system

Abstract

An object of a system according to an embodiment is to detect a fight on an SNS at an early stage and to solve the fight by appropriately intervening.SOLUTION: A system according to an embodiment includes a fight detection unit, an arbitration unit, a cooldown setting unit, and a conflicting point arrangement unit. The fight detection unit analyzes the comments on the SNS and detects a sign of a fight. The arbitrator intervenes in the fight detected by the fight detector. The cool-down setting unit sets a cool-down time for the fight intervened by the arbitration unit. The conflicting point arrangement part arranges and presents conflicting points of opinions after the cool-down time set by the cool-down setting part.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has the problem that it is difficult to detect disputes on social media early and intervene appropriately to resolve them.

[0005] The system according to the embodiment aims to detect disputes on social media at an early stage and intervene appropriately to resolve the disputes. [Means for solving the problem]

[0006] The system according to the embodiment includes a fight detection unit, an arbitration unit, a cool-down setting unit, and a conflict resolution unit. The fight detection unit analyzes comments on social media to detect signs of a fight. The arbitration unit intervenes in a fight detected by the fight detection unit. The cool-down setting unit sets a cool-down time for a fight intervened in by the arbitration unit. The conflict resolution unit resolves and presents the conflicting opinions after the cool-down time set by the cool-down setting unit has elapsed. [Effects of the Invention]

[0007] The system according to the embodiment can detect disputes on social media at an early stage and intervene appropriately to resolve the disputes. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The PeaceTalk system according to an embodiment of the present invention is a system that uses a generation AI called "Arbitration-kun" to smartly resolve disputes and other troubles that occur on social media. This allows the PeaceTalk system to efficiently and smartly resolve disputes and other troubles on social media.

[0029] The PeaceTalk system according to the embodiment includes a fight detection unit, an arbitration unit, a cooldown setting unit, and a conflict resolution unit. The fight detection unit analyzes comments on social media to detect signs of a fight. For example, it analyzes comments containing emotional or aggressive language to detect signs of a fight. The fight detection unit can also detect signs of a fight based on specific keywords or phrases. For example, it can learn from past fight data and detect similar patterns. Furthermore, the fight detection unit can analyze posts on social media in real time to detect signs of a fight early. The arbitration unit intervenes in a fight detected by the fight detection unit. For example, a generation AI called "Arbitration-kun" appears in the thread as an arbitrator and conveys the comments of Person A and Person B to the other party in a gentle manner. The arbitration unit can also generate messages to soften emotional comments. For example, it can convey Person A's emotional comment to Person B in a gentle manner. The arbitration unit can also complement incomplete comments and convey them to the other party. The cool-down setting unit sets a cool-down time for arguments intervened by the mediation unit. For example, if an argument seems likely to escalate, the generation AI sends a message such as "Let's wait a while and discuss this again," limiting speech for a certain period of time. The cool-down setting unit can also predict the time it will take for the user's emotions to calm down and set an appropriate cool-down time. Furthermore, the cool-down setting unit can provide content that helps users relax during the cool-down time. The conflict resolution unit organizes and presents the points of disagreement after the cool-down time set by the cool-down setting unit. For example, the generation AI organizes and presents the points of disagreement in a format such as "Person A thinks this way about XX, while Person B thinks this way about △△." The conflict resolution unit can also visually organize the points of disagreement and present them as infographics. For example, it can display differences of opinion in graphs or charts. Furthermore, the conflict resolution unit can automatically generate solutions to conflicts and propose them to users. This enables the PeaceTalk system to efficiently and intelligently resolve arguments and disputes on social media.For example, it helps to prevent emotional remarks from escalating and allows for calm discussions. Also, by providing neutral advice and mediation from a third party, it makes it easier to resolve arguments that are difficult for the people involved to resolve on their own.

[0030] The fight detection unit analyzes a user's past posting history and learns specific patterns and trigger words, allowing it to detect signs of a fight early. For example, the fight detection unit uses a generation AI to analyze a user's past posting history and learn specific patterns and trigger words. For example, it stores comments and remarks from past fights in a database and uses this information to detect signs of a fight early. The fight detection unit also uses a generation AI to analyze a user's posting history and learn specific emotional words and phrases. For example, it identifies words that indicate "anger" or "aggression" and detects comments that contain these words. Furthermore, the fight detection unit uses a generation AI to analyze a user's past conversation patterns and detect signs of a fight early. For example, it learns conflict patterns that frequently occur between specific users and uses this information to detect signs of a fight. This allows it to detect signs of a fight early.

[0031] The fight detection unit can analyze voice input and detect emotional statements from voice tone and speed. For example, the generation AI in the fight detection unit analyzes voice input and detects emotional statements from voice tone and speed. For example, it analyzes changes in voice pitch and tempo to identify patterns indicating anger or excitement. The generation AI in the fight detection unit also analyzes voice data and detects specific emotional tones. For example, it identifies emotional statements based on changes in voice volume and rhythm. Furthermore, the generation AI in the fight detection unit analyzes voice input in real time to detect emotional statements. For example, it analyzes voice waveforms and spectra to identify patterns indicating heightened emotions. This makes it possible to detect emotional statements from voice tone and speed.

[0032] The fight detection unit can analyze image and video content to detect visual triggers. For example, the generation AI in the fight detection unit analyzes image and video content to detect visual triggers. For example, it identifies images that contain aggressive gestures and facial expressions. The generation AI in the fight detection unit also analyzes video data to detect specific visual patterns. For example, it automatically extracts scenes that indicate fights or conflicts. Furthermore, the generation AI in the fight detection unit uses image recognition technology to detect visual triggers. For example, it analyzes images that contain specific symbols and icons to detect signs of a fight early. This makes it possible to detect visual triggers from image and video content.

[0033] The conflict detection unit detects signs of conflict across different social media platforms in an integrated manner and can mediate across platforms. For example, the generation AI in the conflict detection unit collects data from different social media platforms and detects signs of conflict in an integrated manner. For example, it analyzes data from multiple platforms such as Twitter and Facebook. The conflict detection unit also detects signs of conflict across platforms in an integrated manner and mediates across platforms. For example, it centrally manages conflicts across different platforms. Furthermore, the conflict detection unit analyzes data from different social media platforms in real time and detects signs of conflict early. For example, it analyzes comments and posts from multiple platforms in an integrated manner. This allows for integrated detection of signs of conflict across different social media platforms and mediation across platforms.

[0034] The arbitration unit can refer to the user's past dialogue history and customize the optimal arbitration method for each individual user. For example, the generation AI in the arbitration unit refers to the user's past dialogue history and customizes the optimal arbitration method for each individual user. For example, it analyzes past dialogue patterns and generates the optimal arbitration message. The arbitration unit also analyzes the user's dialogue history and proposes an arbitration method suitable for each individual user. For example, it identifies the user's personality and preferences based on the content of past dialogue. Furthermore, the arbitration unit uses the generation AI to learn the user's past dialogue history and provide the optimal arbitration method for each individual user. For example, it customizes the arbitration message based on past success stories. This enables effective arbitration by referring to the user's past dialogue history and customizing the optimal arbitration method.

[0035] The arbitration unit can automatically generate neutral opinions from a third party to be used in arbitration. For example, the generation AI can automatically generate neutral opinions from a third party to be used in arbitration. For example, it can find a middle ground between conflicting opinions and generate a neutral message. The arbitration unit also automatically generates neutral opinions from a generation AI to present during arbitration. For example, it can generate a message that incorporates both opinions in a balanced manner. Furthermore, the arbitration unit automatically generates neutral opinions from a third party's perspective to be used in arbitration. For example, it can provide neutral comments to soften emotional remarks. This allows the automatic generation of neutral opinions from a third party to be used in arbitration, enabling fairer arbitration.

[0036] The arbitration unit can arbitrate in different languages ​​and handle international social media disputes. For example, the generation AI can arbitrate in different languages ​​and handle international social media disputes. For example, it can generate arbitration messages in multiple languages, such as English and French. The arbitration unit can also build a multilingual arbitration system using the generation AI to handle international users. For example, it can provide messages to resolve conflicts between different languages. Furthermore, the arbitration unit can arbitrate in different languages ​​in real time and resolve international social media disputes. For example, it can use a translation function to generate arbitration messages in multiple languages. This allows arbitration in different languages ​​to handle international social media disputes.

[0037] The arbitration unit can generate messages that take into account the user's cultural background. For example, the generation AI in the arbitration unit generates messages that take into account the user's cultural background. For example, it provides arbitration messages that take into account specific cultures and customs. The arbitration unit also customizes arbitration messages based on cultural background. For example, it generates messages to resolve misunderstandings between different cultures. Furthermore, the arbitration unit uses the generation AI to analyze the user's cultural background and provide arbitration messages based on that. For example, it generates messages that respect cultural differences. This enables more effective arbitration by generating messages that take into account the user's cultural background.

[0038] The cool-down setting unit can learn the user's past behavioral patterns and individually set the optimal cool-down time. In the cool-down setting unit, for example, the generation AI learns the user's past behavioral patterns and individually sets the optimal cool-down time. For example, the cool-down time is adjusted based on past dialogue history. In addition, the cool-down setting unit analyzes the user's behavioral patterns and individually sets the optimal cool-down time. For example, it predicts the time it will take for the heightened emotions to subside. Furthermore, in the cool-down setting unit, the generation AI learns the user's past behavioral data and provides the optimal cool-down time. For example, it adjusts the cool-down time based on past dialogue history. In this way, an effective cool-down can be achieved by learning the user's past behavioral patterns and individually setting the optimal cool-down time.

[0039] The cool-down setting unit can provide content that allows the user to relax during the cool-down time. For example, the cool-down setting unit allows the generation AI to provide music that allows the user to relax during the cool-down time. For example, the cool-down setting unit automatically plays relaxing music that matches the user's preferences. The cool-down setting unit also allows the generation AI to provide videos that allow the user to relax during the cool-down time. For example, the cool-down setting unit automatically plays videos of natural scenery or soothing content. The cool-down setting unit also allows the generation AI to provide content that allows the user to relax during the cool-down time. For example, the cool-down setting unit automatically plays videos of meditation guides or relaxation exercises. This allows the user to effectively calm their emotions by providing relaxing content during the cool-down time.

[0040] The cool-down setting unit can ask reflection questions to the user during the cool-down time to encourage self-reflection. For example, the generation AI may ask reflection questions to the user during the cool-down time. For example, the cool-down setting unit may present a question such as, "What do you think was the problem in this conversation?" The generation AI may also ask questions to encourage self-reflection to the user during the cool-down time. For example, the cool-down setting unit may present a question such as, "How do you think you should respond next time?" The generation AI may also ask reflection questions to the user during the cool-down time to encourage self-reflection. For example, the cool-down setting unit may present a question such as, "What did you learn from this conversation?" In this way, by asking reflection questions during the cool-down time to encourage self-reflection, it is possible to promote a calm response by the user.

[0041] The cool-down setting unit can provide positive feedback to the user during the cool-down time. For example, the cool-down setting unit provides positive feedback to the user during the cool-down time of the generation AI. For example, it displays a message such as "It's great that you were able to respond calmly." Furthermore, the cool-down setting unit provides positive feedback to the user during the cool-down time of the generation AI. For example, it displays a message such as "Your opinion is very important." Furthermore, the cool-down setting unit provides positive feedback to the user during the cool-down time of the generation AI. For example, it displays a message such as "It's great that you were able to continue the discussion calmly." In this way, by providing positive feedback during the cool-down time, the user's emotions can be effectively calmed.

[0042] The conflict point sorting unit can visually organize the conflict points and present them as infographics. In the conflict point sorting unit, for example, the generation AI visually organizes the conflict points and presents them as infographics. For example, differences in opinion are displayed in graphs or charts. In addition, the conflict point sorting unit visually organizes the conflict points and presents them as infographics. For example, conflicting opinions are illustrated to make them easier to understand. In addition, the conflict point sorting unit visually organizes the conflict points and presents them as infographics. For example, differences in opinion are displayed in different colors to make them easier to understand visually. In this way, by visually organizing the conflict points and presenting them as infographics, it becomes easier for users to understand the conflict points.

[0043] The conflict resolution unit can automatically generate solutions to conflicts and propose them to the user. In the conflict resolution unit, for example, the generation AI automatically generates solutions to conflicts and proposes them to the user. For example, it may present a compromise that incorporates the opinions of both parties. In addition, the conflict resolution unit automatically generates solutions to conflicts and proposes them to the user. For example, it may present a specific action plan for reconciling conflicting opinions. In addition, the conflict resolution unit automatically generates solutions to conflicts and proposes them to the user. For example, it may present a new idea that combines the opinions of both parties. In this way, constructive discussions are promoted by automatically generating solutions to conflicts and proposing them to the user.

[0044] The conflict point sorting unit can sort conflict points in different languages, making them easier to understand for international users. For example, the generation AI in the conflict point sorting unit sorts conflict points in different languages, making them easier to understand for international users. For example, the conflict points are presented in multiple languages, such as English and French. The generation AI in the conflict point sorting unit also builds a multilingual conflict point sorting system to accommodate international users. For example, conflict points across different languages ​​are centrally managed. Furthermore, the conflict point sorting unit sorts conflict points in different languages ​​in real time, making them easier to understand for international users. For example, the translation function is used to present conflict points in multiple languages. This allows conflict points to be sorted in different languages, making them easier to understand for international users, making it possible to respond to international SNS troubles.

[0045] The conflict point sorting unit can sort conflict points from different perspectives and encourage multifaceted understanding. In the conflict point sorting unit, for example, the generation AI sorts conflict points from different perspectives and encourages multifaceted understanding. For example, it analyzes both opinions from different perspectives and presents the conflict points. In addition, the conflict point sorting unit organizes conflict points from multiple perspectives and presents them to the user. For example, it interprets conflicting opinions from different perspectives to make them easier to understand. In addition, the conflict point sorting unit organizes conflict points from different perspectives and encourages multifaceted understanding. For example, it analyzes conflict points from multiple perspectives and presents them to the user. In this way, the conflict points are sorted from different perspectives and encouraged to be understood from multiple perspectives, allowing the user to gain a deeper understanding of the conflict points.

[0046] The system's generating AI can learn from past arbitration history and utilize it in the next arbitration. For example, the generating AI can learn from past arbitration history and utilize it in the next arbitration. For example, it can generate optimal arbitration messages based on past success stories. The system also allows the generating AI to analyze arbitration history and extract information useful for the next arbitration. For example, it can customize arbitration messages based on past dialogue patterns. The system also allows the generating AI to learn from past arbitration history and utilize it in the next arbitration. For example, it can propose the optimal arbitration method based on past arbitration results. This allows the system to learn from past arbitration history and utilize it in the next arbitration, enabling more effective arbitration.

[0047] The system allows the generating AI to evaluate the user's progress during arbitration and provide feedback. For example, the system allows the generating AI to evaluate the user's progress during arbitration and provide feedback. For example, positive feedback is displayed if the user is able to respond calmly. The system also allows the generating AI to evaluate the progress of arbitration in real time and provide feedback to the user. For example, it analyzes the content of the user's comments and points out areas for improvement. Furthermore, the system allows the generating AI to continuously evaluate the progress of arbitration and provide feedback to the user. For example, it analyzes the user's dialogue patterns and displays appropriate advice. This allows the system to evaluate the user's progress during arbitration and provide feedback, thereby promoting user growth.

[0048] The system can provide consistent arbitration by having the generating AI integrate arbitration histories across different social media platforms. For example, the system integrates data from multiple platforms, such as Twitter and Facebook. The system also integrates cross-platform arbitration histories and provides consistent arbitration. For example, it centrally manages conflicts across different platforms. Furthermore, the system integrates arbitration histories across different social media platforms in real time and provides consistent arbitration. For example, it comprehensively analyzes comments and posts from multiple platforms. This enables effective arbitration by integrating arbitration histories across different social media platforms and providing consistent arbitration.

[0049] The system allows the generation AI to generate messages that take into account the user's cultural background. For example, the system allows the generation AI to generate messages that take into account the user's cultural background. For example, the system provides an arbitration message that takes into account a specific culture or customs. The system also allows the generation AI to customize arbitration messages based on cultural background. For example, the system generates a message to resolve misunderstandings between different cultures. Furthermore, the system allows the generation AI to analyze the user's cultural background and provide an arbitration message based on that. For example, the system generates a message that respects cultural differences. This enables effective arbitration by generating messages that take into account the user's cultural background.

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

[0051] The PeaceTalk system can also refer to a user's past dialogue history to customize the optimal arbitration method for each individual user. For example, it can analyze past dialogue patterns and generate the optimal arbitration message. The generation AI can also analyze the user's dialogue history and suggest an arbitration method that is suitable for each individual user. Furthermore, customizing arbitration messages based on past success stories enables effective arbitration.

[0052] The PeaceTalk system can comprehensively detect signs of conflict across different social media platforms and mediate across platforms. For example, it can analyze data from multiple platforms, such as Twitter and Facebook, to comprehensively detect signs of conflict. Generative AI can also detect signs of conflict across platforms and mediate across platforms. Furthermore, comprehensive analysis of comments and posts from multiple platforms can detect signs of conflict across different social media platforms early on, enabling effective mediation.

[0053] The PeaceTalk system can automatically generate neutral third-party opinions to aid in arbitration. For example, it can find a middle ground between opposing opinions and generate a neutral message. The generative AI can also automatically generate neutral opinions and present them during arbitration. Furthermore, by providing neutral comments to soften emotional remarks, the system can automatically generate neutral third-party opinions, enabling fairer arbitration.

[0054] The PeaceTalk system's generation AI can arbitrate in different languages, making it possible to handle international social media disputes. For example, it can generate arbitration messages in multiple languages, including English and French. It is also possible to build a multilingual arbitration system to accommodate international users. Furthermore, by using the translation function to generate arbitration messages in multiple languages, arbitration can be conducted in different languages, making it possible to handle international social media disputes.

[0055] The PeaceTalk system's AI can generate messages that take into account the user's cultural background. For example, it can provide arbitration messages that take into account specific cultures and customs. It can also customize arbitration messages based on cultural background. Furthermore, by generating messages that respect cultural differences, it can generate messages that take into account the user's cultural background, enabling effective arbitration.

[0056] The PeaceTalk system's generative AI can learn from past arbitration history and apply it to the next arbitration. For example, it can generate optimal arbitration messages based on past success stories. It can also analyze arbitration history and extract information that will be useful for the next arbitration. Furthermore, by proposing the optimal arbitration method based on past arbitration results, it can learn from past arbitration history and apply it to the next arbitration.

[0057] The processing flow of the first embodiment will be briefly explained below.

[0058] Step 1: The fight detection unit analyzes comments on social media to detect signs of a fight. For example, it analyzes comments that contain emotional language or aggressive remarks to detect signs of a fight. It can also detect signs of a fight based on specific keywords or phrases. It can also learn from data on past fights and detect similar patterns. The fight detection unit analyzes the content of posts on social media in real time to detect signs of a fight at an early stage. Step 2: The arbitration unit intervenes in fights detected by the fight detection unit. For example, a generation AI called "Arbitration-kun" appears in the thread as an arbitrator, and conveys the statements of Person A and Person B to the other person in a gentle manner. It can also generate messages to soften emotional statements, and convey Person A's emotional statements to Person B in a gentle manner. It can also complement statements that are not clear enough and convey them to the other person. Step 3: The cool-down setting unit sets a cool-down time for the fight intervened by the mediation unit. For example, if the fight is about to escalate, the generation AI can send a message such as "Let's wait a little while and discuss it again," limiting speech for a certain period of time. It can also predict how long it will take for the user's emotions to calm down and set an appropriate cool-down time. It can also provide content that will help the user relax during the cool-down time. Step 4: The conflict resolution unit organizes and presents the conflicting points of opinion after the cool-down time set by the cool-down setting unit. For example, the generation AI organizes and presents the conflicting points in the form of "Person A thinks this way about XX, while Person B thinks this way about △△." It can also visually organize the conflicting points and present them as infographics. For example, it can display differences in opinion in graphs or charts. It can also automatically generate solutions to the conflicting points and propose them to the user.

[0059] (Example 2) The PeaceTalk system according to an embodiment of the present invention is a system that uses a generation AI called "Arbitration-kun" to smartly resolve disputes and other troubles that occur on social media. This allows the PeaceTalk system to efficiently and smartly resolve disputes and other troubles on social media.

[0060] The PeaceTalk system according to the embodiment includes a fight detection unit, an arbitration unit, a cooldown setting unit, and a conflict resolution unit. The fight detection unit analyzes comments on social media to detect signs of a fight. For example, it analyzes comments containing emotional or aggressive language to detect signs of a fight. The fight detection unit can also detect signs of a fight based on specific keywords or phrases. For example, it can learn from past fight data and detect similar patterns. Furthermore, the fight detection unit can analyze posts on social media in real time to detect signs of a fight early. The arbitration unit intervenes in a fight detected by the fight detection unit. For example, a generation AI called "Arbitration-kun" appears in the thread as an arbitrator and conveys the comments of Person A and Person B to the other party in a gentle manner. The arbitration unit can also generate messages to soften emotional comments. For example, it can convey Person A's emotional comment to Person B in a gentle manner. The arbitration unit can also complement incomplete comments and convey them to the other party. The cool-down setting unit sets a cool-down time for arguments intervened by the mediation unit. For example, if an argument seems likely to escalate, the generation AI sends a message such as "Let's wait a while and discuss this again," limiting speech for a certain period of time. The cool-down setting unit can also predict the time it will take for the user's emotions to calm down and set an appropriate cool-down time. Furthermore, the cool-down setting unit can provide content that helps users relax during the cool-down time. The conflict resolution unit organizes and presents the points of disagreement after the cool-down time set by the cool-down setting unit. For example, the generation AI organizes and presents the points of disagreement in a format such as "Person A thinks this way about XX, while Person B thinks this way about △△." The conflict resolution unit can also visually organize the points of disagreement and present them as infographics. For example, it can display differences of opinion in graphs or charts. Furthermore, the conflict resolution unit can automatically generate solutions to conflicts and propose them to users. This enables the PeaceTalk system to efficiently and intelligently resolve arguments and disputes on social media.For example, it helps to prevent emotional remarks from escalating and allows for calm discussions. Also, by providing neutral advice and mediation from a third party, it makes it easier to resolve arguments that are difficult for the people involved to resolve on their own.

[0061] The fight detection unit analyzes a user's past posting history and learns specific patterns and trigger words, allowing it to detect signs of a fight early. For example, the fight detection unit uses a generation AI to analyze a user's past posting history and learn specific patterns and trigger words. For example, it stores comments and remarks from past fights in a database and uses this information to detect signs of a fight early. The fight detection unit also uses a generation AI to analyze a user's posting history and learn specific emotional words and phrases. For example, it identifies words that indicate "anger" or "aggression" and detects comments that contain these words. Furthermore, the fight detection unit uses a generation AI to analyze a user's past conversation patterns and detect signs of a fight early. For example, it learns conflict patterns that frequently occur between specific users and uses this information to detect signs of a fight. This allows it to detect signs of a fight early.

[0062] The fight detection unit can analyze voice input and detect emotional statements from voice tone and speed. For example, the generation AI in the fight detection unit analyzes voice input and detects emotional statements from voice tone and speed. For example, it analyzes changes in voice pitch and tempo to identify patterns indicating anger or excitement. The generation AI in the fight detection unit also analyzes voice data and detects specific emotional tones. For example, it identifies emotional statements based on changes in voice volume and rhythm. Furthermore, the generation AI in the fight detection unit analyzes voice input in real time to detect emotional statements. For example, it analyzes voice waveforms and spectra to identify patterns indicating heightened emotions. This makes it possible to detect emotional statements from voice tone and speed.

[0063] The fight detection unit can use the emotion estimation function to monitor the user's emotional state in real time and issue a warning when the user's emotions become heightened. The fight detection unit, for example, uses the emotion estimation function to monitor the user's emotional state in real time. For example, it analyzes the user's input content and behavioral patterns to detect heightened emotions. The fight detection unit also uses the emotion estimation function to analyze the user's emotional state in real time and issue a warning when the user's emotions become heightened. For example, it displays a warning message when the emotion score exceeds a certain threshold. Furthermore, the fight detection unit uses the emotion estimation function to continuously monitor the user's emotional state and automatically issue a warning when the user's emotions become heightened. For example, it tracks changes in emotions in real time and displays a warning at an appropriate time. This makes it possible to monitor the user's emotional state in real time and issue a warning when the user's emotions become heightened.

[0064] The fight detection unit can analyze image and video content to detect visual triggers. For example, the generation AI in the fight detection unit analyzes image and video content to detect visual triggers. For example, it identifies images that contain aggressive gestures and facial expressions. The generation AI in the fight detection unit also analyzes video data to detect specific visual patterns. For example, it automatically extracts scenes that indicate fights or conflicts. Furthermore, the generation AI in the fight detection unit uses image recognition technology to detect visual triggers. For example, it analyzes images that contain specific symbols and icons to detect signs of a fight early. This makes it possible to detect visual triggers from image and video content.

[0065] The conflict detection unit detects signs of conflict across different social media platforms in an integrated manner and can mediate across platforms. For example, the generation AI in the conflict detection unit collects data from different social media platforms and detects signs of conflict in an integrated manner. For example, it analyzes data from multiple platforms such as Twitter and Facebook. The conflict detection unit also detects signs of conflict across platforms in an integrated manner and mediates across platforms. For example, it centrally manages conflicts across different platforms. Furthermore, the conflict detection unit analyzes data from different social media platforms in real time and detects signs of conflict early. For example, it analyzes comments and posts from multiple platforms in an integrated manner. This allows for integrated detection of signs of conflict across different social media platforms and mediation across platforms.

[0066] The fight detection unit can use the emotion estimation function to predict emotional statements before a user posts and display a warning before the post. The fight detection unit, for example, uses the emotion estimation function to predict emotional statements before a user posts. For example, it analyzes input content in real time and detects heightened emotions. The fight detection unit also uses the emotion estimation function to predict emotional statements before a user posts and display a warning. For example, it displays a warning message when the emotion score exceeds a certain threshold. Furthermore, the fight detection unit uses the emotion estimation function to predict emotional statements before a user posts and suggest appropriate actions. For example, it displays advice to stay calm. In this way, by predicting emotional statements before a user posts and displaying a warning, fights can be prevented from occurring.

[0067] The arbitration unit can refer to the user's past dialogue history and customize the optimal arbitration method for each individual user. For example, the generation AI in the arbitration unit refers to the user's past dialogue history and customizes the optimal arbitration method for each individual user. For example, it analyzes past dialogue patterns and generates the optimal arbitration message. The arbitration unit also analyzes the user's dialogue history and proposes an arbitration method suitable for each individual user. For example, it identifies the user's personality and preferences based on the content of past dialogue. Furthermore, the arbitration unit uses the generation AI to learn the user's past dialogue history and provide the optimal arbitration method for each individual user. For example, it customizes the arbitration message based on past success stories. This enables effective arbitration by referring to the user's past dialogue history and customizing the optimal arbitration method.

[0068] The arbitration unit can automatically generate neutral opinions from a third party to be used in arbitration. For example, the generation AI can automatically generate neutral opinions from a third party to be used in arbitration. For example, it can find a middle ground between conflicting opinions and generate a neutral message. The arbitration unit also automatically generates neutral opinions from a generation AI to present during arbitration. For example, it can generate a message that incorporates both opinions in a balanced manner. Furthermore, the arbitration unit automatically generates neutral opinions from a third party's perspective to be used in arbitration. For example, it can provide neutral comments to soften emotional remarks. This allows the automatic generation of neutral opinions from a third party to be used in arbitration, enabling fairer arbitration.

[0069] The arbitration unit can use the emotion estimation function to generate an optimal arbitration message according to the user's emotional state. The arbitration unit, for example, uses the emotion estimation function to generate an optimal arbitration message according to the user's emotional state. For example, it generates a message to calm down based on the emotion score. The arbitration unit also uses the emotion estimation function to analyze the user's emotional state in real time and provide an optimal arbitration message. For example, it displays advice to calm down emotionally charged users. Furthermore, the arbitration unit uses the emotion estimation function to customize the arbitration message according to the user's emotional state. For example, it selects appropriate wording and tone based on the emotion score. This enables effective arbitration by generating an optimal arbitration message according to the user's emotional state.

[0070] The arbitration unit can arbitrate in different languages ​​and handle international social media disputes. For example, the generation AI can arbitrate in different languages ​​and handle international social media disputes. For example, it can generate arbitration messages in multiple languages, such as English and French. The arbitration unit can also build a multilingual arbitration system using the generation AI to handle international users. For example, it can provide messages to resolve conflicts between different languages. Furthermore, the arbitration unit can arbitrate in different languages ​​in real time and resolve international social media disputes. For example, it can use a translation function to generate arbitration messages in multiple languages. This allows arbitration in different languages ​​to handle international social media disputes.

[0071] The arbitration unit can generate messages that take into account the user's cultural background. For example, the generation AI in the arbitration unit generates messages that take into account the user's cultural background. For example, it provides arbitration messages that take into account specific cultures and customs. The arbitration unit also customizes arbitration messages based on cultural background. For example, it generates messages to resolve misunderstandings between different cultures. Furthermore, the arbitration unit uses the generation AI to analyze the user's cultural background and provide arbitration messages based on that. For example, it generates messages that respect cultural differences. This enables more effective arbitration by generating messages that take into account the user's cultural background.

[0072] The arbitration unit can use the emotion estimation function to monitor the user's emotions in real time during arbitration and intervene at the appropriate time. The arbitration unit, for example, uses the emotion estimation function to monitor the user's emotions in real time during arbitration. For example, it intervenes at the appropriate time when the emotion score increases. The arbitration unit also uses the emotion estimation function to analyze the user's emotional state in real time and adjust the timing of arbitration. For example, it displays an intervention message when it detects an increase in emotion. Furthermore, the arbitration unit uses the emotion estimation function to continuously monitor the user's emotions during arbitration and provide an arbitration message at the appropriate time. For example, it adjusts the timing of arbitration according to changes in emotion. This enables effective arbitration by monitoring the user's emotions in real time during arbitration and intervening at the appropriate time.

[0073] The cool-down setting unit can learn the user's past behavioral patterns and individually set the optimal cool-down time. In the cool-down setting unit, for example, the generation AI learns the user's past behavioral patterns and individually sets the optimal cool-down time. For example, the cool-down time is adjusted based on past dialogue history. In addition, the cool-down setting unit analyzes the user's behavioral patterns and individually sets the optimal cool-down time. For example, it predicts the time it will take for the heightened emotions to subside. Furthermore, in the cool-down setting unit, the generation AI learns the user's past behavioral data and provides the optimal cool-down time. For example, it adjusts the cool-down time based on past dialogue history. In this way, an effective cool-down can be achieved by learning the user's past behavioral patterns and individually setting the optimal cool-down time.

[0074] The cool-down setting unit can provide content that allows the user to relax during the cool-down time. For example, the cool-down setting unit allows the generation AI to provide music that allows the user to relax during the cool-down time. For example, the cool-down setting unit automatically plays relaxing music that matches the user's preferences. The cool-down setting unit also allows the generation AI to provide videos that allow the user to relax during the cool-down time. For example, the cool-down setting unit automatically plays videos of natural scenery or soothing content. The cool-down setting unit also allows the generation AI to provide content that allows the user to relax during the cool-down time. For example, the cool-down setting unit automatically plays videos of meditation guides or relaxation exercises. This allows the user to effectively calm their emotions by providing relaxing content during the cool-down time.

[0075] The cool-down setting unit can end the cool-down time after confirming that the user's emotions have calmed down using the emotion estimation function. The cool-down setting unit, for example, uses the emotion estimation function to confirm that the user's emotions have calmed down before ending the cool-down time. For example, the cool-down time ends when the emotion score falls below a certain threshold. The cool-down setting unit also uses the emotion estimation function to analyze the user's emotional state in real time and confirm that the emotions have calmed down. For example, the cool-down setting unit monitors changes in emotions and ends the cool-down time at an appropriate timing. Furthermore, the cool-down setting unit uses the emotion estimation function to confirm that the user's emotions have calmed down before ending the cool-down time. For example, the cool-down setting unit ends the cool-down time when the emotion score stabilizes. This enables an effective cool-down by ending the cool-down time after confirming that the user's emotions have calmed down.

[0076] The cool-down setting unit can ask reflection questions to the user during the cool-down time to encourage self-reflection. For example, the generation AI may ask reflection questions to the user during the cool-down time. For example, the cool-down setting unit may present a question such as, "What do you think was the problem in this conversation?" The generation AI may also ask questions to encourage self-reflection to the user during the cool-down time. For example, the cool-down setting unit may present a question such as, "How do you think you should respond next time?" The generation AI may also ask reflection questions to the user during the cool-down time to encourage self-reflection. For example, the cool-down setting unit may present a question such as, "What did you learn from this conversation?" In this way, by asking reflection questions during the cool-down time to encourage self-reflection, it is possible to promote a calm response by the user.

[0077] The cool-down setting unit can provide positive feedback to the user during the cool-down time. For example, the cool-down setting unit provides positive feedback to the user during the cool-down time of the generation AI. For example, it displays a message such as "It's great that you were able to respond calmly." Furthermore, the cool-down setting unit provides positive feedback to the user during the cool-down time of the generation AI. For example, it displays a message such as "Your opinion is very important." Furthermore, the cool-down setting unit provides positive feedback to the user during the cool-down time of the generation AI. For example, it displays a message such as "It's great that you were able to continue the discussion calmly." In this way, by providing positive feedback during the cool-down time, the user's emotions can be effectively calmed.

[0078] The cool-down setting unit can use the emotion estimation function to monitor the user's emotional changes during the cool-down time and encourage the user to resume at an appropriate time. The cool-down setting unit, for example, uses the emotion estimation function to monitor the user's emotional changes during the cool-down time. For example, it displays a message encouraging the user to resume when the emotion score stabilizes. The cool-down setting unit also uses the emotion estimation function to analyze the user's emotional changes during the cool-down time in real time and encourages the user to resume at an appropriate time. For example, it displays a message encouraging the user to resume when the emotion level subsides. The cool-down setting unit also uses the emotion estimation function to continuously monitor the user's emotional changes during the cool-down time and encourages the user to resume at an appropriate time. For example, it displays a message encouraging the user to resume when the emotion score falls below a certain threshold. In this way, an effective cool-down can be achieved by monitoring the user's emotional changes during the cool-down time and encouraging the user to resume at an appropriate time.

[0079] The conflict point sorting unit can visually organize the conflict points and present them as infographics. In the conflict point sorting unit, for example, the generation AI visually organizes the conflict points and presents them as infographics. For example, differences in opinion are displayed in graphs or charts. In addition, the conflict point sorting unit visually organizes the conflict points and presents them as infographics. For example, conflicting opinions are illustrated to make them easier to understand. In addition, the conflict point sorting unit visually organizes the conflict points and presents them as infographics. For example, differences in opinion are displayed in different colors to make them easier to understand visually. In this way, by visually organizing the conflict points and presenting them as infographics, it becomes easier for users to understand the conflict points.

[0080] The conflict resolution unit can automatically generate solutions to conflicts and propose them to the user. In the conflict resolution unit, for example, the generation AI automatically generates solutions to conflicts and proposes them to the user. For example, it may present a compromise that incorporates the opinions of both parties. In addition, the conflict resolution unit automatically generates solutions to conflicts and proposes them to the user. For example, it may present a specific action plan for reconciling conflicting opinions. In addition, the conflict resolution unit automatically generates solutions to conflicts and proposes them to the user. For example, it may present a new idea that combines the opinions of both parties. In this way, constructive discussions are promoted by automatically generating solutions to conflicts and proposing them to the user.

[0081] The conflict point sorting unit can use the emotion estimation function to analyze the user's emotional reaction to the conflict point and make suggestions to alleviate the emotional conflict. The conflict point sorting unit, for example, uses the emotion estimation function to analyze the user's emotional reaction to the conflict point. For example, it makes suggestions to alleviate the emotional conflict based on the emotion score. The conflict point sorting unit also uses the emotion estimation function to analyze the user's emotional reaction to the conflict point in real time and make suggestions to alleviate the emotional conflict. For example, it provides advice to calm down the emotional upsurge. Furthermore, the conflict point sorting unit uses the emotion estimation function to continuously monitor the user's emotional reaction to the conflict point and make suggestions to alleviate the emotional conflict. For example, it displays a message to calm down when the emotion score increases. In this way, constructive discussions are promoted by analyzing the user's emotional reaction to the conflict point and making suggestions to alleviate the emotional conflict.

[0082] The conflict point sorting unit can sort conflict points in different languages, making them easier to understand for international users. For example, the generation AI in the conflict point sorting unit sorts conflict points in different languages, making them easier to understand for international users. For example, the conflict points are presented in multiple languages, such as English and French. The generation AI in the conflict point sorting unit also builds a multilingual conflict point sorting system to accommodate international users. For example, conflict points across different languages ​​are centrally managed. Furthermore, the conflict point sorting unit sorts conflict points in different languages ​​in real time, making them easier to understand for international users. For example, the translation function is used to present conflict points in multiple languages. This allows conflict points to be sorted in different languages, making them easier to understand for international users, making it possible to respond to international SNS troubles.

[0083] The conflict point sorting unit can sort conflict points from different perspectives and encourage multifaceted understanding. In the conflict point sorting unit, for example, the generation AI sorts conflict points from different perspectives and encourages multifaceted understanding. For example, it analyzes both opinions from different perspectives and presents the conflict points. In addition, the conflict point sorting unit organizes conflict points from multiple perspectives and presents them to the user. For example, it interprets conflicting opinions from different perspectives to make them easier to understand. In addition, the conflict point sorting unit organizes conflict points from different perspectives and encourages multifaceted understanding. For example, it analyzes conflict points from multiple perspectives and presents them to the user. In this way, the conflict points are sorted from different perspectives and encouraged to be understood from multiple perspectives, allowing the user to gain a deeper understanding of the conflict points.

[0084] The conflict point sorting unit can use the emotion estimation function to monitor the user's emotion regarding the conflict point in real time and present it at an appropriate time. The conflict point sorting unit, for example, uses the emotion estimation function to monitor the user's emotion regarding the conflict point in real time. For example, it presents the conflict point when the emotion score increases. The conflict point sorting unit also uses the emotion estimation function to analyze the user's emotional state regarding the conflict point in real time and presents the conflict point at an appropriate time. For example, it presents the conflict point when the emotion level has subsided. Furthermore, the conflict point sorting unit also uses the emotion estimation function to continuously monitor the user's emotion regarding the conflict point and presents the conflict point at an appropriate time. For example, it presents the conflict point when the emotion score falls below a certain threshold. In this way, by monitoring the user's emotion regarding the conflict point in real time and presenting it at an appropriate time, it is possible to effectively sort the conflict point.

[0085] The system's generating AI can learn from past arbitration history and utilize it in the next arbitration. For example, the generating AI can learn from past arbitration history and utilize it in the next arbitration. For example, it can generate optimal arbitration messages based on past success stories. The system also allows the generating AI to analyze arbitration history and extract information useful for the next arbitration. For example, it can customize arbitration messages based on past dialogue patterns. The system also allows the generating AI to learn from past arbitration history and utilize it in the next arbitration. For example, it can propose the optimal arbitration method based on past arbitration results. This allows the system to learn from past arbitration history and utilize it in the next arbitration, enabling more effective arbitration.

[0086] The system allows the generating AI to evaluate the user's progress during arbitration and provide feedback. For example, the system allows the generating AI to evaluate the user's progress during arbitration and provide feedback. For example, positive feedback is displayed if the user is able to respond calmly. The system also allows the generating AI to evaluate the progress of arbitration in real time and provide feedback to the user. For example, it analyzes the content of the user's comments and points out areas for improvement. Furthermore, the system allows the generating AI to continuously evaluate the progress of arbitration and provide feedback to the user. For example, it analyzes the user's dialogue patterns and displays appropriate advice. This allows the system to evaluate the user's progress during arbitration and provide feedback, thereby promoting user growth.

[0087] The system can continuously monitor the user's emotional state using the emotion estimation function and resume arbitration at an appropriate time. For example, the system uses the emotion estimation function to continuously monitor the user's emotional state and resume arbitration at an appropriate time. For example, arbitration is resumed when the emotion score stabilizes. The system also uses the emotion estimation function to analyze the user's emotional state in real time and resume arbitration at an appropriate time. For example, arbitration is resumed when the emotional intensity subsides. The system also uses the emotion estimation function to continuously monitor the user's emotional state and resume arbitration at an appropriate time. For example, arbitration is resumed when the emotion score falls below a certain threshold. This enables effective arbitration by continuously monitoring the user's emotional state and resuming arbitration at an appropriate time.

[0088] The system can provide consistent arbitration by having the generating AI integrate arbitration histories across different social media platforms. For example, the system integrates data from multiple platforms, such as Twitter and Facebook. The system also integrates cross-platform arbitration histories and provides consistent arbitration. For example, it centrally manages conflicts across different platforms. Furthermore, the system integrates arbitration histories across different social media platforms in real time and provides consistent arbitration. For example, it comprehensively analyzes comments and posts from multiple platforms. This enables effective arbitration by integrating arbitration histories across different social media platforms and providing consistent arbitration.

[0089] The system allows the generation AI to generate messages that take into account the user's cultural background. For example, the system allows the generation AI to generate messages that take into account the user's cultural background. For example, the system provides an arbitration message that takes into account a specific culture or customs. The system also allows the generation AI to customize arbitration messages based on cultural background. For example, the system generates a message to resolve misunderstandings between different cultures. Furthermore, the system allows the generation AI to analyze the user's cultural background and provide an arbitration message based on that. For example, the system generates a message that respects cultural differences. This enables effective arbitration by generating messages that take into account the user's cultural background.

[0090] The system can use the emotion estimation function to monitor a user's emotions in real time during arbitration and intervene at an appropriate time. For example, the system uses the emotion estimation function to monitor a user's emotions in real time during arbitration. For example, it intervenes at an appropriate time when the emotion score increases. The system also uses the emotion estimation function to analyze a user's emotional state in real time and adjust the timing of arbitration. For example, it displays an intervention message when it detects an increase in emotion. Furthermore, the system uses the emotion estimation function to continuously monitor a user's emotions during arbitration and provides an arbitration message at an appropriate time. For example, it adjusts the timing of arbitration according to changes in emotion. This enables effective arbitration by monitoring a user's emotions in real time during arbitration and intervening at an appropriate time.

[0091] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0092] The PeaceTalk system can also refer to a user's past dialogue history to customize the optimal arbitration method for each individual user. For example, it can analyze past dialogue patterns and generate the optimal arbitration message. The generation AI can also analyze the user's dialogue history and suggest an arbitration method that is suitable for each individual user. Furthermore, customizing arbitration messages based on past success stories enables effective arbitration.

[0093] The PeaceTalk system can comprehensively detect signs of conflict across different social media platforms and mediate across platforms. For example, it can analyze data from multiple platforms, such as Twitter and Facebook, to comprehensively detect signs of conflict. Generative AI can also detect signs of conflict across platforms and mediate across platforms. Furthermore, comprehensive analysis of comments and posts from multiple platforms can detect signs of conflict across different social media platforms early on, enabling effective mediation.

[0094] The PeaceTalk system uses emotion estimation to predict emotional comments before users post them and displays a warning before posting. For example, it analyzes input content in real time to detect heightened emotions. It can also display a warning message if the emotion score exceeds a certain threshold. Furthermore, by displaying advice on how to stay calm, it can predict emotional comments before users post them and prevent arguments from occurring.

[0095] The PeaceTalk system can automatically generate neutral third-party opinions to aid in arbitration. For example, it can find a middle ground between opposing opinions and generate a neutral message. The generative AI can also automatically generate neutral opinions and present them during arbitration. Furthermore, by providing neutral comments to soften emotional remarks, the system can automatically generate neutral third-party opinions, enabling fairer arbitration.

[0096] The PeaceTalk system uses its emotion estimation function to monitor the user's emotions in real time during arbitration and intervene at the appropriate time. For example, it intervenes when the emotion score increases. It can also analyze the user's emotional state in real time and adjust the timing of arbitration. Furthermore, adjusting the timing of arbitration according to changes in emotions enables effective arbitration.

[0097] The PeaceTalk system's generation AI can arbitrate in different languages, making it possible to handle international social media disputes. For example, it can generate arbitration messages in multiple languages, including English and French. It is also possible to build a multilingual arbitration system to accommodate international users. Furthermore, by using the translation function to generate arbitration messages in multiple languages, arbitration can be conducted in different languages, making it possible to handle international social media disputes.

[0098] The PeaceTalk system uses its emotion estimation function to monitor changes in the user's emotions during the cool-down time and encourages them to resume at the appropriate time. For example, it can display a message encouraging them to resume when the emotion score stabilizes. It can also display a message encouraging them to resume when the emotion level subsides. Furthermore, by displaying a message encouraging them to resume when the emotion score falls below a certain threshold, it can enable an effective cool-down.

[0099] The PeaceTalk system's AI can generate messages that take into account the user's cultural background. For example, it can provide arbitration messages that take into account specific cultures and customs. It can also customize arbitration messages based on cultural background. Furthermore, by generating messages that respect cultural differences, it can generate messages that take into account the user's cultural background, enabling effective arbitration.

[0100] The PeaceTalk system uses its emotion estimation function to analyze the user's emotional response to conflicts and make suggestions to alleviate the emotional conflict. For example, it makes suggestions to alleviate emotional conflicts based on the emotion score. It can also provide advice to calm down when emotions become too high. Furthermore, by displaying a message to calm down when the emotion score becomes too high, the PeaceTalk system can analyze the user's emotional response to conflicts and make suggestions to alleviate the emotional conflict.

[0101] The PeaceTalk system's generative AI can learn from past arbitration history and apply it to the next arbitration. For example, it can generate optimal arbitration messages based on past success stories. It can also analyze arbitration history and extract information that will be useful for the next arbitration. Furthermore, by proposing the optimal arbitration method based on past arbitration results, it can learn from past arbitration history and apply it to the next arbitration.

[0102] The processing flow of the second embodiment will be briefly explained below.

[0103] Step 1: The fight detection unit analyzes comments on social media to detect signs of a fight. For example, it analyzes comments that contain emotional language or aggressive remarks to detect signs of a fight. It can also detect signs of a fight based on specific keywords or phrases. It can also learn from data on past fights and detect similar patterns. The fight detection unit analyzes the content of posts on social media in real time to detect signs of a fight at an early stage. Step 2: The arbitration unit intervenes in fights detected by the fight detection unit. For example, a generation AI called "Arbitration-kun" appears in the thread as an arbitrator, and conveys the statements of Person A and Person B to the other person in a gentle manner. It can also generate messages to soften emotional statements, and convey Person A's emotional statements to Person B in a gentle manner. It can also complement statements that are not clear enough and convey them to the other person. Step 3: The cool-down setting unit sets a cool-down time for the fight intervened by the mediation unit. For example, if the fight is about to escalate, the generation AI can send a message such as "Let's wait a little while and discuss it again," limiting speech for a certain period of time. It can also predict how long it will take for the user's emotions to calm down and set an appropriate cool-down time. It can also provide content that will help the user relax during the cool-down time. Step 4: The conflict resolution unit organizes and presents the conflicting points of opinion after the cool-down time set by the cool-down setting unit. For example, the generation AI organizes and presents the conflicting points in the form of "Person A thinks this way about XX, while Person B thinks this way about △△." It can also visually organize the conflicting points and present them as infographics. For example, it can display differences in opinion in graphs or charts. It can also automatically generate solutions to the conflicting points and propose them to the user.

[0104] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0105] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0106] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0107] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0108] 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.

[0109] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0110] 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.

[0111] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0112] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0113] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0114] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0115] 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.

[0116] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0117] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0118] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0119] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0120] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0121] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0122] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0123] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0124] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0125] 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.

[0126] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0127] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0128] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0129] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0130] 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.

[0131] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0132] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0133] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0134] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0135] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0136] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0137] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0138] 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.

[0139] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0140] 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.

[0141] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0143] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0144] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0145] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0146] 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.

[0147] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0148] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0149] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0150] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0151] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0152] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0153] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0154] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0155] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0156] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0157] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0158] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0159] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0160] 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.

[0161] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0162] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0163] 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.

[0164] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0165] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0166] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0167] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0168] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0169] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0170] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0171] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A fight detection unit that analyzes comments on social media and detects signs of a fight; an arbitration unit that intervenes in a fight detected by the fight detection unit; a cool-down setting unit that sets a cool-down time for a fight intervened by the arbitration unit; a conflict point sorting unit that sorts out and presents conflicting points of opinion after the cool-down time set by the cool-down setting unit has elapsed. A system characterized by:

2. The fight detection unit Analyze users' past posting history and learn specific patterns and trigger words to detect early signs of conflict.

2. The system of claim 1.

3. The fight detection unit Analyzes voice input and detects emotional statements from tone and speed 2. The system of claim 1.

4. The fight detection unit Monitors the user's emotional state in real time and issues alerts when emotions become heightened.

2. The system of claim 1.

5. The fight detection unit Analyzes image and video content to detect visual triggers 2. The system of claim 1.

6. The fight detection unit Integrated detection of conflict signs across different social media platforms and cross-platform mediation 2. The system of claim 1.

7. The fight detection unit Predict emotional comments before users post and display a warning before posting 2. The system of claim 1.

8. The arbitration chamber: Refer to the user's past interaction history to customize the optimal arbitration method for each individual user 2. The system of claim 1.

Images