JP2025049007A - system - Google Patents

Abstract

To provide a system according to the embodiment which analyzes a content and tone of voice of a party concerned, compiles issues, and proposes an appropriate solution in arbitration of a quarrel or dispute.SOLUTION: A system according to the embodiment includes a reception part, an analysis part, a compilation part, and a proposition part. The reception part inputs a story content. The analysis part analyzes the story content and tone of voice inputted by the reception part. The compilation part compiles issues of the story analyzed by the analysis part. The proposition part proposes appropriate solutions on the basis of the issues compiled by the compilation part.SELECTED DRAWING: Figure 1

Description

The technology disclosed herein relates to a system.

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 a description of the chatbot character and an associated instruction sentence, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

JP 2022-180282 A

With conventional technology, when arbitrating arguments or disputes, it was difficult to properly analyze the content and tone of voice of the parties involved, summarize the issues, and propose a solution.

The system according to the embodiment aims to analyze the content and tone of voice of the parties involved in arbitrating fights and disputes, summarize the issues, and propose appropriate solutions.

The system according to the embodiment includes a reception unit, an analysis unit, a summary unit, and a proposal unit. The reception unit inputs the content of the conversation. The analysis unit analyzes the content of the conversation and tone of voice input by the reception unit. The summary unit summarizes the issues in the conversation analyzed by the analysis unit. The proposal unit proposes an appropriate solution based on the issues summarized by the summary unit.

When arbitrating a fight or dispute, the system according to the embodiment can analyze the content and tone of voice of the parties involved, summarize the issues, and propose an appropriate solution.

1 is a conceptual diagram showing an example of a configuration of a data processing system according to a first embodiment. 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. FIG. FIG. 11 is a conceptual diagram showing an example of a configuration of a data processing system according to a second embodiment. FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. FIG. 13 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. FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. 1 shows an emotion map onto which multiple emotions are mapped. 1 shows an emotion map onto which multiple emotions are mapped.

Below, an example of an embodiment of a system related to the technology disclosed herein is described with reference to the attached drawings.

First, let us explain the terminology used in the following explanation.

In the following embodiments, the signed processor (hereinafter simply referred to as the "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. 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).

In the following embodiments, a signed random access memory (RAM) is a memory in which information is temporarily stored and is used by the processor as a working memory.

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

In the following embodiments, a communication I/F (Interface) with a code is an interface including a communication processor and an antenna. 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).

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. In addition, in this specification, the same concept as "A and/or B" is also applied when three or more things are expressed by connecting them with "and/or."

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

As shown in FIG. 1, the 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.

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, the RAM 30, and the 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).

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.

The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with an indicator (e.g., a pen or a finger) to receive user input by the touch of the indicator. 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.

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

The communication I/F 44 is connected to the network 54. The communication I/Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

As shown in FIG. 2, in the data processing device 12, specific processing 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 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.

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 the 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 such examples. Furthermore, the estimation and prediction of emotion also includes, for example, analysis of emotions.

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 in conjunction 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 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 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 use these models to perform processing similar to that of the specific processing unit 290.

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. In addition, 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.

(Example 1)
The quarrel arbitration system according to the embodiment of the present invention is a system that arbitrates quarrels using a generation AI. In this system, the parties input the contents of the talk, and the generation AI analyzes the contents and tone of voice, summarizes the points of dispute in the talk, and proposes an appropriate solution. For example, the parties input the contents of the talk into the app. At this time, the parties can freely input their own opinions and feelings. For example, the parties input the contents of the talk, such as "I am angry that he did not keep his promise." This information is input to the generation AI. Next, the generation AI analyzes the input contents of the talk and the tone of voice. The generation AI analyzes the contents of the talk and identifies which part is the point of dispute. In addition, by analyzing the tone of voice, it is possible to grasp the strength of the emotions and the degree of tension of the parties. For example, the analysis result shows that the part "did not keep the promise" is the point of dispute, and the tone of voice indicates strong anger. Furthermore, the generation AI considers an appropriate solution. The generation AI considers the points of dispute in the talk and the emotions of the parties, and proposes the most appropriate solution. For example, it is possible to propose a solution such as "ask him to apologize." This proposal is displayed to the parties. This mechanism allows the parties to proceed with the discussion calmly. The generation AI analyzes the content of the conversation from a third-party perspective and proposes an appropriate solution, allowing the parties to proceed with the discussion without becoming emotional. In addition, the generation AI can analyze the tone of voice to grasp changes in the parties' emotions and propose a solution at the appropriate time. For example, by proposing a solution when the parties have calmed down, the discussion can proceed smoothly. In this way, the use of the generation AI realizes a system that can efficiently mediate arguments. As a result, the argument mediation system can analyze the content and tone of voice of the parties, summarize the points of contention, and propose an appropriate solution.

The quarrel arbitration system according to the embodiment includes a reception unit, an analysis unit, a summary unit, and a proposal unit. The reception unit receives input of the contents of the talk by the parties. The contents of the talk include, for example, the opinions and feelings of the parties, but are not limited to such examples. The reception unit can receive, for example, text input and voice input. The analysis unit uses a generation AI to analyze the contents of the talk and the tone of voice input by the reception unit. The analysis unit, for example, analyzes the contents of the talk and identifies which part is the point of dispute. The analysis unit can also grasp the strength of the emotions and the degree of tension of the parties by analyzing the tone of voice. For example, the generation AI analyzes the contents of the talk using a text generation AI (for example, LLM) and identifies the points of dispute. The generation AI can also analyze the tone of voice using voice analysis technology and grasp the strength of emotions and the degree of tension. The summary unit uses the generation AI to summarize the points of dispute in the talk analyzed by the analysis unit. The summary unit, for example, extracts important parts of the contents of the talk and organizes the points of dispute. The suggestion unit uses the generation AI to propose an appropriate solution based on the issues summarized by the summary unit. The suggestion unit, for example, considers the issues in the story and the emotions of the parties and proposes the most appropriate solution. For example, the generation AI can propose a solution by referring to past success stories and expert opinions. As a result, the fight arbitration system according to the embodiment can analyze the content and tone of voice of the parties, summarize the issues, and propose an appropriate solution. Some or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit displays a solution to the parties based on the solution proposed by the generation AI. Furthermore, the suggestion unit has a function of evaluating the reliability of the solution. For example, the suggestion unit can evaluate the reliability of the solution proposed by the generation AI and preferentially propose a highly reliable solution. In addition, the suggestion unit has a function of accepting feedback from the user. For example, the suggestion unit can collect feedback from the parties and use it to improve the system. As a result, the fight arbitration system can analyze the content and tone of voice of the parties, summarize the issues, and propose an appropriate solution.

The reception unit receives input of the contents of the talk by the parties. The contents of the talk include, for example, the opinions and feelings of the parties, but are not limited to such examples. The reception unit can receive, for example, text input and voice input. Specifically, in the case of text input, the parties can input their opinions and feelings using a keyboard or touch screen. In the case of voice input, the parties speak through a microphone, and the system converts the voice into text. Voice input is particularly effective for maintaining a natural flow of conversation and can capture the nuances of emotions more accurately. Furthermore, the reception unit has a function of temporarily storing the input data and transmitting it to the subsequent analysis unit and summary unit. This allows the reception unit to efficiently collect the contents of the talk of the parties and smoothly proceed with the processing of the entire system. In addition, the reception unit also has a security function for protecting the privacy of the input data, and can safely manage the information of the parties by encrypting data and controlling access. This allows the reception unit to provide an environment in which the parties can safely input the contents of the talk, thereby improving the reliability of the entire system.

The analysis unit uses the generation AI to analyze the content of the conversation and the tone of voice input by the reception unit. For example, the analysis unit analyzes the content of the conversation and identifies which part is the point of contention. In addition, the analysis unit can grasp the strength of the emotions and the degree of tension of the parties by analyzing the tone of voice. Specifically, the generation AI analyzes the content of the conversation using a text generation AI (for example, LLM) and identifies the points of contention. The text generation AI has learned a large amount of text data, and can extract important keywords and phrases from the content of the conversation input and clarify the points of contention. In addition, the generation AI can analyze the tone of voice using voice analysis technology and grasp the strength of emotions and the degree of tension. The voice analysis technology analyzes characteristics such as the pitch, tempo, and volume of the voice to evaluate the emotional state of the parties. For example, if the voice becomes higher or faster, it is determined that the tension or anger is strong. As a result, the analysis unit can comprehensively analyze both the content of the conversation and the tone of voice and accurately grasp the emotions and points of contention of the parties. Furthermore, the analysis unit can perform more accurate analysis by referring to past data and similar cases. This allows the analysis department to accurately understand the content and emotions of the parties involved and support the arbitration process throughout the system.

The summary unit uses the generation AI to summarize the issues in the story analyzed by the analysis unit. For example, the summary unit extracts important parts of the content of the story and organizes the issues. Specifically, the generation AI extracts important keywords and phrases from the content of the story and organizes them to clarify the issues. The generation AI has learned a large amount of text data and can efficiently summarize the content of the story. For example, it organizes the opinions and feelings of the parties and identifies which parts are most important. The summary unit also has a function to visually display the issues and provide information in a format that is easy for the parties to understand. For example, it visualizes the issues using graphs and charts so that the parties can understand them at a glance. Furthermore, the summary unit can organize the issues by referring to past data and similar cases. This allows the summary unit to efficiently organize the content of the story and provide information in a format that is easy for the parties to understand. This allows the summary unit to efficiently organize the content of the story of the parties and support the arbitration process of the entire system.

The suggestion unit uses the generation AI to propose an appropriate solution based on the issues summarized by the summary unit. The suggestion unit, for example, considers the issues in the story and the feelings of the parties and proposes the most appropriate solution. Specifically, the generation AI can propose a solution by referring to past success cases and expert opinions. The generation AI learns a large amount of data and can identify the most effective solution based on past similar cases and expert opinions. For example, by referring to past success cases, it proposes a solution that was effective in a similar situation. In addition, the suggestion unit has a function to evaluate the reliability of the solution, and can evaluate the reliability of the solution proposed by the generation AI and preferentially propose a highly reliable solution. Furthermore, the suggestion unit has a function to accept feedback from users, and can collect feedback from the parties and use it to improve the system. For example, it evaluates whether the proposed solution was actually effective and reflects it in the next proposal. As a result, the suggestion unit can always provide a highly accurate solution based on the latest information and improve the satisfaction of the parties. As a result, the suggestion unit can consider the content and feelings of the parties and propose the most appropriate solution.

The dispute arbitration system includes a reference section that refers to specific past cases or success cases. The reference section refers to past cases and success cases using the generation AI. For example, the reference section can search a database for similar past cases and refer to them. The reference section can also improve the accuracy of the solution based on successful projects and performance data. For example, the reference section analyzes past success cases and proposes the most effective solution. As a result, the accuracy of the solution is improved by referring to past cases and success cases. Some or all of the above-mentioned processing in the reference section may be performed using, for example, AI, or may be performed without using AI. For example, the reference section can propose a solution based on past cases and success cases searched by the generation AI. Furthermore, the reference section has a function of updating past cases and success cases in real time. For example, the reference section can automatically collect the latest cases and success cases and update the database. As a result, the reference section can always propose a solution based on the latest information.

The dispute arbitration system includes an evaluation unit that evaluates the reliability of the solution. The evaluation unit uses the generation AI to evaluate the reliability of the solution. For example, the evaluation unit can evaluate the reliability of the solution proposed by the generation AI and preferentially propose a highly reliable solution. The evaluation unit evaluates the reliability of the solution, for example, based on performance data or a third party evaluation. For example, the evaluation unit can evaluate the reliability of the solution by referring to past success stories and expert opinions. As a result, the reliability of the proposal is improved by evaluating the reliability of the solution. A part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit displays the solution to the parties based on the reliability of the solution evaluated by the generation AI. Furthermore, the evaluation unit has a function of evaluating the reliability of the solution in real time. For example, the evaluation unit can evaluate the reliability of the solution based on the latest data and propose a highly reliable solution. As a result, the evaluation unit can always evaluate the reliability of the solution based on the latest information.

The fight arbitration system includes a feedback unit that accepts feedback from users. The feedback unit accepts feedback from users using the generation AI. For example, the feedback unit can collect feedback from the parties and use it to improve the system. The feedback unit collects feedback, for example, through questionnaires and user reviews. For example, the feedback unit can conduct a questionnaire for the parties and collect opinions on the usability of the system and the effectiveness of the solution. This allows the system to be improved by accepting feedback from users. Some or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI, or may be performed without using AI. For example, the feedback unit can identify improvements to the system based on the feedback collected by the generation AI. Furthermore, the feedback unit has a function of adjusting the feedback collection method in real time. For example, the feedback unit can select the optimal collection method depending on the situation of the parties. This allows the feedback unit to always collect feedback in the optimal way and use it to improve the system.

The analysis unit can analyze the content of the talk and specifically identify which part is the point of contention. The analysis unit uses the generation AI to analyze the content of the talk and identify which part is the point of contention. For example, the analysis unit uses a text generation AI (e.g., LLM) to analyze the content of the talk and identify the point of contention. The generation AI can analyze the content of the talk and identify the points of contention and important points of discussion. For example, the generation AI can analyze the content of the talk and identify the part that "the promise was not kept" as the point of contention. As a result, by analyzing the content of the talk and identifying the point of contention, an appropriate solution can be proposed. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can propose a solution to the parties based on the point of contention identified by the generation AI. Furthermore, the analysis unit has a function of adjusting the method of identifying the point of contention in real time. For example, the analysis unit can select the optimal identification method according to the situation of the parties. As a result, the analysis unit can always identify the point of contention in the optimal way and propose an appropriate solution.

The analysis unit can analyze the tone of voice and specifically grasp the intensity of the emotions and the degree of tension of the parties. The analysis unit uses the generation AI to analyze the tone of voice and grasp the intensity of the emotions and the degree of tension of the parties. For example, the analysis unit can analyze the tone of voice using voice analysis technology and grasp the intensity of the emotions and the degree of tension. The generation AI can analyze the tone, pitch, speed, etc. of the tone of voice and identify the intensity of the emotions and the degree of tension of the parties. For example, the generation AI can analyze the tone of voice and identify the intensity of the emotions when the parties feel strong anger. In addition, the generation AI can analyze the tone of voice and grasp the degree of tension when the parties are nervous. In this way, the intensity of the emotions and the degree of tension of the parties can be grasped by analyzing the tone of voice. Part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI or may be performed without using AI. For example, the analysis unit can identify the intensity of the emotions and the degree of tension of the parties based on the data of the tone of voice analyzed by the generation AI. Furthermore, the analysis unit has a function of adjusting the analysis method of the tone of voice in real time. For example, the analysis unit can select the most appropriate analysis method depending on the situation of the person involved. This allows the analysis unit to always analyze tone of voice in the most appropriate way and grasp the intensity of the person's emotions and level of tension.

The reception unit can analyze the user's past input history and provide an optimal input interface. The reception unit uses the generation AI to analyze the user's past input history and provide an optimal input interface. For example, the reception unit can automatically display phrases and keywords that have been frequently input in the past as candidates. The reception unit can also preferentially suggest input methods (such as voice and text) that have been used in the past. Furthermore, the reception unit can predict and suggest phrases and keywords that will be used in a specific time period from the past input history. As a result, the reception unit can provide an optimal input interface to the user by analyzing the past input history. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can provide an optimal input interface based on the past input history analyzed by the generation AI. Furthermore, the reception unit has a function of adjusting the method of providing the input interface in real time. For example, the reception unit can select the optimal method of providing depending on the user's situation. As a result, the reception unit can always provide an input interface in an optimal manner, improving user convenience.

The reception unit can filter the input contents based on the user's current situation or interests when inputting the contents of the talk. The reception unit uses the generation AI to filter the input contents based on the user's current situation and interests when inputting the contents of the talk. For example, the reception unit can automatically suggest related keywords when the user inputs the current situation. The reception unit can also filter the input contents based on the user's interests and preferentially display highly relevant information. Furthermore, the reception unit can simplify the input contents according to the user's current situation and allow only necessary information to be input. This makes it possible to provide highly relevant information by filtering the input contents based on the user's current situation and interests. Part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can provide optimal information to the user based on the input contents filtered by the generation AI. Furthermore, the reception unit has a function of adjusting the filtering method of the input contents in real time. For example, the reception unit can select the optimal filtering method according to the user's situation. This allows the reception unit to always filter input content in the most optimal way and provide highly relevant information.

The reception unit can preferentially input highly relevant content by specifically considering the geographical location information of the user when inputting the content of the talk. The reception unit uses the generation AI to preferentially input highly relevant content by considering the geographical location information of the user when inputting the content of the talk. For example, when the user is in a specific location, the reception unit can preferentially input information related to the location. Furthermore, the reception unit can automatically suggest related issues based on the geographical location information of the user. Furthermore, when the user is moving, the reception unit can preferentially input information related to the current location. As a result, highly relevant information can be preferentially input by considering the geographical location information. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can provide optimal information to the user based on the geographical location information considered by the generation AI. Furthermore, the reception unit has a function of adjusting the method of considering the geographical location information in real time. For example, the reception unit can select the optimal method of consideration according to the user's situation. As a result, the reception unit can always consider the geographical location information in the optimal manner and provide highly relevant information.

The reception unit can analyze the user's social media activity and input related content when inputting the content of the talk. The reception unit can use the generation AI to analyze the user's social media activity and input related content when inputting the content of the talk. For example, the reception unit can extract related keywords from the user's social media posts and reflect them in the input content. The reception unit can also analyze the user's social media activity and automatically suggest related issues. Furthermore, the reception unit can analyze the user's emotional expression on social media and adjust the input content. This makes it possible to provide highly relevant information by analyzing social media activity. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can provide optimal information to the user based on the social media activity analyzed by the generation AI. Furthermore, the reception unit has a function of adjusting the analysis method of social media activity in real time. For example, the reception unit can select the optimal analysis method according to the user's situation. This makes it possible for the reception unit to always analyze social media activity in the optimal way and input related content.

The analysis unit can improve the accuracy of the analysis by referring to similar cases in the past when analyzing the content of the talk. The analysis unit can improve the accuracy of the analysis by referring to similar cases in the past when analyzing the content of the talk using the generation AI. For example, the analysis unit can search for similar cases in the past from a database and reflect them in the analysis. The analysis unit can also improve the accuracy of the analysis by referring to successful examples of similar cases. Furthermore, the analysis unit can reduce the risk of the analysis by referring to failed examples of similar cases. As a result, the accuracy of the analysis is improved by referring to similar cases in the past. A part or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit can provide an optimal analysis method based on similar cases in the past searched by the generation AI. Furthermore, the analysis unit has a function of adjusting the method of referring to similar cases in real time. For example, the analysis unit can select the optimal reference method according to the user's situation. As a result, the analysis unit can always refer to similar cases in the past in the optimal way and reflect them in the analysis of the content of the talk.

The analysis unit can perform the analysis by taking into account the attribute information of the user when analyzing the content of the conversation. The analysis unit performs the analysis by taking into account the attribute information of the user using the generation AI when analyzing the content of the conversation. For example, the analysis unit can adjust the viewpoint of the analysis by taking into account the age and gender of the user. In addition, the analysis unit can adjust the content of the analysis by taking into account the occupation and social status of the user. Furthermore, the analysis unit can adjust the method of analysis by taking into account the cultural background of the user. As a result, a more appropriate analysis is possible by taking into account the attribute information of the user. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can provide an optimal analysis method based on the attribute information of the user taken into account by the generation AI. Furthermore, the analysis unit has a function of adjusting the method of taking into account the attribute information in real time. For example, the analysis unit can select the optimal method of taking into account depending on the situation of the user. As a result, the analysis unit can always take into account the attribute information of the user in the optimal method and analyze the content of the conversation.

The analysis unit can perform the analysis while taking into account the geographical distribution when analyzing the content of the talk. The analysis unit performs the analysis while taking into account the geographical distribution using the generation AI when analyzing the content of the talk. For example, the analysis unit can analyze issues specific to a region based on the location of the user. Furthermore, the analysis unit can perform an analysis that reflects the characteristics of each region by taking into account the geographical distribution. Furthermore, the analysis unit can propose a solution for each region based on the geographical distribution. This allows the analysis of issues specific to a region by taking into account the geographical distribution. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can provide an optimal analysis method based on the geographical distribution taken into account by the generation AI. Furthermore, the analysis unit has a function of adjusting the method of taking into account the geographical distribution in real time. For example, the analysis unit can select the optimal method of taking into account depending on the user's situation. This allows the analysis unit to always take into account the geographical distribution in the optimal way and analyze the content of the talk.

The analysis unit can improve the accuracy of the analysis by referring to related literature when analyzing the content of the talk. The analysis unit can improve the accuracy of the analysis by referring to related literature when analyzing the content of the talk using the generation AI. For example, the analysis unit can search for related literature from a database and reflect it in the analysis. The analysis unit can also improve the accuracy of the analysis by referring to successful examples of related literature. Furthermore, the analysis unit can reduce the risk of the analysis by referring to unsuccessful examples of related literature. As a result, the accuracy of the analysis is improved by referring to related literature. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can provide an optimal analysis method based on the related literature searched by the generation AI. Furthermore, the analysis unit has a function of adjusting the method of referring to related literature in real time. For example, the analysis unit can select the optimal reference method according to the user's situation. As a result, the analysis unit can always refer to related literature in the optimal way and reflect it in the analysis of the content of the talk.

The summarizing unit can select the optimal method by referring to past summarizing methods when summarizing the issues. The summarizing unit uses the generation AI to select the optimal method by referring to past summarizing methods when summarizing the issues. For example, the summarizing unit can select the optimal method of summarizing the issues by referring to past successful cases. The summarizing unit can also select a summarizing method that reduces risk by referring to past failure cases. Furthermore, the summarizing unit can search a database for similar past cases and select the optimal summarizing method. As a result, the optimal summarizing method can be selected by referring to past summarizing methods. Part or all of the above-mentioned processing in the summarizing unit may be performed, for example, using AI, or may be performed without using AI. For example, the summarizing unit can provide the optimal summarizing method based on past summarizing methods searched by the generation AI. Furthermore, the summarizing unit has a function of adjusting the summarizing method reference method in real time. For example, the summarizing unit can select the optimal reference method according to the user's situation. As a result, the summarizing unit can always refer to past summarizing methods in the optimal method and reflect them in the summarization of the issues.

The summarizing unit can summarize the issues taking into account the attribute information of the user when summarizing the issues. The summarizing unit uses the generation AI to summarize the issues taking into account the attribute information of the user. For example, the summarizing unit can adjust the way the issues are summarized taking into account the age and sex of the user. The summarizing unit can also adjust the way the issues are summarized taking into account the occupation and social status of the user. Furthermore, the summarizing unit can adjust the way the issues are summarized taking into account the cultural background of the user. This allows for more appropriate summarization by taking into account the attribute information of the user. Some or all of the above-mentioned processing in the summarizing unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarizing unit can provide an optimal way of summarizing based on the attribute information of the user taken into account by the generation AI. Furthermore, the summarizing unit has a function of adjusting the way the attribute information is taken into account in real time. For example, the summarizing unit can select the optimal way of considering depending on the user's situation. This allows the summarizing unit to always take into account the attribute information of the user in the optimal way and summarize the issues.

The summarizing unit can summarize issues taking into account the geographical distribution when summarizing issues. The summarizing unit uses the generation AI to summarize issues taking into account the geographical distribution when summarizing issues. For example, the summarizing unit can summarize issues specific to a region based on the user's location. Furthermore, the summarizing unit can summarize issues reflecting the characteristics of each region by taking into account the geographical distribution. Furthermore, the summarizing unit can propose solutions for each region based on the geographical distribution. As a result, issues specific to each region can be summarized by taking into account the geographical distribution. A part or all of the above-mentioned processing in the summarizing unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarizing unit can provide an optimal summarizing method based on the geographical distribution taken into account by the generation AI. Furthermore, the summarizing unit has a function of adjusting the method of considering the geographical distribution in real time. For example, the summarizing unit can select the optimal method of consideration according to the user's situation. As a result, the summarizing unit can always consider the geographical distribution in the optimal way and summarize issues.

The summarizing unit can improve the accuracy of the summary by referring to related literature when summarizing the issues. The summarizing unit uses the generation AI to improve the accuracy of the summary by referring to related literature when summarizing the issues. For example, the summarizing unit can search for related literature from a database and reflect it in the summary. The summarizing unit can also improve the accuracy of the summary by referring to successful examples of related literature. Furthermore, the summarizing unit can reduce the risk of summarization by referring to unsuccessful examples of related literature. As a result, the accuracy of the summary is improved by referring to related literature. A part or all of the above-mentioned processing in the summarizing unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarizing unit can provide an optimal summarizing method based on the related literature searched by the generation AI. Furthermore, the summarizing unit has a function of adjusting the method of referring to related literature in real time. For example, the summarizing unit can select the optimal reference method according to the user's situation. As a result, the summarizing unit can always refer to related literature in the optimal way and reflect it in the summary of the issues.

When proposing a solution, the suggestion unit can make an optimal proposal by referring to past success cases. When proposing a solution, the suggestion unit uses the generation AI to make an optimal proposal by referring to past success cases. For example, the suggestion unit can search for past success cases from a database and propose an optimal solution. In addition, the suggestion unit can improve the accuracy of the solution by referring to success cases of similar cases. Furthermore, the suggestion unit can analyze past success cases and propose the most effective solution. As a result, the optimal solution can be proposed by referring to past success cases. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can provide an optimal solution based on past success cases searched by the generation AI. Furthermore, the suggestion unit has a function of adjusting the reference method for success cases in real time. For example, the suggestion unit can select the optimal reference method according to the user's situation. As a result, the suggestion unit can always refer to past success cases in the optimal way and reflect them in the proposed solution.

When proposing a solution, the suggestion unit can make a suggestion taking into account the attribute information of the user. When proposing a solution, the suggestion unit makes a suggestion taking into account the attribute information of the user using the generation AI. For example, the suggestion unit can propose an optimal solution taking into account the age and sex of the user. In addition, the suggestion unit can adjust the content of the solution taking into account the occupation and social status of the user. Furthermore, the suggestion unit can adjust the method of the solution taking into account the cultural background of the user. As a result, a more appropriate solution can be proposed by taking into account the attribute information of the user. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can provide an optimal solution based on the attribute information of the user taken into account by the generation AI. Furthermore, the suggestion unit has a function of adjusting the method of considering the attribute information in real time. For example, the suggestion unit can select the optimal consideration method according to the user's situation. As a result, the suggestion unit can always consider the attribute information of the user in the optimal method and propose a solution.

When proposing a solution, the suggestion unit can make a proposal taking into account the geographical distribution. When proposing a solution, the suggestion unit makes a proposal taking into account the geographical distribution using the generation AI. For example, the suggestion unit can propose a solution specific to a region based on the user's location. Also, the suggestion unit can propose a solution that reflects the characteristics of each region by taking into account the geographical distribution. Furthermore, the suggestion unit can propose a solution for each region based on the geographical distribution. As a result, a solution specific to a region can be proposed by taking into account the geographical distribution. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can provide an optimal solution based on the geographical distribution taken into account by the generation AI. Furthermore, the suggestion unit has a function of adjusting the method of considering the geographical distribution in real time. For example, the suggestion unit can select the optimal method of consideration according to the user's situation. As a result, the suggestion unit can always consider the geographical distribution in the optimal way and propose a solution.

When proposing a solution, the suggestion unit can improve the accuracy of the proposal by referring to related literature. When proposing a solution, the suggestion unit uses the generation AI to improve the accuracy of the proposal by referring to related literature. For example, the suggestion unit can search for related literature from a database and reflect it in the proposal. Also, the suggestion unit can improve the accuracy of the proposal by referring to successful examples of related literature. Furthermore, the suggestion unit can reduce the risk of the proposal by referring to failure examples of related literature. As a result, the accuracy of the proposal is improved by referring to related literature. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can provide an optimal proposal method based on the related literature searched by the generation AI. Furthermore, the suggestion unit has a function of adjusting the method of referring to related literature in real time. For example, the suggestion unit can select the optimal reference method according to the user's situation. As a result, the suggestion unit can always refer to related literature in the optimal way and reflect it in the proposal of the solution.

When selecting a reference case, the reference unit can select the optimal case by referring to past success cases. When selecting a reference case, the reference unit uses the generation AI to select the optimal case by referring to past success cases. For example, the reference unit can search a database for past success cases and select the optimal reference case. In addition, the reference unit can improve the accuracy of the reference case by referring to success cases of similar cases. Furthermore, the reference unit can analyze past success cases and select the most effective reference case. As a result, the optimal reference case can be selected by referring to past success cases. A part or all of the above-mentioned processing in the reference unit may be performed, for example, using AI, or may be performed without using AI. For example, the reference unit can provide the optimal reference case based on past success cases searched by the generation AI. Furthermore, the reference unit has a function of adjusting the reference method for success cases in real time. For example, the reference unit can select the optimal reference method according to the user's situation. As a result, the reference unit can always refer to past success cases in the optimal way and reflect them in the selection of the reference case.

When selecting a reference case, the reference unit can select the optimal case by considering the geographical distribution. When selecting a reference case, the reference unit uses the generation AI to select the optimal case by considering the geographical distribution. For example, the reference unit can select a reference case specific to a region based on the location of the user. Also, the reference unit can select a reference case that reflects the characteristics of each region by considering the geographical distribution. Furthermore, the reference unit can select a reference case for each region based on the geographical distribution. As a result, a reference case specific to a region can be selected by considering the geographical distribution. A part or all of the above-mentioned processing in the reference unit may be performed using, for example, AI, or may be performed without using AI. For example, the reference unit can provide an optimal reference case based on the geographical distribution considered by the generation AI. Furthermore, the reference unit has a function of adjusting the method of considering the geographical distribution in real time. For example, the reference unit can select the optimal method of considering the geographical distribution according to the user's situation. As a result, the reference unit can always consider the geographical distribution in the optimal method and select a reference case.

The evaluation unit can improve the accuracy of the evaluation by referring to past evaluation data when evaluating a solution. The evaluation unit uses the generation AI to improve the accuracy of the evaluation by referring to past evaluation data when evaluating a solution. For example, the evaluation unit can search for past evaluation data from a database and reflect it in the evaluation. The evaluation unit can also improve the accuracy of the evaluation by referring to evaluation data of similar cases. Furthermore, the evaluation unit can analyze past evaluation data and select the most effective evaluation method. As a result, the accuracy of the evaluation is improved by referring to the past evaluation data. A part or all of the above-mentioned processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit can provide an optimal evaluation method based on the past evaluation data searched by the generation AI. Furthermore, the evaluation unit has a function of adjusting the method of referring to the evaluation data in real time. For example, the evaluation unit can select the optimal reference method depending on the user's situation. As a result, the evaluation unit can always refer to past evaluation data in the optimal method and reflect it in the evaluation of the solution.

The evaluation unit can perform an evaluation taking into account the geographical distribution when evaluating a solution. The evaluation unit performs an evaluation taking into account the geographical distribution using the generation AI when evaluating a solution. For example, the evaluation unit can perform a region-specific evaluation based on the user's location. Furthermore, the evaluation unit can perform an evaluation that reflects the characteristics of each region by taking into account the geographical distribution. Furthermore, the evaluation unit can perform an evaluation for each region based on the geographical distribution. This makes it possible to perform a region-specific evaluation by taking into account the geographical distribution. A part or all of the above-mentioned processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit can provide an optimal evaluation method based on the geographical distribution taken into account by the generation AI. Furthermore, the evaluation unit has a function of adjusting the method of taking into account the geographical distribution in real time. For example, the evaluation unit can select the optimal method of taking into account the user's situation. This allows the evaluation unit to always take into account the geographical distribution in the optimal method and evaluate the solution.

The feedback unit can improve the accuracy of collection by referring to past feedback data when collecting feedback. The feedback unit uses the generation AI to improve the accuracy of collection by referring to past feedback data when collecting feedback. For example, the feedback unit can search for past feedback data from a database and reflect it in the collection. Also, the feedback unit can improve the accuracy of collection by referring to feedback data of similar cases. Furthermore, the feedback unit can analyze past feedback data and select the most effective collection method. As a result, the accuracy of collection is improved by referring to past feedback data. A part or all of the above-mentioned processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit can provide an optimal collection method based on past feedback data searched by the generation AI. Furthermore, the feedback unit has a function of adjusting the reference method of feedback data in real time. For example, the feedback unit can select the optimal reference method according to the user's situation. As a result, the feedback unit can always refer to past feedback data in the optimal method and reflect it in the collection of feedback.

The feedback unit can collect feedback while taking into account the geographical distribution. The feedback unit uses the generation AI to collect feedback while taking into account the geographical distribution. For example, the feedback unit can collect region-specific feedback based on the user's location. The feedback unit can also collect feedback reflecting the characteristics of each region while taking into account the geographical distribution. Furthermore, the feedback unit can collect feedback for each region based on the geographical distribution. As a result, region-specific feedback can be collected by taking into account the geographical distribution. A part or all of the above-mentioned processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit can provide an optimal collection method based on the geographical distribution taken into account by the generation AI. Furthermore, the feedback unit has a function of adjusting the method of taking into account the geographical distribution in real time. For example, the feedback unit can select the optimal method of taking into account the user's situation. As a result, the feedback unit can always take into account the geographical distribution in the optimal method and collect feedback.

The system according to the embodiment is not limited to the above-mentioned example, and various modifications are possible, for example, as follows:

The conflict arbitration system may further include a hobby analysis unit that takes into account the hobbies and interests of the user. The hobby analysis unit may analyze the hobbies and interests of the user and propose a solution taking these into account. For example, if the user has a particular hobby, a solution related to the hobby may be proposed. The hobby analysis unit may also suggest activities that allow the user to relax and reduce stress. This allows for more personalized solutions to be proposed by taking into account the hobbies and interests of the user.

The dispute arbitration system may further include an economic analysis unit that takes into account the user's economic situation. The economic analysis unit may analyze the user's income and expenses and propose a solution taking these into account. For example, if the user is in a financially difficult situation, the system may propose a cost-free solution. The economic analysis unit may also provide appropriate support depending on the user's economic situation. In this way, a more realistic solution may be proposed by taking into account the user's economic situation.

The dispute mediation system may further include a learning analysis unit that takes into account the learning style of the user. The learning analysis unit may analyze the user's learning style and level of understanding, and may propose a solution taking these into account. For example, if the user is a visual learner, the system may provide visual materials. If the user is an auditory learner, the system may provide audio explanations. In this way, more effective solutions may be proposed by taking into account the user's learning style.

The dispute arbitration system can further include a time management unit that supports the user's time management. The time management unit can analyze the user's schedule and how they use their time, and propose solutions taking these into consideration. For example, if the user has a busy schedule, the system can propose solutions that can be implemented in a short amount of time. The time management unit can also propose solutions at optimal times according to the user's schedule. This makes it possible to propose more efficient solutions by supporting the user's time management.

The conflict mediation system may further include a communication analysis unit that analyzes the user's communication style. The communication analysis unit may analyze the user's communication style and patterns, and may propose a solution by taking these into consideration. For example, if the user prefers direct communication, the system may propose a direct solution. Also, if the user prefers indirect communication, the system may propose an indirect solution. In this way, a more appropriate solution may be proposed by taking the user's communication style into consideration.

The processing flow of Example 1 is briefly explained below.

Step 1: The reception unit receives input of the contents of the conversation by the parties. The contents of the conversation may include, but are not limited to, the opinions and feelings of the parties. The reception unit may receive, for example, text input or voice input.
Step 2: The analysis unit uses the generation AI to analyze the content of the conversation and the tone of voice input by the reception unit. For example, the analysis unit analyzes the content of the conversation and identifies which part is the point of contention. The analysis unit can also grasp the strength of the emotions and the degree of tension of the parties by analyzing the tone of voice. For example, the generation AI can analyze the content of the conversation using a text generation AI (e.g., LLM) and identify the points of contention. The generation AI can also analyze the tone of voice using voice analysis technology and grasp the strength of emotions and the degree of tension.
Step 3: The summary unit uses the generation AI to summarize the points of contention in the story analyzed by the analysis unit. For example, the summary unit extracts important parts of the content of the story and organizes the points of contention.
Step 4: The suggestion unit uses the generation AI to propose an appropriate solution based on the issues summarized by the summary unit. The suggestion unit, for example, considers the issues in the story and the emotions of the parties involved and proposes the most appropriate solution. For example, the generation AI can propose a solution by referring to past success stories and expert opinions. Furthermore, the suggestion unit has a function to evaluate the reliability of the solution and also has a function to accept feedback from the user.

(Example 2)
The quarrel arbitration system according to the embodiment of the present invention is a system that arbitrates quarrels using a generation AI. In this system, the parties input the contents of the talk, and the generation AI analyzes the contents and tone of voice, summarizes the points of dispute in the talk, and proposes an appropriate solution. For example, the parties input the contents of the talk into the app. At this time, the parties can freely input their own opinions and feelings. For example, the parties input the contents of the talk, such as "I am angry that he did not keep his promise." This information is input to the generation AI. Next, the generation AI analyzes the input contents of the talk and the tone of voice. The generation AI analyzes the contents of the talk and identifies which part is the point of dispute. In addition, by analyzing the tone of voice, it is possible to grasp the strength of the emotions and the degree of tension of the parties. For example, the analysis result shows that the part "did not keep the promise" is the point of dispute, and the tone of voice indicates strong anger. Furthermore, the generation AI considers an appropriate solution. The generation AI considers the points of dispute in the talk and the emotions of the parties, and proposes the most appropriate solution. For example, it is possible to propose a solution such as "ask him to apologize." This proposal is displayed to the parties. This mechanism allows the parties to proceed with the discussion calmly. The generation AI analyzes the content of the conversation from a third-party perspective and proposes an appropriate solution, allowing the parties to proceed with the discussion without becoming emotional. In addition, the generation AI can analyze the tone of voice to grasp changes in the parties' emotions and propose a solution at the appropriate time. For example, by proposing a solution when the parties have calmed down, the discussion can proceed smoothly. In this way, the use of the generation AI realizes a system that can efficiently mediate arguments. As a result, the argument mediation system can analyze the content and tone of voice of the parties, summarize the points of contention, and propose an appropriate solution.

The quarrel arbitration system according to the embodiment includes a reception unit, an analysis unit, a summary unit, and a proposal unit. The reception unit receives input of the contents of the talk by the parties. The contents of the talk include, for example, the opinions and feelings of the parties, but are not limited to such examples. The reception unit can receive, for example, text input and voice input. The analysis unit uses a generation AI to analyze the contents of the talk and the tone of voice input by the reception unit. The analysis unit, for example, analyzes the contents of the talk and identifies which part is the point of dispute. The analysis unit can also grasp the strength of the emotions and the degree of tension of the parties by analyzing the tone of voice. For example, the generation AI analyzes the contents of the talk using a text generation AI (for example, LLM) and identifies the points of dispute. The generation AI can also analyze the tone of voice using voice analysis technology and grasp the strength of emotions and the degree of tension. The summary unit uses the generation AI to summarize the points of dispute in the talk analyzed by the analysis unit. The summary unit, for example, extracts important parts of the contents of the talk and organizes the points of dispute. The suggestion unit uses the generation AI to propose an appropriate solution based on the issues summarized by the summary unit. The suggestion unit, for example, considers the issues in the story and the emotions of the parties and proposes the most appropriate solution. For example, the generation AI can propose a solution by referring to past success stories and expert opinions. As a result, the fight arbitration system according to the embodiment can analyze the content and tone of voice of the parties, summarize the issues, and propose an appropriate solution. Some or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit displays a solution to the parties based on the solution proposed by the generation AI. Furthermore, the suggestion unit has a function of evaluating the reliability of the solution. For example, the suggestion unit can evaluate the reliability of the solution proposed by the generation AI and preferentially propose a highly reliable solution. In addition, the suggestion unit has a function of accepting feedback from the user. For example, the suggestion unit can collect feedback from the parties and use it to improve the system. As a result, the fight arbitration system can analyze the content and tone of voice of the parties, summarize the issues, and propose an appropriate solution.

The reception unit receives input of the contents of the talk by the parties. The contents of the talk include, for example, the opinions and feelings of the parties, but are not limited to such examples. The reception unit can receive, for example, text input and voice input. Specifically, in the case of text input, the parties can input their opinions and feelings using a keyboard or touch screen. In the case of voice input, the parties speak through a microphone, and the system converts the voice into text. Voice input is particularly effective for maintaining a natural flow of conversation and can capture the nuances of emotions more accurately. Furthermore, the reception unit has a function of temporarily storing the input data and transmitting it to the subsequent analysis unit and summary unit. This allows the reception unit to efficiently collect the contents of the talk by the parties and smoothly proceed with the processing of the entire system. In addition, the reception unit also has a security function for protecting the privacy of the input data, and can safely manage the information of the parties by encrypting data and controlling access. This allows the reception unit to provide an environment in which the parties can safely input the contents of the talk, thereby improving the reliability of the entire system.

The analysis unit uses the generation AI to analyze the content of the conversation and the tone of voice input by the reception unit. For example, the analysis unit analyzes the content of the conversation and identifies which part is the point of contention. In addition, the analysis unit can grasp the strength of the emotions and the degree of tension of the parties by analyzing the tone of voice. Specifically, the generation AI analyzes the content of the conversation using a text generation AI (for example, LLM) and identifies the points of contention. The text generation AI has learned a large amount of text data, and can extract important keywords and phrases from the content of the conversation input and clarify the points of contention. In addition, the generation AI can analyze the tone of voice using voice analysis technology and grasp the strength of emotions and the degree of tension. The voice analysis technology analyzes characteristics such as the pitch, tempo, and volume of the voice to evaluate the emotional state of the parties. For example, if the voice becomes higher or faster, it is determined that the tension or anger is strong. As a result, the analysis unit can comprehensively analyze both the content of the conversation and the tone of voice and accurately grasp the emotions and points of contention of the parties. Furthermore, the analysis unit can perform more accurate analysis by referring to past data and similar cases. This allows the analysis department to accurately understand the content and emotions of the parties involved and support the arbitration process throughout the system.

The summary unit uses the generation AI to summarize the issues in the story analyzed by the analysis unit. For example, the summary unit extracts important parts of the content of the story and organizes the issues. Specifically, the generation AI extracts important keywords and phrases from the content of the story and organizes them to clarify the issues. The generation AI has learned a large amount of text data and can efficiently summarize the content of the story. For example, it organizes the opinions and feelings of the parties and identifies which parts are most important. The summary unit also has a function to visually display the issues and provide information in a format that is easy for the parties to understand. For example, it visualizes the issues using graphs and charts so that the parties can understand them at a glance. Furthermore, the summary unit can organize the issues by referring to past data and similar cases. As a result, the summary unit can efficiently organize the content of the story and provide information in a format that is easy for the parties to understand. As a result, the summary unit can efficiently organize the content of the story of the parties and support the arbitration process of the entire system.

The suggestion unit uses the generation AI to propose an appropriate solution based on the issues summarized by the summary unit. The suggestion unit, for example, considers the issues in the story and the feelings of the parties and proposes the most appropriate solution. Specifically, the generation AI can propose a solution by referring to past success cases and expert opinions. The generation AI learns a large amount of data and can identify the most effective solution based on past similar cases and expert opinions. For example, by referring to past success cases, it proposes a solution that was effective in a similar situation. In addition, the suggestion unit has a function to evaluate the reliability of the solution, and can evaluate the reliability of the solution proposed by the generation AI and preferentially propose a highly reliable solution. Furthermore, the suggestion unit has a function to accept feedback from users, and can collect feedback from the parties and use it to improve the system. For example, it evaluates whether the proposed solution was actually effective and reflects it in the next proposal. As a result, the suggestion unit can always provide a highly accurate solution based on the latest information and improve the satisfaction of the parties. As a result, the suggestion unit can consider the content and feelings of the parties and propose the most appropriate solution.

The dispute arbitration system includes a reference section that refers to specific past cases or success cases. The reference section refers to past cases and success cases using the generation AI. For example, the reference section can search a database for similar past cases and refer to them. The reference section can also improve the accuracy of the solution based on successful projects and performance data. For example, the reference section analyzes past success cases and proposes the most effective solution. As a result, the accuracy of the solution is improved by referring to past cases and success cases. Some or all of the above-mentioned processing in the reference section may be performed using, for example, AI, or may be performed without using AI. For example, the reference section can propose a solution based on past cases and success cases searched by the generation AI. Furthermore, the reference section has a function of updating past cases and success cases in real time. For example, the reference section can automatically collect the latest cases and success cases and update the database. As a result, the reference section can always propose a solution based on the latest information.

The dispute arbitration system includes an evaluation unit that evaluates the reliability of the solution. The evaluation unit uses the generation AI to evaluate the reliability of the solution. For example, the evaluation unit can evaluate the reliability of the solution proposed by the generation AI and preferentially propose a highly reliable solution. The evaluation unit evaluates the reliability of the solution, for example, based on performance data or a third party evaluation. For example, the evaluation unit can evaluate the reliability of the solution by referring to past success stories and expert opinions. As a result, the reliability of the proposal is improved by evaluating the reliability of the solution. A part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit displays the solution to the parties based on the reliability of the solution evaluated by the generation AI. Furthermore, the evaluation unit has a function of evaluating the reliability of the solution in real time. For example, the evaluation unit can evaluate the reliability of the solution based on the latest data and propose a highly reliable solution. As a result, the evaluation unit can always evaluate the reliability of the solution based on the latest information.

The fight arbitration system includes a feedback unit that accepts feedback from users. The feedback unit accepts feedback from users using the generation AI. For example, the feedback unit can collect feedback from the parties and use it to improve the system. The feedback unit collects feedback, for example, through questionnaires and user reviews. For example, the feedback unit can conduct a questionnaire for the parties and collect opinions on the usability of the system and the effectiveness of the solution. This allows the system to be improved by accepting feedback from users. Some or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI, or may be performed without using AI. For example, the feedback unit can identify improvements to the system based on the feedback collected by the generation AI. Furthermore, the feedback unit has a function of adjusting the feedback collection method in real time. For example, the feedback unit can select the optimal collection method depending on the situation of the parties. This allows the feedback unit to always collect feedback in the optimal way and use it to improve the system.

The analysis unit can analyze the content of the talk and specifically identify which part is the point of contention. The analysis unit uses the generation AI to analyze the content of the talk and identify which part is the point of contention. For example, the analysis unit uses a text generation AI (e.g., LLM) to analyze the content of the talk and identify the point of contention. The generation AI can analyze the content of the talk and identify the points of contention and important points of discussion. For example, the generation AI can analyze the content of the talk and identify the part that "the promise was not kept" as the point of contention. As a result, by analyzing the content of the talk and identifying the point of contention, an appropriate solution can be proposed. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can propose a solution to the parties based on the point of contention identified by the generation AI. Furthermore, the analysis unit has a function of adjusting the method of identifying the point of contention in real time. For example, the analysis unit can select the optimal identification method according to the situation of the parties. As a result, the analysis unit can always identify the point of contention in the optimal way and propose an appropriate solution.

The analysis unit can analyze the tone of voice and specifically grasp the intensity of the emotions and the degree of tension of the parties. The analysis unit uses the generation AI to analyze the tone of voice and grasp the intensity of the emotions and the degree of tension of the parties. For example, the analysis unit can analyze the tone of voice using voice analysis technology and grasp the intensity of the emotions and the degree of tension. The generation AI can analyze the tone, pitch, speed, etc. of the tone of voice and identify the intensity of the emotions and the degree of tension of the parties. For example, the generation AI can analyze the tone of voice and identify the intensity of the emotions when the parties feel strong anger. In addition, the generation AI can analyze the tone of voice and grasp the degree of tension when the parties are nervous. In this way, the intensity of the emotions and the degree of tension of the parties can be grasped by analyzing the tone of voice. Part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI or may be performed without using AI. For example, the analysis unit can identify the intensity of the emotions and the degree of tension of the parties based on the data of the tone of voice analyzed by the generation AI. Furthermore, the analysis unit has a function of adjusting the analysis method of the tone of voice in real time. For example, the analysis unit can select the most appropriate analysis method depending on the situation of the person involved. This allows the analysis unit to always analyze tone of voice in the most appropriate way and grasp the intensity of the person's emotions and level of tension.

The reception unit can estimate the user's emotions and adjust the input method of the content of the talk based on the estimated user's emotions. The reception unit uses the generation AI to estimate the user's emotions and adjust the input method of the content of the talk based on the estimated user's emotions. For example, the reception unit can estimate the user's emotions using voice analysis technology and facial expression recognition technology. The generation AI can analyze the user's tone of voice and facial expression to identify the strength and type of emotion. For example, the generation AI can identify the emotion when the user is stressed and provide a simple interface. In addition, the generation AI can identify the emotion when the user is relaxed and provide detailed input options. Furthermore, the generation AI can identify the emotion when the user is in a hurry and prioritize voice input. This can reduce the burden on the user by adjusting the input method according to the user's emotions. Part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can provide an optimal input method based on the user's emotions estimated by the generation AI. Furthermore, the reception unit has a function of adjusting the estimation method of the user's emotions in real time. For example, the reception unit can select the optimal estimation method depending on the user's situation. This allows the reception unit to always estimate the user's emotions in the optimal method and adjust the method of inputting the content of the conversation.

The reception unit can analyze the user's past input history and provide an optimal input interface. The reception unit uses the generation AI to analyze the user's past input history and provide an optimal input interface. For example, the reception unit can automatically display phrases and keywords that have been frequently input in the past as candidates. The reception unit can also preferentially suggest input methods (such as voice and text) that have been used in the past. Furthermore, the reception unit can predict and suggest phrases and keywords that will be used in a specific time period from the past input history. As a result, the reception unit can provide an optimal input interface to the user by analyzing the past input history. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can provide an optimal input interface based on the past input history analyzed by the generation AI. Furthermore, the reception unit has a function of adjusting the method of providing the input interface in real time. For example, the reception unit can select the optimal method of providing depending on the user's situation. As a result, the reception unit can always provide an input interface in an optimal manner, improving user convenience.

The reception unit can filter the input contents based on the user's current situation or interests when inputting the contents of the talk. The reception unit uses the generation AI to filter the input contents based on the user's current situation and interests when inputting the contents of the talk. For example, the reception unit can automatically suggest related keywords when the user inputs the current situation. The reception unit can also filter the input contents based on the user's interests and preferentially display highly relevant information. Furthermore, the reception unit can simplify the input contents according to the user's current situation and allow only necessary information to be input. This makes it possible to provide highly relevant information by filtering the input contents based on the user's current situation and interests. Part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can provide optimal information to the user based on the input contents filtered by the generation AI. Furthermore, the reception unit has a function of adjusting the filtering method of the input contents in real time. For example, the reception unit can select the optimal filtering method according to the user's situation. This allows the reception unit to always filter input content in the most optimal way and provide highly relevant information.

The reception unit can estimate the user's emotions and determine the priority of the input contents based on the estimated user's emotions. The reception unit uses the generation AI to estimate the user's emotions and determine the priority of the input contents based on the estimated user's emotions. For example, the reception unit can estimate the user's emotions using voice analysis technology and facial expression recognition technology. The generation AI can analyze the user's tone of voice and facial expression to identify the strength and type of emotion. For example, the generation AI can identify the emotion when the user is feeling strong anger and allow the user to input important issues with priority. In addition, the generation AI can identify the emotion when the user is calm and allow the user to input detailed information. Furthermore, the generation AI can identify the emotion when the user is confused and allow the user to input concise input contents with priority. As a result, important information can be input with priority by determining the priority of the input contents according to the user's emotions. Part or all of the above-mentioned processing in the reception unit may be performed using AI, for example, or may be performed without using AI. For example, the reception unit can determine the priority of the input contents based on the user's emotions estimated by the generation AI. Furthermore, the reception unit has a function for adjusting the priority of input contents in real time. For example, the reception unit can select the optimal priority depending on the user's situation. This allows the reception unit to always determine the priority of input contents in the optimal way, and to input important information first.

The reception unit can preferentially input highly relevant content by specifically considering the geographical location information of the user when inputting the content of the talk. The reception unit uses the generation AI to preferentially input highly relevant content by considering the geographical location information of the user when inputting the content of the talk. For example, when the user is in a specific location, the reception unit can preferentially input information related to the location. Furthermore, the reception unit can automatically suggest related issues based on the geographical location information of the user. Furthermore, when the user is moving, the reception unit can preferentially input information related to the current location. As a result, highly relevant information can be preferentially input by considering the geographical location information. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can provide optimal information to the user based on the geographical location information considered by the generation AI. Furthermore, the reception unit has a function of adjusting the method of considering the geographical location information in real time. For example, the reception unit can select the optimal method of consideration according to the user's situation. As a result, the reception unit can always consider the geographical location information in the optimal manner and provide highly relevant information.

The reception unit can analyze the user's social media activity and input related content when inputting the content of the talk. The reception unit can use the generation AI to analyze the user's social media activity and input related content when inputting the content of the talk. For example, the reception unit can extract related keywords from the user's social media posts and reflect them in the input content. The reception unit can also analyze the user's social media activity and automatically suggest related issues. Furthermore, the reception unit can analyze the user's emotional expression on social media and adjust the input content. This makes it possible to provide highly relevant information by analyzing social media activity. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can provide optimal information to the user based on the social media activity analyzed by the generation AI. Furthermore, the reception unit has a function of adjusting the analysis method of social media activity in real time. For example, the reception unit can select the optimal analysis method according to the user's situation. This makes it possible for the reception unit to always analyze social media activity in the optimal way and input related content.

The analysis unit can estimate the user's emotions and adjust the analysis method of the content of the conversation based on the estimated user's emotions. The analysis unit uses the generation AI to estimate the user's emotions and adjust the analysis method of the content of the conversation based on the estimated user's emotions. For example, the analysis unit can estimate the user's emotions using voice analysis technology and facial expression recognition technology. The generation AI can analyze the user's tone of voice and facial expression to identify the strength and type of emotion. For example, the generation AI can identify the emotion when the user feels strong anger and perform analysis with emphasis on the strength of the emotion. In addition, the generation AI can identify the emotion when the user is calm and prioritize logical analysis. Furthermore, the generation AI can identify the emotion when the user is confused and perform a concise and clear analysis. This allows for more appropriate analysis by adjusting the analysis method according to the user's emotions. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit can provide an optimal analysis method based on the user's emotions estimated by the generation AI. Furthermore, the analysis unit has the ability to adjust the analysis method in real time. For example, the analysis unit can select the optimal analysis method depending on the user's situation. This allows the analysis unit to always analyze the content of the conversation in the most optimal way and adjust the analysis method based on the user's emotions.

The analysis unit can improve the accuracy of the analysis by referring to similar cases in the past when analyzing the content of the talk. The analysis unit can improve the accuracy of the analysis by referring to similar cases in the past when analyzing the content of the talk using the generation AI. For example, the analysis unit can search for similar cases in the past from a database and reflect them in the analysis. The analysis unit can also improve the accuracy of the analysis by referring to successful examples of similar cases. Furthermore, the analysis unit can reduce the risk of the analysis by referring to failed examples of similar cases. As a result, the accuracy of the analysis is improved by referring to similar cases in the past. A part or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit can provide an optimal analysis method based on similar cases in the past searched by the generation AI. Furthermore, the analysis unit has a function of adjusting the method of referring to similar cases in real time. For example, the analysis unit can select the optimal reference method according to the user's situation. As a result, the analysis unit can always refer to similar cases in the past in the optimal way and reflect them in the analysis of the content of the talk.

The analysis unit can perform the analysis by taking into account the attribute information of the user when analyzing the content of the conversation. The analysis unit performs the analysis by taking into account the attribute information of the user using the generation AI when analyzing the content of the conversation. For example, the analysis unit can adjust the viewpoint of the analysis by taking into account the age and gender of the user. In addition, the analysis unit can adjust the content of the analysis by taking into account the occupation and social status of the user. Furthermore, the analysis unit can adjust the method of analysis by taking into account the cultural background of the user. As a result, a more appropriate analysis is possible by taking into account the attribute information of the user. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can provide an optimal analysis method based on the attribute information of the user taken into account by the generation AI. Furthermore, the analysis unit has a function of adjusting the method of taking into account the attribute information in real time. For example, the analysis unit can select the optimal method of taking into account depending on the situation of the user. As a result, the analysis unit can always take into account the attribute information of the user in the optimal method and analyze the content of the conversation.

The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user's emotions. The analysis unit uses the generation AI to estimate the user's emotions and adjust the display method of the analysis results based on the estimated user's emotions. For example, the analysis unit can estimate the user's emotions using voice analysis technology and facial expression recognition technology. The generation AI can analyze the user's tone of voice and facial expression to identify the strength and type of emotion. For example, the generation AI can identify the emotion when the user is nervous and provide a simple and highly visible display method. In addition, the generation AI can identify the emotion when the user is relaxed and provide a display method including detailed information. Furthermore, the generation AI can identify the emotion when the user is in a hurry and provide a display method that focuses on the main points. This allows for more appropriate display by adjusting the display method according to the user's emotions. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit can provide an optimal display method based on the user's emotions estimated by the generation AI. Furthermore, the analysis unit has a function for adjusting the display method in real time. For example, the analysis unit can select the optimal adjustment method depending on the user's situation. This allows the analysis unit to always adjust the display method of the analysis results in the optimal way and provide a display method based on the user's emotions.

The analysis unit can perform the analysis while taking into account the geographical distribution when analyzing the content of the talk. The analysis unit performs the analysis while taking into account the geographical distribution using the generation AI when analyzing the content of the talk. For example, the analysis unit can analyze issues specific to a region based on the location of the user. Furthermore, the analysis unit can perform an analysis that reflects the characteristics of each region by taking into account the geographical distribution. Furthermore, the analysis unit can propose a solution for each region based on the geographical distribution. This allows the analysis of issues specific to a region by taking into account the geographical distribution. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can provide an optimal analysis method based on the geographical distribution taken into account by the generation AI. Furthermore, the analysis unit has a function of adjusting the method of taking into account the geographical distribution in real time. For example, the analysis unit can select the optimal method of taking into account depending on the user's situation. This allows the analysis unit to always take into account the geographical distribution in the optimal way and analyze the content of the talk.

The analysis unit can improve the accuracy of the analysis by referring to related literature when analyzing the content of the talk. The analysis unit can improve the accuracy of the analysis by referring to related literature when analyzing the content of the talk using the generation AI. For example, the analysis unit can search for related literature from a database and reflect it in the analysis. The analysis unit can also improve the accuracy of the analysis by referring to successful examples of related literature. Furthermore, the analysis unit can reduce the risk of the analysis by referring to unsuccessful examples of related literature. As a result, the accuracy of the analysis is improved by referring to related literature. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can provide an optimal analysis method based on the related literature searched by the generation AI. Furthermore, the analysis unit has a function of adjusting the method of referring to related literature in real time. For example, the analysis unit can select the optimal reference method according to the user's situation. As a result, the analysis unit can always refer to related literature in the optimal way and reflect it in the analysis of the content of the talk.

The summary unit can estimate the user's emotions and adjust the way the issues are summarized based on the estimated user's emotions. The summary unit uses the generation AI to estimate the user's emotions and adjust the way the issues are summarized based on the estimated user's emotions. For example, the summary unit can estimate the user's emotions using voice analysis technology and facial expression recognition technology. The generation AI can analyze the user's tone of voice and facial expression to identify the strength and type of emotion. For example, when the user feels strong anger, the generation AI can identify the emotion and summarize the issues with emphasis on the strength of the emotion. In addition, when the user is calm, the generation AI can identify the emotion and summarize the issues from a logical perspective. Furthermore, when the user is confused, the generation AI can identify the emotion and summarize the issues concisely and clearly. This allows for more appropriate summary by adjusting the way the issues are summarized according to the user's emotions. Some or all of the above-mentioned processing in the summary unit may be performed using AI, for example, or may be performed without using AI. For example, the summarizing unit can provide an optimal way of summarizing based on the user's emotions estimated by the generation AI. Furthermore, the summarizing unit has a function of adjusting the summarizing adjustment method in real time. For example, the summarizing unit can select the optimal adjustment method depending on the user's situation. This allows the summarizing unit to always adjust the way the issues are summarized in the optimal way and provide a summarizing method based on the user's emotions.

The summarizing unit can select the optimal method by referring to past summarizing methods when summarizing the issues. The summarizing unit uses the generation AI to select the optimal method by referring to past summarizing methods when summarizing the issues. For example, the summarizing unit can select the optimal method of summarizing the issues by referring to past successful cases. The summarizing unit can also select a summarizing method that reduces risk by referring to past failure cases. Furthermore, the summarizing unit can search a database for similar past cases and select the optimal summarizing method. As a result, the optimal summarizing method can be selected by referring to past summarizing methods. Part or all of the above-mentioned processing in the summarizing unit may be performed, for example, using AI, or may be performed without using AI. For example, the summarizing unit can provide the optimal summarizing method based on past summarizing methods searched by the generation AI. Furthermore, the summarizing unit has a function of adjusting the summarizing method reference method in real time. For example, the summarizing unit can select the optimal reference method according to the user's situation. As a result, the summarizing unit can always refer to past summarizing methods in the optimal method and reflect them in the summarization of the issues.

The summarizing unit can summarize the issues taking into account the attribute information of the user when summarizing the issues. The summarizing unit uses the generation AI to summarize the issues taking into account the attribute information of the user. For example, the summarizing unit can adjust the way the issues are summarized taking into account the age and sex of the user. The summarizing unit can also adjust the way the issues are summarized taking into account the occupation and social status of the user. Furthermore, the summarizing unit can adjust the way the issues are summarized taking into account the cultural background of the user. This allows for more appropriate summarization by taking into account the attribute information of the user. Some or all of the above-mentioned processing in the summarizing unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarizing unit can provide an optimal way of summarizing based on the attribute information of the user taken into account by the generation AI. Furthermore, the summarizing unit has a function of adjusting the way the attribute information is taken into account in real time. For example, the summarizing unit can select the optimal way of considering depending on the user's situation. This allows the summarizing unit to always take into account the attribute information of the user in the optimal way and summarize the issues.

The summary unit can estimate the user's emotions and adjust the display method of the summary result based on the estimated user's emotions. The summary unit uses the generation AI to estimate the user's emotions and adjust the display method of the summary result based on the estimated user's emotions. For example, the summary unit can estimate the user's emotions using voice analysis technology and facial expression recognition technology. The generation AI can analyze the user's tone of voice and facial expression to identify the strength and type of emotion. For example, the generation AI can identify the emotion when the user is nervous and provide a simple and highly visible display method. In addition, the generation AI can identify the emotion when the user is relaxed and provide a display method including detailed information. Furthermore, the generation AI can identify the emotion when the user is in a hurry and provide a display method that focuses on the main points. This allows for more appropriate display by adjusting the display method according to the user's emotions. Part or all of the above-mentioned processing in the summary unit may be performed, for example, using AI, or may be performed without using AI. For example, the summary unit can provide an optimal display method based on the user's emotions estimated by the generation AI. Furthermore, the summarizing unit has a function for adjusting the display method adjustment method in real time. For example, the summarizing unit can select the optimal adjustment method depending on the user's situation. This allows the summarizing unit to always adjust the display method of the summary results in the optimal way and provide a display method based on the user's emotions.

The summarizing unit can summarize issues taking into account the geographical distribution when summarizing issues. The summarizing unit uses the generation AI to summarize issues taking into account the geographical distribution when summarizing issues. For example, the summarizing unit can summarize issues specific to a region based on the user's location. Furthermore, the summarizing unit can summarize issues reflecting the characteristics of each region by taking into account the geographical distribution. Furthermore, the summarizing unit can propose solutions for each region based on the geographical distribution. As a result, issues specific to a region can be summarized by taking into account the geographical distribution. A part or all of the above-mentioned processing in the summarizing unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarizing unit can provide an optimal summarizing method based on the geographical distribution taken into account by the generation AI. Furthermore, the summarizing unit has a function of adjusting the method of considering the geographical distribution in real time. For example, the summarizing unit can select the optimal method of consideration according to the user's situation. As a result, the summarizing unit can always consider the geographical distribution in the optimal way and summarize issues.

The summarizing unit can improve the accuracy of the summary by referring to related literature when summarizing the issues. The summarizing unit uses the generation AI to improve the accuracy of the summary by referring to related literature when summarizing the issues. For example, the summarizing unit can search for related literature from a database and reflect it in the summary. The summarizing unit can also improve the accuracy of the summary by referring to successful examples of related literature. Furthermore, the summarizing unit can reduce the risk of summarization by referring to unsuccessful examples of related literature. As a result, the accuracy of the summary is improved by referring to related literature. A part or all of the above-mentioned processing in the summarizing unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarizing unit can provide an optimal summarizing method based on the related literature searched by the generation AI. Furthermore, the summarizing unit has a function of adjusting the method of referring to related literature in real time. For example, the summarizing unit can select the optimal reference method according to the user's situation. As a result, the summarizing unit can always refer to related literature in the optimal way and reflect it in the summary of the issues.

The suggestion unit can estimate the user's emotions and adjust the solution proposal method based on the estimated user's emotions. The suggestion unit uses the generation AI to estimate the user's emotions and adjust the solution proposal method based on the estimated user's emotions. For example, the suggestion unit can estimate the user's emotions using voice analysis technology and facial expression recognition technology. The generation AI can analyze the user's tone of voice and facial expression to identify the strength and type of emotion. For example, the generation AI can identify the emotion when the user feels strong anger and propose a solution with emphasis on the strength of the emotion. In addition, the generation AI can identify the emotion when the user is calm and propose a solution from a logical perspective. Furthermore, the generation AI can identify the emotion when the user is confused and propose a concise and clear solution. As a result, by adjusting the proposal method according to the user's emotions, a more appropriate solution can be proposed. Some or all of the above-mentioned processing in the suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the suggestion unit can provide an optimal proposal method based on the user's emotions estimated by the generation AI. Furthermore, the suggestion unit has a function of adjusting the adjustment method of the proposed method in real time. For example, the suggestion unit can select the optimal adjustment method depending on the user's situation. This allows the suggestion unit to always adjust the solution proposal method in the optimal way and provide the proposed method based on the user's feelings.

When proposing a solution, the suggestion unit can make an optimal proposal by referring to past success cases. When proposing a solution, the suggestion unit uses the generation AI to make an optimal proposal by referring to past success cases. For example, the suggestion unit can search for past success cases from a database and propose an optimal solution. In addition, the suggestion unit can improve the accuracy of the solution by referring to success cases of similar cases. Furthermore, the suggestion unit can analyze past success cases and propose the most effective solution. As a result, the optimal solution can be proposed by referring to past success cases. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can provide an optimal solution based on past success cases searched by the generation AI. Furthermore, the suggestion unit has a function of adjusting the reference method for success cases in real time. For example, the suggestion unit can select the optimal reference method according to the user's situation. As a result, the suggestion unit can always refer to past success cases in the optimal way and reflect them in the proposed solution.

When proposing a solution, the suggestion unit can make a proposal taking into account the attribute information of the user. When proposing a solution, the suggestion unit makes a proposal taking into account the attribute information of the user using the generation AI. For example, the suggestion unit can propose an optimal solution taking into account the age and sex of the user. In addition, the suggestion unit can adjust the content of the solution taking into account the occupation and social status of the user. Furthermore, the suggestion unit can adjust the method of the solution taking into account the cultural background of the user. As a result, a more appropriate solution can be proposed by taking into account the attribute information of the user. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can provide an optimal solution based on the attribute information of the user taken into account by the generation AI. Furthermore, the suggestion unit has a function of adjusting the method of considering the attribute information in real time. For example, the suggestion unit can select the optimal method of consideration according to the user's situation. As a result, the suggestion unit can always consider the attribute information of the user in the optimal method and propose a solution.

The suggestion unit can estimate the user's emotions and determine the priority of suggestions based on the estimated user's emotions. The suggestion unit uses the generation AI to estimate the user's emotions and determine the priority of suggestions based on the estimated user's emotions. For example, the suggestion unit can estimate the user's emotions using voice analysis technology and facial expression recognition technology. The generation AI can analyze the user's tone of voice and facial expression to identify the strength and type of emotion. For example, the generation AI can identify the emotion when the user feels strong anger and determine the priority by emphasizing the strength of the emotion. In addition, the generation AI can identify the emotion when the user is calm and determine the priority from a logical perspective. Furthermore, the generation AI can identify the emotion when the user is confused and determine a concise and clear priority. As a result, by determining the priority of suggestions according to the user's emotions, important solutions can be preferentially proposed. Part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI or may be performed without using AI. For example, the suggestion unit can provide an optimal priority based on the user's emotions estimated by the generation AI. Furthermore, the suggestion unit has a function of adjusting the priority determination method in real time. For example, the suggestion unit can select the optimal determination method depending on the user's situation. This allows the suggestion unit to always determine the priority of suggestions in the optimal method and provide priorities based on the user's emotions.

When proposing a solution, the suggestion unit can make a proposal taking into account the geographical distribution. When proposing a solution, the suggestion unit makes a proposal taking into account the geographical distribution using the generation AI. For example, the suggestion unit can propose a solution specific to a region based on the user's location. Also, the suggestion unit can propose a solution that reflects the characteristics of each region by taking into account the geographical distribution. Furthermore, the suggestion unit can propose a solution for each region based on the geographical distribution. As a result, a solution specific to a region can be proposed by taking into account the geographical distribution. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can provide an optimal solution based on the geographical distribution taken into account by the generation AI. Furthermore, the suggestion unit has a function of adjusting the method of considering the geographical distribution in real time. For example, the suggestion unit can select the optimal method of consideration according to the user's situation. As a result, the suggestion unit can always consider the geographical distribution in the optimal way and propose a solution.

When proposing a solution, the suggestion unit can improve the accuracy of the proposal by referring to related literature. When proposing a solution, the suggestion unit uses the generation AI to improve the accuracy of the proposal by referring to related literature. For example, the suggestion unit can search for related literature from a database and reflect it in the proposal. Also, the suggestion unit can improve the accuracy of the proposal by referring to successful examples of related literature. Furthermore, the suggestion unit can reduce the risk of the proposal by referring to failure examples of related literature. As a result, the accuracy of the proposal is improved by referring to related literature. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can provide an optimal proposal method based on the related literature searched by the generation AI. Furthermore, the suggestion unit has a function of adjusting the method of referring to related literature in real time. For example, the suggestion unit can select the optimal reference method according to the user's situation. As a result, the suggestion unit can always refer to related literature in the optimal way and reflect it in the proposal of the solution.

The reference unit can estimate the user's emotions and select a reference case based on the estimated user's emotions. The reference unit uses the generation AI to estimate the user's emotions and select a reference case based on the estimated user's emotions. For example, the reference unit can estimate the user's emotions using voice analysis technology and facial expression recognition technology. The generation AI can analyze the user's tone of voice and facial expression to identify the strength and type of emotion. For example, the generation AI can identify the emotion when the user feels strong anger and select a reference case with emphasis on the strength of the emotion. In addition, the generation AI can identify the emotion when the user is calm and select a reference case from a logical perspective. Furthermore, the generation AI can identify the emotion when the user is confused and select a concise and clear reference case. As a result, by selecting a reference case according to the user's emotions, a more appropriate case can be provided. Part or all of the above-mentioned processing in the reference unit may be performed, for example, using AI, or may be performed without using AI. For example, the reference unit can provide optimal reference cases based on the user's emotions estimated by the generation AI. Furthermore, the reference unit has a function for adjusting the reference case selection method in real time. For example, the reference unit can select the optimal selection method depending on the user's situation. This allows the reference unit to always select reference cases in the optimal method and provide reference cases based on the user's emotions.

When selecting a reference case, the reference unit can select the optimal case by referring to past success cases. When selecting a reference case, the reference unit uses the generation AI to select the optimal case by referring to past success cases. For example, the reference unit can search a database for past success cases and select the optimal reference case. In addition, the reference unit can improve the accuracy of the reference case by referring to success cases of similar cases. Furthermore, the reference unit can analyze past success cases and select the most effective reference case. As a result, the optimal reference case can be selected by referring to past success cases. A part or all of the above-mentioned processing in the reference unit may be performed, for example, using AI, or may be performed without using AI. For example, the reference unit can provide the optimal reference case based on past success cases searched by the generation AI. Furthermore, the reference unit has a function of adjusting the reference method for success cases in real time. For example, the reference unit can select the optimal reference method according to the user's situation. As a result, the reference unit can always refer to past success cases in the optimal way and reflect them in the selection of the reference case.

The reference unit can estimate the user's emotions and adjust the display method of the reference case based on the estimated user's emotions. The reference unit uses the generation AI to estimate the user's emotions and adjust the display method of the reference case based on the estimated user's emotions. For example, the reference unit can estimate the user's emotions using voice analysis technology and facial expression recognition technology. The generation AI can analyze the user's tone of voice and facial expression to identify the strength and type of emotion. For example, the generation AI can identify the emotion when the user is nervous and provide a simple and highly visible display method. In addition, the generation AI can identify the emotion when the user is relaxed and provide a display method including detailed information. Furthermore, the generation AI can identify the emotion when the user is in a hurry and provide a display method that focuses on the main points. This allows for more appropriate display by adjusting the display method according to the user's emotions. Part or all of the above-mentioned processing in the reference unit may be performed, for example, using AI or may be performed without using AI. For example, the reference unit can provide an optimal display method based on the user's emotions estimated by the generation AI. Furthermore, the reference section has a function for adjusting the display method in real time. For example, the reference section can select the optimal adjustment method depending on the user's situation. This allows the reference section to always adjust the display method of the reference case in the optimal way and provide a display method based on the user's emotions.

When selecting a reference case, the reference unit can select the optimal case by considering the geographical distribution. When selecting a reference case, the reference unit uses the generation AI to select the optimal case by considering the geographical distribution. For example, the reference unit can select a reference case specific to a region based on the location of the user. Also, the reference unit can select a reference case that reflects the characteristics of each region by considering the geographical distribution. Furthermore, the reference unit can select a reference case for each region based on the geographical distribution. As a result, a reference case specific to a region can be selected by considering the geographical distribution. A part or all of the above-mentioned processing in the reference unit may be performed using, for example, AI, or may be performed without using AI. For example, the reference unit can provide an optimal reference case based on the geographical distribution considered by the generation AI. Furthermore, the reference unit has a function of adjusting the method of considering the geographical distribution in real time. For example, the reference unit can select the optimal method of considering the geographical distribution according to the user's situation. As a result, the reference unit can always consider the geographical distribution in the optimal method and select a reference case.

The evaluation unit can estimate the user's emotions and adjust the evaluation method of the solution based on the estimated user's emotions. The evaluation unit uses the generation AI to estimate the user's emotions and adjust the evaluation method of the solution based on the estimated user's emotions. For example, the evaluation unit can estimate the user's emotions using voice analysis technology and facial expression recognition technology. The generation AI can analyze the user's tone of voice and facial expression to identify the strength and type of emotion. For example, the generation AI can identify the emotion when the user feels strong anger and evaluate with emphasis on the strength of the emotion. In addition, the generation AI can identify the emotion when the user is calm and evaluate from a logical perspective. Furthermore, the generation AI can identify the emotion when the user is confused and perform a concise and clear evaluation. This allows for a more appropriate evaluation by adjusting the evaluation method according to the user's emotions. Some or all of the above-mentioned processing in the evaluation unit may be performed using AI, for example, or may be performed without using AI. For example, the evaluation unit can provide an optimal evaluation method based on the user's emotions estimated by the generation AI. Furthermore, the evaluation unit has a function for adjusting the adjustment method of the evaluation method in real time. For example, the evaluation unit can select the optimal adjustment method depending on the user's situation. This allows the evaluation unit to always adjust the evaluation method of the solution in the optimal way and provide the evaluation method based on the user's feelings.

The evaluation unit can improve the accuracy of the evaluation by referring to past evaluation data when evaluating a solution. The evaluation unit uses the generation AI to improve the accuracy of the evaluation by referring to past evaluation data when evaluating a solution. For example, the evaluation unit can search for past evaluation data from a database and reflect it in the evaluation. The evaluation unit can also improve the accuracy of the evaluation by referring to evaluation data of similar cases. Furthermore, the evaluation unit can analyze past evaluation data and select the most effective evaluation method. As a result, the accuracy of the evaluation is improved by referring to the past evaluation data. A part or all of the above-mentioned processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit can provide an optimal evaluation method based on the past evaluation data searched by the generation AI. Furthermore, the evaluation unit has a function of adjusting the method of referring to the evaluation data in real time. For example, the evaluation unit can select the optimal reference method according to the user's situation. As a result, the evaluation unit can always refer to past evaluation data in the optimal method and reflect it in the evaluation of the solution.

The evaluation unit can estimate the user's emotions and adjust the display method of the evaluation result based on the estimated user's emotions. The evaluation unit uses the generation AI to estimate the user's emotions and adjust the display method of the evaluation result based on the estimated user's emotions. For example, the evaluation unit can estimate the user's emotions using voice analysis technology and facial expression recognition technology. The generation AI can analyze the user's tone of voice and facial expression to identify the strength and type of emotion. For example, the generation AI can identify the emotion when the user is nervous and provide a simple and highly visible display method. In addition, the generation AI can identify the emotion when the user is relaxed and provide a display method including detailed information. Furthermore, the generation AI can identify the emotion when the user is in a hurry and provide a display method that focuses on the main points. This allows for more appropriate display by adjusting the display method according to the user's emotions. Part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can provide an optimal display method based on the user's emotions estimated by the generation AI. Furthermore, the evaluation unit has a function for adjusting the display method adjustment method in real time. For example, the evaluation unit can select the optimal adjustment method depending on the user's situation. This allows the evaluation unit to always adjust the display method of the evaluation results in the optimal way and provide a display method based on the user's emotions.

The evaluation unit can perform an evaluation taking into account the geographical distribution when evaluating a solution. The evaluation unit performs an evaluation taking into account the geographical distribution using the generation AI when evaluating a solution. For example, the evaluation unit can perform a region-specific evaluation based on the user's location. Furthermore, the evaluation unit can perform an evaluation that reflects the characteristics of each region by taking into account the geographical distribution. Furthermore, the evaluation unit can perform an evaluation for each region based on the geographical distribution. This makes it possible to perform a region-specific evaluation by taking into account the geographical distribution. A part or all of the above-mentioned processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit can provide an optimal evaluation method based on the geographical distribution taken into account by the generation AI. Furthermore, the evaluation unit has a function of adjusting the method of taking into account the geographical distribution in real time. For example, the evaluation unit can select the optimal method of taking into account the user's situation. This allows the evaluation unit to always take into account the geographical distribution in the optimal method and evaluate the solution.

The feedback unit can estimate the user's emotions and adjust the feedback collection method based on the estimated user's emotions. The feedback unit uses the generation AI to estimate the user's emotions and adjust the feedback collection method based on the estimated user's emotions. For example, the feedback unit can estimate the user's emotions using voice analysis technology and facial expression recognition technology. The generation AI can analyze the user's tone of voice and facial expression to identify the strength and type of emotion. For example, the generation AI can identify the emotion when the user feels strong anger and collect feedback with emphasis on the strength of the emotion. In addition, the generation AI can identify the emotion when the user is calm and collect feedback from a logical perspective. Furthermore, the generation AI can identify the emotion when the user is confused and collect concise and clear feedback. As a result, by adjusting the collection method according to the user's emotions, more appropriate feedback can be collected. Some or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI or may be performed without using AI. For example, the feedback unit can provide an optimal collection method based on the user's emotions estimated by the generation AI. Furthermore, the feedback unit has a function of adjusting the adjustment method of the collection method in real time. For example, the feedback unit can select the optimal adjustment method depending on the user's situation. This allows the feedback unit to always adjust the feedback collection method in the optimal way and provide the collection method based on the user's emotions.

The feedback unit can improve the accuracy of collection by referring to past feedback data when collecting feedback. The feedback unit uses the generation AI to improve the accuracy of collection by referring to past feedback data when collecting feedback. For example, the feedback unit can search for past feedback data from a database and reflect it in the collection. Also, the feedback unit can improve the accuracy of collection by referring to feedback data of similar cases. Furthermore, the feedback unit can analyze past feedback data and select the most effective collection method. As a result, the accuracy of collection is improved by referring to past feedback data. A part or all of the above-mentioned processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit can provide an optimal collection method based on past feedback data searched by the generation AI. Furthermore, the feedback unit has a function of adjusting the reference method of feedback data in real time. For example, the feedback unit can select the optimal reference method according to the user's situation. As a result, the feedback unit can always refer to past feedback data in the optimal method and reflect it in the collection of feedback.

The feedback unit can estimate the user's emotions and adjust the display method of the feedback based on the estimated user's emotions. The feedback unit uses the generation AI to estimate the user's emotions and adjust the display method of the feedback based on the estimated user's emotions. For example, the feedback unit can estimate the user's emotions using voice analysis technology and facial expression recognition technology. The generation AI can analyze the user's tone of voice and facial expression to identify the strength and type of emotion. For example, the generation AI can identify the emotion when the user is nervous and provide a simple and highly visible display method. In addition, the generation AI can identify the emotion when the user is relaxed and provide a display method including detailed information. Furthermore, the generation AI can identify the emotion when the user is in a hurry and provide a display method that focuses on the main points. This allows for more appropriate display by adjusting the display method according to the user's emotions. Part or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI or may be performed without using AI. For example, the feedback unit can provide an optimal display method based on the user's emotions estimated by the generation AI. Furthermore, the feedback unit has a function of adjusting the display method adjustment method in real time. For example, the feedback unit can select the optimal adjustment method according to the user's situation. This allows the feedback unit to always adjust the feedback display method in the optimal way and provide a display method based on the user's emotions.

The feedback unit can collect feedback while taking into account the geographical distribution. The feedback unit uses the generation AI to collect feedback while taking into account the geographical distribution. For example, the feedback unit can collect region-specific feedback based on the user's location. The feedback unit can also collect feedback reflecting the characteristics of each region while taking into account the geographical distribution. Furthermore, the feedback unit can collect feedback for each region based on the geographical distribution. As a result, region-specific feedback can be collected by taking into account the geographical distribution. A part or all of the above-mentioned processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit can provide an optimal collection method based on the geographical distribution taken into account by the generation AI. Furthermore, the feedback unit has a function of adjusting the method of taking into account the geographical distribution in real time. For example, the feedback unit can select the optimal method of taking into account the user's situation. As a result, the feedback unit can always take into account the geographical distribution in the optimal method and collect feedback.

The system according to the embodiment is not limited to the above-mentioned example, and various modifications are possible, for example, as follows:

The dispute arbitration system may further include a history analysis unit that analyzes the user's past behavioral history. The history analysis unit may analyze what emotions the user has shown in what situations in the past, and compare this with the current situation to propose a more appropriate solution. For example, it may refer to what solutions the user has accepted in similar disputes in the past. The history analysis unit may also analyze what changes in emotions the user has shown in the past, and predict current changes in emotions. In this way, by taking into account the user's past behavioral history, it may be possible to propose a more personalized solution.

The dispute arbitration system may further include a health monitoring unit that monitors the user's current health condition. The health monitoring unit may measure the user's heart rate and stress level in real time and suggest a solution based on this data. For example, if the user's heart rate is high, the system may provide the user with advice to relax. Also, if the stress level is high, the system may suggest temporarily postponing the resolution of the dispute. This allows a solution to be suggested at a more appropriate time by taking the user's health condition into account.

The dispute mediation system may further include a network analysis unit that analyzes the user's social network. The network analysis unit may analyze the user's relationships with friends and family and propose a solution by taking these relationships into account. For example, if the user frequently communicates with certain friends and family, the opinions of these people may be taken into consideration. The network analysis unit may also evaluate the user's level of social support and provide support as necessary. This may allow a more comprehensive solution to be proposed by taking the user's social network into account.

The dispute arbitration system can further include a cultural analysis unit that takes into account the cultural background of the user. The cultural analysis unit can analyze the user's cultural background and values, and propose a solution taking these into consideration. For example, if the user has specific cultural values, a solution based on those values can be proposed. The cultural analysis unit can also take into account the user's language and communication style and propose a solution in an appropriate manner. In this way, a more appropriate solution can be proposed by taking into account the user's cultural background.

The fight arbitration system may further include an environment monitoring unit that monitors the user's current environment. The environment monitoring unit may measure environmental factors such as noise levels and temperature in the user's location in real time and suggest solutions based on this data. For example, if the user is in a noisy location, the system may suggest moving to a quieter location. Also, if the temperature is high, the system may suggest cooling methods. This allows more appropriate solutions to be suggested by taking the user's environment into account.

The conflict arbitration system may further include a hobby analysis unit that takes into account the hobbies and interests of the user. The hobby analysis unit may analyze the hobbies and interests of the user and propose a solution taking these into account. For example, if the user has a particular hobby, a solution related to the hobby may be proposed. The hobby analysis unit may also suggest activities that allow the user to relax and reduce stress. This allows for a more personalized solution to be proposed by taking into account the hobbies and interests of the user.

The dispute arbitration system may further include an economic analysis unit that takes into account the user's economic situation. The economic analysis unit may analyze the user's income and expenses and propose a solution taking these into account. For example, if the user is in a financially difficult situation, the system may propose a cost-free solution. The economic analysis unit may also provide appropriate support depending on the user's economic situation. In this way, a more realistic solution may be proposed by taking into account the user's economic situation.

The dispute mediation system may further include a learning analysis unit that takes into account the learning style of the user. The learning analysis unit may analyze the user's learning style and level of understanding, and may propose a solution taking these into account. For example, if the user is a visual learner, the system may provide visual materials. If the user is an auditory learner, the system may provide audio explanations. In this way, more effective solutions may be proposed by taking into account the user's learning style.

The dispute arbitration system can further include a time management unit that supports the user's time management. The time management unit can analyze the user's schedule and how they use their time, and propose solutions taking these into consideration. For example, if the user has a busy schedule, the system can propose solutions that can be implemented in a short amount of time. The time management unit can also propose solutions at optimal times according to the user's schedule. This makes it possible to propose more efficient solutions by supporting the user's time management.

The conflict mediation system may further include a communication analysis unit that analyzes the user's communication style. The communication analysis unit may analyze the user's communication style and patterns, and may propose a solution by taking these into consideration. For example, if the user prefers direct communication, the system may propose a direct solution. Also, if the user prefers indirect communication, the system may propose an indirect solution. In this way, a more appropriate solution may be proposed by taking the user's communication style into consideration.

The process flow for Example 2 is briefly explained below.

Step 1: The reception unit receives input of the contents of the conversation by the parties. The contents of the conversation may include, but are not limited to, the opinions and feelings of the parties. The reception unit may receive, for example, text input or voice input.
Step 2: The analysis unit uses the generation AI to analyze the content of the conversation and the tone of voice input by the reception unit. For example, the analysis unit analyzes the content of the conversation and identifies which part is the point of contention. The analysis unit can also grasp the strength of the emotions and the degree of tension of the parties by analyzing the tone of voice. For example, the generation AI can analyze the content of the conversation using a text generation AI (e.g., LLM) and identify the points of contention. The generation AI can also analyze the tone of voice using voice analysis technology and grasp the strength of emotions and the degree of tension.
Step 3: The summary unit uses the generation AI to summarize the points of contention in the story analyzed by the analysis unit. For example, the summary unit extracts important parts of the content of the story and organizes the points of contention.
Step 4: The suggestion unit uses the generation AI to propose an appropriate solution based on the issues summarized by the summary unit. The suggestion unit, for example, considers the issues in the story and the emotions of the parties involved and proposes the most appropriate solution. For example, the generation AI can propose a solution by referring to past success stories and expert opinions. Furthermore, the suggestion unit has a function to evaluate the reliability of the solution and also has a function to accept feedback from the user.

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 for 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.

The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is generative AI such as ChatGPT (registered trademark) (Internet search <URL: https://openai.com/blog/chatgpt>). 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 a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats such as voice data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and/or summarization. The identification processing unit 290 performs the above-mentioned identification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model to output an inference result from a prompt that does not include an instruction, in which case the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12, etc., the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI other than the generation 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 may perform various processes, but is not limited to such examples. The AI may also be an AI agent. In addition, when the processing of each part described above is performed by AI, the processing is performed in part or in whole by AI, but is not limited to such examples. In addition, the processing performed by AI, including the generating AI, may be replaced with rule-based processing, and the rule-based processing may be replaced with processing performed by AI, including the generating AI.

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. The specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

Each of the multiple elements including the above-mentioned reception unit, analysis unit, summary unit, proposal unit, reference unit, evaluation unit, and feedback unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart device 14, and the parties can input the contents of the talk. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the contents of the talk and the tone of voice. The summary unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and summarizes the points of contention in the talk. The proposal unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and proposes an appropriate solution. The reference unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and refers to past cases and successful examples. The evaluation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and evaluates the reliability of the solution. The feedback unit is realized, for example, by the control unit 46A of the smart device 14, and accepts feedback from the user. The correspondence between each part and the device or control unit is not limited to the above example, and various modifications are possible.

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

As shown in FIG. 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.

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, the RAM 30, and the 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.

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.

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 the voice according to instructions from the processor 46.

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 the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the field of vision of a typical able-bodied person).

The communication I/F 44 is connected to the 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 performed in a secure state.

Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 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.

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.

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 the 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 such examples. Furthermore, the estimation and prediction of emotion also includes, for example, analysis of emotions.

In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores the specific processing program 60. 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 use these models to perform processing similar to that of the specific processing unit 290.

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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device owned by a user (for example, a mobile phone, a robot, a home appliance, etc.).

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 for 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.

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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats such as voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and/or summarization. The identification processing unit 290 performs the above-mentioned identification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model to output an inference result from a prompt that does not include an instruction, in which case the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12, etc., the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI other than the generation 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 may perform various processes, but is not limited to such examples. The AI may also be an AI agent. In addition, when the processing of each part described above is performed by AI, the processing is performed in part or in whole by AI, but is not limited to such examples. In addition, the processing performed by AI, including the generating AI, may be replaced with rule-based processing, and the rule-based processing may be replaced with processing performed by AI, including the generating AI.

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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, 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.

Each of the multiple elements including the above-mentioned reception unit, analysis unit, summary unit, proposal unit, reference unit, evaluation unit, and feedback unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart glasses 214, and the parties can input the content of the talk. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the content and tone of voice of the talk. The summary unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and summarizes the points of contention in the talk. The proposal unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and proposes an appropriate solution. The reference unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and refers to past cases and successful examples. The evaluation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and evaluates the reliability of the solution. The feedback unit is realized, for example, by the control unit 46A of the smart glasses 214, and accepts feedback from the user. The correspondence between each part and the device or control unit is not limited to the above example, and various modifications are possible.

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

As shown in FIG. 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

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, the RAM 30, and the 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.

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.

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 the voice according to instructions from the processor 46.

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 the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the field of vision of a typical able-bodied person).

The communication I/F 44 is connected to the 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 performed in a secure state.

Figure 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Figure 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.

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.

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 the 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 such examples. Furthermore, the estimation and prediction of emotion also includes, for example, analysis of emotions.

In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores the specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific 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 program 60 executed on the RAM 48. 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.

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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device owned by a user (for example, a mobile phone, a robot, a home appliance, etc.).

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 for 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.

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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats such as voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and/or summarization. The identification processing unit 290 performs the above-mentioned identification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model to output an inference result from a prompt that does not include an instruction, in which case the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12, etc., the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI other than the generation 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 may perform various processes, but is not limited to such examples. The AI may also be an AI agent. In addition, when the processing of each part described above is performed by AI, the processing is performed in part or in whole by AI, but is not limited to such examples. In addition, the processing performed by AI, including the generating AI, may be replaced with rule-based processing, and the rule-based processing may be replaced with processing performed by AI, including the generating AI.

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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

Each of the multiple elements including the above-mentioned reception unit, analysis unit, summary unit, proposal unit, reference unit, evaluation unit, and feedback unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the headset type terminal 314, and the parties can input the contents of the talk. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the contents of the talk and the tone of voice. The summary unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and summarizes the points of contention in the talk. The proposal unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and proposes an appropriate solution. The reference unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and refers to past cases and successful examples. The evaluation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and evaluates the reliability of the solution. The feedback unit is realized, for example, by the control unit 46A of the headset type terminal 314, and accepts feedback from the user. The correspondence between each part and the device or control unit is not limited to the above example, and various modifications are possible.

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

As shown in FIG. 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.

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, the RAM 30, and the 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.

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.

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 the voice according to instructions from the processor 46.

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 the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the field of vision of a typical able-bodied person).

The communication I/F 44 is connected to the 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 performed in a secure state.

The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and legs. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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.

Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 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.

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.

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 the 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 such examples. Furthermore, the estimation and prediction of emotion also includes, for example, analysis of emotions.

In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores the specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific 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 program 60 executed on the RAM 48. The robot 414 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.

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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device owned by a user (for example, a mobile phone, a robot, a home appliance, etc.).

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 the user input for 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.

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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats such as voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and/or summarization. The identification processing unit 290 performs the above-mentioned identification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model to output an inference result from a prompt that does not include an instruction, in which case the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12, etc., the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI other than the generation 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 may perform various processes, but is not limited to such examples. The AI may also be an AI agent. In addition, when the processing of each part described above is performed by AI, the processing is performed in part or in whole by AI, but is not limited to such examples. In addition, the processing performed by AI, including the generating AI, may be replaced with rule-based processing, and the rule-based processing may be replaced with processing performed by AI, including the generating AI.

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. In addition, 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.

Each of the multiple elements including the above-mentioned reception unit, analysis unit, summary unit, proposal unit, reference unit, evaluation unit, and feedback unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the robot 414, and the parties can input the contents of the talk. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the contents and tone of voice of the talk. The summary unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and summarizes the points of contention in the talk. The proposal unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and proposes an appropriate solution. The reference unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and refers to past cases and successful examples. The evaluation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and evaluates the reliability of the solution. The feedback unit is realized, for example, by the control unit 46A of the robot 414, and accepts feedback from the user. The correspondence between each part and the device or control unit is not limited to the above example, and various modifications are possible.

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

9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. Emotions that represent states and actions arising from a state of mind are arranged on the outer sides of the concentric circles. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, 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 in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

These emotions are distributed in the three o'clock direction of emotion map 400, and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness takes precedence over internal sensations, resulting in a sense of calm.

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

Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and remaining battery power, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https://ci.nii.ac.jp/naid/500000375379). The left half of the emotion map is lined with emotions that belong to an area called "reaction" where sensation is dominant. The right half of the emotion map is lined with emotions that belong to an area called "situation" where situation recognition is dominant.

The emotion map defines two emotions that encourage learning. The first is the negative emotion around the middle of "repentance" or "reflection" on the situation side. In other words, this is 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 the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

The emotion identification model 59 inputs user input to 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 learning 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 Figure 10. Figure 10 shows an example in which multiple emotions, "peace of mind," "calm," and "reassuring," have similar emotion values.

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.

In the above embodiment, an example has been described in which the specific processing program 56 is stored in the storage 32, 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 Universal Serial Bus (USB) 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.

The specific processing program 56 may also 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.

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.

The various processors listed below can be used as hardware resources for executing specific processes. Examples of processors include a CPU, which is a general-purpose processor that functions as a hardware resource for executing specific processes by executing software, i.e., a program. Examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which are processors with a circuit configuration designed specifically to execute specific processes. All of these processors have built-in or connected memory, and all of these processors execute specific processes by using the memory.

The hardware resource that executes the specific process may be composed of one of these various processors, or may be composed of a combination of two or more processors of the same or different types (e.g., a combination of multiple FPGAs, or a combination of a CPU and an FPGA). The hardware resource that executes the specific process may also be a single processor.

As an example of a configuration using a single processor, first, there is a configuration in which one processor is configured by combining one or more CPUs with software, and this processor functions as a hardware resource that executes a specific process. Secondly, there is a configuration in which a processor is used that realizes the functions of the 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 various processors mentioned above as hardware resources.

More specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processing described above is merely an example. It goes without saying that unnecessary steps can be deleted, new steps can be added, and the processing order can be changed without departing from the spirit of the invention.

In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are only examples, and they may be combined with each other, or may be other devices. Also, in the above example, the first and second embodiments have been described separately, but these may be combined.

The above 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 explanation of the configuration, function, action, and effect is an explanation of an example of the configuration, function, action, and effect 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 description and illustrations, within the scope of the gist of the technology of the present disclosure. Also, in order to avoid confusion and to make it easier to understand the parts related to the technology of the present disclosure, the above description and illustrations omit explanations of technical common sense that do not require particular explanation to enable the implementation of the technology of the present disclosure.

All publications, patent applications, and technical standards mentioned in this specification are incorporated by reference into this specification to the same extent as if each individual publication, patent application, and technical standard was specifically and individually indicated to be incorporated by reference.

(Appendix 1)
A reception section for inputting the contents of the talk;
an analysis unit that analyzes the contents of the speech and the tone of voice input by the reception unit;
a summary section for summarizing the issues of the story analyzed by the analysis section;
A suggestion unit that proposes an appropriate solution based on the issues summarized by the summary unit.
(Appendix 2)
The system according to claim 1, further comprising a reference section for referring to specific past cases or success stories.
(Appendix 3)
The system according to claim 1, further comprising an evaluation unit for evaluating the reliability of the solution.
(Appendix 4)
The system according to claim 1, further comprising a feedback unit for receiving feedback from a user.
(Appendix 5)
The analysis unit includes:
The system according to claim 1, characterized in that it analyzes the content of the speech and specifically identifies which parts are at issue.
(Appendix 6)
The analysis unit includes:
The system according to claim 1, characterized in that it analyzes tone of voice and specifically grasps the intensity of emotions and degree of tension of the person concerned.
(Appendix 7)
The reception unit is
The system according to claim 1, further comprising: estimating a user's emotion; and adjusting a method of inputting speech content based on the estimated user's emotion.
(Appendix 8)
The reception unit is
The system according to claim 1, further comprising: analyzing a user's past input history and providing an optimal input interface.
(Appendix 9)
The reception unit is
2. The system of claim 1, wherein, as content of a conversation is entered, the input is filtered based specifically on the user's current situation or interests.
(Appendix 10)
The reception unit is
The system according to claim 1, further comprising: estimating a user's emotion; and determining a priority of input contents based on the estimated user's emotion.
(Appendix 11)
The reception unit is
The system according to claim 1, characterized in that when inputting content of a conversation, the system takes into account the user's geographical location information specifically and inputs content with high relevance with priority.
(Appendix 12)
The reception unit is
The system described in claim 1, characterized in that when the content of the story is input, the system analyzes the user's social media activity and inputs related content.
(Appendix 13)
The analysis unit includes:
The system according to claim 1, further comprising: estimating a user's emotion; and adjusting a method of analyzing the content of the speech based on the estimated user's emotion.
(Appendix 14)
The analysis unit includes:
The system according to claim 1, characterized in that when analyzing the content of a conversation, the system improves the accuracy of the analysis by referring to similar cases from the past.
(Appendix 15)
The analysis unit includes:
The system according to claim 1, wherein the analysis is performed taking into account attribute information of the user when analyzing the content of the conversation.
(Appendix 16)
The analysis unit includes:
The system according to claim 1, further comprising: estimating a user's emotion; and adjusting a display method of the analysis result based on the estimated user's emotion.
(Appendix 17)
The analysis unit includes:
The system according to claim 1, characterized in that when analyzing the content of a conversation, the analysis is performed taking into account geographical distribution.
(Appendix 18)
The analysis unit includes:
The system according to claim 1, further comprising: a processor for executing a processing step of processing the content of a conversation;
(Appendix 19)
The summary section includes:
The system of claim 1, further comprising: estimating a user's sentiment; and adjusting a way of formulating the issues based on the estimated user's sentiment.
(Appendix 20)
The summary section includes:
The system according to claim 1, characterized in that when summarizing issues, the system refers to past methods of summarizing and selects the most appropriate method.
(Appendix 21)
The summary section includes:
The system according to claim 1, characterized in that when summarizing issues, the summarization is performed taking into account user attribute information.
(Appendix 22)
The summary section includes:
The system according to claim 1, further comprising: estimating a user's emotion; and adjusting a display method of the summary result based on the estimated user's emotion.
(Appendix 23)
The summary section includes:
The system according to claim 1, characterized in that when summarizing issues, the summarization is performed taking into account geographical distribution.
(Appendix 24)
The summary section includes:
The system according to claim 1, characterized in that when summarizing issues, the accuracy of the summary is improved by referring to related literature.
(Appendix 25)
The suggestion unit,
The system of claim 1, further comprising: estimating a user's emotion; and adjusting a solution proposal method based on the estimated user's emotion.
(Appendix 26)
The suggestion unit,
The system according to claim 1, characterized in that when proposing a solution, the system makes an optimal proposal by referring to past successful examples.
(Appendix 27)
The suggestion unit,
The system according to claim 1, wherein when proposing a solution, the system takes into consideration attribute information of the user.
(Appendix 28)
The suggestion unit,
2. The system of claim 1, further comprising: estimating a user's emotion; and prioritizing suggestions based on the estimated user's emotion.
(Appendix 29)
The suggestion unit,
The system according to claim 1, characterized in that when proposing a solution, the proposal is made taking into account geographical distribution.
(Appendix 30)
The suggestion unit,
The system according to claim 1, further comprising: a step of: referring to related literature when proposing a solution to improve the accuracy of the proposal.
(Appendix 31)
The reference part is
The system according to claim 2, further comprising: a user's emotion estimation unit; and a reference case estimation unit that estimates the user's emotion and selects a reference case based on the estimated user's emotion.
(Appendix 32)
The reference part is
The system according to claim 2, wherein when selecting a reference case, the system refers to past successful cases to select an optimal case.
(Appendix 33)
The reference part is
The system according to claim 2, further comprising: estimating a user's emotion; and adjusting a display method of the reference case based on the estimated user's emotion.
(Appendix 34)
The reference part is
The system according to claim 2, wherein when selecting reference cases, the system selects the most suitable case taking into consideration geographical distribution.
(Appendix 35)
The evaluation unit is
4. The system of claim 3, further comprising: estimating a user's emotion; and adjusting a solution evaluation method based on the estimated user's emotion.
(Appendix 36)
The evaluation unit is
The system according to claim 3, further comprising: a step of: referencing past evaluation data when evaluating a solution to improve the accuracy of the evaluation.
(Appendix 37)
The evaluation unit is
The system according to claim 3, further comprising: estimating a user's emotion; and adjusting a method for displaying the evaluation result based on the estimated user's emotion.
(Appendix 38)
The evaluation unit is
The system of claim 3, further comprising: a geographical distribution of solutions being considered when evaluating the solutions.
(Appendix 39)
The feedback unit is
The system of claim 4, further comprising: estimating a user's emotion; and adjusting a feedback collection method based on the estimated user's emotion.
(Appendix 40)
The feedback unit is
The system according to claim 4, further comprising: a feedback collection system that, when collecting feedback, refers to past feedback data to improve the accuracy of the collection.
(Appendix 41)
The feedback unit is
The system of claim 4, further comprising: estimating a user's emotion; and adjusting a feedback display method based on the estimated user's emotion.
(Appendix 42)
The feedback unit is
The system according to claim 4, wherein the feedback is collected while taking into account geographical distribution.

10, 210, 310, 410 Data processing system 12 Data processing device 14 Smart device 214 Smart glasses 314 Headset type terminal 414 Robot

Claims (7)

A reception section for inputting the contents of the talk;
an analysis unit that analyzes the contents of the speech and the tone of voice input by the reception unit;
a summary section for summarizing the issues of the story analyzed by the analysis section;
A suggestion unit that proposes an appropriate solution based on the issues summarized by the summary unit. The system according to claim 1, further comprising a reference section for referring to specific past cases or success stories. The system according to claim 1 , further comprising an evaluation unit for evaluating reliability of the solution. The system according to claim 1 , further comprising a feedback unit for receiving feedback from a user. The analysis unit includes:
2. The system according to claim 1, further comprising: analyzing tone of voice to specifically grasp the intensity of emotion and degree of tension of the person concerned. The reception unit is
The system of claim 1 , further comprising: estimating a user's emotion; and adjusting a speech input method based on the estimated user's emotion. The reception unit is
The system according to claim 1, further comprising: analyzing a user's past input history and providing an optimal input interface.

Images