Agent control device

Intelligent body control device technical field

[0001] The present disclosure relates to an agent control device that performs agent-related processing in response to a user's request.

Background technique

[0002] In Japanese Patent Laid-Open No. 2018789984, a voice dialogue agent is disclosed, which accepts an input voice signal, and performs voice recognition processing on the input voice signal, and based on the result of the voice recognition processing and the agent information , Decide which agent to use to implement processing based on the input voice signal.

[0003] When an agent performs a function that requires continuity, such as a call, it is desirable to suppress the operation of other agents. On the other hand, when other agents have functions that are more important than functions that require continuity such as calls, such as assisting rescue activities when an emergency occurs, it is desirable to make other agents functions Important function execution.

Summary of the invention

[0004] The purpose of the present disclosure is to provide an agent control device, which is able to perform the interruption of the function when another agent is activated in the process of performing a function that requires continuity. Suppress, and can give priority to the execution of important functions of other agents under certain conditions.

[0005] The agent control device of the first aspect is an agent control device capable of operating a plurality of agents, and includes a storage unit that stores an interruption permission list, and the interruption permission list defines Whether each function of the running agent or the operation of the one agent can be interrupted relative to the running status of the one agent; a first request unit, which requests the operation of each agent under a predetermined opportunity; a second request Section, which requests the operation of other agents under a specific opportunity; the setting section, which is accompanied by the operation of the one agent, and refers to the interrupt permission list to determine whether the operation of the other agent is relevant Whether the information can be set; the management part, which manages in the following manner, that is, when the first request part has information about the other agent during the operation of the one agent under the predetermined opportunity In the case where the request for the operation of the agent and the availability information indicates that the other agent is not operational, the agent does not respond to the request, but makes the one agent continue. When the specific opportunity occurs in the When a request for the operation of the other agent is received from the second requesting unit during the operation of one agent, the other agent is operated based on the request.

[0006] The agent control device of the first aspect is configured to be capable of operating a plurality of agents. In this agent control device, the storage unit stores an interruption permission list that defines the availability of interruption of each function of one agent being executed or the operation status of one agent. In addition, in this agent control device, one agent is requested through the first requesting unit, and the other agents are requested through the first requesting unit and the second requesting unit. Here, the "predetermined opportunity" requested by the first request unit refers to, for example, the user's utterance to the microphone and the depression of a PTT (Push-To-Talk) switch. In addition, the "specified trigger" of the second request unit's request refers to, for example, the user's utterance with respect to the microphone based on a specific sentence or the pressing of a specific switch. When the first agent runs, the setting unit refers to the interrupt permission list to set the permission information related to the running permission of other agents.

[0007] Furthermore, the management section manages in the following manner, that is, when the first request section has a request for the operation of another agent during the operation of one agent, but the permission information indicates that the other agent cannot be operated. Next, instead of responding to the request, an agent is allowed to continue. As a result, in the agent control device, it is possible to suppress the interruption of the function due to the activation of other agents when one agent is performing a function that requires continuity at a normal time.

[0008] On the other hand, the management unit performs management in such a way that when a request for the operation of another agent is requested from the second requesting unit during the operation of one agent, the request is made based on the request. Other agents run. As a result, in this agent control device, it is possible to give priority to the execution of important functions of other agents under specific conditions.

[0009] In the agent control device of the second aspect, in the agent control device described in the first aspect, in the interruption permission list, the required continuity of the function of the one agent is specified In order to be uninterruptible, the other agent has a function provided in an emergency, and the specific opportunity is the utterance based on a sentence associated with an emergency situation.

[0010] In the agent control device described in the second method, although the function is usually not interrupted during the operation of an agent's required continuous function, when it is received, it will be associated with an emergency situation. When an emergency function of another agent is requested, the emergency function will be executed. Therefore, according to this agent control device, it is possible to prioritize the execution of functions and the like for assisting rescue activities in other agents in an emergency.

[0011] The agent control device of the third aspect is that in the agent control device described in the first aspect or the second aspect, the management unit performs management in the following manner, that is, when the agent is in the In the case that there is a request for the operation of the other agent from the first request part during the operation and the availability information indicates that the other agent cannot be operated, the request is reserved and the one The agent continues, and after the operation of the one agent that is continued to run ends, the other agent is operated in response to the reserved request.

[0012] The agent control device of the third mode does not abandon the operation request of the other agent but retains it even when the other agent cannot run during the operation of one agent. Therefore, according to the agent control device, after one agent ends, other agents can be run without having to run another agent again.

[0013] According to the present disclosure, it is possible to suppress the interruption of the function due to the activation of other agents when an agent is performing a function that requires continuity at ordinary times, and to enable it under certain conditions. Important functions of other agents are executed first.

Description of the drawings

[0014] The exemplary embodiments of the present disclosure will be described in detail based on the following drawings, in which:

[0015] FIG. 1 is a diagram showing a schematic configuration of an intelligent body system according to the first embodiment.

[0016] FIG. 2 is a block diagram showing the hardware configuration of the vehicle according to the first embodiment.

[0017] FIG. 3 is a diagram showing the contents of the interruption permission list of the first embodiment.

[0018] FIG. 4 is a block diagram showing the functional configuration of the host in the first embodiment.

[0019] FIG. 5 is a sequence diagram showing the flow of processing in the agent system of the first embodiment.

[0020] FIG. 6 is a sequence diagram showing the flow of processing in the agent system of the first embodiment, and is a diagram continuation of FIG. 5.

[0021] FIG. 7 is a sequence diagram showing the flow of processing in the agent system of the second embodiment.

Detailed ways

[0022] [First Embodiment]

[0023] As shown in FIGS. 1 and 2, the agent system 10 of the first embodiment is configured to include a vehicle 12, a server 14 of the company, and a server 16 of another company. The vehicle 12 is equipped with a head unit 20 as an intelligent body control device, a communication device 22, a touch panel 24, a speaker 26, and a microphone 28. The communication device 22 of the vehicle 12, the own company's server 14, and the other company's server 16 are connected to each other via a network N, respectively.

[0024] The company's server 14 is a server owned by the company that is the manufacturer of the vehicle 12. The company server 14 has a function of estimating the intention of the user U to utter a voice in order to realize the function of the company agent as a service of the company. The companys intelligent body has functions such as calling, obtaining weather/news, obtaining vehicle information, searching destinations, and requesting rescue. Here, the rescue request is a function provided to the user U in an emergency. For example, when the user U as the driver becomes unwell or the vehicle 12 has an accident, the emergency vehicle can be deployed by the operator. The company's agent is an example of other agents.

[0025] The other company server 16 is a server owned by another company that is not the manufacturer of the vehicle 12. The other company server 16 has a function of inferring the user U's intention to speak in order to realize the function of the other company agent as a service of the other company. In other company's agents, it has functions such as calling, settlement, obtaining weather/news, providing music, audiobooks, etc. The other company agent is an example of an agent. In addition, the same function can also be realized by the company's agent and other company's agents.

[0026] (Vehicle)

[0027] As shown in FIG. 2, the host 20 is configured to include a CPU (Central Processing Unit, central processing unit) 20A, a ROM (Read Only Memory, read only memory) 20B, and a RAM (Random Access Memory, random access memory). ) 20C, memory 20D, communication I/F (Inter Face, connect to D) 20E, and input/output I/F 20F. The CPU 20A, the ROM 20B, the RAM 20C, the storage 20D, the communication I/F 20E, and the input/output I/F 20F are connected via an internal bus 20G so as to be able to communicate with each other. The CPU 20A is an example of a processor, and the RAM 20C is an example of a memory.

[0028] The CPU 20A is a central processing unit that executes various programs or controls various parts. That is, the CPU 20A reads the program from the ROM 20B or the storage 20D, and executes the program using the RAM 20C as a work area.

[0029] The ROM 20B stores various programs and various data. In the ROM 20B of this embodiment, a control program for controlling the host 20 is stored.

[0030] The RAM 20C is used as a work area to temporarily store programs or data.

[0031] The storage 20D as a storage unit is composed of an HDD (Hard Disk Drive) or an SSD (Solid State Drive), and stores various programs and various data. The storage 20D of this embodiment stores the processing program 100 and the interruption permission list 110.

[0032] The processing program 100 is a program for controlling the own company agent and other company agents.

[0033] As shown in FIG. 3, the interruption permission list 110 is a list that specifies the interruption permission of the function in the execution of each function of the agent of another company. In the interruption permission list 110, if it is a function of another company's agent that requires continuity, it is specified that the function being executed cannot be interrupted even if the company's agent is requested. For example, when the executed function of the agent of another company is "call" and "settlement", it is specified that the interruption of the function is set to "unavailable".

[0034] In addition to the dagger, for example, the function of the agent of another company being executed is "Get Weather/News" and "Music"

In this case, it is specified as "available" that the interruption of the function is enabled.

[0035] As shown in FIG. 2, the communication I/F 20E is an interface for connecting with the communication device 22. The interface uses, for example, a communication standard based on the CAN protocol. The communication I/F 20E is connected to the external bus 20H.

[0036] The input/output I/F 20F is an interface for communicating with the touch panel 24, the speaker 26, and the microphone 28 mounted on the vehicle 12. In addition, the touch panel 24, the speaker 26, and the microphone 28 may be directly connected to the internal bus 20G. [0037] The communication device 22 is a wireless communication module for communicating with the server 14 of the company and the servers 16 of other companies. This wireless communication module uses communication standards such as 5G, LTE, and Wi-Fi (registered trademark), for example. The communication device 22 is connected to the network N.

[0038] The touch panel 24 is provided on the instrument panel, and has the functions of a liquid crystal display as a display unit and a touch panel as an input unit.

[0039] The speaker 26 is provided on an instrument panel, a center console, a front pillar, a front wall, etc., and is a device for outputting voices related to the own company's agent and other company's agents.

[0040] The microphone 28 is provided on the front pillar or dash panel of the vehicle 12, and is a device that collects the voice uttered by the user U who is an occupant of the vehicle 12.

[0041] As shown in FIG. 4, in the host 20 of this embodiment, the CPU 20A executes the processing program 100 to serve as the first request unit 200, the second request unit 210, the first execution unit 220, and the second execution unit 230. , The setting unit 240 and the management unit 250 function.

[0042] The first requesting unit 200 has a function of requesting the operation of an agent under a predetermined opportunity. Here, the "predetermined opportunity" includes the utterance of the user U to the microphone 28 and the pressing of a PTT (Push-ToTalk) switch (not shown) provided on a steering wheel or the like. When the voice information based on the utterance of the user U includes a normal wake-up word for the company's agent, the first request unit 200 sends the voice information to the company's server 14 to request the operation of the company's agent. In addition, when the voice information based on the utterance of the user U includes a wake-up word for the agent of another company, the first request unit 200 sends the voice information to the server 16 of the other company to request the operation of the agent of the other company.

[0043] The second requesting unit 210 has a function of requesting the operation of another agent under a specific opportunity. Here, the "specific opportunity" includes the user U's utterance with respect to the microphone 28 based on a specific sentence and the pressing of a specific switch. The specific sentence is a sentence that associates with an emergency situation, for example, has a sentence including "Help", "emergency situation", "request for rescue", and so on. In addition, the specific switch is a dedicated switch for requesting rescue provided separately from the PTT switch. The second request unit 210 is executed when the possession flag described below is turned on.

[0044] The first execution unit 220 has a function of operating the company's agent. The first execution unit 220 executes the function of the own company agent based on the intention information provided from the own company server 14 that has transmitted the voice information based on the utterance.

[0045] The second execution unit 230 has a function of causing other company agents to operate. The second execution unit 230 executes the function of the agent of the other company based on the intention information provided from the server 16 of the other company that has transmitted the voice information based on the utterance.

[0046] The setting unit 240 has a function of referring to the interruption permission list 110 to set the permission information related to the running permission of each agent. The availability information of this embodiment is an possession flag that is a flag that can be set to on (ON) and off (OFF), and the setting unit 240 will be based on each of the other company agents specified in the interruption permission list 110. Whether each function can be interrupted or not is used to set the occupied flag. Specifically, the setting unit 240 sets the possession flag when the function of the agent of the other company is uninterruptible.

Is turned on, and the occupancy flag is set to off when the function ends.

[0047] The management unit 250 has a function of managing the operation of each agent. The management part 250 of this embodiment manages in the following manner, that is, when the first request part 200 has a request for the operation of the own company's agent during the operation of another company's agent, and the possession flag is turned on In this case, it does not respond to the request for the operation of the own company's agent, but makes the other company's agent continue. In addition, when there is a request for the operation of the own company's agent from the second request unit 210 during the operation of the other company's agent, the management unit 250 causes the own company's agent to operate based on the request.

[0048] (Control flow)

[0049] Using the sequence diagrams of FIGS. 5 and 6, the flow of processing executed in the intelligent body system 10 of the present embodiment will be described. The processing in the host 20 is realized by the CPU 20A functioning as the first request unit 200, the second request unit 210, the first execution unit 220, the second execution unit 230, the setting unit 240, and the management unit 250 described above.

[0050] In step S10 of FIG. 5, the user U speaks toward the host 20. For example, the user U utters the Agent, I want to go to X", "Assistant, call Ya", etc., to send a request to the agent.

[0051] In step S11, the host 20 implements voice recognition of the voice generated by the utterance of the user U.

[0052] In step S12, the host 20 detects which of the company's agent and the other company's agent is to be activated based on the voice information generated by the voice recognition. For example, if there is a wake-up word of "Agent" in the uttered voice, the host 20 detects the agent of the company as the agent to be activated. In addition, if there is a wake-up word of "Assistant" in the uttered voice, the host 20 detects an agent of another company as an agent to be activated.

[0053] In step S13, the host 20 determines whether the possession flag is off. When the host 20 determines that the occupancy flag is not off, that is, it is on, it proceeds to step S14. On the other hand, when the host 20 determines that the possession flag is off, the process proceeds to step S15.

[0054] In step S14, the host 20 discards the request for the agent. Then, the execution process of the agent ends.

[0055] In step S15, the host 20 transmits voice information to the server of the agent detected in step S12. Figure 5 is an example of making a request related to the agent of another company. When the user U utters "Assistant, call ύ", the voice message of "call ya" will be sent to the other company Server 16.

[0056] In step S16, the other company server 16 performs voice recognition based on the received voice information, and performs intention extraction. For example, extract the intention to call ya from the voice information of "call ya".

[0057] In step S17, the other company server 16 transmits the extracted intention to the host 20 as intention information.

[0058] In step S18, the host 20 starts the operation of the agent of another company. That is, when the host 20 receives the intention information to call y from the server 16 of another company, it activates the call function, and refers to the contact information of y obtained from the server 16 of the other company or stored in the memory 20D. Come call y. As a result, the host 20 starts talking.

[0059] In step S19, the host 20 refers to the interrupt permission list 110. For example, as shown in FIG. 3, when another company's agent is making a call, information that the interruption of the other company's agent is set to "impossible" is acquired.

[0060] In step S20 of FIG. 5, the host 20 determines whether the agent of another company is uninterruptible. When the host 20 determines that the agent of the other company is uninterruptible, the process proceeds to step S21. On the other hand, when the host 20 determines that the agent of another company is not uninterruptible, the process proceeds to step S22 in FIG. 6.

[0061] In step S21, the host 20 sets the occupancy flag to on.

[0062] The processing from step S22 to step S24 in FIG. 6 is the same as the processing from step S10 to step S12 described above.

[0063] Next, when the occupancy flag is on, in step S25, the host 20 determines whether it is in an emergency state. Specifically, when the result of the voice recognition in step S23 includes a sentence that is associated with an emergency situation, the host 20 determines that it is an emergency state. When the host 20 determines that it is not in an emergency state, the process proceeds to step S26. On the other hand, when the host 20 determines that it is an emergency state, the process proceeds to step S30.

[0064] The processing of step S26 and step S27 is the same as the processing of step S13 and step S14 described above.

[0065] In step S28, the host 20 determines whether the agent of another company has ended. When the host 20 determines that the other company agent has not ended, that is, when the other company agent is still running, the process returns to step S22. On the other hand, if the host 20 determines that the agent of another company has ended, the process proceeds to step S29.

[0066] In step S29, the host 20 sets the occupancy flag to off. Then, the execution process of the agent ends.

[0067] When it is determined that the possession flag is off in step S26, in step S30, the host 20 transmits voice information to the server of the agent detected in step S24. Figure 6 is an example of making a request related to our companys agent. When the user U utters "Agent, I want to go to X", a voice message such as "I want to go to X" will be sent to the company Server 14. In addition, when the user U utters "request for rescue" as a sentence associated with an emergency situation, the uttered voice information is sent to the server 14 of the company.

[0068] In step S31, the company's server 14 performs voice recognition based on the received voice information, and performs intention extraction. For example, the intention of searching for the destination X is extracted from the voice information of "I want to go to X". In addition, for example, the intention to talk with the operator who assists the rescue request is extracted from the voice message of "request for rescue".

[0069] In step S32, the server 14 of the company sends the extracted intention as intention information to the host 20.

[0070] In step S33, the host 20 starts the operation of the company's agent. In the event of an emergency, other company agents that are running will be interrupted and terminated, enabling a call with the operator.

[0071] (Summary of the first embodiment)

[0072] The host computer 20 of the present embodiment is configured to be capable of operating the own company agent and other company agents as a plurality of agents. In the host 20, an interruption permission list 110 that specifies whether or not to interrupt each function of the agent of another company that is running is stored in the storage 20D. In the present embodiment, the first requesting unit 200 requests the operation of the own company agent or other company agents at a predetermined opportunity generated by the utterance, the operation of the PTT switch, and the like. In addition, the second request unit 210 requests the operation of the own company's agent at a specific opportunity based on the utterance of a specific sentence and the operation of a specific switch. In the present embodiment, when another company agent is operating, the setting unit 240 refers to the interruption permission list 110 to set the availability information related to the availability of the own company agent as an possession flag.

[0073] Furthermore, the management section 250 performs management in the following manner, that is, when the first request section 200 has a request for the operation of the own companys agent during the operation of another companys agent, but the possession flag is turned on Next, discard the request and let other company agents continue. That is, according to the present embodiment, it is possible to deal with the situation where the agent of the company is activated while the agent of another company is performing a function that requires continuity, such as call or settlement, and the function that is required continuity is interrupted. Suppress.

[0074] On the other hand, the management unit 250 performs management in a manner that, when a request for the operation of the own company's agent is received from the second requesting unit 210 during the operation of another company's agent, based on This request causes the company's agent to operate. That is, according to the present embodiment, it is possible to give priority to the operation of the own company's agent under certain conditions.

[0075] In addition to daggers, in this embodiment, the important function of assisting rescue activities is set to specific conditions.

In this case, the second requesting unit 210 receives a sentence reminiscent of an emergency situation and requests the emergency function of the company's agent. Therefore, according to the present embodiment, it is possible to give priority to the function of assisting rescue activities in the company's agent in an emergency.

[0076] In addition, according to the present embodiment, by setting the possession flag as the availability information, it is possible to collectively manage agents with different functions by turning the possession flag on and off.

[0077] [Second Embodiment]

[0078] The first embodiment adopts the following manner, that is, when the possession flag is on, the operation request of the new agent is discarded. In contrast, the second embodiment is formed to reserve the operation request of the new agent when the possession flag is on. Hereinafter, the differences from the first embodiment will be described. In addition, the other structure is the same as that of the first embodiment, so detailed description is omitted.

[0079] The management part 250 of this embodiment is for the case where a request for the operation of the own company's agent is requested from the first requesting part 200 during the operation of another company's agent, and the possession flag is turned on. The request regarding the operation of the own company's agent is reserved and the other company's agent continues. Then, the management unit 250 causes the own company agent whose request is in the reserved state to operate after the other company agent that has been continuously running ends.

[0080] The processing executed in the agent system 10 of the present embodiment differs from that of the first embodiment as shown in FIG. 7. That is, instead of the processing from step S27 to step S29 in FIG. 6, the processing from step S40 to step S42 is executed.

[0081] When it is determined in step S26 that the possession flag is not off, in step S40, the host 20 reserves the request for the agent.

[0082] In step S41, the host 20 determines whether another company agent has ended. When the host 20 determines that the other company agent has not ended, that is, when the other company agent is still running, the process returns to step S22. On the other hand, if the host 20 determines that the agent of another company has ended, the process proceeds to step S42.

[0083] In step S42, the host 20 sets the occupancy flag to off. Then, it proceeds to step S30.

[0084] In addition, the request for the agent that was reserved in step S40 is reflected in step S30 to step S33. Thus, in step S33, the operation of the retained own company agent is started.

[0085] (Summary of the second embodiment)

[0086] The host 20 of the second embodiment is formed so that even when the agent of the company cannot run during the operation of the agent of another company, it does not abandon the request for the operation of the agent of the company. Make reservations. Therefore, according to this embodiment, after the completion of the other company's agent, the company's agent can be operated without requiring the first requesting unit 200 to perform the request of the company's agent again.

[0087] [Note]

[0088] Each of the above-mentioned embodiments is a method for separately determining whether the function can be interrupted for each function executed by another company agent. However, it is not limited to this, and it is also possible to judge whether the function can be interrupted during operation according to the operation status of the agent of another company. The interruption permission list 110 in this case specifies whether or not the interruption is possible for other company agents of the level corresponding to the operating conditions of the other company agents.

[0089] For example, if there is "shopping" in the function set as the agent of another company, it is defined as the level A where the interruption of the processing is set to not possible during the settlement process, and it is specified during the purchase procedure. In order to set the operation of the company's agent to the reserved level B, it is specified as the level C where the interruption of the processing is set to be possible during the item search process. As a result, when the agent of another company is performing shopping, it can provide information to other companies according to its operating status.

The interruption of the agent and the operation of the company's agent are controlled.

[0090] In addition to dagger, although in each of the above-mentioned embodiments, the operation of the agent of the company is usually controlled based on whether the operation of the agent of the other company stored in the interruption permission list 110 is performed, it is not limited to this. . That is, it is also possible to store the operation permission of the own company's agent in the interruption permission list 110, and control the operation of the other company's agent based on the operation ability of the own company's agent.

[0091] The host 20 of the second embodiment is formed to reserve the request of the own company agent, and send the reserved request as voice information to the own company server 14 at the stage when the other company agent ends. However, it is not limited to this, and it may be formed that when the host 20 discards the request of the agent of the company, the user U is asked again for the request at the stage when the agent of the other company is finished, that is, the request is made again. Vocalize.

[0092] In addition, various processes that the CPU 20A reads and executes software (programs) in the above-described embodiment may be executed by various processors other than the CPU. Examples of processors in this case include FPGA (Field Programmable Gate Array) and PLD (Programmable Logic Device) that can change the circuit structure after manufacturing, and ASIC (Application Specific Integrated Circuit: A processor with a specially designed circuit structure, that is, a dedicated circuit, etc., in order to perform specific processing. In addition, the above-mentioned acceptance processing can be executed by one of these various processors, or by a combination of two or more processors of the same type or different types (for example, multiple FPGAs, and CPUs and FPGAs). Combination, etc.) to perform. In addition, more specifically, the hardware configuration of these various processors is a circuit in which circuit elements such as semiconductor elements are combined.

[0093] In addition to the above, in the above-mentioned embodiments, the description has been given in a manner that each program is stored (installed) in a non-transitory recording medium readable by a computer in advance. For example, the processing program 100 in the host 20 is stored in the storage 20D in advance. However, it is not limited to this. The programs can also be recorded on CD-ROM (Compact Disc Read Only Memory), DVD-ROM (Digital Versatile Disc Read Only Memory), and USB (Universal Serial Bus: Universal Serial Bus) is provided in a non-temporary recording medium such as memory. In addition, the program may be downloaded from an external device via a network. [0094] The flow of the processing described in the above embodiment is also an example, and it is also possible to delete unnecessary steps, add new steps, or replace the processing order without departing from the scope of the subject matter.