG. 25, for example, in the selection unit 380, the topic title 2 (Company A; IR; tell me) searched last time is included in the topic title 1 or topic title 2 searched this time. In this case, specify the priority 1 associated with the previously searched topic title 2 (Company A; IR; Tell me). This selection unit 380 selects the topic title 1 (A device; IR; tell me) associated with the priority 2 next to the specified priority 1 from the topic title 1 or the topic title 2 searched this time. elect.

【0239】

Next, the answer sentence search unit 370 performs a step of searching the answer sentence associated with the topic title based on the topic title selected by the selection unit 380 (S207). Specifically, as shown in FIG. 25, the answer sentence search unit 370 corresponds to the topic title 2 when the topic title 2 (Company A; IR; tell me) is selected by the selection unit 380, for example. Get the attached answer sentence 2 (IR of company A is ~). The output unit 600 outputs the answer sentence 2 (IR of company A is ~) acquired by the answer sentence search unit 370.

【0240】

(Action and effect of conversation control device and conversation control method) According to the invention having the above configuration, as each topic title including the first morpheme information (IR; tell) extracted by the sentence structure analysis unit 430, the topic title If 1 (A device; IR (Inazuma Rush); Tell me) and topic title 2 (Company A; IR (Investor Relations); Tell me) are searched, the selection department 380 will find the searched topic title 1 And, from the topic titles 2, the topic titles 2 to which the high priority is associated can be selected (see Fig. 25).

【0241】

Here, the fact that each phrase including the input information is searched for a plurality of times, or that the second morpheme information including the first morpheme information constituting the input information is searched for a plurality of times means that the input information is regarded as having a plurality of meanings. Means that. Therefore, when the utterance content is grasped in a plurality of meanings, that is, when a plurality of topic titles are searched, the selection unit 380 wants to develop in advance from each topic title in the conversation control device 1 as described above. Topic titles related to topics (topic titles associated with high priority) can be selected. As a result, the answer sentence search unit 370 can output an answer sentence (for example, a sentence for guiding to a specific topic) associated with the topic title based on the topic title selected by the selection unit 380. ..

【0242】

In addition, the conversation control device 1 does not output a passive answer sentence based on the content of the utterance from the user (for example, faithfully answering the content of the question from the user), but voluntarily from the conversation control device. It is possible to output an active answer sentence that guides the current topic to a specific topic.

【0243】

Further, since the answer sentence includes the content for guiding to a specific topic, the answer sentence search unit 370 expands the current topic in advance by outputting the answer sentence via the output unit 600. You can more accurately guide to the topic you want to make. That is, the conversation control device 1 can internally take the initiative on the current topic and more accurately guide the current topic to a specific story.

【0244】

Furthermore, the answer sentence search unit 370 searches for the corresponding answer sentence using the morphemes excluding the Japanese-specific particles (te, ni, o, etc.) included in the above input information, so that each morpheme is searched. Based on the meaning and content that can be grasped from, the answer sentence created in advance can be obtained more accurately. That is, the answer sentence search unit 370 can search for the answer sentence more suitable for the input information, rather than simply searching for the answer sentence associated with the keyword by using the entire input information as a keyword.

【0245】

In addition, since the topic search unit 360 searches for topic titles including the first morpheme information, it is not necessary to search for topic titles that completely match the input information from the user. As a result, the developer who develops the conversation control device 1 does not need to store a huge amount of answer sentences corresponding to the input information expected to be input by the user in advance, and the capacity of the storage unit can be reduced. it can.

【0246】

(Modification Example) The present invention is not limited to the above embodiment, and the following modifications can be made. When each topic title searched this time by the topic search unit 360 is searched more than a predetermined standard number of times, the selection unit 380 searches for a topic title different from the previously selected topic title. It may be selected from topic titles.

【0247】

Specifically, in the selection unit 380, for example, the topic title 1 (A device; IR; tell me) selected last time is included in the topic title 1 or the topic title 2 searched this time, and the topic title searched this time. Identify whether 1 or topic title 2 has been searched more than a predetermined reference number of times (for example, 5 times).

【0248】

When the specified number of times exceeds a predetermined reference number of times (for example, 5 times), the selection unit 380 has a priority associated with the previously selected topic title 1 (A device; IR; tell). Identify one. The selection unit 380 selects the topic title 2 (Company A; IR; tell me) associated with the priority 2 next to the specified priority 1 from the topic title 1 or the topic title 2 searched this time. To do.

【0249】

On the other hand, if the number of times counted does not exceed the standard number of times (for example, 5 times), the selection unit 380 assigns the previously searched topic title 1 (A device; IR; tell) to another topic title 2, Priority is given to topic title 3. The answer sentence search unit 370 searches for the answer sentence associated with the topic title based on the topic title selected by the selection unit 380. The answer sentence search unit 370 outputs the answer sentence acquired via the management unit 310 to the output unit 600.

【0250】

As a result, if the topic title selected last time is included in each topic title searched this time by the topic search unit 360, and each topic title searched this time is searched more than a predetermined standard number of times, the selection unit The 380 can select a topic title different from the topic title selected last time from each topic title searched this time.

【0251】

That is, when the same utterance content is repeatedly uttered by the user, the selection unit 380 can sequentially change the topic title according to the number of times the utterance is repeated. As a result, the conversation control device 1 can output an answer sentence that guides the current topic to a specific topic according to the number of repeated utterance contents. In addition, when the same utterance content is repeatedly spoken, the conversation control device 1 guides the current topic to another topic, so that the user can feel as if he / she is talking to a human being. ..

【0252】

The present invention is not limited to a device or the like (conversation robot or the like) for the purpose of having a conversation, and this function can also be used in a game machine or the like.

【0253】

[Effect of the invention]

As described above, according to the present invention, when the content of a user's utterance is understood to have a plurality of meanings, the current topic can be specified by outputting an answer sentence related to a specific topic to be developed in advance. You can lead to a topic.

[Simple explanation of drawings]

FIG. 1 is a block diagram showing a schematic configuration of a conversation control system according to the first embodiment.

FIG. 2 is a block diagram showing an internal structure of a conversation control unit and a sentence analysis unit according to the first embodiment.

FIG. 3 is a diagram showing the contents of each morpheme extracted by the morpheme extraction unit in the first embodiment.

FIG. 4 is a diagram showing the contents of each clause extracted by the clause analysis unit in the first embodiment.

FIG. 5 is a diagram showing the contents of a case specified by the sentence structure analysis unit in the first embodiment.

FIG. 6 is a diagram showing a speech sentence type specified by the utterance type determination unit in the first embodiment.

FIG. 7 is a diagram showing the contents of each dictionary stored in the utterance type database in the first embodiment.

FIG. 8 is a diagram showing the contents of a hierarchical structure constructed inside the conversation database in the first embodiment.

FIG. 9 is a diagram showing a detailed relationship of a hierarchical structure constructed inside the conversation database in the first embodiment.

FIG. 10 is a diagram showing the contents of a topic title constructed inside the conversation database in the first embodiment.

FIG. 11 is a diagram showing the contents of a response sentence type associated with a topic title constructed inside the conversation database in the first embodiment.

FIG. 12 is a diagram showing the contents of a topic title and a answer sentence belonging to the discourse range constructed inside the conversation database in the first embodiment.

FIG. 13 is a diagram showing the contents of reflective element information stored in the reflective element database in the first embodiment.

FIG. 14 is a diagram showing the contents of the morphemes of the Echolalia element and the Echolalia element stored in the Echolalia element database in the first embodiment.

FIG. 15 is a flow chart showing a procedure of a conversation control method according to the first embodiment.

FIG. 16 is a diagram showing utterance contents arranged by the morpheme extraction unit in the first modification example.

FIG. 17 is a diagram showing an internal configuration of a topic search unit in the second modification example.

FIG. 18 is a diagram showing how the ratio calculation unit in the second modification collates each morpheme belonging to the case structure with each topic title for each topic title.

FIG. 19 is a diagram showing how the ratio calculation unit in the second modification collates each morpheme belonging to each configuration with each morpheme belonging to topic title for each case.

FIG. 20 is a diagram showing a schematic configuration of a conversation control system in a third modification example.

FIG. 21 is a diagram showing an internal configuration of a topic search unit in the fifth modification example.

FIG. 22 is a diagram showing how the topic search unit in the sixth modification collates the first morpheme information with the topic title or answer sentence.

FIG. 23 is a diagram showing a recording medium for storing a program according to the first embodiment.

FIG. 24 is a block diagram showing an internal configuration of a conversation control device according to a second embodiment.

FIG. 25 is a diagram showing the contents of a topic title and a answer sentence constructed inside the conversation database in the second embodiment.

FIG. 26 is a diagram showing a processing procedure of the conversation control method according to the second embodiment.

[Explanation of symbols]

1 ... conversation control device, 2 ... server, 100 ... input unit, 200 ... voice recognition unit, 300 ... conversation control unit, 310 ... management unit, 320 ... reflexive Judgment unit, 330 ... Echolalia judgment unit, 340 ... Discourse range determination unit, 350 ... Abbreviation completion unit, 360 ... Topic search unit, 361 ... Ratio calculation unit, 362 ... Selection Department, 363 ... Delete Department, 364 ... Discourse Addition Department, 370 ... Answer Sentence Search Department, 380 ... Selection Department, 400 ... Sentence Analysis Department, 410 ... Morphological Extraction Department, 420 ... Phrase analysis department, 430 ... Sentence structure analysis department, 440 ... Speech type determination unit, 450 ... Morphological database, 460 ... Speech type database, 500 ... Conversation database, 600 .. Output unit, 700 ... voice recognition dictionary storage unit, 800 ... communication unit, 801 ... reflective element database, 802 ... calculation element database, 900 ... communication unit, 1000 ... communication network , 1100 ... hard disk, 1200 ... flexible disk, 1300 ... compact disk, 1400 ... IC chip, 1500 ... cassette tape