Information Processing Apparatus, Information Processing Method, and Program

Abstract

Provide the evaluation results of other users on the user and / or the evaluation results of the user on other users without squeezing out the conversation time for the user. 【Solution means】The information processing apparatus 100 includes an agent creation unit 140 that creates an AI agent based on agent information, a first AI agent created based on first agent information, and a second AI agent created based on second agent information. A dialogue control unit 160 that obtains a first evaluation result for the first AI agent reflecting the conscious load of the second AI agent and / or a second evaluation result for the second AI agent reflecting the conscious load of the first AI agent by having them converse under a predetermined purpose, a result creation unit 170 that creates a matching result based on the first evaluation result and / or the second evaluation result, and output units 120 and 180 that output the matching result.

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, an information processing method, and a program.

Background Art

[0002] In recent years, services using AI agents that interact with people have been increasing.

[0003] In the system described in Patent Document 1, a virtual animated interactive agent can be rendered for visual and auditory communication with one or more users within an application. For example, a conversational artificial intelligence (AI) assistant can be rendered and displayed for visual communication in addition to auditory communication with an end user. Thereby, the system aims to utilize the visual area in addition to the auditory area, including the interaction of the AI assistant with the virtual environment in which the AI assistant is rendered, so that the AI assistant can communicate with the user more clearly. In addition, the system aims to utilize voice, video, and / or text input from the user to determine the user's requests, mood, gestures, and / or postures for the AI assistant to respond to the user more accurately and interact with the user.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, in the prior art including the system described in Patent Document 1, it is premised that a person and an AI assistant interact with each other, and without squeezing out interaction time for the user, it is impossible to provide the evaluation result of another user with respect to the user or the evaluation result of the user with respect to another user.

[0006] Therefore, an object of the present invention is to provide the evaluation result of another user with respect to the user and / or the evaluation result of the user with respect to another user without squeezing out interaction time for the user.

Means for Solving the Problems

[0007] An information processing apparatus according to an aspect of the present invention includes an agent creation unit that creates an AI agent based on agent information, a first AI agent created based on first agent information, and a second AI agent created based on second agent information. A dialogue control unit that makes the second AI agent and the first AI agent interact with each other for a predetermined purpose to obtain a first evaluation result for the first AI agent reflecting the consciousness load of the second AI agent and / or a second evaluation result for the second AI agent reflecting the consciousness load of the first AI agent; a result creation unit that creates a matching result based on the first evaluation result and / or the second evaluation result; and an output unit that outputs the matching result.

Effects of the Invention

[0008] According to the present invention, it becomes possible to provide the evaluation result of another user with respect to the user and / or the evaluation result of the user with respect to another user without squeezing out interaction time for the user.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Mode for Carrying Out the Invention

[0010] Embodiments of the present invention will be described with reference to the accompanying drawings. Note that the following embodiments are for facilitating the understanding of the present invention and are not for limiting the interpretation of the present invention. Further, the present invention can be variously modified without departing from its gist. Furthermore, those skilled in the art can adopt embodiments in which each element described below is replaced with an equivalent one, and such embodiments are also included in the scope of the present invention.

[0011] (System Configuration) The outline of the present invention will be described with reference to FIG. 1. FIG. 1 is a configuration diagram of an information processing system according to an embodiment of the present invention. The information processing system includes an information processing apparatus 100 and a plurality of client terminals 200a, 200b,..., 200n (hereinafter referred to as client terminal 200), and each client terminal 200 is communicably connected to the information processing apparatus 100 via a communication network N. The communication network N may be either a wired communication network or a wireless communication network configured by a wired or wireless line, and may be the Internet or a Local Area Network (LAN).

[0012] The information processing apparatus 100 causes a first AI agent created based on first agent information and a second AI agent created based on second agent information to have a conversation for a predetermined purpose, obtains an evaluation result of the second AI agent with respect to the first AI agent and / or an evaluation result of the first AI agent with respect to the second AI agent based on the conversation content, and can output a matching result based on the evaluation result. The purposes of the conversation are assumed to include, but are not limited to, personnel recruitment, dating matching, etc.

[0013] The client terminal 200 is a terminal used by a user, such as a smartphone, a tablet terminal, a personal computer, etc. Here, the users include users who apply for job offers, persons in charge of personnel recruitment, users of dating matching, service providers of dating matching, etc. The user can provide the agent information used to embody the AI agent to the information processing apparatus 100 via the client terminal 200. Also, the user can receive the matching result from the information processing apparatus 100 via the client terminal 200.

[0014] The AI agent may be a software program using generative AI. The AI agent is an interactive software that, when an instruction or request in natural language is input, identifies the processing necessary to respond to the input instruction or request and automatically executes it. The generative AI may be, for example, text generation AI, image generation AI, or multimodal generation AI.

[0015] (Functional configuration: Information processing apparatus) FIG. 2 is a diagram showing the configuration of the information processing apparatus according to an embodiment of the present invention. In FIG. 2, a single information processing apparatus 100 is assumed and only the necessary functional configurations are shown, but the information processing apparatus 100 can also be configured as part of a multi-functional distributed system by a plurality of computer systems.

[0016] The information processing apparatus 100 includes a storage unit 110, a site providing unit 120, a registration unit 130, an agent creation unit 140, a collection unit 150, a dialogue control unit 160, a result creation unit 170, and an output unit 180. Each unit shown in FIG. 2 can be realized, for example, by using a storage area or by the processor executing a program stored in the storage area.

[0017] In the present embodiment, it is desirable that the storage unit 110 has an agent storage unit 111, a user storage unit 112, an extraction model 113, and a recommendation method storage unit 114.

[0018] Agent information is stored in the agent storage unit 111. In one embodiment, as shown in FIG. 3, it is desirable that the agent storage unit 111 includes an agent ID, an agent name, a dialogue purpose, evaluation points, and attributes. The agent ID is information that can uniquely identify the agent. The agent name is information indicating the name of the agent used at the time of output. Information indicating the purpose of the dialogue, such as "1: Job application", "2: Talent recruitment", "3: Matching", etc., is stored in the dialogue purpose.

[0019] The evaluation points are information indicating the content that is particularly emphasized during the evaluation of employment or matching. The content that works in the positive direction or the negative direction of the evaluation may be specified. Various information of the agent corresponding to the dialogue purpose is stored in the attributes. When the dialogue purpose is "1: Job application", for example, information including age, gender, academic background, work experience, and appeal points is stored as attributes. When the dialogue purpose is "2: Talent recruitment", for example, information including company name, job type, and employment conditions is stored as attributes. When the dialogue purpose is "3: Matching", for example, information including age, gender, academic background, work experience, hobbies, and place of origin is stored as attributes.

[0020] An appeal point is information that an applicant user particularly wants to appeal to the hiring staff. The job type is information indicating the job type for which hiring is planned. As described above, the information of the agent includes information necessary for interacting with other AI agents, characteristics of the AI agent that affect the interaction content and mutual evaluation of the interaction, that is, information corresponding to a person's personality, and information related to attributes such as age and gender.

[0021] The user memory unit 112 stores user information. In one embodiment, as shown in FIG. 4, it is desirable that the user memory unit 112 includes a user ID, a usage purpose, an agent ID, and an email address. The user ID is information that can uniquely identify a user of the matching service site provided by the information processing apparatus 100. The usage purpose stores information indicating the purpose for which the user uses the information processing system, such as "1: Job application", "2: Talent recruitment", "3: Matching participation - 1", "4: Matching participation - 2", "5: Matching success", etc. Note that "3: Matching participation - 1" and "4: Matching participation - 2" can be used when dividing users participating in the matching into two groups. For example, in the case of dating matching, one of the information is stored according to gender. Also, in the case of matching between entrepreneurs and investors, one of the information is stored according to the position.

[0022] The agent ID stores information indicating the agent ID of the agent memory unit 111. For example, when the purpose of use is "1: Job Application", the agent ID stores the agent ID of the agent memory unit 111 that identifies the agent corresponding to the user himself / herself. Also, when the purpose of use is "2: Recruitment", the agent ID stores the agent ID of the agent memory unit 111 that identifies the agent corresponding to the recruiter of the company to which the user belongs. Further, when the purpose of use is "3: Matching Participation - 1" or "4: Matching Participation - 2", the agent ID stores the agent ID of the agent memory unit 111 that identifies the agent corresponding to the user himself / herself. Note that when the purpose of use is "5: Matching Success", the agent ID may not store any information.

[0023] The extraction model 113 is a model that extracts information regarding behavior change techniques (BCT: Behavior Change Technique) included in the input data.

[0024] Here, the behavior change technique (BCT) according to the present embodiment is a technique or method that acts on (affects) behavior change. For example, according to BCTTv1 (Michie S, Richardson M, Johnston M, et al.: The behavior change technique taxonomy (v1) of 93 hierarchically clustered techniques: building an international consensus for the reporting of behavior change interventions. Ann Behav Med 2013; 46: 81~95.), 93 BCTs in 16 groups are defined. Note that the definition of BCT is not limited to BCTTv1, and it may be defined in any way as long as it comprehensively covers behavior change techniques.

[0025] The extraction model 113 may be generated by learning using data with BCT annotation information attached.

[0026] The recommended method storage unit 114 stores information on BCTs that are recommended to be included in the dialogue content. In one embodiment, it is desirable for the recommended method storage unit 114 to include the dialogue purpose and the recommended BCTs. The dialogue purpose is the same information as the dialogue purpose in the agent storage unit 111. The recommended BCTs are information indicating the BCTs that are recommended to be included in the dialogue content for the target dialogue purpose.

[0027] The site providing unit 120 provides the matching service site provided by the information processing apparatus 100 on a network N such as the Internet. On the website, registration and browsing of data related to matching can be performed. For this purpose, the site providing unit 120 transmits a web page described in HTML (HyperText Markup Language) or the like to the client terminal 200, and receives input results and the like from the user from the client terminal 200.

[0028] The site providing unit 120 creates a corresponding web page in response to an input from the user or the like and transmits it to the client terminal 200. Specifically, the site providing unit 120 transmits various web pages such as a web page for the user to register the user's information and / or the agent's information, a web page for the user to select an agent with whom the user can communicate, and a web page for the user to confirm the matching result to the client terminal 200.

[0029] The registration unit 130 registers user information and / or agent information. In this embodiment, when receiving a registration request from the client terminal 200, the registration unit 130 generates a user ID and / or an agent ID, and registers them in the user storage unit 112 and / or the agent storage unit 111 based on the information included in the registration request. In one embodiment, a registration request including agent information in addition to the purpose of use, which is user information, is sent from the client terminal 200. For example, it is assumed that a user applying for a job sends a registration request including an agent name and attributes as information of the agent corresponding to the user via the client terminal 200 in addition to the purpose of use "1: Job Application".

[0030] Also, in one embodiment, a registration request including user information and a registration request for registering agent information are separately sent from the client terminal 200. For example, it is assumed that a user who is a matching service provider first sends a registration request including the purpose of use "5: Matching Success" via the client terminal 200, and then sends a registration request including an agent name, the purpose of conversation "3: Matching", and attributes as information of the agent corresponding to the matching participants.

[0031] The agent creation unit 140 creates an AI agent that mimics a desired user based on the agent information. In this embodiment, when receiving a conversation request from the client terminal 200, at least two or more AI agents are created based on the information included in the conversation request. In one example, the conversation request includes a user ID, an agent ID, etc. For example, if user X applying for a job hopes to have an interview with the recruitment staff of Company A from a list of interviewable agents, it is assumed that a conversation request including the user ID corresponding to user X and the agent ID corresponding to the agent of the recruitment staff of Company A is sent from the client terminal 200.

[0032] In another example, the dialogue request includes a user ID, agent conditions, etc. For example, if female user F who participates in matching hopes to match with a male agent, it is assumed that a dialogue request including the user ID corresponding to user F and the agent condition "30 years old or above" is sent from the client terminal 200.

[0033] In another example, the dialogue request includes a user ID, dialogue purpose, agent keywords, etc. For example, if user X who applies for a job hopes to have an interview with the recruitment staff of company E that is not in the list of agents available for interviews, it is assumed that a dialogue request including the user ID corresponding to user X, the dialogue purpose "2: Talent recruitment", and the agent keywords "company E, sales position" is sent from the client terminal 200.

[0034] Note that the AI agent may be a configuration of the information processing device 100 or a configuration of an external information processing device.

[0035] The collection unit 150 collects agent information. In this embodiment, when receiving a dialogue request including agent keywords from the client terminal 200, the collection unit 150 performs an Internet search based on the dialogue purpose and agent keywords included in the dialogue request, and registers the agent information in the agent storage unit 111 based on the information collected from the Internet.

[0036] The dialogue control unit 160 causes the first AI agent and the second AI agent to have a dialogue under a predetermined purpose. For example, when causing the applicant agent with the dialogue purpose "1: Job application" and the recruitment staff agent with the dialogue content "2: Talent recruitment" to have a dialogue, the dialogue control unit 160: 1) obtains the question information to be asked to the applicant agent from the recruitment staff agent; 2) inputs the question information to the applicant agent to obtain the answer information; 3) inputs the question information and the answer information to the recruitment staff agent to obtain the evaluation result for the applicant agent.

[0037] The evaluation result may be an evaluation represented by numbers, for example, or it may be a ranking represented by letters or symbols such as ABC or A, B, C, or other evaluation results. Note that in this embodiment, the dialogue control unit 160 obtains an evaluation result that reflects the mental load.

[0038] Here, the mental load is a value corresponding to the mental load or attention resources imposed on the user who processes predetermined information. In this embodiment, it is a value corresponding to the mental load or attention resources that are assumed to be imposed when the user imitated by the AI agent processes information related to the dialogue. The mental load can be imposed on both the agent that asks the question and the agent that receives the question and gives an answer. For example, the agent that asks the question is subject to a mental load for generating question information, and the agent that receives the question and gives an answer is subject to a mental load for understanding the question information and generating answer information. Furthermore, the agent that asks the question is subject to a mental load for understanding and evaluating the answer information.

[0039] Also, when causing agent 1 with the dialogue purpose of "3: Matching" to dialogue with agent 2 with the dialogue purpose of "3: Matching", the dialogue control unit 160: 1) obtains question information 1 to be asked to agent 1 from agent 2, 2) inputs the question information 1 to agent 1 to obtain answer information 1, 3) inputs the question information 1 and the answer information 1 to agent 2 to obtain an evaluation result 1 for agent 1, 4) obtains question information 2 to be asked to agent 2 from agent 1, 5) inputs the question information 2 to agent 2 to obtain answer information 2, 6) inputs the question information 2 and the answer information 2 to agent 1 to obtain an evaluation result 2 for agent 2.

[0040] The dialogue control unit 160 can generate input information for the agent using the evaluation points and attributes in the agent memory unit 111. For example, when acquiring question information from the recruitment agent, the dialogue control unit 160 can generate input information using the evaluation points and obtain question information considering the evaluation points. Also, when acquiring the evaluation result for the applicant agent, the dialogue control unit 160 can generate input information using the evaluation points and obtain an evaluation result considering the evaluation points.

[0041] The result creation unit 170 creates a matching result based on the evaluation result acquired by the dialogue control unit 160. For example, when the dialogue control unit 160 acquires the evaluation result for the applicant agent, the result creation unit 170 creates a matching result for the user related to the recruitment agent and / or a matching result for the user related to the applicant agent.

[0042] In one embodiment, the result creation unit 170 may input the question information and the answer information into the extraction model 113 to extract the information of the BCT included in the input data. When the information of the BCT included in the input data is extracted, the result creation unit 170 may create a matching result including the extracted information of the BCT.

[0043] Also, in one embodiment, the result creation unit 170 may refer to the recommended method storage unit 114 based on the dialogue purpose and obtain the information of the BCT recommended to be included in the dialogue content. When the information of the BCT recommended to be included in the dialogue content is acquired, the result creation unit 170 may create a matching result including the acquired information of the BCT. In addition, when the information of the BCT included in the input data is also extracted, the result creation unit 170 may generate a matching result including the difference information between the information of the BCT included in the input data and the information of the BCT recommended to be included in the dialogue content.

[0044] The output unit 180 outputs the matching result. In the present embodiment, the output unit 180 transmits the matching result created by the result creation unit 170 to the desired client terminal 200.

[0045] (Functional configuration: Client terminal)

[0046] FIG. 5 is a diagram showing the configuration of a client terminal according to an embodiment of the present invention. The client terminal 200 includes a storage unit 210, a registration request unit 220, an interaction request unit 230, and a display unit 240. Each unit shown in FIG. 5 can be realized, for example, by using a storage area or by the processor executing a program stored in the storage area. In the present embodiment, the registration request unit 220, the interaction request unit 230, and the display unit 240 can be realized by a browser realized by the processor executing a program stored in the storage area. However, in other embodiments, they may be realized by executing an application of the matching service stored in the storage area of the client terminal 200.

[0047] The registration request unit 220 transmits a registration request for a user and / or an agent. In one embodiment, the registration request unit 220 transmits a registration request including the purpose of use, agent information, etc. to the information processing apparatus 100. In another embodiment, the registration request unit 220 separately transmits a registration request including the purpose of use and a registration request including agent information to the information processing apparatus 100.

[0048] The interaction request unit 230 transmits an interaction request for designating a plurality of agents that desire an interaction. In one embodiment, the interaction request unit 230 transmits an interaction request including a user ID and an incoming agent ID to the information processing apparatus 100. In another embodiment, the interaction request unit 230 transmits an interaction request including a user ID and agent conditions to the information processing apparatus 100. In another embodiment, the interaction request unit 230 transmits an interaction request including a user ID, an interaction purpose, and an agent keyword to the information processing apparatus 100.

[0049] The display unit 240 receives the matching result as a response to the dialogue request and displays it on the display device of the client terminal 200.

[0050] (Operation) Referring to FIG. 6, the processing in the information processing apparatus 100 according to an embodiment of the present invention will be described in detail. In the present embodiment, it is assumed that various data are stored in the agent storage unit 111, the extraction model 113, and the recommendation method storage unit 114 of the storage unit 110 before the processing of FIG. 6 is started.

[0051] (Example 1) In this example, an example will be described in which user X who applies for a job hopes for an interview with the recruitment staff of Company A from a list of agents who can conduct interviews.

[0052] In step S101, the site providing unit 120 of the information processing apparatus 100 transmits a web page for registering user information and / or agent information to the client terminal 200.

[0053] When a registration request is transmitted from the client terminal 200 in response to the operation of user X on the browser (step S102), in step S103, the registration unit 130 of the information processing apparatus 100 generates a user ID and / or an agent ID and registers them in the user storage unit 112 and / or the agent storage unit 111 based on the information included in the registration request. Here, a registration request including the usage purpose "1: Job application", the agent name "Applicant X", and attributes is received from the client terminal 200, and the registration unit 130 generates a user ID "XXXXX" and an agent ID "U001", and it is assumed that the records in the user storage unit 112 and the records in the agent storage unit 111 are registered.

[0054] In step S104, the site providing unit 120 transmits a web page for the user to select an agent who can conduct an interview to the client terminal 200.

[0055] When an interaction request is sent from the client terminal 200 in response to an operation by user X on the browser (step S105), in step S106, the agent creation unit 140 of the information processing apparatus 100 creates at least two or more AI agents based on the information included in the interaction request. Here, assume that the agent creation unit 140 receives an interaction request including the user ID "XXXXX" and the agent ID "C001" from the client terminal 200, and refers to the agent storage unit 111 shown in Fig. 3(A) to create an applicant agent based on the information of the agent with the agent ID "U001" related to the user ID "XXXXX" and an employment responsible agent based on the information of the agent with the agent ID "C001".

[0056] In step S107, the dialogue control unit 160 of the information processing apparatus 100 causes the first AI agent and the second AI agent to have a dialogue for a predetermined purpose. Here, assume that the dialogue control unit 160 sequentially performs the following processes: 1) obtains question information for questioning the applicant agent from the employment responsible agent; 2) inputs the question information to the applicant agent to obtain answer information; 3) inputs the question information and the answer information to the employment responsible agent to obtain an evaluation result for the applicant agent.

[0057] As described above, in this embodiment, the dialogue control unit 160 obtains an evaluation result that reflects the cognitive load. Here, the dialogue control unit 160 obtains an evaluation result that reflects the cognitive load on the employment responsible agent for generating the question information for questioning the applicant agent and the cognitive load on the employment responsible agent for evaluating the applicant agent based on the answer information.

[0058] In one example, the less resources the recruitment agent referred to in order to generate the question information, the lower the awareness load of the evaluation result obtained. Similarly, the less resources the recruitment agent referred to in order to understand the answer information, the lower the awareness load of the evaluation result obtained. Also, the less the number of dialogues until the answer information is obtained, the lower the awareness load of the evaluation result obtained. For example, when the applicant agent cannot understand the question information and the answer information for the first question information is not the intended answer information, the dialogue control unit 160 inputs the first question information and the first answer information to the recruitment agent, obtains the second question information obtained by rephrasing the first question information, and inputs the second question information to the applicant agent to obtain the second answer information. In this way, the dialogue control unit 160 obtains the rephrased question information until the answer information for the question information becomes the intended answer information, and the less the number of dialogues until the intended answer information is obtained, the lower the awareness load of the evaluation result obtained.

[0059] In step S108, the result creation unit 170 of the information processing apparatus 100 creates a matching result based on the evaluation result obtained by the dialogue control unit 160. Here, the result creation unit 170 creates a matching result for the user related to the recruitment agent and a matching result for the user related to the applicant agent based on the evaluation result for the applicant agent obtained by the dialogue control unit 160.

[0060] In one embodiment, the result creation unit 170 may input the question information and the answer information to the extraction model 113 to extract the information of the BCT included in the input data. When the information of the BCT included in the input data is extracted, the result creation unit 170 may create a matching result including the extracted information of the BCT.

[0061] Also, in one embodiment, the result creation unit 170 may refer to the recommended method storage unit 114 based on the dialogue purpose and acquire information on BCTs that are recommended to be included in the dialogue content. When information on BCTs that are recommended to be included in the dialogue content is acquired, the result creation unit 170 may create a matching result including the acquired BCT information. In addition, when information on BCTs included in the input data is also extracted, the result creation unit 170 may generate a matching result including difference information between the information on BCTs included in the input data and the information on BCTs that are recommended to be included in the dialogue content.

[0062] In step S109, the site providing unit 120 transmits a web page for confirming the matching result to the client terminal 200. Here, it is assumed that the site providing unit 120 transmits a web page of the matching result for the user related to the applicant agent to the client terminal 200 of user X.

[0063] In step S110, the output unit 180 of the information processing apparatus 100 transmits the matching result to the client terminal 200. Here, the output unit 180 transmits the matching result for the user related to the recruitment agent to the email address of the recruitment staff of Company A. Note that it is desirable to transmit the matching result to the recruitment staff of Company A selected as the dialogue partner instead of user X who sent the dialogue request after obtaining the consent of user X who sent the dialogue request.

[0064] (Additional Embodiment: Dialogue Environment Setting) In the above Example 1, an example in which the applicant agent and the recruitment agent are made to have a dialogue with only the dialogue purpose specified has been described. However, in another embodiment, in addition to the dialogue purpose, the applicant agent and the recruitment agent can be made to have a dialogue with other dialogue environment settings specified.

[0065] Up to steps S101 to S104 in FIG. 6, the processing proceeds in the same manner as in the above-described First Embodiment. Here, in the present embodiment, for example, on the web page for selecting an agent transmitted in step S104 in FIG. 6, user X can specify the dialogue environment settings. For example, the dialogue environment settings include the dialogue date, the dialogue start time, the dialogue language, and the like.

[0066] When user X specifies the dialogue environment settings using the browser, a dialogue request including the dialogue environment settings is transmitted from the client terminal 200 (step S105). Here, it is assumed that a dialogue request including the user ID "XXXXX" corresponding to user X, the agent ID "C001", the interview start time "13:00", and the dialogue language "Japanese" is transmitted from the client terminal 200.

[0067] Similar to the above-described First Embodiment, in step S106, the agent creation unit 140 of the information processing apparatus 100 creates at least two or more AI agents based on the information included in the dialogue request. Here, it is assumed that the agent creation unit 140 refers to the agent storage unit 111 shown in FIG. 3(A) and creates an applicant agent based on the information of the agent with the agent ID "U001" related to the user ID "XXXXX" and an employment responsible agent based on the information of the agent with the agent ID "C001".

[0068] In step S107, the dialogue control unit 160 of the information processing apparatus 100 causes the first AI agent and the second AI agent to have a dialogue for a predetermined purpose. Here, it is assumed that the dialogue control unit 160 sequentially performs the following processes: 1) obtains question information for questioning the applicant agent from the employment responsible agent; 2) inputs the question information to the applicant agent to obtain answer information; and 3) inputs the question information and the answer information to the employment responsible agent to obtain an evaluation result for the applicant agent.

[0069] As described above, the dialogue control unit 160 obtains an evaluation result reflecting the mental load. In the present embodiment, in addition to the number of resources referred to and the number of dialogues required to obtain the response information described in the above Example 1, or instead of the number of resources referred to and the number of dialogues required to obtain the response information, the mental load corresponding to the dialogue environment setting may be reflected in the evaluation result.

[0070] Specifically, the dialogue control unit 160 can generate input information for the agent using the dialogue environment setting in addition to the evaluation points and attributes of the agent memory unit 111. For example, when acquiring question information from the recruitment agent in charge, the dialogue control unit 160 can generate input information using the dialogue environment setting and acquire question information considering the dialogue environment setting. Further, when acquiring the evaluation result for the applicant agent, the dialogue control unit 160 can generate input information using the dialogue environment setting and acquire the evaluation result considering the dialogue environment setting.

[0071] In one example, it is conceivable that the recruitment agent in charge returns different evaluation results depending on the interview start time even when interacting with the same applicant agent. For example, in the case of a recruitment agent in charge who tends to communicate with others in the morning and concentrate on their own work in the afternoon, an evaluation result with a lower mental load is obtained when the interview start time is in the morning than when it is in the afternoon.

[0072] Also, in another example, it is conceivable that the recruitment agent in charge returns different evaluation results depending on the dialogue language even when interacting with the same applicant agent. For example, in the case of a recruitment agent in charge who is more proficient in English than Japanese, an evaluation result with a lower mental load is obtained when the dialogue language is English than when it is Japanese.

[0073] Since the processing after step S108 is the same as that in the above Example 1, detailed description thereof is omitted.

[0074] (Additional Embodiment) In the above-described Example 1, an example was described in which user X who applies for a job selects the recruitment staff of Company A from the list of agents who can conduct an interview. However, in another embodiment, user X who applies for a job can hope to have an interview with the recruitment staff of Company E who is not in the list of agents who can conduct an interview.

[0075] Up to steps S101 to S104 in FIG. 6, the processing proceeds in the same manner as in the above-described Example 1. In step S105, for example, according to the operation of user X on the web page for selecting an agent transmitted in step S104 of FIG. 6, instead of an agent in the list of agents who can conduct an interview, a dialogue request for hoping to have an interview with an agent created based on the dialogue purpose "2: Recruitment" and the agent keyword "Company E, Sales position" is transmitted from the client terminal 200. Here, it is assumed that a dialogue request including the user ID "XXXXX" corresponding to user X, the dialogue purpose "2: Recruitment", and the agent keyword "Company E, Sales position" is transmitted from the client terminal 200.

[0076] In step S106, prior to the processing of the agent creation unit 140, the collection unit 150 of the information processing apparatus 100 collects information on the agent. In the present embodiment, the collection unit 150 performs an Internet search based on the dialogue purpose and the agent keyword included in the dialogue request, and registers the information on the agent in the agent storage unit 111 based on the information collected from the Internet. Here, it is assumed that the collection unit 150 performs an Internet search based on the dialogue purpose "2: Recruitment" and the agent keyword "Company E, Sales position", and registers the information on the agent in the agent storage unit 111 based on the information collected from the Internet.

[0077] Subsequently, the agent creation unit 140 creates an AI agent. Here, the agent creation unit 140 refers to the agent storage unit 111 shown in Fig. 3(A) and creates an applicant agent based on the information of the agent with agent ID "U001" related to the user ID "XXXXX" and an employment agent based on the information of the agent with agent ID "A001".

[0078] The processing after step S107 is the same as that in the first embodiment, so detailed description is omitted. In this embodiment, the agent selected as the conversation partner is not created based on the information of the agent storage unit 111 registered in advance in relation to the user who wishes to have a conversation, but is created based on the information collected based on predetermined conditions. Therefore, the processing in step S110 is skipped and the information processing apparatus 100 ends the processing.

[0079] (Embodiment 2) In this embodiment, an example in which a female user F participating in a dating matching wishes to match with a male agent will be described.

[0080] In step S101, the site providing unit 120 of the information processing apparatus 100 transmits a web page for registering user information and / or agent information to the client terminal 200.

[0081] When a registration request is sent from the client terminal 200 in response to the operation of user F on the browser (step S102), in step S103, the registration unit 130 of the information processing apparatus 100 generates a user ID and / or an agent ID, and registers them in the user storage unit 112 and / or the agent storage unit 111 based on the information included in the registration request. Here, a registration request including the usage purpose "3: Matching participation - 1", the agent name "Female agent 1", and attributes is received from the client terminal 200, and the registration unit 130 generates the user ID "F0101" and the agent ID "U101", and it is assumed that the records of the user storage unit 112 and the records of the agent storage unit 111 are registered.

[0082] In step S104, the site providing unit 120 transmits a web page for selecting an agent for matching to the client terminal 200.

[0083] When an interaction request is sent from the client terminal 200 in response to the operation of user F on the browser (step S105), in step S106, the agent creation unit 140 of the information processing apparatus 100 creates at least two or more AI agents based on the information included in the interaction request. Here, an interaction request including the user ID "F0101" and the agent condition "30 years old or older" is received from the client terminal 200, and the agent creation unit 140 refers to the agent storage unit 111 shown in FIG. 3(B), and based on the information of the female agent 1 related to the agent ID "U101" of the user ID "F0101" and the male agents 1 to 10 of the usage purpose "4: Matching participation - 2" that satisfy the agent condition "30 years old or older", it is assumed that they are created.

[0084] In step S107, the dialogue control unit 160 of the information processing apparatus 100 causes the first AI agent and the second AI agent to have a dialogue for a predetermined purpose. Here, since a total of 10 male agents were created, it is assumed that the dialogue control unit 160 acquires each male agent one by one and performs the following processes. Specifically, the dialogue control unit 160: 1) acquires question information 1 for questioning female agent 1 from the male agent, 2) inputs question information 1 into female agent 1 to acquire answer information 1, 3) inputs question information 1 and answer information 1 into the male agent to acquire evaluation result 1 for female agent 1, 4) acquires question information 2 for questioning the male agent from female agent 1, 5) inputs question information 2 into the male agent to acquire answer information 2, 6) inputs question information 2 and answer information 2 into female agent 1 to acquire evaluation result 2 for the male agent, and sequentially performs the processes.

[0085] As described above, in the present embodiment, the dialogue control unit 160 acquires an evaluation result that reflects the consciousness load. Here, the dialogue control unit 160 acquires evaluation result 1 for female agent 1 that reflects the consciousness load imposed on the male agent for generating question information 1 for questioning female agent 1 and the consciousness load imposed on the male agent for evaluating female agent 1 based on answer information 1. Similarly, the dialogue control unit 160 acquires evaluation result 2 for the male agent that reflects the consciousness load imposed on female agent 1 for generating question information 2 for questioning the male agent and the consciousness load imposed on female agent 1 for evaluating the male agent based on answer information 2.

[0086] In one example, as described in Example 1, the evaluation result may reflect the mental load based on the number of resources referred to and the number of dialogues required to obtain the response information. Also, in one example, the closer the number of characters in the question information and the number of characters in the response information are, the lower the evaluation result of the mental load is obtained. In this example, it is assumed that the closer the number of characters is, the better the tempo of the dialogue is and the lower the mental load is. Conversely, when the number of characters on one side is much larger than the other, it is assumed that the tempo of the dialogue is poor and the mental load is high.

[0087] Also, in one example, the more similar the attributes of Female Agent 1 and the attributes of the male agent are, the lower the evaluation result of the mental load is obtained. For example, the closer the age and educational level are, the lower the evaluation result of the mental load is obtained. Also, when they have the same hobby or place of origin, an evaluation result with a lower mental load is obtained compared to the case where their hobbies and places of origin are different.

[0088] In step S108, the result creation unit 170 of the information processing apparatus 100 creates a matching result based on the evaluation result acquired by the dialogue control unit 160. Here, the result creation unit 170 creates a matching result for the user F related to Female Agent 1 based on the evaluation result for Female Agent 1 and / or the evaluation result 2 for the male agent acquired by the dialogue control unit 160.

[0089] The result creation unit 170 may include in the matching result an evaluation result in which the evaluation of Female Agent 1 is higher than a predetermined standard, or may include in the matching result an evaluation result in which the evaluation of the male agent is higher than a predetermined standard, or may include in the matching result an evaluation result in which the evaluation of Female Agent 1 is higher than a predetermined standard and the evaluation of the male agent is higher than a predetermined standard.

[0090] In step S109, the site providing unit 120 transmits a web page for confirming the matching result to the client terminal 200. Here, it is assumed that the site providing unit 120 transmits a web page of the matching result for users related to the female agent 1 to the client terminal 200 of user F. In this embodiment, the process of step S110 is skipped, and the information processing apparatus 100 ends the process.

[0091] (Additional Embodiment: Interaction Environment Setting) In the above-described second embodiment, an example in which the female agent 1 and the male agent are made to interact with only the interaction purpose specified has been described. However, in another embodiment, in addition to the interaction purpose, the female agent 1 and the male agent can be made to interact with other interaction environment settings specified.

[0092] Up to steps S101 to S104 in FIG. 6, the process proceeds in the same manner as in the above-described second embodiment. Here, in this embodiment, for example, in the web page for selecting an agent to perform matching, which is transmitted in step S104 in FIG. 6, user F can specify the interaction environment setting. For example, the interaction environment setting includes the interaction date, the interaction start time, the interaction means, the interaction schedule, and the like. For the interaction means, for example, information indicating the means of interaction such as "1: Direct Interaction", "2: Phone", "3: Email", etc. is specified. For the interaction schedule, for example, information indicating the schedule of interaction from the start of interaction until the evaluation result is obtained such as "1: Once", "2: Every Day / One Week", "3: Once a Week / One Month", etc. is specified.

[0093] When user F specifies the interaction environment setting using a browser, an interaction request including the interaction environment setting is transmitted from the client terminal 200 (step S105). Here, it is assumed that an interaction request including the user ID "F0101", the agent condition "30 years old or older", the interaction start time "19:00", the interaction means "3: Email", and the interaction schedule "2: Every Day / One Week" is transmitted from the client terminal 200.

[0094] Similar to the above-described Example 2, in step S106, the agent creation unit 140 of the information processing apparatus 100 creates at least two or more AI agents based on the information included in the dialogue request. Here, the agent creation unit 140 refers to the agent storage unit 111 shown in FIG. 3(B), and creates a female agent 1 based on the information of the agent with the agent ID "U101" related to the user ID "F0101", and male agents 1 to 10 for the usage purpose "4: Matching participation - 2" that satisfy the agent condition "30 years old or older".

[0095] In step S107, the dialogue control unit 160 of the information processing apparatus 100 causes the first AI agent and the second AI agent to have a dialogue for a predetermined purpose. Here, since a total of 10 male agents are created, the dialogue control unit 160 is assumed to sequentially acquire each male agent and perform the following processing. Specifically, the dialogue control unit 160: 1) acquires question information 1 for questioning the female agent 1 from the male agent, 2) inputs the question information 1 to the female agent 1 to acquire answer information 1, 3) inputs the question information 1 and the answer information 1 to the male agent to acquire an evaluation result 1 for the female agent 1, 4) acquires question information 2 for questioning the male agent from the female agent 1, 5) inputs the question information 2 to the male agent to acquire answer information 2, 6) inputs the question information 2 and the answer information 2 to the female agent 1 to acquire an evaluation result 2 for the male agent, and sequentially performs the processing.

[0096] As described above, the dialogue control unit 160 obtains an evaluation result reflecting the cognitive load. In the present embodiment, in addition to or instead of the number of resources referred to, the number of dialogues required to obtain the response information, as described in the first embodiment, and the tempo of the dialogue and the similarity of the agent's attributes based on the number of characters of the question information and the number of characters of the response information, as described in the second embodiment, the cognitive load according to the dialogue environment setting may be reflected in the evaluation result. In one example, it is conceivable that a male agent returns different evaluation results depending on the dialogue start time, dialogue means, and dialogue schedule even when interacting with the same female agent 1. Similarly, it is conceivable that female agent 1 returns different evaluation results depending on the dialogue start time, dialogue means, and dialogue schedule even when interacting with the same male agent.

[0097] For example, in the case of a male agent who tends to prefer face-to-face conversations as a dialogue means, an evaluation result with a lower cognitive load is obtained in the case of face-to-face conversations than in the case of phone calls or emails. Also, for example, in the case of a male agent who tends to prefer frequent conversations with the opposite sex, an evaluation result with a lower cognitive load is obtained when the dialogue schedule is daily rather than once or once a week.

[0098] The processing after step S108 is the same as that in the second embodiment described above, and thus detailed description thereof is omitted.

[0099] (Embodiment 3) In the present embodiment, an example will be described in which user Z, who is a service provider for dating matching, wishes to obtain pairs with a high matching rate.

[0100] In step S101, the site providing unit 120 of the information processing apparatus 100 transmits a web page for registering user information and / or agent information to the client terminal 200.

[0101] When a registration request is sent from the client terminal 200 in response to the operation of user Z on the browser (step S102), in step S103, the registration unit 130 of the information processing apparatus 100 generates a user ID and / or an agent ID, and registers them in the user storage unit 112 and / or the agent storage unit 111 based on the information included in the registration request. Here, the registration unit 130 receives a registration request including the usage purpose "5: Matching established" from the client terminal 200, and generates a user ID "ZZZZZ" and registers it in the record of the user storage unit 112.

[0102] In step S104, the site providing unit 120 transmits a web page for selecting an agent for performing matching to the client terminal 200.

[0103] When an interaction request is sent from the client terminal 200 in response to the operation of user Z on the browser (step S105), in step S106, the agent creation unit 140 of the information processing apparatus 100 creates at least two or more AI agents based on the information included in the interaction request. Here, the agent creation unit 140 receives an interaction request including the user ID "ZZZZZ" and the agent condition "unspecified" from the client terminal 200, and creates a plurality of female agents 1 to N and a plurality of male agents 1 to M by referring to the agent storage unit 111 shown in FIG. 3(B).

[0104] In step S107, the dialogue control unit 160 of the information processing apparatus 100 causes the first AI agent and the second AI agent to have a dialogue for a predetermined purpose. Here, since a total of N female agents and a total of M male agents are created, the dialogue control unit 160 acquires one female agent and one male agent at a time and performs the following processing. Specifically, the dialogue control unit 160: 1) acquires question information 1 for questioning the female agent from the male agent; 2) inputs the question information 1 into the female agent to acquire answer information 1; 3) inputs the question information 1 and the answer information 1 into the male agent to acquire an evaluation result 1 for the female agent; 4) acquires question information 2 for questioning the male agent from the female agent; 5) inputs the question information 2 into the male agent to acquire answer information 2; 6) inputs the question information 2 and the answer information 2 into the female agent to acquire an evaluation result 2 for the male agent, and sequentially performs the processing. As described above, in the present embodiment, the dialogue control unit 160 acquires an evaluation result reflecting the conscious load.

[0105] In step S108, the result creation unit 170 of the information processing apparatus 100 creates a matching result based on the evaluation result acquired by the dialogue control unit 160. Here, the result creation unit 170 creates a matching result for user Z based on the evaluation result for the female agent and the evaluation result 2 for the male agent acquired by the dialogue control unit 160.

[0106] The result creation unit 170 may include in the matching result all pairs of a female agent and a male agent whose evaluation results for the female agent are higher than a predetermined standard and whose evaluation results for the male agent are higher than a predetermined standard, or may include in the matching result the top 10 pairs among the pairs whose mutual evaluations are higher than a predetermined standard.

[0107] In step S109, the site providing unit 120 transmits a web page for confirming the matching result to the client terminal 200. Here, it is assumed that the site providing unit 120 transmits the web page of the matching result to the client terminal 200 of user Z. In this embodiment, the process of step S110 is skipped, and the information processing apparatus 100 ends the process.

[0108] (Hardware Configuration: Information Processing Apparatus) Next, with reference to FIG. 7, an example of the hardware configuration of the information processing apparatus 100 will be described. As shown in FIG. 7, the information processing apparatus 100 includes, for example, a processor 101, a memory 102, a storage device 103, an input I / F unit 104, a data I / F unit 105, a communication I / F unit 106, and a display device 107.

[0109] The processor 101 is a control unit that controls various processes in the information processing apparatus 100 by executing programs stored in the memory 102.

[0110] The memory 102 is a storage medium such as, for example, a RAM (Random Access Memory). The memory 102 temporarily stores program codes of programs executed by the processor 101 and data required during program execution.

[0111] The storage device 103 is a non-volatile storage medium such as, for example, a hard disk drive (HDD) or a flash memory. The storage device 103 stores an operating system and various programs for realizing the above-described respective configurations.

[0112] The input I / F unit 104 is a device for receiving inputs from the user. The input I / F unit 104 is, for example, a keyboard, a mouse, a touch panel, various sensors, a wearable device, etc. The input I / F unit 104 may be connected to the information processing apparatus 100 via an interface such as, for example, USB (Universal Serial Bus).

[0113] The data I / F unit 105 is a device for inputting data from outside the information processing apparatus 100. The data I / F unit 105 is, for example, a drive device or the like for reading data stored in various storage media. The data I / F unit 105 may be provided outside the information processing apparatus 100. When the data I / F unit 105 is provided outside the information processing apparatus 100, the data I / F unit 105 is connected to the information processing apparatus 100 via an interface such as USB or the like.

[0114] The communication I / F unit 106 is a device for performing data communication with a device outside the information processing apparatus 100 via a network such as the Internet, either wired or wirelessly. The communication I / F unit 106 may be provided outside the information processing apparatus 100. When the communication I / F unit 106 is provided outside the information processing apparatus 100, the communication I / F unit 106 is connected to the information processing apparatus 100 via an interface such as USB or the like.

[0115] The display device 107 is a device for displaying various information. The display device 107 is, for example, a liquid crystal display, an organic EL (Electro-Luminescence) display, a display of a wearable device, or the like. The display device 107 may be provided outside the information processing apparatus 100. When the display device 107 is provided outside the information processing apparatus 100, the display device 107 is connected to the information processing apparatus 100 via a display cable or the like. Further, when a touch panel is adopted as the input I / F unit 104, the display device 107 may be configured integrally with the input I / F unit 104.

[0116] (Hardware Configuration: Client Terminal) Next, with reference to FIG. 8, an example of the hardware configuration of the client terminal 200 will be described. As shown in FIG. 8, the client terminal 200 includes, for example, a processor 201, a memory 202, a storage device 203, an input I / F unit 204, a data I / F unit 205, a communication I / F unit 206, and a display device 207.

[0117] Note that since the processor 201, memory 202, storage device 203, input I / F unit 204, data I / F unit 205, communication I / F unit 206, and display device 207 each have the same configuration as the processor 101, memory 102, storage device 103, input I / F unit 104, data I / F unit 105, communication I / F unit 106, and display device 107, detailed descriptions thereof are omitted.

[0118] As described above, according to the present embodiment, the information processing apparatus 100 causes a first AI agent created based on first agent information and a second AI agent created based on second agent information to have a dialogue under a predetermined purpose, and obtains and outputs a first evaluation result for the first AI agent reflecting the conscious load of the second AI agent and / or a second evaluation result for the second AI agent reflecting the conscious load of the first AI agent, thereby providing the evaluation result of another user for the user and / or the evaluation result of the user for another user without squeezing out dialogue time for the user. Specifically, the dialogue between the first AI agent imitating the personality, behavior, habits, etc. of the user and the AI agent imitating the personality, behavior, habits, etc. of another user imitates the dialogue between the user and another user. As a result, the evaluation result between the AI agents can be provided as the evaluation result between the users.

[0119] Furthermore, by reflecting the conscious load of the AI agent in the acquisition of the evaluation result, it can be expected that the evaluation result between the AI agents will be closer to the evaluation result between the users. Specifically, the information processing apparatus 100 can obtain an evaluation result reflecting a value corresponding to the mental load and attention resources that are assumed to be required when each AI agent processes information related to the dialogue of the user it imitates.

[0120] In addition, by enabling the creation of a plurality of second AI agents, the information processing apparatus 100 can provide evaluation results of each second AI agent with respect to the first AI agent in a one-to-N combination. Further, the information processing apparatus 100 can receive conditions for specifying second agent information, create a plurality of second AI agents based on the conditions, and cause the second AI agent that meets the conditions to interact with the first AI agent.

[0121] In addition, the information processing apparatus 100 can obtain an evaluation that reflects the cognitive load of the AI agent according to the attentional resources by obtaining an evaluation result with a lower cognitive load as the resources referred to by each AI agent are fewer.

[0122] In addition, the information processing apparatus 100 can obtain an evaluation that reflects the cognitive load of the AI agent according to the mental load by obtaining an evaluation result with a lower cognitive load as the number of dialogues until a predetermined response information is obtained is fewer.

[0123] In addition, the information processing apparatus 100 can obtain an evaluation result that reflects the cognitive load according to the dialogue environment setting including at least one of the dialogue date, dialogue start time, dialogue language, dialogue means, and dialogue schedule, so that even for dialogues between the same AI agents, different evaluation results can be obtained according to the dialogue environment setting.

[0124] In addition, the information processing apparatus 100 can obtain an evaluation that reflects the cognitive load of the AI agent according to the mental load by obtaining an evaluation result with a lower cognitive load as the number of characters in the question information and the number of characters in the response information are closer.

[0125] In addition, by enabling the creation of a plurality of first AI agents and a plurality of second AI agents, the information processing apparatus 100 can provide evaluation results of each second AI agent with respect to each first AI agent in an N-to-M combination.

Explanation of Signs

[0126] 100 Information processing apparatus, 101 Processor, 102 Memory, 103 Storage device, 104 Input I / F unit, 105 Data I / F unit, 106 Communication I / F unit, 107 Display device, 110 Storage unit, 111 Agent storage unit, 112 User storage unit, 113 Extraction model, 114 Recommendation method storage unit, 120 Site providing unit (output unit), 130 Registration unit, 140 Agent creation unit (reception unit), 150 Collection unit, 160 Dialogue control unit, 170 Result creation unit, 180 Output unit, 200 Client terminal, 201 Processor, 202 Memory, 203 Storage device, 204 Input I / F unit, 205 Data I / F unit, 206 Communication I / F unit, 207 Display device, 210 Storage unit, 220 Registration request unit, 230 Dialogue request unit, 240 Display unit, N Network

Claims

1. An agent creation unit that creates an AI agent based on agent information, A first AI agent created based on the first agent information and a second AI agent created based on the second agent information are made to interact under a predetermined purpose, and a first evaluation result for the first AI agent reflecting the conscious load of the second AI agent and / or a second evaluation result for the second AI agent reflecting the conscious load of the first AI agent are obtained. A dialogue control unit, A result creation unit that creates a matching result based on the first evaluation result and / or the second evaluation result, An output unit that outputs the matching result An information processing apparatus comprising:

2. The agent creation unit creates a plurality of second AI agents, The dialogue control unit causes the first AI agent to interact with each second AI agent to obtain each first evaluation result for each second AI agent with respect to the first AI agent and / or each second evaluation result for the first AI agent with respect to each second AI agent. The information processing apparatus according to claim 1. The information processing apparatus according to claim 1.

3. The dialogue control unit obtains an evaluation result reflecting a value corresponding to the mental load and attention resources that are assumed to be involved when the user imitated by each AI agent processes information related to the dialogue. The information processing apparatus according to claim 1 or 2.

4. The information processing apparatus according to claim 1 or 2, wherein the lower the number of resources referred to by each AI agent, the lower the evaluation result of the conscious load.

5. The dialogue control unit obtains question information to be asked to the first AI agent from the second AI agent, inputs the question information to the first AI agent to obtain answer information, inputs the question information and the answer information to the second AI agent, and obtains an evaluation result for the first AI agent. The information processing apparatus according to claim 1 or 2, wherein the lower the number of dialogues until the answer information is obtained, the lower the evaluation result of the conscious load.

6. Further comprising a receiving unit that receives a dialogue environment setting including at least one of a dialogue date, a dialogue start time, a dialogue language, a dialogue means, and a dialogue schedule, The information processing apparatus according to claim 1 or 2, wherein the dialogue control unit obtains an evaluation result reflecting the cognitive load according to the dialogue environment setting.

7. The dialogue control unit obtains question information to be asked to the first AI agent from the second AI agent, inputs the question information to the first AI agent to obtain answer information, inputs the question information and the answer information to the second AI agent, and obtains an evaluation result for the first AI agent. The information processing apparatus according to claim 1 or 2, wherein the closer the number of characters of the question information and the number of characters of the answer information are, the lower the cognitive load is, and an evaluation result is obtained.

8. The agent creation unit creates a plurality of first AI agents and a plurality of second AI agents. The dialogue control unit causes each first AI agent and each second AI agent to have a dialogue, and obtains each first evaluation result of each second AI agent for each first AI agent and / or each second evaluation result of each first AI agent for each second AI agent. The information processing apparatus according to claim 1.

9. A computer creates an AI agent based on agent information; causes a first AI agent created based on first agent information and a second AI agent created based on second agent information to have a dialogue for a predetermined purpose, and obtains a first evaluation result for the first AI agent reflecting the cognitive load of the second AI agent and / or a second evaluation result for the second AI agent reflecting the cognitive load of the first AI agent; creates a matching result based on the first evaluation result and / or the second evaluation result; outputs the matching result and includes a method.

10. On a computer a process of creating an AI agent based on agent information; Causing a first AI agent created based on first agent information and a second AI agent created based on second agent information to have a dialogue under a predetermined purpose, and obtaining a first evaluation result for the first AI agent reflecting the conscious load of the second AI agent and / or a second evaluation result for the second AI agent reflecting the conscious load of the first AI agent; Creating a matching result based on the first evaluation result and / or the second evaluation result; Outputting the matching result A program for executing the above.

Images