System

Abstract

An object of a system according to an embodiment is to improve communication by automatically detecting a Logihara utterance and alerting a sender.SOLUTION: A system according to an embodiment includes a speech monitoring unit, a logic violation detection unit, and a warning message generation unit. The remark monitoring unit monitors the communication tool and the content of the chat. A Logihara detection part detects a Logihara utterance from the contents monitored by the utterance monitoring part. A warning message generation part generates a message for calling attention to the transmitter on the basis of the Logihara utterance detected by the Logihara detection 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 was unable to automatically detect logical harassment and warn the sender, posing a challenge to improving communication.

[0005] The system according to the embodiment aims to improve communication by automatically detecting logical harassment remarks and alerting the sender. [Means for solving the problem]

[0006] The system according to the embodiment includes a comment monitoring unit, a logical harassment detection unit, and a warning message generation unit. The comment monitoring unit monitors the content of communication tools and chats. The logical harassment detection unit detects logical harassment comments from the content monitored by the comment monitoring unit. The warning message generation unit generates a message to warn the sender of the logical harassment comment based on the logical harassment comment detected by the logical harassment detection unit. [Effects of the Invention]

[0007] The system according to the embodiment can improve communication by automatically detecting logical harassment remarks and alerting the sender. [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 logical harassment monitoring system according to an embodiment of the present invention is a system that monitors statements made at work that are intended to corner a colleague with logical reasoning, known as logical harassment, and points out the problem to the sender, thereby improving communication. This allows the sender to become aware of their own statements and improve the quality of communication.

[0029] A logical harassment monitoring system according to an embodiment includes a comment monitoring unit, a logical harassment detection unit, and a warning message generation unit. The comment monitoring unit monitors the content of communication tools and chats. For example, it monitors text messages, such as chat apps, video conferencing tools, and emails, in real time. The comment monitoring unit can also monitor non-text data, such as images and links. The logical harassment detection unit detects logical harassment comments from the content monitored by the comment monitoring unit. For example, the generation AI analyzes specific keywords and contexts based on previously learned characteristics of logical harassment comments to identify logical harassment comments. The generation AI can also use text generation AI (e.g., LLM) to detect logically aggressive or emotionless comments. The warning message generation unit generates a warning message for the sender based on the logical harassment comments detected by the logical harassment detection unit. For example, the generation AI generates a message such as, "Your comments may be too logical and may corner your colleagues. Please try to use softer expressions," and sends it to the sender. The warning message generation unit can also suggest specific improvements or alternative expressions to the sender. As a result, the logic harassment monitoring system according to the embodiment can improve communication by detecting logic harassment remarks and alerting the sender.

[0030] The logic harassment detection unit understands the context behind a statement and can detect logic harassment statements under specific circumstances. For example, the logic harassment detection unit uses a generation AI to analyze the context behind a statement and detect logic harassment statements under specific circumstances. For example, it takes into account the progress of a project and the content of a meeting. The logic harassment detection unit also understands the context of a statement and identifies it as logic harassment if it contains specific keywords or phrases. For example, it detects statements related to specific topics. The logic harassment detection unit also uses context analysis to consider the background information of a statement and identify logic harassment statements. For example, it automatically detects statements made under specific circumstances. This allows for understanding the context and accurately detecting logic harassment statements under specific circumstances.

[0031] The logical harassment detection unit can analyze voice data and detect logical harassment remarks from the tone and strength of the voice. For example, the logical harassment detection unit uses a generation AI to analyze voice data and detect logical harassment remarks from the tone and strength of the voice. For example, if the voice tone is high or strong, it will identify it as a logical harassment remark. The logical harassment detection unit also analyzes voice data and builds a system that detects logical harassment remarks if they contain a specific voice tone or strength. For example, it issues a warning if the voice tone is above a certain level. The logical harassment detection unit also analyzes voice tone and strength to identify logical harassment remarks. For example, if the voice strength is high, it will detect it as a logical harassment remark. This improves the accuracy of detecting logical harassment remarks by analyzing voice data.

[0032] The logical harassment detection unit can analyze video conference footage and detect signs of logical harassment from facial expressions and gestures. For example, the logical harassment detection unit uses a generative AI to analyze video conference footage and detect signs of logical harassment from facial expressions and gestures. For example, it detects facial expressions of anger or irritation. The logical harassment detection unit also analyzes video data and builds a system that detects signs of logical harassment when specific facial expressions or gestures are included. For example, it analyzes hand movements and facial expressions. The logical harassment detection unit also analyzes facial expressions and gestures to identify signs of logical harassment. For example, it detects logical harassment when specific facial expressions or gestures are included. This makes it possible to detect signs of logical harassment early by analyzing video conference footage.

[0033] The warning message generation unit can analyze the sender's past speech history and warn them based on specific patterns. For example, the generation AI analyzes the sender's past speech history and warns them based on specific patterns. For example, it issues a warning if there have been many instances of logical harassment in the past. The warning message generation unit also analyzes the speech history and builds a system that warns them if a specific pattern is included. For example, it issues a warning if there are many instances of specific keywords or phrases. The warning message generation unit also detects specific patterns based on the past speech history and warns them. For example, it issues a warning if past speech has been aggressive. In this way, by analyzing the past speech history, it is possible to warn the sender appropriately.

[0034] The warning message generation unit can learn the personality traits of the sender and generate individually optimized warning messages. For example, the warning message generation unit uses a generation AI to learn the personality traits of the sender and generate individually optimized warning messages. For example, gentle expressions are used according to the sender's personality. The warning message generation unit also builds a system that learns personality traits and generates warning messages according to specific personality traits. For example, gentle expressions are used for introverted personalities. The warning message generation unit also generates individually optimized warning messages based on the sender's personality traits. For example, appropriate expressions are used according to the personality. In this way, by generating warning messages according to the sender's personality traits, effective warnings can be given.

[0035] The warning message generation unit can suggest specific examples of improvement and alternative expressions to the sender. For example, the generation AI of the warning message generation unit suggests specific examples of improvement and alternative expressions to the sender. For example, it replaces "You're doing it wrong" with "Why don't you try this method?" The warning message generation unit also builds a system that suggests examples of improvement and alternative expressions to the sender for specific statements. For example, it replaces aggressive expressions with softer expressions. The warning message generation unit also suggests specific examples of improvement and alternative expressions to support the sender in better communication. For example, it replaces negative expressions with positive expressions. In this way, by suggesting specific examples of improvement and alternative expressions, it is possible to support the sender in better communication.

[0036] The warning message generation unit can provide the sender with an infographic that visually shows the impact of a logical harassment remark. For example, the warning message generation unit uses a generation AI to provide the sender with an infographic that visually shows the impact of a logical harassment remark. For example, the impact of the remark on colleagues is shown in a graph. The warning message generation unit also builds a system that provides the sender with an infographic that visually shows the impact of a logical harassment remark. For example, the impact of the remark is shown in a diagram or chart. The warning message generation unit also uses an infographic to visually show the impact of a logical harassment remark and help the sender understand that impact. For example, the impact of the remark on the entire team is shown. In this way, by visually showing the impact of a logical harassment remark, the sender can more easily understand that impact.

[0037] The logical harassment detection unit analyzes the time period and frequency of comments and can identify trends in which logical harassment comments occur frequently during certain time periods. For example, the generation AI analyzes the time period and frequency of comments and identifies trends in which logical harassment comments occur frequently during certain time periods. For example, logical harassment comments increase in the latter half of a meeting. The logical harassment detection unit also analyzes the time period and frequency of comments and builds a system that identifies trends in which logical harassment comments occur frequently during certain time periods. For example, comments are concentrated on certain days of the week or at certain time periods. The logical harassment detection unit also analyzes the time period and frequency and identifies trends in which logical harassment comments occur frequently. For example, comments increase before a project deadline. In this way, by analyzing the time period and frequency of comments, it is possible to identify trends in which logical harassment comments occur frequently.

[0038] The logical harassment detection unit can identify periods when stress will increase by analyzing the content of comments and the progress of the project, correlating it with the content of comments. For example, the generation AI can analyze the content of comments and the progress of the project to identify periods when stress will increase. For example, logical harassment comments increase before the project deadline. The logical harassment detection unit can also build a system that analyzes the content of comments and the progress of the project to identify trends in stress increasing at specific periods. For example, comments increase before important milestones. The logical harassment detection unit can also analyze the content of comments based on the progress of the project to identify periods when stress will increase. For example, logical harassment comments increase when the project is delayed. In this way, by correlating and analyzing the content of comments and the progress of the project, it is possible to identify periods when stress will increase.

[0039] The logical harassment detection unit can share the records of comments with other team members and consider improvement measures for the entire team. For example, the generation AI can share the records of comments with other team members and consider improvement measures for the entire team. For example, the records of comments are shared at regular meetings. The logical harassment detection unit can also build a system to share the records of comments and consider improvement measures for the entire team. For example, they can discuss areas for improvement based on the records of comments. The logical harassment detection unit can also share the records of comments with team members and consider improvement measures. For example, they can provide feedback based on the records of comments. In this way, by sharing the records of comments, the entire team can consider improvement measures.

[0040] The logical harassment detection unit can provide a dashboard that visualizes trends in logical harassment comments based on records of comments. For example, the logical harassment detection unit provides a dashboard that visualizes trends in logical harassment comments based on records of comments made by a generation AI. For example, it displays the frequency and time period of comments in a graph. The logical harassment detection unit also builds a dashboard that visualizes trends in logical harassment comments based on records of comments. For example, it shows changes in comments over a specific period. The logical harassment detection unit also uses the dashboard to visualize trends in logical harassment comments and consider improvement measures for the entire team. For example, it provides feedback based on trends in comments. In this way, by visualizing trends in logical harassment comments, improvement measures can be considered for the entire team.

[0041] The warning message generation unit can analyze the sender's past statements and provide feedback on specific areas for improvement. For example, the warning message generation unit uses a generation AI to analyze the sender's past statements and provide feedback on specific areas for improvement. For example, it can point out past logical harassment statements and suggest areas for improvement. The warning message generation unit can also build a system that analyzes the sender's past statements and provides feedback on specific areas for improvement. For example, it can point out specific keywords or phrases. The warning message generation unit can also provide feedback on specific areas for improvement based on past statements. For example, it can suggest replacing aggressive language with softer language. In this way, it is possible to provide feedback on specific areas for improvement by analyzing past statements.

[0042] The warning message generation unit can learn the communication style of the sender and provide individually optimized feedback. For example, the warning message generation unit uses a generation AI to learn the communication style of the sender and provide individually optimized feedback. For example, feedback is provided according to the sender's personality. The warning message generation unit also builds a system that learns communication styles and provides feedback according to a specific style. For example, gentle feedback is provided to an introverted personality. The warning message generation unit also provides individually optimized feedback based on the sender's communication style. For example, appropriate feedback is provided according to personality. This makes it possible to support effective improvement by providing feedback according to the sender's communication style.

[0043] The warning message generation unit can suggest to the caller a training program to improve their communication skills. For example, the generation AI of the warning message generation unit suggests to the caller a training program to improve their communication skills. For example, it suggests online courses or workshops. The warning message generation unit also builds a system that suggests to the caller a training program to improve specific communication skills. For example, it suggests role-playing or simulations. The warning message generation unit also suggests a training program to improve communication skills and supports the caller in better communication. For example, it customizes the training program based on feedback. In this way, it is possible to support the caller in improving their skills by suggesting a training program to improve their communication skills.

[0044] The warning message generation unit can provide the sender with a specific action plan based on the feedback. For example, the generation AI of the warning message generation unit provides the sender with a specific action plan based on the feedback. For example, it suggests steps to improve a specific statement. The warning message generation unit also builds a system that provides the sender with a specific action plan based on the feedback. For example, it presents areas for improvement as a specific action plan. The warning message generation unit also provides a specific action plan based on the feedback, supporting the sender in better communication. For example, it suggests improvement measures based on the feedback. In this way, it is possible to support the sender's improvement by providing a specific action plan based on the feedback.

[0045] The logical harassment detection unit can analyze the communication patterns of the entire team and identify areas for improvement. For example, the logical harassment detection unit uses a generation AI to analyze the communication patterns of the entire team and identify areas for improvement. For example, if there is a lack of communication between certain members, it will propose improvement measures. The logical harassment detection unit can also analyze the communication patterns of the entire team and build a system to identify areas for improvement when certain patterns are observed. For example, it will propose improvement measures if communication is concentrated during certain time periods. The logical harassment detection unit can also identify areas for improvement for the entire team based on the communication patterns and propose specific improvement measures. For example, it will make suggestions to improve the frequency and quality of communication. In this way, areas for improvement can be identified by analyzing the communication patterns of the entire team.

[0046] The logical harassment detection unit can collect mutual evaluations between team members and provide feedback. For example, the logical harassment detection unit uses a generation AI to collect mutual evaluations between team members and provide feedback. For example, it suggests areas for improvement based on the evaluations between members. The logical harassment detection unit also collects mutual evaluations between team members and builds a system that provides feedback based on specific evaluations. For example, it suggests improvement measures when the evaluation score is low. The logical harassment detection unit also provides feedback for the entire team based on the mutual evaluations and suggests specific improvement measures. For example, it suggests areas for improvement based on the evaluation results. In this way, appropriate feedback can be provided by collecting mutual evaluations between team members.

[0047] The logical harassment detection unit can propose and implement communication training and workshops for the entire team. For example, the generation AI in the logical harassment detection unit proposes and implements communication training and workshops for the entire team. For example, it proposes training to regularly improve communication skills. The logical harassment detection unit also proposes communication training and workshops for the entire team and builds a system aimed at improving specific skills. For example, it proposes training using role-playing and simulation. The logical harassment detection unit also proposes communication training and workshops to improve the communication skills of the entire team. For example, it proposes a training program based on feedback. In this way, by proposing and implementing communication training and workshops for the entire team, it is possible to improve the communication skills of the entire team.

[0048] The logical harassment detection unit provides a tool that visualizes communication across the entire team, allowing for the sharing of areas for improvement. For example, the logical harassment detection unit uses a generation AI to provide a tool that visualizes communication across the entire team, allowing for the sharing of areas for improvement. For example, it displays the frequency and quality of communication in a graph. The logical harassment detection unit also builds a tool that visualizes communication across the entire team, providing a system for sharing specific areas for improvement. For example, it visualizes communication patterns. The logical harassment detection unit also uses the visualization tool to analyze communication across the entire team, allowing for the sharing of areas for improvement. For example, it provides feedback based on communication trends. In this way, by providing a tool that visualizes communication across the entire team and sharing areas for improvement, it is possible to improve communication across the entire team.

[0049] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0050] The logical harassment monitoring system can further include a cultural analysis unit that analyzes the cultural elements behind the statements. The cultural analysis unit analyzes the cultural elements behind the statements and identifies logical harassment statements based on a specific cultural background. For example, if a statement made in a specific cultural sphere is perceived as offensive in another cultural sphere, the statement is detected as logical harassment. The cultural analysis unit also understands the cultural background of a statement and identifies it as logical harassment if it contains specific cultural elements. For example, it detects statements based on specific cultural customs or values. This allows for more accurate identification of logical harassment statements by taking cultural elements into account.

[0051] The logic harassment monitoring system can further include a psychology analysis unit that analyzes the psychological factors behind the statements. The psychology analysis unit analyzes the psychological factors behind the statements and identifies logic harassment statements based on a specific psychological state. For example, if the speaker is feeling stressed or anxious, the statement is detected as logic harassment. The psychology analysis unit also understands the psychological background of the statement and identifies it as logic harassment if it contains a specific psychological state. For example, it detects the statement if the speaker is overly nervous. In this way, logic harassment statements can be identified more accurately by taking psychological factors into consideration.

[0052] The logical harassment monitoring system can further include a social analysis unit that analyzes the social factors behind the comments. The social analysis unit analyzes the social factors behind the comments and identifies logical harassment comments based on specific social situations. For example, if a comment based on a specific social status or role is perceived as aggressive toward other members, the comment is detected as logical harassment. The social analysis unit also understands the social background of the comment and identifies it as logical harassment if it contains specific social factors. For example, it detects comments based on a specific job title or authority. This allows for more accurate identification of logical harassment comments by taking social factors into account.

[0053] The logic harassment monitoring system can further include a history analysis unit that analyzes historical factors behind statements. The history analysis unit analyzes historical factors behind statements and identifies logic harassment statements based on specific historical background. For example, if a statement based on a specific historical incident or event is perceived as offensive to other members, the statement is detected as logic harassment. The history analysis unit also understands the historical background of a statement and identifies it as logic harassment if it contains specific historical factors. For example, it detects statements related to specific historical events. This allows for more accurate identification of logic harassment statements by taking historical factors into account.

[0054] The logic harassment monitoring system can further include a technical analysis unit that analyzes the technical elements behind the comments. The technical analysis unit analyzes the technical elements behind the comments and identifies logic harassment comments based on specific technical backgrounds. For example, if a comment based on specific technical knowledge or skills is perceived as offensive to other members, the comment is detected as logic harassment. The technical analysis unit also understands the technical background of the comment and identifies it as logic harassment if it contains specific technical elements. For example, it detects comments based on specific technical terms or concepts. This allows for more accurate identification of logic harassment comments by taking technical elements into account.

[0055] The logic harassment monitoring system can further include an education analysis unit that analyzes educational factors behind the statements. The education analysis unit analyzes the educational factors behind the statements and identifies logic harassment statements based on a specific educational background. For example, if a statement based on the speaker's specific educational knowledge or skills is perceived as offensive to other members, the statement is detected as logic harassment. The education analysis unit also understands the educational background of the statement and identifies it as logic harassment if it contains specific educational factors. For example, it detects statements based on specific educational terms or concepts. This allows for more accurate identification of logic harassment statements by taking educational factors into consideration.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The message monitoring unit monitors the content of communication tools and chats. For example, it monitors text messages such as chat apps, video conferencing tools, and emails in real time. The message monitoring unit can also monitor non-text data such as images and links. Step 2: The logical harassment detection unit detects logical harassment remarks from the content monitored by the remark monitoring unit. For example, the generation AI analyzes specific keywords and contexts based on the characteristics of logical harassment remarks that it has learned in advance, and identifies logical harassment remarks. The generation AI can also use text generation AI (e.g., LLM) to detect remarks that ignore logical aggression or emotion in the remarks. Step 3: The warning message generator generates a message to warn the sender based on the logical harassment remarks detected by the logical harassment detection unit. For example, the generation AI generates a message such as, "Your remarks are too logical and may corner your colleague. Try to use softer expressions," and sends it to the sender. The warning message generator can also suggest specific examples of improvement or alternative expressions to the sender.

[0058] (Example 2) The logical harassment monitoring system according to an embodiment of the present invention is a system that monitors statements made at work that are intended to corner a colleague with logical reasoning, known as logical harassment, and points out the problem to the sender, thereby improving communication. This allows the sender to become aware of their own statements and improve the quality of communication.

[0059] A logical harassment monitoring system according to an embodiment includes a comment monitoring unit, a logical harassment detection unit, and a warning message generation unit. The comment monitoring unit monitors the content of communication tools and chats. For example, it monitors text messages, such as chat apps, video conferencing tools, and emails, in real time. The comment monitoring unit can also monitor non-text data, such as images and links. The logical harassment detection unit detects logical harassment comments from the content monitored by the comment monitoring unit. For example, the generation AI analyzes specific keywords and contexts based on previously learned characteristics of logical harassment comments to identify logical harassment comments. The generation AI can also use text generation AI (e.g., LLM) to detect logically aggressive or emotionless comments. The warning message generation unit generates a warning message for the sender based on the logical harassment comments detected by the logical harassment detection unit. For example, the generation AI generates a message such as, "Your comments may be too logical and may corner your colleagues. Please try to use softer expressions," and sends it to the sender. The warning message generation unit can also suggest specific improvements or alternative expressions to the sender. As a result, the logic harassment monitoring system according to the embodiment can improve communication by detecting logic harassment remarks and alerting the sender.

[0060] The logical harassment detection unit can analyze the emotional tone of a statement and identify emotionally aggressive statements. For example, the logical harassment detection unit uses a generation AI to analyze the emotional tone of a statement and identify statements that contain aggressive emotions. For example, it detects statements that contain strong emotions of anger or irritation. The logical harassment detection unit also analyzes the emotional tone of a statement and identifies a statement as logical harassment if it has a high specific emotional score. For example, it automatically detects statements with an emotional score above a certain level. The logical harassment detection unit also uses emotional tone analysis to measure the emotional intensity of a statement and identify aggressive statements. For example, it detects statements with high emotional intensity as logical harassment. This improves the accuracy of detecting logical harassment statements by identifying emotionally aggressive statements.

[0061] The logic harassment detection unit understands the context behind a statement and can detect logic harassment statements under specific circumstances. For example, the logic harassment detection unit uses a generation AI to analyze the context behind a statement and detect logic harassment statements under specific circumstances. For example, it takes into account the progress of a project and the content of a meeting. The logic harassment detection unit also understands the context of a statement and identifies it as logic harassment if it contains specific keywords or phrases. For example, it detects statements related to specific topics. The logic harassment detection unit also uses context analysis to consider the background information of a statement and identify logic harassment statements. For example, it automatically detects statements made under specific circumstances. This allows for understanding the context and accurately detecting logic harassment statements under specific circumstances.

[0062] The logical harassment detection unit uses an emotion estimation function to estimate the speaker's emotional state and can predict a logical harassment remark when stress or anger is high. The logical harassment detection unit, for example, uses the emotion estimation function to analyze the speaker's emotional state in real time and predict a logical harassment remark when stress or anger is high. For example, it analyzes the speaker's facial expression and voice. The logical harassment detection unit also builds a system that estimates the speaker's emotional state and predicts a logical harassment remark when stress or anger is high. For example, it issues a warning when the emotion score is above a certain level. The logical harassment detection unit also analyzes the speaker's emotional state based on the emotion estimation data and predicts a logical harassment remark. For example, it identifies a remark as a logical harassment remark when the emotion score is high. In this way, by estimating the speaker's emotional state, the accuracy of predicting logical harassment remarks is improved.

[0063] The logical harassment detection unit can analyze voice data and detect logical harassment remarks from the tone and strength of the voice. For example, the logical harassment detection unit uses a generation AI to analyze voice data and detect logical harassment remarks from the tone and strength of the voice. For example, if the voice tone is high or strong, it will identify it as a logical harassment remark. The logical harassment detection unit also analyzes voice data and builds a system that detects logical harassment remarks if they contain a specific voice tone or strength. For example, it issues a warning if the voice tone is above a certain level. The logical harassment detection unit also analyzes voice tone and strength to identify logical harassment remarks. For example, if the voice strength is high, it will detect it as a logical harassment remark. This improves the accuracy of detecting logical harassment remarks by analyzing voice data.

[0064] The logical harassment detection unit can analyze video conference footage and detect signs of logical harassment from facial expressions and gestures. For example, the logical harassment detection unit uses a generative AI to analyze video conference footage and detect signs of logical harassment from facial expressions and gestures. For example, it detects facial expressions of anger or irritation. The logical harassment detection unit also analyzes video data and builds a system that detects signs of logical harassment when specific facial expressions or gestures are included. For example, it analyzes hand movements and facial expressions. The logical harassment detection unit also analyzes facial expressions and gestures to identify signs of logical harassment. For example, it detects logical harassment when specific facial expressions or gestures are included. This makes it possible to detect signs of logical harassment early by analyzing video conference footage.

[0065] The logical harassment detection unit uses the emotion estimation function to analyze the emotional response of the recipient and can identify a logical harassment statement when the recipient shows displeasure. The logical harassment detection unit, for example, uses the emotion estimation function to analyze the emotional response of the recipient in real time and identify a logical harassment statement when the recipient shows displeasure. For example, it analyzes the recipient's facial expressions and voice. The logical harassment detection unit also builds a system that analyzes the recipient's emotional response and identifies a logical harassment statement when the recipient shows displeasure. For example, it issues a warning when the emotion score is above a certain level. The logical harassment detection unit also analyzes the recipient's emotional response based on the emotion estimation data and identifies a logical harassment statement. For example, it detects a high emotion score as a logical harassment statement. In this way, by analyzing the recipient's emotional response, the accuracy of identifying logical harassment statements is improved.

[0066] The warning message generation unit can analyze the sender's past speech history and warn them based on specific patterns. For example, the generation AI analyzes the sender's past speech history and warns them based on specific patterns. For example, it issues a warning if there have been many instances of logical harassment in the past. The warning message generation unit also analyzes the speech history and builds a system that warns them if a specific pattern is included. For example, it issues a warning if there are many instances of specific keywords or phrases. The warning message generation unit also detects specific patterns based on the past speech history and warns them. For example, it issues a warning if past speech has been aggressive. In this way, by analyzing the past speech history, it is possible to warn the sender appropriately.

[0067] The warning message generation unit can learn the personality traits of the sender and generate individually optimized warning messages. For example, the warning message generation unit uses a generation AI to learn the personality traits of the sender and generate individually optimized warning messages. For example, gentle expressions are used according to the sender's personality. The warning message generation unit also builds a system that learns personality traits and generates warning messages according to specific personality traits. For example, gentle expressions are used for introverted personalities. The warning message generation unit also generates individually optimized warning messages based on the sender's personality traits. For example, appropriate expressions are used according to the personality. In this way, by generating warning messages according to the sender's personality traits, effective warnings can be given.

[0068] The warning message generation unit can use the emotion estimation function to generate flexible warning messages according to the emotional state of the sender. The warning message generation unit, for example, uses the emotion estimation function to generate flexible warning messages according to the emotional state of the sender. For example, if the sender is feeling stressed, a gentle expression is used. The warning message generation unit also analyzes the emotional state of the sender and builds a system that generates warning messages according to a specific emotional state. For example, if the emotion score is high, a gentle expression is used. The warning message generation unit also generates flexible warning messages according to the emotional state of the sender based on the emotion estimation data. For example, if the sender is feeling angry, a calm expression is used. In this way, by generating flexible warning messages according to the emotional state of the sender, it is possible to effectively warn the sender.

[0069] The warning message generation unit can suggest specific examples of improvement and alternative expressions to the sender. For example, the generation AI of the warning message generation unit suggests specific examples of improvement and alternative expressions to the sender. For example, it replaces "You're doing it wrong" with "Why don't you try this method?" The warning message generation unit also builds a system that suggests examples of improvement and alternative expressions to the sender for specific statements. For example, it replaces aggressive expressions with softer expressions. The warning message generation unit also suggests specific examples of improvement and alternative expressions to support the sender in better communication. For example, it replaces negative expressions with positive expressions. In this way, by suggesting specific examples of improvement and alternative expressions, it is possible to support the sender in better communication.

[0070] The warning message generation unit can provide the sender with an infographic that visually shows the impact of a logical harassment remark. For example, the warning message generation unit uses a generation AI to provide the sender with an infographic that visually shows the impact of a logical harassment remark. For example, the impact of the remark on colleagues is shown in a graph. The warning message generation unit also builds a system that provides the sender with an infographic that visually shows the impact of a logical harassment remark. For example, the impact of the remark is shown in a diagram or chart. The warning message generation unit also uses an infographic to visually show the impact of a logical harassment remark and help the sender understand that impact. For example, the impact of the remark on the entire team is shown. In this way, by visually showing the impact of a logical harassment remark, the sender can more easily understand that impact.

[0071] The warning message generation unit uses the emotion estimation function to analyze the emotional response of the sender when receiving a warning message, and can warn the sender at the optimal timing. The warning message generation unit, for example, uses the emotion estimation function to analyze the emotional response of the sender when receiving a warning message in real time, and can warn the sender at the optimal timing. For example, the warning message generation unit warns the sender when the sender is in a calm state. The warning message generation unit also analyzes the sender's emotional response and builds a system that transmits a warning message according to a specific emotional state. For example, the warning message generation unit warns the sender when the emotional score is low. The warning message generation unit also analyzes the sender's emotional response based on the emotion estimation data, and can warn the sender at the optimal timing. For example, the warning message generation unit warns the sender when the sender is relaxed. In this way, by analyzing the sender's emotional response, it is possible to warn the sender at the optimal timing.

[0072] The logical harassment detection unit analyzes the time period and frequency of comments and can identify trends in which logical harassment comments occur frequently during certain time periods. For example, the generation AI analyzes the time period and frequency of comments and identifies trends in which logical harassment comments occur frequently during certain time periods. For example, logical harassment comments increase in the latter half of a meeting. The logical harassment detection unit also analyzes the time period and frequency of comments and builds a system that identifies trends in which logical harassment comments occur frequently during certain time periods. For example, comments are concentrated on certain days of the week or at certain time periods. The logical harassment detection unit also analyzes the time period and frequency and identifies trends in which logical harassment comments occur frequently. For example, comments increase before a project deadline. In this way, by analyzing the time period and frequency of comments, it is possible to identify trends in which logical harassment comments occur frequently.

[0073] The logical harassment detection unit can identify periods when stress will increase by analyzing the content of comments and the progress of the project, correlating it with the content of comments. For example, the generation AI can analyze the content of comments and the progress of the project to identify periods when stress will increase. For example, logical harassment comments increase before the project deadline. The logical harassment detection unit can also build a system that analyzes the content of comments and the progress of the project to identify trends in stress increasing at specific periods. For example, comments increase before important milestones. The logical harassment detection unit can also analyze the content of comments based on the progress of the project to identify periods when stress will increase. For example, logical harassment comments increase when the project is delayed. In this way, by correlating and analyzing the content of comments and the progress of the project, it is possible to identify periods when stress will increase.

[0074] The logical harassment detection unit can use the emotion estimation function to track the speaker's emotional changes over the long term and detect signs of logical harassment remarks. The logical harassment detection unit, for example, uses the emotion estimation function to track the speaker's emotional changes over the long term and detect signs of logical harassment remarks. For example, it issues a warning if the emotion score gradually increases. The logical harassment detection unit also builds a system that analyzes the speaker's emotional changes over the long term and detects signs of logical harassment remarks when a specific pattern is observed. For example, it issues a warning if the emotion score continues for a certain period of time or more. The logical harassment detection unit also analyzes the speaker's emotional changes based on the long-term emotion estimation data and identifies signs of logical harassment remarks. For example, it issues a warning if the emotion score changes suddenly. In this way, by tracking the speaker's emotional changes over the long term, it is possible to detect signs of logical harassment remarks.

[0075] The logical harassment detection unit can share the records of comments with other team members and consider improvement measures for the entire team. For example, the generation AI can share the records of comments with other team members and consider improvement measures for the entire team. For example, the records of comments are shared at regular meetings. The logical harassment detection unit can also build a system to share the records of comments and consider improvement measures for the entire team. For example, they can discuss areas for improvement based on the records of comments. The logical harassment detection unit can also share the records of comments with team members and consider improvement measures. For example, they can provide feedback based on the records of comments. In this way, by sharing the records of comments, the entire team can consider improvement measures.

[0076] The logical harassment detection unit can provide a dashboard that visualizes trends in logical harassment comments based on records of comments. For example, the logical harassment detection unit provides a dashboard that visualizes trends in logical harassment comments based on records of comments made by a generation AI. For example, it displays the frequency and time period of comments in a graph. The logical harassment detection unit also builds a dashboard that visualizes trends in logical harassment comments based on records of comments. For example, it shows changes in comments over a specific period. The logical harassment detection unit also uses the dashboard to visualize trends in logical harassment comments and consider improvement measures for the entire team. For example, it provides feedback based on trends in comments. In this way, by visualizing trends in logical harassment comments, improvement measures can be considered for the entire team.

[0077] The logical harassment detection unit can use the emotion estimation function to analyze the emotional state of the entire team based on the utterance records and propose improvement measures. The logical harassment detection unit, for example, uses the emotion estimation function to analyze the emotional state of the entire team based on the utterance records and propose improvement measures. For example, improvement measures are proposed when the emotion score is low. The logical harassment detection unit also builds a system that analyzes the emotional state of the entire team based on the utterance records and proposes improvement measures according to specific emotional states. For example, improvement measures are proposed when the emotion score is above a certain level. The logical harassment detection unit also analyzes the emotional state of the entire team based on the emotion estimation data and proposes improvement measures. For example, feedback is provided when the emotion score is low. In this way, appropriate improvement measures can be proposed by analyzing the emotional state of the entire team.

[0078] The warning message generation unit can analyze the sender's past statements and provide feedback on specific areas for improvement. For example, the warning message generation unit uses a generation AI to analyze the sender's past statements and provide feedback on specific areas for improvement. For example, it can point out past logical harassment statements and suggest areas for improvement. The warning message generation unit can also build a system that analyzes the sender's past statements and provides feedback on specific areas for improvement. For example, it can point out specific keywords or phrases. The warning message generation unit can also provide feedback on specific areas for improvement based on past statements. For example, it can suggest replacing aggressive language with softer language. In this way, it is possible to provide feedback on specific areas for improvement by analyzing past statements.

[0079] The warning message generation unit can learn the communication style of the sender and provide individually optimized feedback. For example, the warning message generation unit uses a generation AI to learn the communication style of the sender and provide individually optimized feedback. For example, feedback is provided according to the sender's personality. The warning message generation unit also builds a system that learns communication styles and provides feedback according to a specific style. For example, gentle feedback is provided to an introverted personality. The warning message generation unit also provides individually optimized feedback based on the sender's communication style. For example, appropriate feedback is provided according to personality. This makes it possible to support effective improvement by providing feedback according to the sender's communication style.

[0080] The warning message generation unit can provide flexible feedback according to the emotional state of the sender using the emotion estimation function. The warning message generation unit, for example, uses the emotion estimation function to provide flexible feedback according to the emotional state of the sender. For example, if the sender is feeling stressed, gentle feedback is provided. The warning message generation unit also analyzes the emotional state of the sender and builds a system that provides feedback according to a specific emotional state. For example, if the emotion score is high, gentle feedback is provided. The warning message generation unit also provides flexible feedback according to the emotional state of the sender based on the emotion estimation data. For example, if the sender is feeling angry, calm feedback is provided. In this way, by providing flexible feedback according to the emotional state of the sender, effective improvement can be supported.

[0081] The warning message generation unit can suggest to the caller a training program to improve their communication skills. For example, the generation AI of the warning message generation unit suggests to the caller a training program to improve their communication skills. For example, it suggests online courses or workshops. The warning message generation unit also builds a system that suggests to the caller a training program to improve specific communication skills. For example, it suggests role-playing or simulations. The warning message generation unit also suggests a training program to improve communication skills and supports the caller in better communication. For example, it customizes the training program based on feedback. In this way, it is possible to support the caller in improving their skills by suggesting a training program to improve their communication skills.

[0082] The warning message generation unit can provide the sender with a specific action plan based on the feedback. For example, the generation AI of the warning message generation unit provides the sender with a specific action plan based on the feedback. For example, it suggests steps to improve a specific statement. The warning message generation unit also builds a system that provides the sender with a specific action plan based on the feedback. For example, it presents areas for improvement as a specific action plan. The warning message generation unit also provides a specific action plan based on the feedback, supporting the sender in better communication. For example, it suggests improvement measures based on the feedback. In this way, it is possible to support the sender's improvement by providing a specific action plan based on the feedback.

[0083] The warning message generation unit can analyze the effect of feedback using the emotion estimation function and continuously improve the optimal feedback method. The warning message generation unit, for example, uses the emotion estimation function to analyze the effect of feedback in real time and continuously improve the optimal feedback method. For example, it analyzes the emotion score after feedback. The warning message generation unit also analyzes the effect of feedback and builds a system to evaluate whether a specific feedback method is effective. For example, it adjusts the feedback method based on changes in the emotion score. The warning message generation unit also analyzes the effect of feedback based on the emotion estimation data and continuously improves the optimal feedback method. For example, it adjusts the feedback method based on changes in emotion after feedback. In this way, by analyzing the effect of feedback and continuously improving the optimal feedback method, it is possible to support the improvement of the sender.

[0084] The logical harassment detection unit can analyze the communication patterns of the entire team and identify areas for improvement. For example, the logical harassment detection unit uses a generation AI to analyze the communication patterns of the entire team and identify areas for improvement. For example, if there is a lack of communication between certain members, it will propose improvement measures. The logical harassment detection unit can also analyze the communication patterns of the entire team and build a system to identify areas for improvement when certain patterns are observed. For example, it will propose improvement measures if communication is concentrated during certain time periods. The logical harassment detection unit can also identify areas for improvement for the entire team based on the communication patterns and propose specific improvement measures. For example, it will make suggestions to improve the frequency and quality of communication. In this way, areas for improvement can be identified by analyzing the communication patterns of the entire team.

[0085] The logical harassment detection unit can collect mutual evaluations between team members and provide feedback. For example, the logical harassment detection unit uses a generation AI to collect mutual evaluations between team members and provide feedback. For example, it suggests areas for improvement based on the evaluations between members. The logical harassment detection unit also collects mutual evaluations between team members and builds a system that provides feedback based on specific evaluations. For example, it suggests improvement measures when the evaluation score is low. The logical harassment detection unit also provides feedback for the entire team based on the mutual evaluations and suggests specific improvement measures. For example, it suggests areas for improvement based on the evaluation results. In this way, appropriate feedback can be provided by collecting mutual evaluations between team members.

[0086] The logical harassment detection unit can use the emotion estimation function to analyze the emotional state of the entire team and make suggestions for improving communication. The logical harassment detection unit, for example, uses the emotion estimation function to analyze the emotional state of the entire team and make suggestions for improving communication. For example, it proposes improvement measures when the emotion score is low. The logical harassment detection unit also builds a system that analyzes the emotional state of the entire team and proposes improvement measures according to specific emotional states. For example, it proposes improvement measures when the emotion score is above a certain level. The logical harassment detection unit also analyzes the emotional state of the entire team based on the emotion estimation data and makes suggestions for improving communication. For example, it provides feedback when the emotion score is low. In this way, by analyzing the emotional state of the entire team, it is possible to make appropriate suggestions for improving communication.

[0087] The logical harassment detection unit can propose and implement communication training and workshops for the entire team. For example, the generation AI in the logical harassment detection unit proposes and implements communication training and workshops for the entire team. For example, it proposes training to regularly improve communication skills. The logical harassment detection unit also proposes communication training and workshops for the entire team and builds a system aimed at improving specific skills. For example, it proposes training using role-playing and simulation. The logical harassment detection unit also proposes communication training and workshops to improve the communication skills of the entire team. For example, it proposes a training program based on feedback. In this way, by proposing and implementing communication training and workshops for the entire team, it is possible to improve the communication skills of the entire team.

[0088] The logical harassment detection unit provides a tool that visualizes communication across the entire team, allowing for the sharing of areas for improvement. For example, the logical harassment detection unit uses a generation AI to provide a tool that visualizes communication across the entire team, allowing for the sharing of areas for improvement. For example, it displays the frequency and quality of communication in a graph. The logical harassment detection unit also builds a tool that visualizes communication across the entire team, providing a system for sharing specific areas for improvement. For example, it visualizes communication patterns. The logical harassment detection unit also uses the visualization tool to analyze communication across the entire team, allowing for the sharing of areas for improvement. For example, it provides feedback based on communication trends. In this way, by providing a tool that visualizes communication across the entire team and sharing areas for improvement, it is possible to improve communication across the entire team.

[0089] The logical harassment detection unit can use the emotion estimation function to monitor the emotional state of the entire team in real time and propose improvement measures at the appropriate time. The logical harassment detection unit, for example, uses the emotion estimation function to monitor the emotional state of the entire team in real time and propose improvement measures at the appropriate time. For example, it proposes improvement measures when the emotion score is low. The logical harassment detection unit also builds a system that analyzes the emotional state of the entire team in real time and proposes improvement measures according to specific emotional states. For example, it proposes improvement measures when the emotion score is above a certain level. The logical harassment detection unit also monitors the emotional state of the entire team in real time based on the emotion estimation data and proposes improvement measures at the appropriate time. For example, it provides feedback when the emotion score is low. In this way, by monitoring the emotional state of the entire team in real time and proposing improvement measures at the appropriate time, it is possible to improve communication throughout the team.

[0090] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0091] The logical harassment monitoring system can further include a cultural analysis unit that analyzes the cultural elements behind the statements. The cultural analysis unit analyzes the cultural elements behind the statements and identifies logical harassment statements based on a specific cultural background. For example, if a statement made in a specific cultural sphere is perceived as offensive in another cultural sphere, the statement is detected as logical harassment. The cultural analysis unit also understands the cultural background of a statement and identifies it as logical harassment if it contains specific cultural elements. For example, it detects statements based on specific cultural customs or values. This allows for more accurate identification of logical harassment statements by taking cultural elements into account.

[0092] The logic harassment monitoring system can further include a psychology analysis unit that analyzes the psychological factors behind the statements. The psychology analysis unit analyzes the psychological factors behind the statements and identifies logic harassment statements based on a specific psychological state. For example, if the speaker is feeling stressed or anxious, the statement is detected as logic harassment. The psychology analysis unit also understands the psychological background of the statement and identifies it as logic harassment if it contains a specific psychological state. For example, it detects the statement if the speaker is overly nervous. In this way, logic harassment statements can be identified more accurately by taking psychological factors into consideration.

[0093] The logical harassment monitoring system can further include a social analysis unit that analyzes the social factors behind the comments. The social analysis unit analyzes the social factors behind the comments and identifies logical harassment comments based on specific social situations. For example, if a comment based on a specific social status or role is perceived as aggressive toward other members, the comment is detected as logical harassment. The social analysis unit also understands the social background of the comment and identifies it as logical harassment if it contains specific social factors. For example, it detects comments based on a specific job title or authority. This allows for more accurate identification of logical harassment comments by taking social factors into account.

[0094] The logic harassment monitoring system can further include a history analysis unit that analyzes historical factors behind statements. The history analysis unit analyzes historical factors behind statements and identifies logic harassment statements based on specific historical background. For example, if a statement based on a specific historical incident or event is perceived as offensive to other members, the statement is detected as logic harassment. The history analysis unit also understands the historical background of a statement and identifies it as logic harassment if it contains specific historical factors. For example, it detects statements related to specific historical events. This allows for more accurate identification of logic harassment statements by taking historical factors into account.

[0095] The logic harassment monitoring system can further include a technical analysis unit that analyzes the technical elements behind the comments. The technical analysis unit analyzes the technical elements behind the comments and identifies logic harassment comments based on specific technical backgrounds. For example, if a comment based on specific technical knowledge or skills is perceived as offensive to other members, the comment is detected as logic harassment. The technical analysis unit also understands the technical background of the comment and identifies it as logic harassment if it contains specific technical elements. For example, it detects comments based on specific technical terms or concepts. This allows for more accurate identification of logic harassment comments by taking technical elements into account.

[0096] The logical harassment monitoring system can further include an emotion analysis unit that analyzes the emotional elements behind the statements. The emotion analysis unit analyzes the emotional elements behind the statements and identifies logical harassment statements based on a specific emotional state. For example, if the speaker is feeling angry or irritated, the statement is detected as logical harassment. The emotion analysis unit also understands the emotional background of the statement and identifies it as logical harassment if it contains a specific emotional state. For example, it detects a statement if the speaker is overly emotional. In this way, by taking emotional elements into consideration, logical harassment statements can be identified more accurately.

[0097] The logic harassment monitoring system can further include a body analysis unit that analyzes the physical factors behind the statements. The body analysis unit analyzes the physical factors behind the statements and identifies logic harassment statements based on a specific physical state. For example, if the speaker feels tired or unwell, the statement is detected as logic harassment. The body analysis unit also understands the physical background of the statement and identifies it as logic harassment if it includes a specific physical state. For example, it detects the statement if the speaker is excessively tired. In this way, logic harassment statements can be identified more accurately by taking physical factors into account.

[0098] The logical harassment monitoring system can further include an environmental analysis unit that analyzes environmental factors behind the statements. The environmental analysis unit analyzes the environmental factors behind the statements and identifies logical harassment statements based on specific environmental conditions. For example, if the speaker is experiencing environmental stress such as noise or temperature, the statement is detected as logical harassment. The environmental analysis unit also understands the environmental background of the statement and identifies it as logical harassment if it contains specific environmental conditions. For example, it detects the statement if the speaker is in an excessively hot environment. This allows for more accurate identification of logical harassment statements by taking environmental factors into consideration.

[0099] The logic harassment monitoring system can further include an economic analysis unit that analyzes the economic factors behind the statements. The economic analysis unit analyzes the economic factors behind the statements and identifies logic harassment statements based on specific economic circumstances. For example, if the speaker is feeling economic pressure, the unit detects the statement as logic harassment. The economic analysis unit also understands the economic background of the statement and identifies it as logic harassment if it includes specific economic circumstances. For example, it detects the statement if the speaker is feeling financial anxiety. In this way, logic harassment statements can be identified more accurately by taking economic factors into consideration.

[0100] The logic harassment monitoring system can further include an education analysis unit that analyzes educational factors behind the statements. The education analysis unit analyzes the educational factors behind the statements and identifies logic harassment statements based on a specific educational background. For example, if a statement based on the speaker's specific educational knowledge or skills is perceived as offensive to other members, the statement is detected as logic harassment. The education analysis unit also understands the educational background of the statement and identifies it as logic harassment if it contains specific educational factors. For example, it detects statements based on specific educational terms or concepts. This allows for more accurate identification of logic harassment statements by taking educational factors into consideration.

[0101] The processing flow of the second embodiment will be briefly explained below.

[0102] Step 1: The message monitoring unit monitors the content of communication tools and chats. For example, it monitors text messages such as chat apps, video conferencing tools, and emails in real time. The message monitoring unit can also monitor non-text data such as images and links. Step 2: The logical harassment detection unit detects logical harassment remarks from the content monitored by the remark monitoring unit. For example, the generation AI analyzes specific keywords and contexts based on the characteristics of logical harassment remarks that it has learned in advance, and identifies logical harassment remarks. The generation AI can also use text generation AI (e.g., LLM) to detect remarks that ignore logical aggression or emotion in the remarks. Step 3: The warning message generator generates a message to warn the sender based on the logical harassment remarks detected by the logical harassment detection unit. For example, the generation AI generates a message such as, "Your remarks are too logical and may corner your colleague. Try to use softer expressions," and sends it to the sender. The warning message generator can also suggest specific examples of improvement or alternative expressions to the sender.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0107] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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).

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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 AI 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.

[0120] 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.

[0121] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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).

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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 AI 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.

[0135] 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.

[0136] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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).

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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 AI 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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).

[0156] 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.

[0157] 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."

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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]

[0170] 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 comment monitoring unit that monitors the content of communication tools and chats; a logic harassment detection unit that detects logic harassment comments from the content monitored by the comment monitoring unit; a warning message generating unit that generates a message to warn the sender based on the logic harassment remark detected by the logic harassment detection unit; A system characterized by:

2. The logic harassment detection unit Analyze the emotional tone of statements and identify emotionally aggressive statements 2. The system of claim 1.

3. The logic harassment detection unit Understand the context behind statements and detect such harassment in specific situations 2. The system of claim 1.

4. The logic harassment detection unit Estimate the speaker's emotional state and predict the above-mentioned harassing remarks when stress or anger is high 2. The system of claim 1.

5. The logic harassment detection unit Analyze the voice data and detect the logical harassment remarks from the tone and strength of the voice.

2. The system of claim 1.

6. The logic harassment detection unit Analyzing video conference footage to detect signs of logical harassment from facial expressions and gestures 2. The system of claim 1.

Images