System

Abstract

The system according to the embodiment aims to achieve a reasonable solution even when there is an emotional conflict.SOLUTION: A system includes a virtual arbitrator character setting unit, a situation arrangement unit, a pain division proposal unit, an arbitration plan presentation unit, and a dispute resolution support unit. The virtual mediator character setting unit sets a virtual mediator character. The situation organizing unit organizes the situation based on the information provided by the virtual mediator character set by the virtual mediator character setting unit. The pain classification proposal unit proposes pain classification based on the situations organized by the situation organizing unit. The arbitration plan presentation unit presents a specific arbitration plan based on the contents proposed by the pain classification proposal unit. The dispute resolution support unit supports a discussion between the parties based on the arbitration plan presented by the arbitration plan presentation unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional techniques make it difficult to achieve rational resolution when emotional conflicts arise, and there is room for improvement.

[0005] The system according to the embodiment aims to achieve rational resolution even in the case of emotional conflicts. [Means for solving the problem]

[0006] The system according to the embodiment includes a virtual arbitrator character setting unit, a situation management unit, a tie-breaking proposal unit, an arbitration proposal presentation unit, and a dispute resolution support unit. The virtual arbitrator character setting unit sets a virtual arbitrator character. The situation management unit allows the virtual arbitrator character set by the virtual arbitrator character setting unit to organize the situation based on information provided by the parties. The tie-breaking proposal unit proposes a tie-breaking proposal based on the situation organized by the situation management unit. The arbitration proposal presentation unit presents a specific arbitration proposal based on the content proposed by the tie-breaking proposal unit. The dispute resolution support unit supports discussions between the parties based on the arbitration proposal presented by the arbitration proposal presentation unit. [Effects of the Invention]

[0007] The system according to the embodiment can achieve rational resolution even in the case of emotional conflicts. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) In a dispute resolution system according to an embodiment of the present invention, in situations where parties in a dispute tend to become emotional, a generation AI sets up a virtual arbitrator character and receives proposals for arbitration and resolution methods in a simple manner. This allows the dispute resolution system to rationally resolve disputes between parties who tend to become emotional.

[0029] A dispute resolution system according to an embodiment includes a virtual arbitrator character setting unit, a situation management unit, a dispute-sharing proposal unit, an arbitration proposal presentation unit, and a dispute resolution support unit. The virtual arbitrator character setting unit sets a virtual arbitrator character. For example, the generation AI sets a virtual arbitrator character to assist the parties in resolving the dispute. This character acts as a neutral presence, allowing the parties to proceed with the discussion without becoming emotional. The generation AI responds, for example, with a message such as, "Hello, I'm the arbitrator who will resolve your dispute. First, let's organize the situation." The situation management unit uses the virtual arbitrator character set by the virtual arbitrator character setting unit to organize the situation based on information provided by the parties. For example, the parties provide their respective arguments and evidence, and the generation AI analyzes and organizes them. This clarifies the cause and background of the dispute. The dispute-sharing proposal unit makes a dispute-sharing proposal based on the situation organized by the situation management unit. For example, the message may be, "Considering your arguments, the following solution is possible. By making small concessions on both sides, we believe we can reach an agreement." The arbitration proposal presentation unit presents a specific arbitration proposal based on the content proposed by the pain-sharing proposal unit. For example, the arbitration proposal may be presented in the form of, "We propose an agreement on the following conditions. This will be a solution that both parties can agree on." The dispute resolution support unit supports discussions between the parties based on the arbitration proposal presented by the arbitration proposal presentation unit. For example, the support may be presented in the form of, "Let's continue discussions on this arbitration proposal. Let's aim to reach a final agreement while respecting each other's opinions." This allows the dispute resolution system according to the embodiment to rationally resolve disputes between parties that tend to become emotional.

[0030] The virtual arbitrator character setting unit can adopt a personalized approach based on the parties' past behavioral history and statements. For example, the virtual arbitrator character in the virtual arbitrator character setting unit responds individually based on the parties' past behavioral history and statements. For example, the virtual arbitrator character will speak in a calm tone to a party who has made emotional statements in the past. The virtual arbitrator character setting unit can also analyze the parties' past behavioral history to find specific patterns, and the virtual arbitrator character will take an appropriate approach based on those patterns. For example, if the party has made concessions in the past, the virtual arbitrator character will emphasize that point. The virtual arbitrator character can also send personalized messages to build trust based on the parties' past statements. For example, the virtual arbitrator character can express empathy by quoting past statements. This makes it possible to respond individually based on the parties' past behavioral history and statements.

[0031] The virtual arbitrator character setting unit can customize the appearance and voice to factors that the parties find most trustworthy. The virtual arbitrator character setting unit, for example, customizes the appearance of the virtual arbitrator character to factors that the parties find most trustworthy. For example, it adjusts the age, gender, clothing, etc. The virtual arbitrator character setting unit also customizes the character's voice to a tone and accent that the parties find most trustworthy. For example, it selects a calm tone and a friendly accent. The virtual arbitrator character setting unit also customizes the appearance and voice of the virtual arbitrator character to match the cultural background of the parties. For example, it selects an appearance and voice that are familiar to a particular culture or region. This makes it possible to set a character that is easy to trust.

[0032] The virtual arbitrator character setting unit can be adapted to different cultures and languages, making it applicable to international dispute resolution. For example, the virtual arbitrator character setting unit is equipped with a multilingual support function to allow the virtual arbitrator character to adapt to different cultures and languages. For example, it supports multiple languages, such as English, French, and Chinese. To accommodate different cultures, the virtual arbitrator character setting unit also customizes the appearance and speech of the virtual arbitrator character to match the cultural background. For example, it may incorporate clothing and greetings familiar to a particular culture. To accommodate international dispute resolution, the virtual arbitrator character also understands different legal systems and customs and provides appropriate advice based on that understanding. For example, it may make proposals based on the laws and regulations of each country. This enables international dispute resolution that adapts to different cultures and languages.

[0033] The virtual arbitrator character setting unit can increase persuasiveness by having the virtual arbitrator character quote expert opinions and past precedents. The virtual arbitrator character setting unit increases persuasiveness by, for example, having the virtual arbitrator character quote expert opinions. For example, the citation may be in the form of, "Regarding this issue, according to expert opinion...". The virtual arbitrator character setting unit also cites past precedents to provide the basis for a proposal by the virtual arbitrator character. For example, the citation may be in the form of, "In past precedents, this solution was adopted." The virtual arbitrator character also provides specific advice based on expert opinions and past precedents. For example, the advice may be in the form of, "Based on expert opinion, we propose this solution." In this way, citing expert opinions and past precedents increases persuasiveness.

[0034] The situation organization unit can organize the information provided by the parties in chronological order and visualize the flow of the conflict from the inception to the present. The situation organization unit, for example, organizes the information provided by the parties in chronological order and visualizes the flow of the conflict from the inception to the present. For example, it displays it in a timeline format. The situation organization unit also organizes the provided information in chronological order and highlights important events and statements. For example, it highlights events that occurred on specific dates and times. The situation organization unit also uses graphs and charts to visualize the flow of the conflict from the inception to the present. For example, it displays the frequency of events and changes in emotions in a graph. In this way, visualizing the flow of the conflict makes it easier to understand the situation.

[0035] The situation sorting unit can automatically evaluate the provided evidence based on its reliability and relevance and rank its importance. For example, the situation sorting unit automatically evaluates the provided evidence based on its reliability and relevance and ranks its importance. For example, it calculates a reliability score for the evidence and preferentially displays evidence with a high score. The situation sorting unit also analyzes the relevance of the evidence and identifies evidence that is important in dispute resolution. For example, it distinguishes between direct evidence and indirect evidence. The situation sorting unit also ranks the evidence based on its reliability and relevance and highlights evidence with a high degree of importance. For example, it displays evidence with a high degree of importance in a different color. This allows the importance of the evidence to be evaluated based on its reliability and relevance.

[0036] The situation sorting unit can compare different dispute cases and automatically extract similarities and differences. For example, the situation sorting unit extracts different dispute cases from a database and compares them with the current dispute. For example, it automatically analyzes the similarities and differences between past and current dispute cases. The situation sorting unit also develops an algorithm for extracting similarities and differences and compares different dispute cases with the current dispute. For example, it compares them based on specific keywords or phrases. The situation sorting unit also compares different dispute cases with the current dispute and visually displays the similarities and differences. For example, it displays common elements and different elements in different colors. This makes it possible to compare different dispute cases and extract similarities and differences.

[0037] The situation organization unit can convert the provided information into visual notes or mind maps to make it easier to understand visually. For example, the situation organization unit can convert the provided information into visual notes to make it easier to understand visually. For example, it can show important points with diagrams or icons. The situation organization unit can also convert the information into a mind map format to visually organize related keywords and concepts. This allows the overall picture of the information to be understood at a glance. The situation organization unit can also develop tools that automatically generate visual notes or mind maps to enable users to easily display information visually. For example, it can provide a function for visualizing information using drag and drop. This makes it easier to understand information visually.

[0038] The pain-sharing proposal unit can reflect the parties' past agreement history and concession patterns in the proposal content. The pain-sharing proposal unit, for example, analyzes the parties' past agreement history and reflects it in the proposal content. For example, it adjusts the current proposal based on the content of past agreements. The pain-sharing proposal unit also analyzes the parties' concession patterns and reflects it in the proposal content. For example, it adjusts the current proposal taking into account points on which past concessions were made. The pain-sharing proposal unit also personalizes the proposal content based on the parties' past agreement history and concession patterns. For example, it makes the optimal proposal based on past data. In this way, by reflecting the parties' past agreement history and concession patterns, more appropriate proposals can be made.

[0039] The pain-sharing proposal unit can simulate the effects of the proposal and predict the long-term impact. The pain-sharing proposal unit, for example, simulates the effects of the proposal content and predicts the long-term impact. For example, it creates multiple scenarios for when the proposal is implemented and compares the results of each scenario. The pain-sharing proposal unit also evaluates the long-term impact of the proposal content based on the simulation results. For example, it predicts the economic impact and social impact. The pain-sharing proposal unit also develops an algorithm for simulating the effects of the proposal and predicts the long-term impact. For example, it performs a simulation based on past data. This makes it possible to simulate the effects of the proposal and predict the long-term impact.

[0040] The pain-sharing proposal unit can present multiple different solutions and allow the parties to choose from. For example, the pain-sharing proposal unit may present multiple different solutions and allow the parties to choose from. For example, multiple scenarios may be presented and the parties may choose the most acceptable solution. The pain-sharing proposal unit may also present the proposals as multiple options and allow the parties to choose from. For example, the advantages and disadvantages of each option may be explained. The pain-sharing proposal unit may also develop an algorithm to present different solutions and allow the parties to choose from. For example, the optimal option may be generated based on past data. This may allow different solutions to be presented and the parties to choose from.

[0041] The pain-sharing proposal unit can compare the effectiveness of proposals under different scenarios and conditions. For example, the pain-sharing proposal unit simulates proposals under different scenarios and conditions and compares the effects. For example, it evaluates the economic and social impacts. The pain-sharing proposal unit also develops algorithms for comparing the effectiveness of proposals under different scenarios and conditions. For example, it performs simulations based on past data. The pain-sharing proposal unit also compares the effectiveness of proposals under different scenarios and conditions and selects the optimal proposal. For example, it adjusts proposals based on multiple scenarios. This makes it possible to compare the effects under different scenarios and conditions.

[0042] The arbitration proposal presentation unit can cite past success stories and precedents in the arbitration proposal to increase its persuasiveness. The arbitration proposal presentation unit can, for example, cite past success stories in the arbitration proposal to increase its persuasiveness. For example, the citation can be in the form of, "In past cases, such a solution was successful." The arbitration proposal presentation unit can also cite precedents to demonstrate the basis for the arbitration proposal. For example, the citation can be in the form of, "In past cases, such a solution was adopted." The arbitration proposal presentation unit can also specifically explain the arbitration proposal based on past success stories and precedents. For example, the explanation can be in the form of, "This solution is proposed based on past cases." In this way, the persuasiveness of the arbitration proposal can be increased by citing past success stories and precedents.

[0043] The arbitration proposal presentation unit can provide detailed explanations and grounds for each element of the arbitration proposal. The arbitration proposal presentation unit, for example, provides a detailed explanation for each element of the arbitration proposal. For example, it specifically explains the purpose and effect of each element. The arbitration proposal presentation unit also provides the grounds for the arbitration proposal to enable the parties to be convinced. For example, it provides a detailed explanation of the background and reasons for the proposal contents. The arbitration proposal presentation unit also creates a document to provide detailed explanations and grounds for each element of the arbitration proposal. For example, it provides a detailed explanation of the proposal contents. In this way, by providing detailed explanations and grounds for each element of the arbitration proposal, the parties can be more easily convinced.

[0044] The arbitration proposal presentation unit can present multiple different arbitration proposals and allow the parties to choose from them. For example, the arbitration proposal presentation unit may present multiple different arbitration proposals and allow the parties to choose from them. For example, it may present multiple scenarios and allow the parties to select the most acceptable proposal. The arbitration proposal presentation unit may also present multiple arbitration proposals as options and allow the parties to choose from them. For example, it may explain the advantages and disadvantages of each option. The arbitration proposal presentation unit may also develop an algorithm for presenting different arbitration proposals and allow the parties to choose from them. For example, it may generate the optimal option based on past data. This may allow different arbitration proposals to be presented and the parties to choose from them.

[0045] The arbitration proposal presentation unit can compare the effectiveness of arbitration proposals under different scenarios and conditions. For example, the arbitration proposal presentation unit simulates arbitration proposals under different scenarios and conditions and compares their effectiveness. For example, it evaluates the economic and social impacts. The arbitration proposal presentation unit also develops algorithms for comparing the effectiveness of arbitration proposals under different scenarios and conditions. For example, it performs simulations based on past data. The arbitration proposal presentation unit also compares the effectiveness of arbitration proposals under different scenarios and conditions and selects the optimal proposal. For example, it adjusts the arbitration proposal based on multiple scenarios. This makes it possible to compare the effectiveness under different scenarios and conditions.

[0046] The dispute resolution support department can track the progress of dispute resolution in real time and visualize the progress. For example, the dispute resolution support department builds a system that tracks the progress of dispute resolution in real time and visualizes the progress. For example, the progress is displayed in graphs and charts. The dispute resolution support department also tracks the progress of dispute resolution in real time and highlights important milestones. For example, it highlights goals that were achieved on a specific date and time. The dispute resolution support department also develops a tool for visualizing the progress, allowing users to easily check the progress. For example, the progress is displayed in a dashboard format. This makes it possible to track the progress of dispute resolution in real time and visualize the progress.

[0047] The dispute resolution support department can follow up on solutions after they are implemented and evaluate their long-term effectiveness. The dispute resolution support department, for example, builds a system for following up on solutions after they are implemented and evaluating their long-term effectiveness. For example, it periodically checks the progress and evaluates their effectiveness. The dispute resolution support department also follows up on solutions after they are implemented and develops an algorithm for evaluating their long-term effectiveness. For example, it predicts their effectiveness based on past data. The dispute resolution support department also evaluates the effectiveness of solutions based on the results of the follow-up and makes adjustments as necessary. For example, if the effectiveness is insufficient, it proposes additional measures. This makes it possible to follow up on solutions after they are implemented and evaluate their long-term effectiveness.

[0048] The dispute resolution support unit can present multiple different solutions and allow the parties to choose from. For example, the dispute resolution support unit may present multiple different solutions and allow the parties to choose from. For example, multiple scenarios may be presented and the parties may choose the most acceptable solution. The dispute resolution support unit may also present multiple solution options and allow the parties to choose from. For example, the unit may explain the advantages and disadvantages of each option. The dispute resolution support unit may also develop an algorithm to present different solutions and allow the parties to choose from. For example, the unit may generate the optimal option based on past data. This may allow different solutions to be presented and the parties to choose from.

[0049] The dispute resolution support unit can simulate the effects of a solution and predict its long-term impact. The dispute resolution support unit, for example, simulates the effects of a solution and predicts its long-term impact. For example, it creates multiple scenarios for when a solution is implemented and compares the results of each scenario. The dispute resolution support unit also evaluates the long-term impact of the solution based on the simulation results. For example, it predicts the economic and social impacts. The dispute resolution support unit also develops an algorithm for simulating the effects of a solution and predicts its long-term impact. For example, it performs a simulation based on past data. This makes it possible to simulate the effects of a solution and predict its long-term impact.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The virtual arbitrator character setting unit can further include a "cultural adaptation unit." The cultural adaptation unit can adjust the virtual arbitrator character's response taking into account the cultural backgrounds of the parties. For example, it can reflect the values ​​and communication styles that are important in a particular culture. The cultural adaptation unit can also provide advice to avoid cultural misunderstandings in conflicts between different cultures. Furthermore, the cultural adaptation unit can train the virtual arbitrator character to have multicultural skills. This enables conflict resolution that takes cultural backgrounds into consideration.

[0052] The virtual arbitrator character setting unit may further include a "health status monitoring unit." The health status monitoring unit can monitor the health status of the parties in real time and identify factors that affect the progress of the dispute resolution. For example, it can measure stress levels and heart rates and suggest taking a break if the parties' health status is deteriorating. The health status monitoring unit can also adjust the response of the virtual arbitrator character according to the parties' health status. Furthermore, the health status monitoring unit can provide advice to optimize the progress of the dispute resolution based on the health status data. This enables dispute resolution that takes health status into consideration.

[0053] The processing flow of the first embodiment will be briefly explained below.

[0054] Step 1: The virtual arbitrator character setting unit sets up a virtual arbitrator character. For example, the generation AI sets up a virtual arbitrator character to help resolve the dispute between the parties. This character acts as a neutral presence to help the parties proceed with the discussion without getting emotional. The generation AI responds, for example, by saying, "Hello, I am the arbitrator to resolve your dispute. First, let's clarify the situation." Step 2: In the situation analysis section, the virtual arbitrator character set by the virtual arbitrator character setting section analyzes the situation based on the information provided by the parties. For example, the parties provide their respective arguments and evidence, and the AI ​​generation analyzes and organizes them. This clarifies the cause and background of the dispute. Step 3: The Pain-Sharing Proposal Team makes a pain-sharing proposal based on the situation summarized by the Situation Analysis Team. For example, they might propose something like, "Taking your arguments into consideration, the following solution is possible. By making small concessions on both sides, we should be able to reach an agreement." Step 4: The arbitration proposal presentation section presents a specific arbitration proposal based on the proposal made by the pain-sharing proposal section. For example, the proposal may be presented in the form of, "We propose to agree on the following conditions. This will be a solution that both parties can agree on." Step 5: The Dispute Resolution Support Department supports discussions between the parties based on the arbitration proposal presented by the Arbitration Proposal Department. For example, the department may provide support by saying, "Let's continue discussions on this arbitration proposal. Let's aim to reach a final agreement while respecting each other's opinions."

[0055] (Example 2) In a dispute resolution system according to an embodiment of the present invention, in situations where parties in a dispute tend to become emotional, a generation AI sets up a virtual arbitrator character and receives proposals for arbitration and resolution methods in a simple manner. This allows the dispute resolution system to rationally resolve disputes between parties who tend to become emotional.

[0056] A dispute resolution system according to an embodiment includes a virtual arbitrator character setting unit, a situation management unit, a dispute-sharing proposal unit, an arbitration proposal presentation unit, and a dispute resolution support unit. The virtual arbitrator character setting unit sets a virtual arbitrator character. For example, the generation AI sets a virtual arbitrator character to assist the parties in resolving the dispute. This character acts as a neutral presence, allowing the parties to proceed with the discussion without becoming emotional. The generation AI responds, for example, with a message such as, "Hello, I'm the arbitrator who will resolve your dispute. First, let's organize the situation." The situation management unit uses the virtual arbitrator character set by the virtual arbitrator character setting unit to organize the situation based on information provided by the parties. For example, the parties provide their respective arguments and evidence, and the generation AI analyzes and organizes them. This clarifies the cause and background of the dispute. The dispute-sharing proposal unit makes a dispute-sharing proposal based on the situation organized by the situation management unit. For example, the message may be, "Considering your arguments, the following solution is possible. By making small concessions on both sides, we believe we can reach an agreement." The arbitration proposal presentation unit presents a specific arbitration proposal based on the content proposed by the pain-sharing proposal unit. For example, the arbitration proposal may be presented in the form of, "We propose an agreement on the following conditions. This will be a solution that both parties can agree on." The dispute resolution support unit supports discussions between the parties based on the arbitration proposal presented by the arbitration proposal presentation unit. For example, the support may be presented in the form of, "Let's continue discussions on this arbitration proposal. Let's aim to reach a final agreement while respecting each other's opinions." This allows the dispute resolution system according to the embodiment to rationally resolve disputes between parties that tend to become emotional.

[0057] The virtual arbitrator character setting unit can adopt a personalized approach based on the parties' past behavioral history and statements. For example, the virtual arbitrator character in the virtual arbitrator character setting unit responds individually based on the parties' past behavioral history and statements. For example, the virtual arbitrator character will speak in a calm tone to a party who has made emotional statements in the past. The virtual arbitrator character setting unit can also analyze the parties' past behavioral history to find specific patterns, and the virtual arbitrator character will take an appropriate approach based on those patterns. For example, if the party has made concessions in the past, the virtual arbitrator character will emphasize that point. The virtual arbitrator character can also send personalized messages to build trust based on the parties' past statements. For example, the virtual arbitrator character can express empathy by quoting past statements. This makes it possible to respond individually based on the parties' past behavioral history and statements.

[0058] The virtual arbitrator character setting unit can customize the appearance and voice to factors that the parties find most trustworthy. The virtual arbitrator character setting unit, for example, customizes the appearance of the virtual arbitrator character to factors that the parties find most trustworthy. For example, it adjusts the age, gender, clothing, etc. The virtual arbitrator character setting unit also customizes the character's voice to a tone and accent that the parties find most trustworthy. For example, it selects a calm tone and a friendly accent. The virtual arbitrator character setting unit also customizes the appearance and voice of the virtual arbitrator character to match the cultural background of the parties. For example, it selects an appearance and voice that are familiar to a particular culture or region. This makes it possible to set a character that is easy to trust.

[0059] The virtual arbitrator character setting unit can use the emotion estimation function to automatically adjust the tone and language used according to the emotional state of the parties. For example, the virtual arbitrator character setting unit uses the emotion estimation function to analyze the emotional state of the parties in real time and automatically adjust the tone and language used by the virtual arbitrator character. For example, if the parties are feeling angry, the virtual arbitrator character setting unit speaks in a calm tone. The virtual arbitrator character setting unit also selects appropriate language for the virtual arbitrator character according to the emotional state of the parties. For example, if the parties are feeling sad, the virtual arbitrator character setting unit uses encouraging words. The virtual arbitrator character setting unit also uses the emotion estimation function to dynamically change the response of the virtual arbitrator character according to changes in the parties' emotions. For example, if the parties are emotionally charged, the virtual arbitrator character setting unit urges them to stay calm. This makes it possible to respond appropriately according to their emotional states.

[0060] The virtual arbitrator character setting unit can be adapted to different cultures and languages, making it applicable to international dispute resolution. For example, the virtual arbitrator character setting unit is equipped with a multilingual support function to allow the virtual arbitrator character to adapt to different cultures and languages. For example, it supports multiple languages, such as English, French, and Chinese. To accommodate different cultures, the virtual arbitrator character setting unit also customizes the appearance and speech of the virtual arbitrator character to match the cultural background. For example, it may incorporate clothing and greetings familiar to a particular culture. To accommodate international dispute resolution, the virtual arbitrator character also understands different legal systems and customs and provides appropriate advice based on that understanding. For example, it may make proposals based on the laws and regulations of each country. This enables international dispute resolution that adapts to different cultures and languages.

[0061] The virtual arbitrator character setting unit can increase persuasiveness by having the virtual arbitrator character quote expert opinions and past precedents. The virtual arbitrator character setting unit increases persuasiveness by, for example, having the virtual arbitrator character quote expert opinions. For example, the citation may be in the form of, "Regarding this issue, according to expert opinion...". The virtual arbitrator character setting unit also cites past precedents to provide the basis for a proposal by the virtual arbitrator character. For example, the citation may be in the form of, "In past precedents, this solution was adopted." The virtual arbitrator character also provides specific advice based on expert opinions and past precedents. For example, the advice may be in the form of, "Based on expert opinion, we propose this solution." In this way, citing expert opinions and past precedents increases persuasiveness.

[0062] The virtual arbitrator character setting unit can use the emotion estimation function to provide feedback on the emotions of the parties in real time and encourage an appropriate response. For example, the virtual arbitrator character setting unit uses the emotion estimation function to have the virtual arbitrator character analyze the emotions of the parties in real time and feed back the results. For example, the virtual arbitrator character setting unit provides feedback in the form of, "You seem to be feeling angry right now. Please stay calm." The virtual arbitrator character setting unit also encourages the virtual arbitrator character to take an appropriate response depending on the emotional state of the parties. For example, if the parties are feeling sad, the virtual arbitrator character encourages the virtual arbitrator character to take a short break. The virtual arbitrator character setting unit also uses the emotion estimation function to have the virtual arbitrator character dynamically change its response depending on changes in the parties' emotions. For example, if the parties are feeling emotionally charged, the virtual arbitrator character encourages the virtual arbitrator character to take a deep breath and stay calm. This allows for real-time feedback of emotions to enable an appropriate response.

[0063] The situation organization unit can organize the information provided by the parties in chronological order and visualize the flow of the conflict from the inception to the present. The situation organization unit, for example, organizes the information provided by the parties in chronological order and visualizes the flow of the conflict from the inception to the present. For example, it displays it in a timeline format. The situation organization unit also organizes the provided information in chronological order and highlights important events and statements. For example, it highlights events that occurred on specific dates and times. The situation organization unit also uses graphs and charts to visualize the flow of the conflict from the inception to the present. For example, it displays the frequency of events and changes in emotions in a graph. In this way, visualizing the flow of the conflict makes it easier to understand the situation.

[0064] The situation sorting unit can automatically evaluate the provided evidence based on its reliability and relevance and rank its importance. For example, the situation sorting unit automatically evaluates the provided evidence based on its reliability and relevance and ranks its importance. For example, it calculates a reliability score for the evidence and preferentially displays evidence with a high score. The situation sorting unit also analyzes the relevance of the evidence and identifies evidence that is important in dispute resolution. For example, it distinguishes between direct evidence and indirect evidence. The situation sorting unit also ranks the evidence based on its reliability and relevance and highlights evidence with a high degree of importance. For example, it displays evidence with a high degree of importance in a different color. This allows the importance of the evidence to be evaluated based on its reliability and relevance.

[0065] The situation organization unit can use the emotion estimation function to track changes in the emotions of the parties involved and identify emotional peaks. For example, the situation organization unit uses the emotion estimation function to track changes in the emotions of the parties involved in real time and identify emotional peaks. For example, peaks of anger or sadness are displayed in a graph. The situation organization unit also analyzes the emotional changes of the parties involved and identifies the timing at which emotional peaks occurred. For example, if a specific statement or event causes an emotional peak, the timing is highlighted. The situation organization unit also uses the emotion estimation function to develop an algorithm for tracking changes in the emotions of the parties involved and identifying emotional peaks. For example, peaks are detected based on fluctuations in emotion scores. This makes it possible to track changes in emotions and identify emotional peaks.

[0066] The situation sorting unit can compare different dispute cases and automatically extract similarities and differences. For example, the situation sorting unit extracts different dispute cases from a database and compares them with the current dispute. For example, it automatically analyzes the similarities and differences between past and current dispute cases. The situation sorting unit also develops an algorithm for extracting similarities and differences and compares different dispute cases with the current dispute. For example, it compares them based on specific keywords or phrases. The situation sorting unit also compares different dispute cases with the current dispute and visually displays the similarities and differences. For example, it displays common elements and different elements in different colors. This makes it possible to compare different dispute cases and extract similarities and differences.

[0067] The situation organization unit can convert the provided information into visual notes or mind maps to make it easier to understand visually. For example, the situation organization unit can convert the provided information into visual notes to make it easier to understand visually. For example, it can show important points with diagrams or icons. The situation organization unit can also convert the information into a mind map format to visually organize related keywords and concepts. This allows the overall picture of the information to be understood at a glance. The situation organization unit can also develop tools that automatically generate visual notes or mind maps to enable users to easily display information visually. For example, it can provide a function for visualizing information using drag and drop. This makes it easier to understand information visually.

[0068] The situation management unit can dynamically change the method of managing the situation based on the emotional reaction of the party using the emotion estimation function. The situation management unit, for example, uses the emotion estimation function to analyze the emotional reaction of the party in real time and dynamically change the method of managing the situation based on the results. For example, if the party is emotionally aroused, it urges the party to stay calm. The situation management unit also adjusts the method of managing the situation based on the emotional reaction of the party. For example, if the party is emotionally aroused, it provides detailed information, and if the party is emotionally aroused, it provides concise information. The situation management unit also uses the emotion estimation function to develop an algorithm for dynamically changing the method of managing the situation based on changes in the party's emotions. For example, it adjusts the method of managing the situation based on fluctuations in the emotion score. This makes it possible to dynamically change the method of managing the situation based on the emotional reaction.

[0069] The pain-sharing proposal unit can reflect the parties' past agreement history and concession patterns in the proposal content. The pain-sharing proposal unit, for example, analyzes the parties' past agreement history and reflects it in the proposal content. For example, it adjusts the current proposal based on the content of past agreements. The pain-sharing proposal unit also analyzes the parties' concession patterns and reflects it in the proposal content. For example, it adjusts the current proposal taking into account points on which past concessions were made. The pain-sharing proposal unit also personalizes the proposal content based on the parties' past agreement history and concession patterns. For example, it makes the optimal proposal based on past data. In this way, by reflecting the parties' past agreement history and concession patterns, more appropriate proposals can be made.

[0070] The pain-sharing proposal unit can simulate the effects of the proposal and predict the long-term impact. The pain-sharing proposal unit, for example, simulates the effects of the proposal content and predicts the long-term impact. For example, it creates multiple scenarios for when the proposal is implemented and compares the results of each scenario. The pain-sharing proposal unit also evaluates the long-term impact of the proposal content based on the simulation results. For example, it predicts the economic impact and social impact. The pain-sharing proposal unit also develops an algorithm for simulating the effects of the proposal and predicts the long-term impact. For example, it performs a simulation based on past data. This makes it possible to simulate the effects of the proposal and predict the long-term impact.

[0071] The pain-sharing proposal unit uses the emotion estimation function to evaluate the emotional impact of the proposal on the parties involved and can select the optimal proposal. The pain-sharing proposal unit, for example, uses the emotion estimation function to evaluate the emotional impact of the proposal on the parties involved in real time. For example, it calculates an emotion score for the proposal content and selects the optimal proposal. The pain-sharing proposal unit also adjusts the proposal content based on the emotional reactions of the parties involved. For example, it preferentially selects proposals that cause less emotional burden. The pain-sharing proposal unit also uses the emotion estimation function to develop an algorithm for evaluating the emotional impact of the proposal content and selecting the optimal proposal. For example, it adjusts the proposal content based on fluctuations in the emotion score. This makes it possible to evaluate the emotional impact and select the optimal proposal.

[0072] The pain-sharing proposal unit can present multiple different solutions and allow the parties to choose from. For example, the pain-sharing proposal unit may present multiple different solutions and allow the parties to choose from. For example, multiple scenarios may be presented and the parties may choose the most acceptable solution. The pain-sharing proposal unit may also present the proposals as multiple options and allow the parties to choose from. For example, the advantages and disadvantages of each option may be explained. The pain-sharing proposal unit may also develop an algorithm to present different solutions and allow the parties to choose from. For example, the optimal option may be generated based on past data. This may allow different solutions to be presented and the parties to choose from.

[0073] The pain-sharing proposal unit can compare the effectiveness of proposals under different scenarios and conditions. For example, the pain-sharing proposal unit simulates proposals under different scenarios and conditions and compares the effects. For example, it evaluates the economic and social impacts. The pain-sharing proposal unit also develops algorithms for comparing the effectiveness of proposals under different scenarios and conditions. For example, it performs simulations based on past data. The pain-sharing proposal unit also compares the effectiveness of proposals under different scenarios and conditions and selects the optimal proposal. For example, it adjusts proposals based on multiple scenarios. This makes it possible to compare the effects under different scenarios and conditions.

[0074] The pain-sharing proposal unit can use the emotion estimation function to monitor the emotional reactions of the parties to the proposal in real time and adjust the proposal content. The pain-sharing proposal unit, for example, uses the emotion estimation function to monitor the emotional reactions of the parties to the proposal in real time. For example, it calculates an emotion score for the proposal content and adjusts the proposal content. The pain-sharing proposal unit also dynamically changes the proposal content based on the emotional reactions of the parties. For example, it preferentially selects proposals that cause less emotional stress. The pain-sharing proposal unit also uses the emotion estimation function to evaluate the emotional impact of the proposal content and develops an algorithm for adjusting the proposal content in real time. For example, it adjusts the proposal content based on fluctuations in the emotion score. This makes it possible to monitor the emotional reactions to the proposal in real time and adjust the proposal content.

[0075] The arbitration proposal presentation unit can cite past success stories and precedents in the arbitration proposal to increase its persuasiveness. The arbitration proposal presentation unit can, for example, cite past success stories in the arbitration proposal to increase its persuasiveness. For example, the citation can be in the form of, "In past cases, such a solution was successful." The arbitration proposal presentation unit can also cite precedents to demonstrate the basis for the arbitration proposal. For example, the citation can be in the form of, "In past cases, such a solution was adopted." The arbitration proposal presentation unit can also specifically explain the arbitration proposal based on past success stories and precedents. For example, the explanation can be in the form of, "This solution is proposed based on past cases." In this way, the persuasiveness of the arbitration proposal can be increased by citing past success stories and precedents.

[0076] The arbitration proposal presentation unit can provide detailed explanations and grounds for each element of the arbitration proposal. The arbitration proposal presentation unit, for example, provides a detailed explanation for each element of the arbitration proposal. For example, it specifically explains the purpose and effect of each element. The arbitration proposal presentation unit also provides the grounds for the arbitration proposal to enable the parties to be convinced. For example, it provides a detailed explanation of the background and reasons for the proposal contents. The arbitration proposal presentation unit also creates a document to provide detailed explanations and grounds for each element of the arbitration proposal. For example, it provides a detailed explanation of the proposal contents. In this way, by providing detailed explanations and grounds for each element of the arbitration proposal, the parties can be more easily convinced.

[0077] The arbitration proposal presentation unit can use the emotion estimation function to evaluate the emotional impact of the arbitration proposal on the parties and select the optimal proposal. The arbitration proposal presentation unit, for example, uses the emotion estimation function to evaluate the emotional impact of the arbitration proposal on the parties in real time. For example, it calculates an emotion score for the arbitration proposal and selects the optimal proposal. The arbitration proposal presentation unit also adjusts the arbitration proposal based on the emotional reactions of the parties. For example, it prioritizes the selection of a proposal that causes less emotional burden. The arbitration proposal presentation unit also uses the emotion estimation function to develop an algorithm for evaluating the emotional impact of the arbitration proposal and selecting the optimal proposal. For example, it adjusts the arbitration proposal based on fluctuations in the emotion score. This makes it possible to evaluate the emotional impact and select the optimal arbitration proposal.

[0078] The arbitration proposal presentation unit can present multiple different arbitration proposals and allow the parties to choose from them. For example, the arbitration proposal presentation unit may present multiple different arbitration proposals and allow the parties to choose from them. For example, it may present multiple scenarios and allow the parties to select the most acceptable proposal. The arbitration proposal presentation unit may also present multiple arbitration proposals as options and allow the parties to choose from them. For example, it may explain the advantages and disadvantages of each option. The arbitration proposal presentation unit may also develop an algorithm for presenting different arbitration proposals and allow the parties to choose from them. For example, it may generate the optimal option based on past data. This may allow different arbitration proposals to be presented and the parties to choose from them.

[0079] The arbitration proposal presentation unit can compare the effectiveness of arbitration proposals under different scenarios and conditions. For example, the arbitration proposal presentation unit simulates arbitration proposals under different scenarios and conditions and compares their effectiveness. For example, it evaluates the economic and social impacts. The arbitration proposal presentation unit also develops algorithms for comparing the effectiveness of arbitration proposals under different scenarios and conditions. For example, it performs simulations based on past data. The arbitration proposal presentation unit also compares the effectiveness of arbitration proposals under different scenarios and conditions and selects the optimal proposal. For example, it adjusts the arbitration proposal based on multiple scenarios. This makes it possible to compare the effectiveness under different scenarios and conditions.

[0080] The arbitration proposal presenting unit can use the emotion estimation function to monitor the parties' emotional reactions to the arbitration proposal in real time and adjust the proposal. The arbitration proposal presenting unit, for example, uses the emotion estimation function to monitor the parties' emotional reactions to the arbitration proposal in real time. For example, it calculates an emotion score for the arbitration proposal and adjusts the proposal. The arbitration proposal presenting unit also dynamically changes the arbitration proposal based on the parties' emotional reactions. For example, it prioritizes selecting a proposal that causes less emotional stress. The arbitration proposal presenting unit also uses the emotion estimation function to evaluate the emotional impact of the arbitration proposal and develop an algorithm for adjusting the proposal in real time. For example, it adjusts the arbitration proposal based on fluctuations in the emotion score. This makes it possible to monitor the emotional reactions to the arbitration proposal in real time and adjust the proposal.

[0081] The dispute resolution support department can track the progress of dispute resolution in real time and visualize the progress. For example, the dispute resolution support department builds a system that tracks the progress of dispute resolution in real time and visualizes the progress. For example, the progress is displayed in graphs and charts. The dispute resolution support department also tracks the progress of dispute resolution in real time and highlights important milestones. For example, it highlights goals that were achieved on a specific date and time. The dispute resolution support department also develops a tool for visualizing the progress, allowing users to easily check the progress. For example, the progress is displayed in a dashboard format. This makes it possible to track the progress of dispute resolution in real time and visualize the progress.

[0082] The dispute resolution support department can follow up on solutions after they are implemented and evaluate their long-term effectiveness. The dispute resolution support department, for example, builds a system for following up on solutions after they are implemented and evaluating their long-term effectiveness. For example, it periodically checks the progress and evaluates their effectiveness. The dispute resolution support department also follows up on solutions after they are implemented and develops an algorithm for evaluating their long-term effectiveness. For example, it predicts their effectiveness based on past data. The dispute resolution support department also evaluates the effectiveness of solutions based on the results of the follow-up and makes adjustments as necessary. For example, if the effectiveness is insufficient, it proposes additional measures. This makes it possible to follow up on solutions after they are implemented and evaluate their long-term effectiveness.

[0083] The dispute resolution support unit can use the emotion estimation function to evaluate the emotional impact of a solution on the parties and provide optimal support. The dispute resolution support unit, for example, uses the emotion estimation function to evaluate the emotional impact of a solution on the parties in real time. For example, it calculates an emotion score for the solution and provides optimal support. The dispute resolution support unit also adjusts the solution based on the emotional reactions of the parties. For example, it prioritizes selecting a solution that causes less emotional burden. The dispute resolution support unit also uses the emotion estimation function to develop an algorithm for evaluating the emotional impact of a solution and providing optimal support. For example, it adjusts the solution based on fluctuations in the emotion score. This allows the dispute resolution support unit to evaluate the emotional impact of a solution on the parties and provide optimal support.

[0084] The dispute resolution support unit can present multiple different solutions and allow the parties to choose from. For example, the dispute resolution support unit may present multiple different solutions and allow the parties to choose from. For example, multiple scenarios may be presented and the parties may choose the most acceptable solution. The dispute resolution support unit may also present multiple solution options and allow the parties to choose from. For example, the unit may explain the advantages and disadvantages of each option. The dispute resolution support unit may also develop an algorithm to present different solutions and allow the parties to choose from. For example, the unit may generate the optimal option based on past data. This may allow different solutions to be presented and the parties to choose from.

[0085] The dispute resolution support unit can simulate the effects of a solution and predict its long-term impact. The dispute resolution support unit, for example, simulates the effects of a solution and predicts its long-term impact. For example, it creates multiple scenarios for when a solution is implemented and compares the results of each scenario. The dispute resolution support unit also evaluates the long-term impact of the solution based on the simulation results. For example, it predicts the economic and social impacts. The dispute resolution support unit also develops an algorithm for simulating the effects of a solution and predicts its long-term impact. For example, it performs a simulation based on past data. This makes it possible to simulate the effects of a solution and predict its long-term impact.

[0086] The dispute resolution support unit can use the emotion estimation function to monitor the parties' emotional reactions to the solution in real time and adjust the support content. The dispute resolution support unit, for example, uses the emotion estimation function to monitor the parties' emotional reactions to the solution in real time. For example, it calculates an emotion score for the solution and adjusts the support content. The dispute resolution support unit also dynamically changes the solution based on the parties' emotional reactions. For example, it prioritizes selecting a solution that causes less emotional stress. The dispute resolution support unit also uses the emotion estimation function to evaluate the emotional impact of the solution and develops an algorithm for adjusting the support content in real time. For example, it adjusts the solution based on fluctuations in the emotion score. This makes it possible to monitor the parties' emotional reactions to the solution in real time and adjust the support content.

[0087] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0088] The dispute resolution system can further include an "emotion history analysis unit." The emotion history analysis unit can analyze changes in the emotions of the parties in past dispute resolutions and use the information to help resolve current disputes. For example, it can analyze the emotional changes shown by the parties in past disputes and predict how they will change in similar situations. The emotion history analysis unit can also identify points where the parties are likely to become emotional based on past emotional data and take measures in advance. Furthermore, the emotion history analysis unit can use past emotional data to suggest approaches that are less likely to cause the parties to become emotional. This makes it possible to utilize past emotional history for more effective dispute resolution.

[0089] The virtual arbitrator character setting unit can further include a "cultural adaptation unit." The cultural adaptation unit can adjust the virtual arbitrator character's response taking into account the cultural backgrounds of the parties. For example, it can reflect the values ​​and communication styles that are important in a particular culture. The cultural adaptation unit can also provide advice to avoid cultural misunderstandings in conflicts between different cultures. Furthermore, the cultural adaptation unit can train the virtual arbitrator character to have multicultural skills. This enables conflict resolution that takes cultural backgrounds into consideration.

[0090] The virtual arbitrator character setting unit may further include a "health status monitoring unit." The health status monitoring unit can monitor the health status of the parties in real time and identify factors that affect the progress of the dispute resolution. For example, it can measure stress levels and heart rates and suggest taking a break if the parties' health status is deteriorating. The health status monitoring unit can also adjust the response of the virtual arbitrator character according to the parties' health status. Furthermore, the health status monitoring unit can provide advice to optimize the progress of the dispute resolution based on the health status data. This enables dispute resolution that takes health status into consideration.

[0091] The virtual arbitrator character setting unit can further include an "emotion prediction unit." The emotion prediction unit can predict future changes in emotions based on the parties' past actions and statements. For example, it can analyze past data and predict what emotions the parties will show in a specific situation. The emotion prediction unit can also adjust the virtual arbitrator character's response in advance based on the predicted changes in emotions. Furthermore, the emotion prediction unit can develop algorithms for predicting changes in emotions and improve accuracy. This makes it possible to predict future changes in emotions and respond appropriately.

[0092] The virtual arbitrator character setting unit can further include an "emotion sharing unit." The emotion sharing unit can share emotions between the parties and promote mutual understanding. For example, it can visually display the emotions felt by the parties and help them understand each other's emotions. By sharing emotions, the emotion sharing unit can also create empathy and facilitate conflict resolution. Furthermore, the emotion sharing unit can provide advice for building trust between the parties through the sharing of emotions. This makes it possible to deepen mutual understanding and promote conflict resolution through the sharing of emotions.

[0093] The virtual arbitrator character setting unit may further include an "emotion mitigation unit." The emotion mitigation unit may provide techniques to ease the emotions of the parties. For example, it may provide relaxation music or guided meditation to calm the emotions. The emotion mitigation unit may also suggest breathing techniques or stretches to calm down when emotions are high. Furthermore, the emotion mitigation unit may also provide advice on aromatherapy or massage to ease emotions. This allows emotions to be eased and conflict resolution to proceed in a calm state.

[0094] The virtual mediator character setting department may further include an "emotional education department." The emotional education department may educate the parties on how to control their emotions. For example, it may provide training on how to recognize and express emotions. The emotional education department may also hold workshops and seminars to teach emotion control techniques. Furthermore, the emotional education department may provide teaching materials and resources on emotion control so that the parties can learn independently. This allows them to learn how to control their emotions and use them to resolve conflicts.

[0095] The virtual arbitrator character setting unit may further include an "emotion feedback unit." The emotion feedback unit can provide real-time feedback on the emotional state of the parties and encourage them to respond appropriately. For example, if they are emotionally charged, it can encourage them to stay calm. The emotion feedback unit can also visually display changes in emotions, allowing the parties to objectively understand their own emotions. Furthermore, the emotion feedback unit can provide advice to help the parties control their emotions through emotional feedback. This allows for appropriate responses through emotional feedback.

[0096] The virtual arbitrator character setting unit can further include an "emotion prediction unit." The emotion prediction unit can predict future changes in emotions based on the parties' past actions and statements. For example, it can analyze past data and predict what emotions the parties will show in a specific situation. The emotion prediction unit can also adjust the virtual arbitrator character's response in advance based on the predicted changes in emotions. Furthermore, the emotion prediction unit can develop algorithms for predicting changes in emotions and improve accuracy. This makes it possible to predict future changes in emotions and respond appropriately.

[0097] The virtual arbitrator character setting unit can further include an "emotion sharing unit." The emotion sharing unit can share emotions between the parties and promote mutual understanding. For example, it can visually display the emotions felt by the parties and help them understand each other's emotions. By sharing emotions, the emotion sharing unit can also create empathy and facilitate conflict resolution. Furthermore, the emotion sharing unit can provide advice for building trust between the parties through the sharing of emotions. This makes it possible to deepen mutual understanding and promote conflict resolution through the sharing of emotions.

[0098] The processing flow of the second embodiment will be briefly explained below.

[0099] Step 1: The virtual arbitrator character setting unit sets up a virtual arbitrator character. For example, the generation AI sets up a virtual arbitrator character to help resolve the dispute between the parties. This character acts as a neutral presence to help the parties proceed with the discussion without getting emotional. The generation AI responds, for example, by saying, "Hello, I am the arbitrator to resolve your dispute. First, let's clarify the situation." Step 2: In the situation analysis section, the virtual arbitrator character set by the virtual arbitrator character setting section analyzes the situation based on the information provided by the parties. For example, the parties provide their respective arguments and evidence, and the AI ​​generation analyzes and organizes them. This clarifies the cause and background of the dispute. Step 3: The Pain-Sharing Proposal Team makes a pain-sharing proposal based on the situation summarized by the Situation Analysis Team. For example, they might propose something like, "Taking your arguments into consideration, the following solution is possible. By making small concessions on both sides, we should be able to reach an agreement." Step 4: The arbitration proposal presentation section presents a specific arbitration proposal based on the proposal made by the pain-sharing proposal section. For example, the proposal may be presented in the form of, "We propose to agree on the following conditions. This will be a solution that both parties can agree on." Step 5: The Dispute Resolution Support Department supports discussions between the parties based on the arbitration proposal presented by the Arbitration Proposal Department. For example, the department may provide support by saying, "Let's continue discussions on this arbitration proposal. Let's aim to reach a final agreement while respecting each other's opinions."

[0100] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0101] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0102] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0103] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0104] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0105] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0106] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0107] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0108] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0109] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0110] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0111] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0112] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0113] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0114] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0115] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0116] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0117] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0118] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0119] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0120] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0121] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0122] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0123] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0124] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0125] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0126] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0127] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0128] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0129] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0130] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0131] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0132] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0133] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0134] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0135] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0136] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0137] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0138] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0139] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0140] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0141] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0142] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0143] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0144] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0145] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0146] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0147] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0148] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0149] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0150] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0151] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0152] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0153] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0154] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0155] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0156] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0157] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0158] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0159] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0160] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0161] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0162] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0163] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0164] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0165] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0166] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0167] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a virtual arbitrator character setting unit that sets a virtual arbitrator character; a situation management unit that manages the virtual arbitrator character set by the virtual arbitrator character setting unit to manage the situation based on information provided by the parties; a sharing proposal unit that proposes sharing based on the situation organized by the situation organization unit; an arbitration proposal presentation unit that presents a specific arbitration proposal based on the content proposed by the pain-sharing proposal unit; a dispute resolution support unit that supports discussions between the parties based on the arbitration proposal presented by the arbitration proposal presentation unit. A system characterized by:

2. The virtual arbitrator character setting unit Adopt a personalized approach based on the person's past behavior and statements 2. The system of claim 1.

3. The virtual arbitrator character setting unit Customize the appearance and voice of the person to make them most likely to trust you.

2. The system of claim 1.

4. The virtual arbitrator character setting unit Automatically adjust tone and language based on the emotional state of the person in question 2. The system of claim 1.

5. The virtual arbitrator character setting unit Adapting to cultures and languages, and applying it to international dispute resolution 2. The system of claim 1.

6. The virtual arbitrator character setting unit Increase persuasiveness by citing expert opinions and past court cases 2. The system of claim 1.

Images