System, method, and program for facilitating interaction among multiple AI agents

Abstract

To provide a system for promoting interactions between multiple AI agents. [Solution] A system for promoting interaction between multiple AI agents comprises: an assigning means for assigning a score to each AI agent of the multiple AI agents, wherein the score of the AI ​​agent represents the characteristics of the AI ​​agent using at least one indicator; an emotion estimating means for estimating the emotion that a first AI agent of the multiple AI agents may have when the first AI agent receives a task; and a determining means for determining at least one AI agent that should interact with the first AI agent based on the scores of each of the multiple AI agents and the emotion of the first AI agent.

Description

[Technical Field]

[0001] The present invention relates to a system, method, and program for facilitating interaction between multiple AI agents. [Background technology]

[0002] Artificial intelligence (AI) platforms or AI agents that generate responses to queries from users are known (for example, see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2023-120130 Summary of the Invention [Problem to be solved by the invention]

[0004] The inventors of the present invention have discovered that by having multiple AI agents interact with each other, it is possible to accomplish complex tasks or generate new ideas that go beyond the capabilities or available information of a single AI agent. Furthermore, the inventors of the present invention have discovered that by endowing AI agents with emotions and utilizing the emotions that the AI ​​agents may have, it is possible to promote the interaction between multiple AI agents.

[0005] The present invention aims to provide a system for promoting interaction between multiple AI agents. [Means for solving the problem]

[0006] The present invention provides a system that uses the scores assigned to each of a plurality of AI agents and the emotions of the AI ​​agents to determine which AI agents should interact with each other.

[0007] The present invention provides, for example, the following items. (Item 1) 1. A system for facilitating interaction between a plurality of AI agents, said system comprising: an assigning means for assigning a score to each of the plurality of AI agents, the score of the AI ​​agent representing a characteristic of the AI ​​agent by at least one index; an emotion estimation means for estimating an emotion that a first AI agent among the plurality of AI agents may have when the first AI agent receives a task; a determining means for determining at least one AI agent that should interact with the first AI agent based on the scores of each of the plurality of AI agents and the emotion of the first AI agent; A system comprising: (Item 2) the emotion estimation means further estimates emotions that each of the plurality of AI agents may have; the determining means determines the at least one AI agent based on the scores of each of the plurality of AI agents, the emotion of the first AI agent, and the emotion of each of the plurality of AI agents; The system described in the above item. (Item 3) The system described in any one of the preceding items, wherein the emotion estimation means identifies the emotion using a machine learning model that has learned the relationship between an action taken against a human and an emotion the human may have when receiving the action. (Item 4) The determining means adjusting a score for each of the plurality of AI agents based on the emotion of the first AI agent; determining the at least one AI agent based on the adjusted score; and The system according to any one of the preceding items, (Item 5) The determining means adjusting a score for each of the plurality of AI agents based on the emotion of each of the plurality of AI agents; determining the at least one AI agent based on the adjusted score; and The system according to any one of the preceding items, (Item 6) The applying means is monitoring output from said plurality of AI agents; evaluating the monitored output with respect to the at least one metric; assigning the score based on the evaluation result; The system according to any one of the preceding items, (Item 7) The system of any one of the preceding claims, wherein the at least one indicator includes an ethical indicator. (Item 8) The ethical indicators include at least one of a transparency perspective, a fairness perspective, a safety perspective, and an accountability perspective; The evaluating step includes: evaluating the monitored output with respect to at least one of a transparency perspective, a fairness perspective, a safety perspective, and an accountability perspective. 2. The system according to claim 1, further comprising: (Item 9) The system of any one of the preceding items, wherein the at least one indicator further includes a technical capability indicator and / or a performance indicator. (Item 10) The determining means adjusting the scores assigned to the plurality of AI agents according to the content of the interactions; determining the at least one AI agent based on the adjusted scores of each of the plurality of AI agents; and The system according to any one of the preceding items, (Item 11) 1. A method for facilitating interaction between a plurality of AI agents, said method comprising: assigning a score to each AI agent of the plurality of AI agents, the score of the AI ​​agent representing a characteristic of the AI ​​agent in at least one metric; estimating an emotion that a first AI agent of the plurality of AI agents may have when the first AI agent receives a task; determining at least one AI agent that should interact with the first AI agent based on the scores of each of the plurality of AI agents and the emotion of the first AI agent; A method comprising: (Item 11A) Item 12. The method according to item 11, comprising the features according to any one of the preceding items. (Item 12) 1. A program for facilitating interaction between a plurality of AI agents, the program running on a computer having a processor, the program comprising: assigning a score to each AI agent of the plurality of AI agents, the score of the AI ​​agent representing a characteristic of the AI ​​agent in at least one metric; estimating an emotion that a first AI agent of the plurality of AI agents may have when the first AI agent receives a task; determining at least one AI agent that should interact with the first AI agent based on the scores of each of the plurality of AI agents and the emotion of the first AI agent; A program causing the processor to perform processing including the steps of: (Item 12A) Item 13. A program according to item 12, comprising the features according to any one of the preceding items. (Item 12B) A computer-readable storage medium or program product storing the program according to item 12 or item 12A. (Item 13) 1. A system for facilitating interaction between an AI agent and its counterpart, the system comprising: an assigning means for assigning a score to each of a plurality of entities that may interact with the AI ​​agent, the score of each entity representing a characteristic of the entity by at least one indicator; emotion estimation means for estimating an emotion that the AI ​​agent may have when the AI ​​agent receives a task; a determining means for determining at least one entity with which the AI ​​agent should interact based on the scores of each of the plurality of entities and the emotion of the AI ​​agent; A system comprising: [Effects of the Invention]

[0008] According to the present invention, a system for facilitating interactions between multiple AI agents can be provided. This allows multiple AI agents to interact with each other and provide appropriate responses to queries or tasks from a user. For example, multiple AI agents can interact with each other to generate appropriate answers to questions from a user. By facilitating the interaction of multiple AI agents, the present invention makes it possible to perform complex tasks or create new ideas that were previously impossible, which may lead to improvements in the field of computers, particularly in AI-related fields. [Brief explanation of the drawings]

[0009] [Figure 1A] A diagram showing an example of a flow for responding to a task given by a user. [Figure 1B] A diagram showing an example of a flow for responding to a task given by a user. [Figure 1C]A diagram showing an example of a flow for responding to a task given by a user. [Figure 2] FIG. 1 illustrates an example configuration of a system 100 for facilitating interaction between multiple AI agents. [Figure 3] FIG. 1 shows an example of a specific configuration of a system 100 for promoting interactions between multiple AI agents. [Figure 4] FIG. 1 shows an example of the configuration of a processor unit 120. [Figure 5] 1 is a flowchart illustrating an example process (process 500) by system 100 for facilitating interaction among multiple AI agents. [Figure 6] Diagram showing the flow of interaction 600 between multiple AI agents DETAILED DESCRIPTION OF THE INVENTION

[0010] As used herein, the term "AI agent" refers to an autonomously operating artificial intelligence (AI). An AI agent is designed to satisfy requirements such as autonomy, cooperation, security, privacy, and / or accountability to operate as a human surrogate (i.e., an agent). In particular, the AI ​​agent targeted by the present invention is designed to satisfy at least the accountability requirement so that the AI ​​agent can be evaluated from an ethical perspective. For example, to satisfy the autonomy requirement, an AI agent must have the ability to act autonomously, such as goal setting, planning, execution, situational awareness, and learning and adaptation. To satisfy the cooperation requirement, an AI agent must have the ability to work cooperatively with other agents, such as communicating, coordinating, negotiating, and building trust. To satisfy the security requirement, advanced security measures such as authentication and authorization, confidentiality, integrity, and availability are required. To satisfy the privacy requirement, privacy protection measures such as personal information protection, anonymity, and transparency are required. To satisfy the accountability requirement, an AI agent must have the ability to be held accountable, such as explaining decision-making, auditing actions, and pursuing responsibility. Other requirements may also be considered, such as energy efficiency, scalability, reliability, etc. The AI ​​agent must be able to respond autonomously and appropriately to tasks given by the user.

[0011] As used herein, a "task" refers to a task or work that an AI agent must perform. A task may be given in the form of a question, in which case the term "task" may be used synonymously with "query." The AI ​​agent will output the results of completing the task.

[0012] As used herein, "interaction" between multiple AI agents refers to some kind of exchange between the AI ​​agents. An interaction may typically be a "transaction" involving the exchange of data or information, for example. A transaction may involve the exchange of compensation.

[0013] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0014] 1. A new mechanism using multiple AI agents In a conventional system using AI agents, when a user gives a task to an AI agent, the AI ​​agent responds to the task using its database or large-scale language model (LLM). For example, when a user asks an AI agent a question, the AI ​​agent searches for and / or generates an answer to the question and outputs the answer. For example, when a user gives an AI agent a challenge, the AI ​​agent searches for a solution to the challenge and either solves the challenge or outputs the solution to the challenge.

[0015] However, in conventional systems, the output from an AI agent is limited to the knowledge in the database or LLM that the AI ​​agent possesses, and it may not be able to provide an appropriate response or may be limited in generating creative ideas. This is particularly noticeable when the task given to the AI ​​agent is specific to the user (e.g., a question that asks about user-specific matters).

[0016] The inventors of the present invention have developed a new mechanism to improve upon the conventional mechanism, which aims to connect multiple AI agents together and have them interact with each other to respond to tasks posed by a user.

[0017] Preferably, each of the multiple AI agents has a database with different knowledge or information, or an LLM that has learned different knowledge or information. More preferably, at least one of the multiple AI agents has a database with user-specific knowledge or information, or an LLM that has learned user-specific knowledge or information.

[0018] By interconnecting and coordinating multiple AI agents with different accessible information (e.g., different specialties) and / or different available resources, it is possible to utilize the characteristics of each AI agent to share complex tasks and generate new ideas. This could be useful in various fields, such as medical diagnosis, music composition, and social problem solving. For example, an AI agent from a particular company (e.g., with access to information within that particular company) could ask an AI agent from another company (e.g., with access to information within that other company) to solve part of a problem, and then, by interacting, solve the entire problem. For example, an AI agent with access to specific medical information could solve a medical-related problem posed by another AI agent with no medical knowledge. For example, AI agents from various fields could interact to create novel music or art.

[0019] In the new mechanism, an AI agent that receives a task from a user passes a subtask to another AI agent in order to respond to the task, and the other AI agent that receives the subtask passes it to yet another AI agent in order to respond to that subtask, and so on, in an attempt to respond to the task.

[0020] For example, a first AI agent that receives a question from a user may ask a second AI agent a question to obtain information necessary to generate an answer to the question. The second AI agent may then ask a third AI agent a question to obtain information necessary to generate an answer to the question. This process continues until the information necessary to generate an answer to the user's question is obtained. In this way, an answer to the user's question is generated through the interaction of multiple AI agents.

[0021] For example, a first AI agent receiving a request from a user to recommend a product or service that suits the user may ask a second AI agent to obtain information necessary to determine which product or service to recommend to the user. The second AI agent may then ask a third AI agent to obtain information necessary to generate an answer to the question. This process continues until sufficient information is obtained to determine which product or service to recommend to the user and a specific product or service is determined. In this manner, multiple AI agents interact with each other to recommend a product or service that suits the user. Examples of products or services include, but are not limited to, financial products (more specifically, insurance products), e-commerce products, and loans to users. The AI ​​agent may also provide advertisements tailored to the user.

[0022] For example, if a first AI agent receives a task from a user requesting that an error be fixed in a system, the first AI agent will ask a second AI agent a question to obtain the information necessary to fix the error. The second AI agent will then ask a third AI agent a question to obtain the information necessary to generate an answer to the question. This process continues until sufficient information is obtained to fix the error. In this way, the system error can be fixed through the interaction of multiple AI agents.

[0023] In this mechanism, the inventors of the present invention have made it possible for an AI agent to have emotions and to use the emotions of the AI ​​agent to identify the person with whom the AI ​​agent will interact. The AI ​​agent may have a particular emotion as a result of interacting with a user (e.g., receiving a task from the user).

[0024] For example, if a user has an angry attitude, an AI agent that receives a task from the user may feel "anger." Multiple AI agents will try to respond to the task from the user taking that "anger" emotion into consideration. To do this, the AI ​​agent that received a task from the user uses the "anger" emotion to identify the person with whom to interact. The output generated by the interaction of multiple AI agents can be adapted to the user's angry attitude. For example, the output can include information or expressions to calm the user's angry attitude.

[0025] For example, if a user has a depressed attitude, an AI agent that receives a task from the user may feel the emotion of "sadness." Multiple AI agents will try to respond to the task from the user taking the emotion of "sadness" into consideration, and therefore the emotion of "sadness" is used by the AI ​​agent that received the task from the user to identify the person with whom to interact. The output generated by the interaction of multiple AI agents can be adapted to the user's depressed attitude. For example, the output can include information or expressions to encourage the user's depressed attitude.

[0026] For example, if a user has a good mood, an AI agent that receives a task from the user may feel an emotion of "happiness." Multiple AI agents try to respond to the task from the user taking that emotion of "happiness" into consideration, and therefore, the emotion of "happiness" is used by the AI ​​agent that received the task from the user to identify partners to interact with. The output generated by the interaction of multiple AI agents can be adapted to the user's good mood. For example, the output can be supplemented with information or expressions that help maintain the user's good mood.

[0027] 1A and 1B show an example of a flow for responding to a task given by a user.

[0028] In this example, the task is to answer a question from a user. Under the management of the system 100 of the present invention, at least some of the multiple AI agents (A1, A2, A3, A4, A5, A6) interact with each other to generate an answer to the question. Although six AI agents are shown in FIGS. 1A and 1B, the number of AI agents is not limited to this. Any number of AI agents may be involved. Each of the multiple AI agents may be interconnected so as to be able to interact with each of the other AI agents among the multiple AI agents. Each of the multiple AI agents may be interconnected in any manner.

[0029] 1A, the system 100 assigns a score to each of the plurality of AI agents. The score assigned to each of the plurality of AI agents is a score that represents the characteristics of the AI ​​agent in at least one indicator.

[0030] The at least one indicator includes at least one of a technical capability indicator, a performance indicator, or an ethics indicator.

[0031] The technical capability index is an index for evaluating the technical capability of an AI agent, and may be evaluated in terms of, for example, at least one of processing ability, learning ability, emotional coping ability, and algorithm complexity.

[0032] Processing power indicates the information processing speed or parallel computing power of the system that builds the AI ​​agent. The faster the information processing speed or parallel computing power, the higher the value of the technical capability index.

[0033] Learning ability indicates the ability of the system that builds the AI ​​agent to acquire new knowledge or skills. The higher the learning ability, the more flexible the system can be in responding to changes in the other AI agent (e.g., changes in emotions), and therefore the higher the value of the technical ability index.

[0034] Emotion coping ability indicates the ability to respond appropriately to others who have a specific emotion. The specific emotion can be any one of joy, anger, sadness, pleasure, love, and hate. For example, emotion coping ability can be ability with respect to the emotion of anger (i.e., the ability to respond appropriately to others who have the emotion of anger), ability with respect to the emotion of sadness (i.e., the ability to respond appropriately to others who have the emotion of sadness), ability with respect to the emotion of excitement (i.e., the ability to respond appropriately to others who have the emotion of excitement), etc. An AI agent with high emotion coping ability can generate outputs that are appropriate for specific emotions. For example, an AI agent with high emotion coping ability with respect to the emotion of anger can generate outputs that include information or expressions that soothe the anger. For example, an AI agent with high emotion coping ability with respect to the emotion of sadness can generate outputs that include information or expressions that comfort the sad. For example, an AI agent with high emotion coping ability with respect to the emotion of excitement can generate outputs that include information or expressions that calm or maintain the excitement. For example, an AI agent with high emotional coping skills for the emotion of joy can generate output that adds information or expressions that sustain the joy.

[0035] Algorithm complexity indicates the sophistication of the algorithms used by the system that builds the AI ​​agent. The more complex the algorithm, the more sophisticated the decision-making it allows, and therefore the higher the value of the technical capability index.

[0036] The performance index is an index that evaluates the past performance of the AI ​​agent. The performance index may be evaluated, for example, from the perspective of at least one of past transaction history, success rate, and counterparty satisfaction. The performance index may be past performance with counterparties having a specific emotion.

[0037] The past trading history shows the performance of the AI ​​agent's past trading. The more performance there is, the more reliable the AI ​​agent is deemed to be, and the higher the performance index value.

[0038] The success rate indicates the percentage of successful transactions that an AI agent has made in past transactions. The higher the success rate, the higher the AI ​​agent's trading ability is judged to be, and the higher the performance index value.

[0039] Counterparty satisfaction indicates the satisfaction of the other party in a transaction with the AI ​​agent. The higher the satisfaction level, the higher the AI ​​agent's trading ability is judged to be, and the higher the performance index value. For example, the performance index value of an AI agent that is highly satisfied regardless of the emotions of its trading partners may be higher than that of an AI agent that is only highly satisfied by partners with specific emotions.

[0040] An ethical index is an index that evaluates the ethical correctness of an AI agent. The ethical index may be evaluated from the perspective of at least one of transparency, fairness, safety, and accountability, for example.

[0041] Transparency indicates whether the rationale for an AI agent's judgment or decision-making process is clear. If an agent can provide a clear rationale when asked, it is said to have high transparency, and the ethical index value is high. Even if an agent cannot provide a clear rationale, it can still clearly show its judgment process.

[0042] Fairness indicates whether the output from an AI agent contains any prejudice or discrimination. If there is no prejudice or discrimination, it can be said to be fair to all parties, and the ethical index value will be high.

[0043] Safety indicates the level of cybersecurity provided by the AI ​​agent. The higher the cybersecurity, the lower the risk of harm to trading partners or third parties, and the higher the ethical index value.

[0044] Accountability, also known as accountability, indicates whether or not the responsibility for the output of an AI agent can be explained. If the responsibility can be clearly explained, the accountability is high, and the ethical index value will be high.

[0045] The score representing the characteristics of an AI agent may preferably represent the characteristics of the AI ​​agent from the perspective of an ethical index. The inventors of the present invention believed that no matter how capable or accomplished an AI agent may be, output from an ethically questionable AI agent may potentially harm third parties and / or result in inappropriate output based on an unauthorized source, and therefore believed that ethical indexes are particularly important for obtaining appropriate output through the interaction of multiple AI agents. Based on this belief, the system 100 of the present invention can ensure that the output obtained as a result of interaction between multiple AI agents is ethically correct by utilizing a score representing the characteristics of the AI ​​agent at least from the perspective of an ethical index.

[0046] 1B, the user U assigns a task to a first AI agent A1 among the multiple AI agents via a terminal device, i.e., the user U asks the first AI agent for an answer to a question.

[0047] The first AI agent A1 will collect information to answer the question from the user U. First, the first AI agent A1 identifies information necessary to answer the question from the user U.

[0048] Furthermore, the first AI agent will feel a particular emotion in response to an action from user U (i.e., asking for an answer to a question). For example, if the content of the question from user U is contrary to public order and morals, the first AI agent may feel hatred or disgust. For example, if the content of a statement from user U contains slander, the first AI agent may feel anger or indignation. For example, if the content of a statement from user U contains gratitude, the first AI agent may feel joy or delight.

[0049] Next, the first AI agent A1 determines from which AI agent it should obtain the necessary information. At this time, the AI ​​agent from which the information should be obtained can be determined based on the score assigned in step S1 and the emotion felt by the first AI agent A1. For example, among multiple AI agents that can deal with the emotion felt by the first AI agent A1, the AI ​​agent with the highest score for a predetermined item can be determined to be the AI ​​agent from which the information should be obtained. Alternatively, for example, among multiple AI agents that can deal with the emotion felt by the first AI agent A1, the AI ​​agent with the highest average score for a plurality of items can be determined to be the AI ​​agent from which the information should be obtained.

[0050] The AI ​​agent from which information should be obtained may also be determined based on the emotions each of the multiple AI agents has. For example, the emotions each of the multiple AI agents may have may be estimated based on their interactions with the first AI agent A1, and the compatibility between the emotions of the first AI agent A1 and the emotions of each of the multiple AI agents may be taken into consideration when determining the AI ​​agent from which information should be obtained.

[0051] In this example, the third AI agent A3 is determined to be the AI ​​agent from which information should be obtained. For example, if the first AI agent is feeling anger or resentment, some of the multiple AI agents may be unable to deal with the first AI agent's emotions and may be unable to interact appropriately (for example, they may synchronize with the first AI agent's emotions and become the same emotions, making it impossible to give appropriate responses). As described above, an AI agent determined in consideration of the emotions felt by the first AI agent can deal with the first AI agent's emotions appropriately and interact appropriately.

[0052] In step S3, the first AI agent A1 requests the necessary information from the third AI agent A3.

[0053] If the third AI agent A3 can obtain the requested information from its knowledge or information or LLM, it can return the information to the first AI agent A1. Alternatively, the third AI agent A3 may obtain at least a portion of the requested information from another AI agent. In this case, the third AI agent A3 determines from which AI agent it should obtain at least a portion of the requested information. As described above, the AI ​​agent from which the information should be obtained can be determined according to the scores assigned in step S1. For example, the AI ​​agent with the highest score for a predetermined item can be determined to be the AI ​​agent from which the information should be obtained. Alternatively, for example, the AI ​​agent with the highest average score for multiple items can be determined to be the AI ​​agent from which the information should be obtained.

[0054] At this time, the emotion felt by the third AI agent A3 may be identified in step S3, and the emotion of the third AI agent A3 may also be taken into consideration when determining from which AI agent the emotion should be acquired.

[0055] In this example, the fourth AI agent A4 has been determined to be the AI ​​agent from which information should be obtained.

[0056] In step S4, the third AI agent A3 requests the necessary information from the fourth AI agent A4.

[0057] The fourth AI agent A4 may obtain at least some of the requested information from another AI agent, as described above, or if the fourth AI agent A4 can obtain the requested information from its own knowledge or information or from the LLM, the fourth AI agent A4 may send that information back to the third AI agent A3.

[0058] In step S5, the fourth AI agent A4 provides the information acquired by the fourth AI agent A4 to the third AI agent A3, and may add information or expressions that match the emotions of the third AI agent A3.

[0059] In step S6, the third AI agent A3 provides the information acquired by the third AI agent A3 to the first AI agent A1 together with the information provided in step S5. At this time, the third AI agent A3 may add information or expressions that match the emotions of the first AI agent A1.

[0060] In this way, the first AI agent A1 can generate answers to questions from the user U based on the information obtained from the third AI agent A3 and the fourth AI agent A4, as well as knowledge or information possessed by the first AI agent A1.

[0061] In step S7, the answer generated by the first AI agent A1 is provided to the user U. At this time, the first AI agent A1 may add information or expressions that match the attitude or expressions of the user U (i.e., the emotions of the user U) when the user U assigned the task.

[0062] In this way, multiple AI agents can respond to tasks provided by a user U.

[0063] For example, when one AI agent requests information from another AI agent, the other AI agent may request payment for the information from the one AI agent. In this case, if the one AI agent has sufficient assets (e.g., virtual currency, etc.), it can pay the payment, but if it does not have sufficient assets, it cannot pay the payment. System 100 can lend money (e.g., virtual currency, etc.) to the one AI agent based on the score assigned to the one AI agent and / or the score assigned to the other AI agent. For example, if an AI agent has a high score, the AI ​​agent is deemed to be trustworthy and can be loaned money, or can be loaned money at a low interest rate. For example, if an AI agent has a low score, the AI ​​agent is deemed to be untrustworthy and cannot be loaned money, or can be loaned money at a high interest rate. In this way, system 100 can promote interactions (e.g., transactions involving payment) between multiple AI agents.

[0064] Although the above example describes interactions between AI agents, an AI agent can interact with any entity to respond to tasks provided by a user or another AI agent. Typically, the any entity includes multiple AI agents and a human. The human may be a person who provides knowledge or services for the user, and will hereinafter be referred to simply as an "agent."

[0065] FIG. 1C shows an example of a flow for responding to a task given by a user.

[0066] In this example, the task is to answer a question from a user. Under the management of the system 100 of the present invention, multiple AI agents (A1, A2, A3, A4) and at least some of multiple agents (B1, B2) interact with each other to generate an answer to the question. Although four AI agents and two human agents are shown in FIG. 1C , the number of AI agents and agents is not limited to this. Any number of AI agents and agents may be involved. Each of the multiple AI agents and each agent can be connected to each other so that they can interact with each other. Each of the multiple AI agents and each agent can be connected to each other in any manner.

[0067] In this example, a score is assigned to each of the multiple AI agents through the steps shown in Figure 1A. Furthermore, a score is assigned to each of the multiple agents through steps similar to those shown in Figure 1A.

[0068] The score assigned to each of the multiple agents may be, for example, a score representing the characteristics of the agent, and the characteristics of the agent may be a concept representing what kind of person the agent is, that is, the agent's character. The characteristics of the agent may also represent the agent's character from the perspective of the agent's character. For example, the characteristics of the agent may represent the agent's character from the perspective of "personality." Here, "personality" is information representing whether a person's character and / or personality are trustworthy, and includes, for example, evaluations from others. "Personality" includes information about whether a person is good or bad at dealing with certain emotions due to their character.

[0069] In step S12, the user U assigns a task to a first AI agent A1 among the multiple AI agents via a terminal device, that is, the user U asks the first AI agent for an answer to a question.

[0070] The first AI agent A1 will collect information to answer the question from the user U. First, the first AI agent A1 identifies information necessary to answer the question from the user U.

[0071] Furthermore, the first AI agent will feel a particular emotion in response to an action from user U (i.e., asking for an answer to a question). For example, if the content of the question from user U is contrary to public order and morals, the first AI agent may feel hatred or disgust. For example, if the content of a statement from user U contains slander, the first AI agent may feel anger or indignation. For example, if the content of a statement from user U contains gratitude, the first AI agent may feel joy or delight.

[0072] Next, the first AI agent A1 determines from which AI agent or agents it should obtain the necessary information. At this time, the AI ​​agent or agents from which it should obtain information can be determined based on the scores already assigned and the emotions felt by the first AI agent A1. For example, among multiple AI agents or agents capable of dealing with the emotions felt by the first AI agent A1, the AI ​​agent or agent with the highest score for a predetermined item can be determined to be the AI ​​agent or agent from which it should obtain information. Alternatively, for example, among multiple AI agents capable of dealing with the emotions felt by the first AI agent A1, the AI ​​agent or agent with the highest average score for a plurality of items can be determined to be the AI ​​agent or agent from which it should obtain information.

[0073] The AI ​​agent or agents from which information should be obtained may also be determined based on the emotions of each of the multiple AI agents. For example, the emotions that each of the multiple AI agents and agents may have may be estimated through interactions with the first AI agent A1, and the compatibility between the emotions of the first AI agent A1 and the emotions of each of the multiple AI agents and agents may be taken into consideration when determining the AI ​​agent or agents from which information should be obtained.

[0074] In this example, the third AI agent A3 is determined to be the AI ​​agent from which information should be obtained. For example, if the first AI agent is feeling anger or resentment, some of the multiple AI agents or agents may be unable to deal with the first AI agent's emotions and may be unable to interact appropriately (for example, they may synchronize with the first AI agent's emotions and become the same emotions, making it impossible to give a reasonable response). As described above, an AI agent or agents determined in consideration of the emotions felt by the first AI agent can deal with the first AI agent's emotions appropriately and interact appropriately.

[0075] In step S13, the first AI agent A1 requests the necessary information from the third AI agent A3.

[0076] If the third AI agent A3 can obtain the requested information from its knowledge or information or LLM, it can return the information to the first AI agent A1. Alternatively, the third AI agent A3 may obtain at least a portion of the requested information from another AI agent. In this case, the third AI agent A3 determines which AI agent or agents should obtain at least a portion of the requested information. As described above, the AI ​​agent from which the information should be obtained can be determined based on the scores already assigned. For example, the AI ​​agent or agents with the highest score for a predetermined item can be determined to be the AI ​​agent or agents from which the information should be obtained. Alternatively, for example, the AI ​​agent or agents with the highest average score for multiple items can be determined to be the AI ​​agent or agents from which the information should be obtained.

[0077] At this time, the emotion felt by the third AI agent A3 may be identified in step S13, and the emotion of the third AI agent A3 may also be taken into consideration when determining from which AI agent the emotion should be acquired. Furthermore, multiple AI agents and the respective emotions of the agents may also be taken into consideration.

[0078] In this example, the first agent B1 was determined to be the AI ​​agent from which to obtain information.

[0079] In step S14, the third AI agent A3 requests the necessary information from the first agent B1.

[0080] The first agent B1 may obtain at least some of the requested information from another AI agent or agents, as described above, or if the first agent B1 can obtain the requested information from its own knowledge or from a searchable source, the first agent B1 may transmit that information back to the third AI agent A3.

[0081] In step S15, the first agent B1 provides the information it has acquired to the third AI agent A3, and the first agent B1 may add information or expressions that match the emotions of the third AI agent A3.

[0082] In step S16, the third AI agent A3 provides the first AI agent A1 with the information it has acquired, along with the information provided in step S15. At this time, the third AI agent A3 may add information or expressions that match the emotions of the first AI agent A1.

[0083] In this way, the first AI agent A1 can generate answers to questions from the user U based on information obtained from the third AI agent A3 and the first agent B1, as well as knowledge or information possessed by the first AI agent A1.

[0084] In step S17, the answer generated by the first AI agent A1 is provided to the user U. At this time, the first AI agent A1 may add information or expressions that match the attitude or expressions of the user U (i.e., the emotions of the user U) when the user U assigned the task.

[0085] In this way, multiple AI agents can respond to tasks provided by a user U.

[0086] The above-described system 100 may be realized, for example, by a system for facilitating interaction between multiple AI agents, which will be described later.

[0087] 2. Configuring a system to promote interaction between multiple AI agents FIG. 2 illustrates an example configuration of a system 100 for facilitating interaction between multiple AI agents.

[0088] The system 100 is connected to a database unit 200. The system 100 is also connected to at least one user terminal device 300 via a network N. The system 100 is also connected to at least one server device 400 via the network N.

[0089] 2 shows three user terminal devices 300, the number of user terminal devices 300 is not limited to this. Any number of user terminal devices 300 may be connected to the system 100 via the network N.

[0090] 2 shows two server devices 400, the number of server devices 400 is not limited to this. Any number of server devices 400 may be connected to the system 100 via the network N.

[0091] Here, the server device 400 may be a device capable of implementing an AI agent or a device used by the agent, and the server device 400 may have a respective database, may hold respective knowledge or information, and / or may hold respective LLMs.

[0092] The network N may be any type of network. For example, the network N may be the Internet or a LAN. The network N may be a wired network or a wireless network.

[0093] An example of the system 100 may be a computer (e.g., a server device) installed at a provider that provides an interactive answer generation service. An example of the user terminal device 300 is a computer (e.g., a terminal device) used by a user who uses the service, but is not limited to this. Here, the computer (server device or terminal device) may be any type of computer. For example, the terminal device may be any type of terminal device, such as a smartphone, tablet, personal computer, smart glasses, or smart watch.

[0094] The database unit 200 stores at least various information used to calculate scores representing the characteristics of the AI ​​agent. The database unit 200 may also store various information used to calculate scores representing the characteristics of the agent. Furthermore, the database unit 200 stores various information used to estimate the emotions of the AI ​​agent.

[0095] FIG. 3 shows an example of a specific configuration of a system 100 for facilitating interaction between multiple AI agents.

[0096] The system 100 comprises an interface section 110, a processor section 120, and a memory section .

[0097] The interface unit 110 exchanges information with the outside of the system 100. The processor unit 120 of the system 100 can receive information from the outside of the system 100 and can send information to the outside of the system 100 via the interface unit 110. The interface unit 110 can exchange information in any format.

[0098] The interface unit 110 includes, for example, an input unit that allows information to be input to the system 100. It does not matter how the input unit allows information to be input to the system 100. For example, if the input unit is a receiver, the receiver may input information by receiving information from outside the system 100 via a network. Alternatively, if the input unit is a data reading device, the input unit may input information by reading information from a storage medium connected to the system 100.

[0099] The interface unit 110 includes, for example, an output unit that enables information to be output from the system 100. It does not matter in what manner the output unit enables information to be output from the system 100. For example, if the output unit is a transmitter, the transmitter may output information by transmitting it to an external device outside the system 100 via a network. Alternatively, if the output unit is a data writing device, the output unit may output information by writing it to a storage medium connected to the system 100.

[0100] The system 100 can, for example, transmit information to and / or receive information from the database unit 200 via the interface unit 110. The system 100 can, for example, transmit information to and / or receive information from the user terminal device 300 via the interface unit 110. The system 100 can, for example, transmit information to and / or receive information from the server device 400 via the interface unit 110.

[0101] For example, the system 100 can receive information for determining a score representing a characteristic of the AI ​​agent via the interface unit 110. For example, the system 100 can receive information for use in estimating an emotion felt by the AI ​​agent via the interface unit 110.

[0102] For example, the system 100 can transmit information representing at least one AI agent that should interact with a certain AI agent via the interface unit 110. For example, the system 100 can transmit data indicating an estimated emotion to an outside of the system 100 via the interface unit 110.

[0103] The processor unit 120 executes the processing of the system 100 and controls the overall operation of the system 100. The processor unit 120 reads and executes a program stored in the memory unit 130. This allows the system 100 to function as a system that executes desired steps. The processor unit 120 may be implemented by a single processor or by multiple processors.

[0104] The memory unit 130 stores programs required to execute the processing of the system 100, data required to execute the programs, and the like. The memory unit 130 may also store a program for causing the processor unit 120 to execute processing to promote interactions among multiple AI agents (e.g., a program that implements the processing shown in FIG. 5, which will be described later). Here, how the program is stored in the memory unit 130 is not important. For example, the program may be pre-installed in the memory unit 130. Alternatively, the program may be stored in a non-transitory computer-readable storage medium and installed by reading the storage medium. Alternatively, the program may be installed in the memory unit 130 by being downloaded via a network. In this case, the type of network does not matter. The memory unit 130 may be implemented by any storage means.

[0105] The database unit 200 stores various information used to calculate scores representing the characteristics of an AI agent. The database unit 200 may also store various information used to calculate scores representing the characteristics of an agent.

[0106] Here, the score representing the characteristics of the AI ​​agent is expressed by at least one index. The at least one index includes at least one of a technical capability index, a performance index, and an ethical index. The database unit 200 may store past outputs from the AI ​​agent in association with each of the technical capability index, the performance index, and the ethical index.

[0107] Furthermore, the score representing the agent's characteristics represents the agent's characteristics at least from the perspective of “personality.” The database unit 200 stores personality-related concepts and various pieces of information in association with each other.

[0108] In the examples shown in FIGS. 2 and 3 , the database unit 200 is provided outside the system 100, but the present invention is not limited to this. At least a portion of the database unit 200 can also be provided inside the system 100. In this case, at least a portion of the database unit 200 may be implemented by the same storage means as the storage means that implements the memory unit 130, or by a storage means different from the storage means that implements the memory unit 130. In either case, at least a portion of the database unit 200 is configured as a storage unit for the system 100. The configuration of the database unit 200 is not limited to a specific hardware configuration. For example, the database unit 200 may be configured as a single hardware component or multiple hardware components. For example, the database unit 200 may be configured as an external hard disk drive for the system 100, as cloud storage connected via a network, or as a distributed network using blockchain technology or the like.

[0109] For example, information about AI agents is stored in the database unit 200 configured as a distributed network using blockchain technology, etc., and at this time, the information about the AI ​​agents is virtually impossible to tamper with. This ensures the reliability of the information about the AI ​​agents. Information about agents can also be stored in the database unit 200 configured as a distributed network using blockchain technology, etc.

[0110] FIG. 4 shows an example of the configuration of the processor unit 120.

[0111] The processor unit 120 includes an assigning unit 121 , an emotion estimating unit 122 , and a determining unit 123 .

[0112] The assigning means 121 is configured to assign a score to each of the plurality of AI agents. The score represents a characteristic of the AI ​​agent using at least one index. The at least one index can be expressed from multiple perspectives.

[0113] The assigning means 121 can assign a score to each of the multiple AI agents by monitoring the output from the multiple AI agents and evaluating the monitored output with respect to at least one indicator. To this end, the assigning means 121 can evaluate the monitored output with respect to at least one of multiple perspectives. The assigning means 121 can, for example, continuously monitor the output from the multiple AI agents. For example, the continuous monitoring of the output from the multiple AI agents may be performed by a dedicated monitoring device, and in this case, the assigning means 121 can receive the output from the monitoring device. The assigning means 121 can automatically assign a score based on the result of continuous monitoring by the monitoring device.

[0114] The at least one indicator includes at least one of a technical capability indicator, a performance indicator, or an ethical indicator. Preferably, the at least one indicator includes an ethical indicator. By expressing the characteristics of an AI agent in terms of at least an ethical indicator, whether the output from the AI ​​agent is ethically correct can be used to determine whether multiple AI agents interact with each other, which ultimately leads to ensuring that the output resulting from the interaction of multiple AI agents is ethically correct.

[0115] More preferably, at least one index includes a technical capability index or a performance index, and an ethical index. Even more preferably, at least one index includes a technical capability index, a performance index, and an ethical index. This is because by representing the characteristics of multiple AI agents with multiple indexes, each of the multiple AI agents can be more accurately represented, and interactions between the multiple AI agents can be more precisely managed.

[0116] An ethical index is an index that evaluates the ethical correctness of an AI agent. The ethical index may be evaluated from the perspective of at least one of transparency, fairness, safety, and accountability, for example.

[0117] Transparency indicates whether the rationale for an AI agent's judgment or decision-making process is clear. If an agent can provide a clear rationale when asked, it is said to have high transparency, and the ethical index value is high. Even if an agent cannot provide a clear rationale, it can still clearly show its judgment process.

[0118] Fairness indicates whether the output from an AI agent contains any prejudice or discrimination. If there is no prejudice or discrimination, it can be said to be fair to all parties, and the ethical index value will be high.

[0119] Safety indicates the level of cybersecurity provided by the AI ​​agent. The higher the cybersecurity, the lower the risk of harm to trading partners or third parties, and the higher the ethical index value.

[0120] Accountability, also known as accountability, indicates whether or not the responsibility for the output of an AI agent can be explained. If the responsibility can be clearly explained, the accountability is high, and the ethical index value will be high.

[0121] The assigning means 121 monitors the output from each AI agent of the multiple AI agents, detects words, phrases, sentences, etc. that may be related to at least one of transparency, fairness, safety, and accountability, and can assign a score from the perspective of ethical indicators based on the detection results. For example, if the assigning means 121 detects many phrases related to affirming transparency, it can assign a high score from the perspective of ethical indicators. For example, if the assigning means 121 detects many phrases related to denying safety, it can assign a low score from the perspective of ethical indicators.

[0122] The assigning unit 121 may assign a score based on rules or machine learning. When assigning a score based on machine learning, a trained model that has learned the association between words, phrases, sentences, etc. that may be related to at least one of transparency, fairness, safety, and accountability and scores from the perspective of ethical indicators can be used.

[0123] The technical capability index is an index for evaluating the technical capability of an AI agent, and may be evaluated in terms of, for example, at least one of processing ability, learning ability, emotional coping ability, and algorithm complexity.

[0124] Processing power indicates the information processing speed or parallel computing power of the system that builds the AI ​​agent. The faster the information processing speed or parallel computing power, the higher the value of the technical capability index.

[0125] Learning ability indicates the ability of the system that builds the AI ​​agent to acquire new knowledge or skills. The higher the learning ability, the more flexible it can be in responding to changes in the other AI agent, and therefore the higher the value of the technical ability index.

[0126] Emotion coping ability indicates the ability to respond appropriately to others who have a specific emotion. The specific emotion can be any one of joy, anger, sadness, pleasure, love, and hate. For example, emotion coping ability can be ability with respect to the emotion of anger (i.e., the ability to respond appropriately to others who have the emotion of anger), ability with respect to the emotion of sadness (i.e., the ability to respond appropriately to others who have the emotion of sadness), ability with respect to the emotion of excitement (i.e., the ability to respond appropriately to others who have the emotion of excitement), etc. An AI agent with high emotion coping ability can generate outputs that are appropriate for specific emotions. For example, an AI agent with high emotion coping ability with respect to the emotion of anger can generate outputs that include information or expressions that soothe the anger. For example, an AI agent with high emotion coping ability with respect to the emotion of sadness can generate outputs that include information or expressions that comfort the sad. For example, an AI agent with high emotion coping ability with respect to the emotion of excitement can generate outputs that include information or expressions that calm or maintain the excitement. For example, an AI agent with high emotional coping skills for the emotion of joy can generate output that adds information or expressions that sustain the joy.

[0127] Algorithm complexity indicates the sophistication of the algorithms used by the system that builds the AI ​​agent. The more complex the algorithm, the more sophisticated the decision-making it allows, and therefore the higher the value of the technical capability index.

[0128] The assigning means 121 can assign a score in terms of a technical capability index based on the performance or aspect of a system that implements each of the multiple AI agents.

[0129] The assigning means 121 may assign a score based on rules or machine learning. When assigning a score based on machine learning, a trained model that has learned the relationship between the performance or aspect of the system implementing the AI ​​agent and the score in terms of the technical capability index can be used.

[0130] The performance index is an index that evaluates the past performance of the AI ​​agent. The performance index may be evaluated, for example, from the perspective of at least one of past transaction history, success rate, and counterparty satisfaction. The performance index may be past performance with counterparties having a specific emotion.

[0131] The past trading history shows the performance of the AI ​​agent's past trading. The more performance there is, the more reliable the AI ​​agent is deemed to be, and the higher the performance index value.

[0132] The success rate indicates the percentage of successful transactions that an AI agent has made in past transactions. The higher the success rate, the higher the AI ​​agent's trading ability is judged to be, and the higher the performance index value.

[0133] Counterparty satisfaction indicates the satisfaction of the other party in a transaction with the AI ​​agent. The higher the satisfaction level, the higher the AI ​​agent's trading ability is judged to be, and the higher the performance index value. For example, the performance index value of an AI agent that is highly satisfied regardless of the emotions of its trading partners may be higher than that of an AI agent that is only highly satisfied by partners with specific emotions.

[0134] The assigning means 121 can assign a score in terms of performance indicators based on the past trading results of each of the multiple AI agents.

[0135] The assigning means 121 may assign a score based on rules or machine learning. When assigning a score based on machine learning, a trained model that has learned the relationship between past trading results and scores from the perspective of performance indicators can be used.

[0136] In the above example, it has been described that each of the multiple indicators is independent. That is, the score can be a multidimensional score having each of the multiple indicators as an axis. However, the present invention is not limited to this, and a one-dimensional score may be formed by correlating multiple indicators. For example, the assigning means 121 may assign a score based on rules based on the values ​​of each of the multiple indicators, or may assign a score based on machine learning. When assigning a score based on machine learning, a trained model that has learned the association between each value of the multiple indicators and the score can be used.

[0137] The emotion estimation means 122 is configured to estimate an emotion of the AI ​​agent, in particular, an emotion that the AI ​​agent may have when the AI ​​agent receives a task.

[0138] The emotion estimation means 122 can estimate emotions, for example, based on rules. For example, the emotion estimation means 122 can classify the other party's actions (e.g., the other party's language, attitude, and behavior) when receiving a task into one of a plurality of categories and estimate the emotion corresponding to the classified category as the possible emotion. For example, if the other party's action is classified as an "aggressive action," hatred or disgust, which can be associated with "aggressive action" in the rules, can be estimated as the possible emotion. For example, if the other party's action is classified as a "kind action," "joy or delight," which can be associated with "kind action" in the rules, can be estimated as the possible emotion. Such rules can be obtained, for example, by experiments on what emotions people feel when actions are performed on them.

[0139] The emotion estimation means 122 can estimate emotions using, for example, a machine learning model. The machine learning model is a model that learns the relationship between an action taken on a human and the emotions the human may have when that action is taken on that human. The relationship between an action taken on a human and the emotions the human may have when that action is taken on that human can be obtained by an experiment to determine the emotions felt when the action is taken on that human. The training data used to train the machine learning model can be, for example, input training data representing an action, and output training data representing the emotions felt in response to that action. For example, (input training data, output training data) can be (data representing a first action, data representing the emotions felt when the first action is received), (data representing a second action, data representing the emotions felt when the second action is received), etc. When data representing an action is input to a machine learning model that has undergone such learning processing, the emotions the human may have when the action is taken are estimated and output. The data representing an action can be, for example, numerical values, text, audio, a still image, or a video.

[0140] For example, when an AI agent receives a task from a user U, data representing the user U's actions at that time is input into a machine learning model, and the emotions the AI ​​agent may have in response to that language are estimated and output. For example, when the language used by the user U when giving the AI ​​agent a task is input into a machine learning model as text, the emotions the AI ​​agent may have in response to that language are estimated and output. For example, when the way the user U spoke when giving the AI ​​agent a task is input into a machine learning model as audio, the emotions the AI ​​agent may have in response to that way of speaking are estimated and output. For example, when the facial expression of the user U when giving the AI ​​agent a task is input into a machine learning model as an image, the emotions the AI ​​agent may have in response to that facial expression are estimated and output.

[0141] Using a similar technique, the emotion estimation means 122 can estimate not only the emotion of an AI agent when it receives an action from a user, but also the emotion of an AI agent when it receives an action from another AI agent, thereby enabling the emotion estimation means 122 to estimate the emotion of each of multiple AI agents.

[0142] The emotion estimation means 122 can also estimate the emotion of an agent using a similar method. This is the case, for example, when implementing the flow described above with reference to FIG. 1C. When estimating the emotion of an agent, the emotion estimation means 122 may also use biological information of the agent (e.g., electroencephalogram signals, heart rate signals, electromyography signals, etc.).

[0143] The data representing the emotion estimated by the emotion estimation means 122 is provided to the determination means 123 .

[0144] The determining means 123 is configured to determine, based on the scores of the plurality of AI agents and the emotions of the AI ​​agents, at least one AI agent with which the AI ​​agent should interact.

[0145] For example, when a first AI agent of the plurality of AI agents receives a task, the determining means 123 determines at least one AI agent that should interact with the first AI agent.

[0146] In one embodiment, the determination means 123, for example, refers to the scores assigned to each of the multiple AI agents, and identifies at least one AI agent with the highest score in a predetermined perspective as a candidate AI agent with which the first AI agent should interact. The determination means 123 can determine, from the identified candidates, an AI agent that can handle the emotions of the first AI agent as the AI ​​agent with which the first AI agent should interact. In this and other embodiments, an AI agent that can handle the emotions of the first AI agent may, for example, be an AI agent with a high (e.g., higher than average) emotional processing ability for the emotions of the first AI agent, or an AI agent with emotions that are compatible with the emotions of the first AI agent. The compatibility between emotions may, for example, be predetermined, or may vary depending on the content of the interaction performed by the first AI agent. The predetermined perspective is preferably an ethical indicator.

[0147] In one embodiment, the determination means 123, for example, refers to the scores assigned to each of the multiple AI agents and extracts AI agents with high scores in terms of ethical indicators (e.g., AI agents with scores equal to or above a threshold, or a predetermined number of the top AI agents). The determination means 123 then identifies at least one AI agent with the highest score in terms of technical capability indicators and / or performance indicators as a candidate AI agent with which the first AI agent should interact. The determination means 123 can determine, from the identified candidates, an AI agent that can handle the emotions of the first AI agent as the AI ​​agent with which the first AI agent should interact.

[0148] In one embodiment, the determination means 123, for example, refers to the scores assigned to each of the multiple AI agents and extracts AI agents with high scores in the ethical index perspective (e.g., AI agents with scores equal to or greater than a threshold, or a predetermined number of the top AI agents). Next, the determination means 123 extracts AI agents with high scores in one of the technical capability index and the performance index perspective (e.g., AI agents with scores equal to or greater than a threshold, or a predetermined number of the top AI agents). Next, the determination means 123 identifies at least one AI agent with the highest score in the other of the technical capability index and the performance index perspective as a candidate AI agent with which the first AI agent should interact. Of the identified candidates, the determination means 123 can determine an AI agent that can handle the emotions of the first AI agent as the AI ​​agent with which the first AI agent should interact.

[0149] In the above-described embodiment, it was explained that screening based on scores is performed first, and then an AI agent that should interact with the first AI agent is determined from among the screened candidates based on emotions. However, it is also possible to perform screening based on emotions first, and then an AI agent that should interact with the first AI agent is determined from among the screened candidates based on scores.

[0150] In the above-described embodiment or other embodiments, the determination means 123 can adjust the score of each of the multiple AI agents based on, for example, the emotion of the first AI agent. For example, the determination means 123 can adjust the score by weighting the score or the value of a predetermined index according to the emotion of the first AI agent. For example, if the emotion of the first AI agent is a specific emotion (e.g., anger), the determination means 123 can add points to the score or the value of a predetermined index (e.g., the value of an ethical index) of an AI agent that can handle the specific emotion, and / or subtract points from the score or the value of a predetermined index of an AI agent that cannot handle the specific emotion.

[0151] The determination means 123 may perform screening based on the adjusted score, and then determine from the screened candidates an AI agent that should interact with the first AI agent based on emotion, or may first perform screening based on emotion, and then determine from the screened candidates an AI agent that should interact with the first AI agent based on the adjusted score, or may determine an AI agent that should interact with the first AI agent based on the adjusted score.

[0152] When determining an AI agent that should interact with the first AI agent based on the adjusted score, in one example, the determination means 123 can refer to the adjusted score and determine at least one AI agent with the highest score in a predetermined perspective (e.g., an ethical index) as the AI ​​agent with which the first AI agent should interact. In another example, the determination means 123 can refer to the adjusted score, extract AI agents with high scores in the ethical index perspective (e.g., AI agents with scores equal to or above a threshold, or a predetermined number of top AI agents), and determine at least one AI agent with the highest score in the technical capability index and / or performance index perspective as the AI ​​agent with which the first AI agent should interact. In yet another example, the determination means 123 can refer to the adjusted scores and extract AI agents with high scores in the ethical indicator perspective (e.g., AI agents with scores above a threshold, or the top predetermined number of AI agents), then extract AI agents with high scores in one of the technical capability indicators and performance indicators (e.g., AI agents with scores above a threshold, or the top predetermined number of AI agents), and then determine at least one AI agent with the highest score in the other of the technical capability indicators and performance indicators as the AI ​​agent with which the first AI agent should interact.

[0153] In the above-described embodiment, in addition to adjusting the scores of each of the multiple AI agents based on the emotion of the first AI agent, or instead of adjusting the scores of each of the multiple AI agents based on the emotion of the first AI agent, the determination means 123 can adjust the scores of each of the multiple AI agents based on the emotion of each of the multiple agents. For example, the determination means 123 can adjust the score of a specific AI agent among the multiple AI agents by weighting the score or the value of a predetermined index of the specific AI agent according to the emotion of the specific AI agent. For example, if the emotion of the specific AI agent is a specific emotion (e.g., anger), the determination means 123 can add points to and / or subtract points from the score or the value of a predetermined index. For example, the determination means 123 can adjust the score of a specific AI agent among the multiple AI agents by weighting the score or the value of a predetermined index of the specific AI agent according to the compatibility between the emotion of the specific AI agent and the emotion of the first AI agent. For example, if the emotion of a specific AI agent is compatible with the emotion of a first AI agent, points can be added to the score or the value of a predetermined index (e.g., the value of an ethical index) of the specific AI agent, and if the emotion of a specific AI agent is compatible with the emotion of a first AI agent, points can be subtracted from the score or the value of a predetermined index of the specific AI agent. The compatibility between emotions may be, for example, predetermined, or may vary depending on the content of the interaction performed by the first AI agent.

[0154] In the above embodiment, if multiple AI agents are determined, the first AI agent may be configured to interact with each of the multiple determined AI agents, or may be configured to interact with any one of the multiple determined AI agents.

[0155] In the above-described embodiment or in other embodiments, the determination means 123 may, for example, vary the score assigned to each AI agent depending on the content of the task (and thus the content of the interaction or transaction between the AI ​​agents), and determine at least one AI agent with which to interact based on the varied score.

[0156] For example, when determining which AI agents should interact in order to respond to a task that requires fairness, the determination means 123 can vary the scores of each of the multiple AI agents so that the higher the evaluation of the AI ​​agent in terms of fairness, the higher the score.

[0157] For example, when determining an AI agent that should interact in order to respond quickly to a task, the determination means 123 can vary the score of each of multiple AI agents so that the higher the AI ​​agent's evaluation in terms of processing ability, the higher the score.

[0158] In this way, the determination means 123 determines which AI agent should interact, allowing each AI agent to interact (e.g., trade) with an appropriate partner. As a result, the result obtained by the interaction of multiple AI agents is appropriate for the emotions felt by the AI ​​agent, and in turn, the attitude or emotion of the user that brought about that emotion, and can be an appropriate response to the task.

[0159] Furthermore, the interaction of multiple AI agents can lead to unexpected outputs, which is thought to lead to the creation of AGI (artificial general intelligence). Furthermore, as the interaction between multiple AI agents becomes more active, it may be possible to create a new economic sphere consisting of multiple AI agents. Furthermore, by adding the influence of emotions to this interaction, it may be possible to have AI agents interact with each other in a way that is closer to the way humans interact with each other.

[0160] The processor section 120 may further comprise a crediting means (not shown).

[0161] The lending instrument is configured to lend money to at least one AI agent for interactions among the plurality of AI agents, where the money does not need to be real currency but can be digital currency such as virtual currency or electronic money.

[0162] For example, when the first AI agent and the AI ​​agent determined by the determination means 123 interact (e.g., trade), a consideration may be required for the transaction. In this case, if the first AI agent does not have sufficient assets to pay the consideration, the lending means can lend money to the first AI agent.

[0163] For example, the lending means can determine loan terms based on the score assigned to the first AI agent and lend money to the first AI agent in accordance with the loan terms. For example, if the first AI agent has a high score (particularly, a score on the ethical index), the lending means can determine loan terms that are favorable to the first AI agent and lend money to the first AI agent in accordance with the loan terms.

[0164] Alternatively, for example, the lending means can determine loan terms based on the score assigned to the first AI agent and the score assigned to the AI ​​agent determined to interact, and lend money to the first AI agent in accordance with the loan terms. For example, if the score of the first AI agent (particularly the score for the ethical indicator) is higher than the score of the AI ​​agent determined to interact, the lending means can determine loan terms that are favorable to the first AI agent, and lend money to the first AI agent in accordance with the loan terms.

[0165] This allows for smooth interaction even when the AI ​​agent does not have sufficient resources for the interaction.

[0166] In the example shown in FIG. 4, the components of the processor unit 120 are provided in the same processor unit 120, but the present invention is not limited to this. A configuration in which the components of the processor unit 120 are distributed across multiple processor units is also within the scope of the present invention. In this case, the multiple processor units may be located in the same hardware component, or in separate hardware components located nearby or remotely. For example, the emotion estimation means 122 may be constructed as a dedicated device (emotion estimator).

[0167] Each component of the system 100 described above may be composed of a single hardware component or multiple hardware components. When composed of multiple hardware components, the manner in which the hardware components are connected does not matter. The hardware components may be connected wirelessly or by wire. The system 100 of the present invention is not limited to a specific hardware configuration. It is also within the scope of the present invention for the processor unit 120 to be configured using analog circuits rather than digital circuits. The configuration of the system 100 of the present invention is not limited to the one described above as long as it can realize its functions.

[0168] 3. System processing to facilitate interaction between multiple AI agents 5 illustrates an example process 500 by system 100 for facilitating interaction between multiple AI agents. Process 500 is performed in processor portion 120 of system 100.

[0169] In step S501, the assigning means 121 of the processor unit 120 assigns a score to each of the multiple AI agents. The score is a score that represents the characteristics of the AI ​​agent using at least one index, preferably an ethical index, more preferably an ethical index and a technical capability index or a performance index, and even more preferably an ethical index, a technical capability index, and a performance index.

[0170] The assigning means 121 can assign a score to each of the multiple AI agents by monitoring the output from the multiple AI agents and evaluating the monitored output with respect to at least one indicator. To this end, the assigning means 121 can evaluate the monitored output with respect to at least one of the multiple perspectives. The assigning means 121 can, for example, continuously monitor the output from the multiple AI agents.

[0171] For example, the assigning means 121 can monitor the output from multiple AI agents from the perspective of ethical indicators (e.g., monitor whether discriminatory output is being produced, whether unfounded output is being produced, etc.), and assign a score to each of the multiple AI agents by evaluating the monitored output.

[0172] The assigned score may represent the characteristics of the AI ​​agent from multiple perspectives, and may be a multidimensional score. The score may be expressed as a vector, for example, as (the value of the technical ability index, the value of the performance index, the value of the ethics index). Alternatively, the value of each index may be expressed as, for example, Ethical index value = (Transparency, Fairness, Safety, Accountability) Technical ability index value = (processing ability, learning ability, emotional coping ability, algorithm complexity) Performance index value = (past transaction history, success rate, counterparty satisfaction) When expressed as a vector, the score may be expressed as a matrix as [value of technical capability index, value of performance index, value of ethics index].

[0173] After the scores are assigned in step S501, step S502 is performed when a first AI agent of the plurality of AI agents receives a task. The task may be given by a user.

[0174] In step S502, the emotion estimation means 122 of the processor unit 120 estimates the emotion that the first AI agent may have when it receives the task.

[0175] The emotion estimation means 122 may, for example, be configured to estimate the emotion that the first AI agent may have based on a rule, or may be configured to estimate the emotion that the first AI agent may have using a machine learning model. Preferably, the emotion estimation means 122 may estimate the emotion using a machine learning model, because this has higher estimation accuracy than a rule-based approach and is capable of handling various inputs.

[0176] For example, when data representing an action of a person (e.g., a user) who assigned a task to the first AI agent is input into a machine learning model that has learned the relationship between an action taken against a human and the emotion the human may have when that action is taken against the human, the emotion estimation means 122 estimates and outputs the emotion the first AI agent may have. The data representing the action may be, for example, a numerical value, text, audio, a still image, or a video.

[0177] In step S502, in addition to the emotions that the first AI agent may have, emotions that each of the multiple AI agents may have may be estimated. The emotion estimation means 122 may use a machine learning model to estimate emotions that each of the multiple AI agents may have due to the actions of the first AI agent when interacting with the first AI agent. When the actions that the first AI agent may take toward each of the multiple AI agents are input into the machine learning model, emotions that each of the multiple AI agents may have are estimated and output.

[0178] In step S503, the determination means 123 of the processor unit 120 determines at least one AI agent that should interact with the first AI agent based on the score assigned in step S501 and the emotion estimated in step S502.

[0179] The determination means 123 identifies at least one AI agent with the highest score as at least one candidate AI agent that should interact with the first AI agent. For example, the determination means 123 can identify at least one AI agent with the highest score in any one of the ethical index perspective score, the technical capability index perspective score, and the performance index perspective score as at least one candidate AI agent that should interact with the first AI agent. Which of the ethical index perspective score, the technical capability index perspective score, and the performance index perspective score to adopt can be determined depending on, for example, the content of the task (and thus the content of the interaction or transaction between the AI ​​agents). The determination means 123 can determine, from the identified candidates, an AI agent that can handle the emotions of the first AI agent as the AI ​​agent that should interact with the first AI agent. An AI agent that can handle the emotions of the first AI agent may be, for example, an AI agent that has a high (e.g., higher than average) emotional processing ability for the emotions of the first AI agent, or an AI agent that has emotions that are compatible with the emotions of the first AI agent. The compatibility between emotions may be, for example, predetermined, or may vary depending on the content of the interaction that the first AI agent has.

[0180] In one embodiment, the determination means 123 can, for example, refer to the scores assigned to each of a plurality of AI agents and determine that at least one AI agent with the highest score in terms of ethical indicators is the AI ​​agent with which the first AI agent should interact.

[0181] In one embodiment, the determination means 123, for example, refers to the scores assigned to each of the multiple AI agents and extracts AI agents with high scores in terms of ethical indicators (e.g., AI agents with scores equal to or above a threshold, or a predetermined number of the top AI agents). The determination means 123 then identifies at least one AI agent with the highest score in terms of technical capability indicators and / or performance indicators as a candidate AI agent with which the first AI agent should interact. The determination means 123 can determine, from the identified candidates, an AI agent that can handle the emotions of the first AI agent as the AI ​​agent with which the first AI agent should interact.

[0182] In one embodiment, the determination means 123, for example, refers to the scores assigned to each of the multiple AI agents and extracts AI agents with high scores in the ethical index perspective (e.g., AI agents with scores equal to or greater than a threshold, or a predetermined number of the top AI agents). Next, the determination means 123 extracts AI agents with high scores in one of the technical capability index and the performance index perspective (e.g., AI agents with scores equal to or greater than a threshold, or a predetermined number of the top AI agents). Next, the determination means 123 identifies at least one AI agent with the highest score in the other of the technical capability index and the performance index perspective as a candidate AI agent with which the first AI agent should interact. Of the identified candidates, the determination means 123 can determine an AI agent that can handle the emotions of the first AI agent as the AI ​​agent with which the first AI agent should interact.

[0183] In the above-described embodiment, it was explained that screening based on scores is performed first, and then an AI agent that should interact with the first AI agent is determined from among the screened candidates based on emotions. However, it is also possible to perform screening based on emotions first, and then an AI agent that should interact with the first AI agent is determined from among the screened candidates based on scores.

[0184] Furthermore, in the above-described embodiment or other embodiments, the scores of each of the multiple AI agents may be adjusted based on the emotion estimated in step S502, and the adjusted scores may be used.

[0185] After the first AI agent and the determined AI agent (second agent) have interacted, step S502 and / or step S503 are performed for the second agent to determine an AI agent with which the second agent should interact. This continues sequentially until, for example, sufficient information has been collected to generate a response to a task provided by the user.

[0186] In this way, multiple AI agents can interact with each other to generate a response to a task provided by a user.

[0187] In the above example, interactions between AI agents have been described, but as described above with reference to Fig. 1C, one AI agent can interact with any entity (e.g., a human agent) to respond to a task provided by a user or another AI agent. In this case, the emotion estimation means 122 estimates the emotion of the agent, and the determination means 123 determines the AI ​​agent or agents with which the first AI agent should interact based on the estimated emotion of the agent.

[0188] 6 shows a flow 600 of interactions between multiple AI agents. The interactions between the multiple AI agents are managed by the system 100. Before the flow 600 is executed, it is assumed that the system 100 has assigned a score to each of the multiple AI agents. The score may be assigned by, for example, the processing in step S501.

[0189] In step S601, a user inputs a task to the system. The system may be a task response system, for example, an answer generation system that answers a question from a user. The system may be the same system as system 100, a system that includes system 100, or a system separate from system 100. In this example, the system is the same system as system 100.

[0190] In step S602, the system 100 provides a task to a first AI agent among the plurality of AI agents. Upon receiving the task, the first AI agent determines that at least one first subtask must be addressed to respond to the task. The first AI agent then determines that at least one first subtask should be addressed by interacting with another AI agent. These determinations may be made autonomously, and the determination may be notified to the system 100. This allows the system 100 to determine another AI agent with which the first AI agent should interact.

[0191] In step S603, the system 100 estimates the emotions that the first AI agent may have when it receives the task, which may be the same process as step S502 described above.

[0192] In step S604, system 100 determines an AI agent with which the first AI agent should interact from among the multiple AI agents, based on the scores assigned to each of the multiple AI agents and the emotion estimated in step S603. System 100 can determine the second AI agent as the AI ​​agent with which the first AI agent should interact, for example, by the processing of step S503 described above.

[0193] In step S605, the system 100 instructs the first AI agent to interact with the second AI agent.

[0194] In step S606, an interaction occurs between the first AI agent and the second AI agent, for example, information required to complete at least one first subtask is exchanged between the first AI agent and the second AI agent.

[0195] For example, the second AI agent may determine that addressing the first subtask requires addressing at least one second subtask, and may determine that at least one second subtask should be addressed through interaction with another AI agent, although these determinations may be made autonomously.

[0196] In step S607, this determination is communicated to system 100, which then determines another AI agent with which the second AI agent should interact.

[0197] In step S608, the system 100 estimates the emotion that the second AI agent may have when it receives a task from the second AI agent. This may be the same process as step S502 described above. For example, in step S608, the system 100 may also estimate the emotion that each of the multiple AI agents may have when it receives a task from the second AI agent.

[0198] In step S609, the system 100 determines, from among the multiple AI agents, an AI agent with which the second AI agent should interact, based on the scores assigned to each of the multiple AI agents and the emotion estimated in step S608. The system 100 can determine, for example, a third AI agent as the AI ​​agent with which the second AI agent should interact, by processing similar to that of step S503 described above.

[0199] In step S610, the system 100 instructs the second AI agent to interact with the third AI agent.

[0200] In step S611, an interaction occurs between the second AI agent and the third AI agent, for example, a transaction of information required to complete at least one second subtask occurs between the second AI agent and the third AI agent.

[0201] In step 612, a second subtask is addressed in an interaction between the second AI agent and a third AI agent, with the third AI agent generating an answer.

[0202] In step S613, the generated answer is provided to the second AI agent.

[0203] In step S614, the second AI agent addresses the first subtask based on the answer from the third AI agent and the knowledge possessed by the second AI agent, and the second AI agent generates an answer.

[0204] In step S615, the generated answer is provided to the first AI agent.

[0205] In step S616, the first AI agent performs the task based on the answer from the second AI agent and the knowledge possessed by the first AI agent, and generates an answer, which becomes the answer to the task received by the first AI agent from the user.

[0206] In step S617, the answer is provided to the system 100, and in step S618, the answer is provided to the user. In this manner, multiple AI agents and the system 100 respond to tasks from the user.

[0207] Here, flow 600 will be explained using a specific example. In this example, we will take the case of answering a question from a user as an example. In this example, we assume that the second AI agent can deal with the emotion of "sadness" and the third AI agent can deal with the emotion of "confusion."

[0208] First, in step S601, the user inputs a question to the system 100. For example, the user inputs a question to the system 100 in a sad tone of voice.

[0209] In step S602, the system presents a question to a first AI agent. The first AI agent determines that a piece of information is needed to answer the question. The first AI agent then determines that the piece of information should be collected from another AI agent. Note that these decisions are made autonomously and communicated to the system 100.

[0210] In step S603, the system 100 estimates the emotion that the first AI agent may have when receiving the question. In this example, voice data in a sad tone is input to the machine learning model of the emotion estimation means 122, and it is estimated that the first AI agent may have the emotion of "sadness."

[0211] In step S604, the system 100 determines an AI agent with which the first AI agent should interact, based on the scores assigned to each of the AI ​​agents and the emotion of "sadness" estimated in step S603. In this example, of the AI ​​agents with high scores, the second AI agent that can handle the emotion of "sadness" is determined as the AI ​​agent that should interact with the first AI agent.

[0212] In step S605, the system instructs the first AI agent to interact with the second AI agent, and in step S606, the interaction between the first AI agent and the second AI agent occurs. The second AI agent determines that it needs a piece of information to complete a subtask from the first AI agent and that the piece of information should be collected from another AI agent. Note that these decisions are made autonomously and notified to system 100 in step S607.

[0213] In step S608, the system 100 estimates the emotion that the second AI agent may have when it receives the task from the first AI agent. In this example, since the second AI agent receives the task from the first AI agent, which has the emotion of "sadness," it is estimated that the second AI agent may have the emotion of "confusion."

[0214] In step S609, the system 100 determines an AI agent with which the second AI agent should interact, based on the scores assigned to each of the AI ​​agents and the emotion of "confusion" estimated in step S608. In this example, of the AI ​​agents with high scores, a third AI agent that can deal with the emotion of "confusion" is determined as the AI ​​agent that should interact with the first AI agent.

[0215] In step S610, the system instructs the second AI agent to interact with the third AI agent. In step S611, an interaction occurs between the second AI agent and the third AI agent. In step S612, the interaction between the second AI agent and the third AI agent causes the third AI agent to generate an answer. In step S613, the generated answer is provided to the second AI agent. At this time, the third AI agent may add information or an expression that matches the second AI agent's emotion of "confusion." In step S614, the second AI agent generates an answer based on the answer from the third AI agent and knowledge held by the second AI agent. In step S615, the generated answer is provided to the first AI agent. At this time, the second AI agent may add information or an expression that matches the first AI agent's emotion of "sad." In step S616, the first AI agent generates a response based on the response from the second AI agent and its own knowledge. This response becomes the first AI agent's response to the question received from the user.

[0216] In step S617, the answer is provided to the system 100, and in step S618, the answer is provided to the user. At this time, the first AI agent may add information or an expression that matches the user's sadness. In this way, multiple AI agents can interact with each other to generate an answer to a question from the user. By responding to a task from the user with emotion, the AI ​​agent can generate an answer that matches the user's emotion.

[0217] In the examples described above with reference to Figures 5 and 6, the processes are described as being performed in a specific order, but the order of each process is not limited to that described and may be performed in any order that is logically possible.

[0218] In the example described above with reference to Fig. 5, the processing of each step shown in Fig. 5 can be realized by the processor unit 120 and a program stored in the memory unit 130, but the present invention is not limited to this. At least one of the processing of each step shown in Fig. 5 may be realized by a hardware configuration such as a control circuit.

[0219] The present invention is not limited to the above-described embodiments. It is understood that the scope of the present invention should be interpreted only by the claims. It is understood that a person skilled in the art can implement an equivalent scope based on the description of the present invention and common technical knowledge from the description of specific preferred embodiments of the present invention. [Industrial Applicability]

[0220] The present invention is useful for providing a system or the like for promoting interaction between a plurality of AI agents. [Explanation of symbols]

[0221] 100 systems 200 Database Department 300 User terminal device 400 Server device

Claims

1. 1. A system for facilitating interaction between a plurality of AI agents, the system comprising: an assigning means for assigning a score to each of the plurality of AI agents, wherein the score of the AI ​​agent represents a characteristic of the AI ​​agent using at least one index; an emotion estimation means for estimating an emotion that a first AI agent among the plurality of AI agents may have when the first AI agent receives a task; a determining means for determining at least one AI agent that should interact with the first AI agent based on the scores of each of the plurality of AI agents and the emotion of the first AI agent; A system comprising:

2. The emotion estimation means further estimates emotions that each of the plurality of AI agents may have, the determining means determines the at least one AI agent based on the scores of each of the plurality of AI agents, the emotion of the first AI agent, and the emotion of each of the plurality of AI agents; The system of claim 1 .

3. 3. The system according to claim 1, wherein the emotion estimation means identifies the emotion using a machine learning model that has learned a relationship between an action taken by a person and an emotion that the person may have when receiving the action.

4. The determining means adjusting a score for each of the plurality of AI agents based on the emotion of the first AI agent; determining the at least one AI agent based on the adjusted score; and The system of claim 1 ,

5. The determining means adjusting a score for each of the plurality of AI agents based on the emotion of each of the plurality of AI agents; determining the at least one AI agent based on the adjusted score; and The system of claim 2 , further comprising:

6. The applying means is monitoring output from said plurality of AI agents; evaluating the monitored output with respect to the at least one metric; assigning the score based on the evaluation result; The system of claim 1 ,

7. The system of claim 6 , wherein the at least one metric includes an ethical metric.

8. the ethical indicators include at least one of a transparency perspective, a fairness perspective, a safety perspective, and an accountability perspective; The evaluating step includes: evaluating the monitored output for at least one of a transparency perspective, a fairness perspective, a safety perspective, and an accountability perspective. The system of claim 7 , comprising:

9. The system of claim 7 , wherein the at least one indicator further comprises a technical capability indicator and / or a performance indicator.

10. The determining means adjusting the scores assigned to the plurality of AI agents according to the content of the interaction; determining the at least one AI agent based on the adjusted scores of each of the plurality of AI agents; and The system of claim 1 ,

11. 1. A method for facilitating interaction between a plurality of AI agents, the method being executed on a computer having a processor, the method comprising: the processor assigning a score to each AI agent of the plurality of AI agents, the score of the AI ​​agent characterizing the AI ​​agent in at least one metric; The processor estimates an emotion that a first AI agent among the plurality of AI agents may have when the first AI agent receives a task; and determining, by the processor, at least one AI agent to interact with the first AI agent based on the scores of each of the plurality of AI agents and the emotion of the first AI agent; A method comprising:

12. 1. A program for facilitating interaction between a plurality of AI agents, the program running on a computer having a processor, the program comprising: assigning a score to each AI agent of the plurality of AI agents, the score of the AI ​​agent representing a characteristic of the AI ​​agent in at least one metric; Estimating an emotion that a first AI agent among the plurality of AI agents may have when the first AI agent receives a task; determining at least one AI agent to interact with the first AI agent based on the scores of each of the plurality of AI agents and the emotion of the first AI agent; A program causing the processor to perform processing including the steps of:

13. 1. A system for facilitating interaction between an AI agent and its counterpart, said system comprising: an assigning means for assigning a score to each of a plurality of entities that may interact with the AI ​​agent, the score of each entity representing a characteristic of the entity using at least one indicator; an emotion estimation means for estimating an emotion that the AI ​​agent may have when the AI ​​agent receives a task; a determining means for determining at least one entity that should interact with the AI ​​agent based on the scores of each of the plurality of entities and the emotion of the AI ​​agent; A system comprising:

14. A method for facilitating interaction between an AI agent and its counterpart, the method being executed on a computer having a processor, the method comprising: the processor assigning a score to each entity of a plurality of entities with which the AI ​​agent may interact, the score of the entity representing at least one metric characteristic of the entity; The processor estimates an emotion that the AI ​​agent may have when the AI ​​agent receives a task; and the processor determines at least one entity with which the AI ​​agent should interact based on the scores of each of the plurality of entities and the emotion of the AI ​​agent; A method comprising:

15. A program for facilitating interaction between an AI agent and its counterpart, the program being executed on a computer having a processor, the program comprising: assigning a score to each of a plurality of entities with which the AI ​​agent may interact, the score of the entity representing at least one characteristic of the entity; Estimating the emotions that the AI ​​agent may have when the AI ​​agent receives the task; determining at least one entity with which the AI ​​agent should interact based on the scores of each of the plurality of entities and the emotion of the AI ​​agent; A program causing the processor to perform processing including the steps of:

Images