System

Abstract

An object of a system according to an embodiment is to remove a prejudice based on an emotion or a status in a field of discussion and promote fair communication.SOLUTION: A system includes a logical structure analysis part, a schematization part, a bias removal part, and a solution presentation part. The logical structure analysis unit analyzes the content of the discussion. The schematization unit schematizes the content analyzed by the logical structure analysis unit. The bias removal unit removes a bias based on emotion or identity from the contents schematized by the schematization unit. A solution presentation part presents a solution when learning the past discussion and getting stuck.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has had the problem that prejudices based on emotions and status can arise in discussions, making fair communication difficult.

[0005] The system according to the embodiment aims to eliminate prejudice based on emotions and status in discussions and promote fair communication. [Means for solving the problem]

[0006] The system according to the embodiment includes a logical structure analysis unit, a diagramming unit, a bias removal unit, and a solution presentation unit. The logical structure analysis unit analyzes the content of a discussion. The diagramming unit diagrams the content analyzed by the logical structure analysis unit. The bias removal unit removes bias based on emotions or status from the content diagrammed by the diagramming unit. The solution presentation unit studies past discussions and presents solutions when a problem arises. [Effects of the Invention]

[0007] The system according to the embodiment can eliminate prejudice based on emotions and status in discussions and promote fair communication. [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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[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 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[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 AI-based solution according to an embodiment of the present invention is a system that diagrams the logical structure of a conversation in real time and generates illogical statements and the reasons for them, thereby promoting clear and fair communication and deriving high-quality conclusions.

[0029] The AI-based solution according to the embodiment includes a logical structure analysis unit, a diagramming unit, a bias removal unit, and a solution presentation unit. The logical structure analysis unit analyzes the content of an argument. For example, it analyzes the content of the argument using natural language processing technology and extracts arguments, counterarguments, evidence, etc. The logical structure analysis unit can also analyze the emotional aspects of the argument using sentiment analysis technology. For example, it calculates a sentiment score and evaluates the emotional tone of the argument. The logical structure analysis unit can also analyze the logical flow of the argument using a logical structure analysis algorithm. For example, it can detect logical errors and contradictions. The diagramming unit diagrams the content analyzed by the logical structure analysis unit. For example, it can visually show the flow of the argument using a flowchart. The diagramming unit can also organize the structure of the argument using a mind map. For example, it can arrange arguments, counterarguments, and evidence as nodes and connect them with links. The diagramming unit can also show the conceptual relationships of the argument using a concept diagram. For example, it can show the relationships between concepts using arrows. The bias removal unit removes biases based on emotions and status from the content schematized by the schematization unit. For example, it converts emotional expressions into neutral expressions. The bias removal unit can also detect and remove social biases. For example, it identifies and corrects biases based on specific status or background. The bias removal unit can also detect and remove cultural biases. For example, it considers and corrects biases based on different cultures. The solution presentation unit learns from past discussions and presents solutions when a problem arises. For example, it analyzes data from similar past discussions and proposes successful solutions. The solution presentation unit can also learn from unsuccessful cases and present the reasons for failure. For example, it analyzes the causes of failure and proposes areas for improvement. The solution presentation unit can also analyze discussion progression patterns and trends and present solutions based on the results. For example, it can analyze discussion progression patterns over time to identify trends. As a result, the AI-based solution according to the embodiment can promote clear and fair communication and derive high-quality conclusions. For example, in meetings and discussions, all participants can exchange opinions logically and fairly and make optimal decisions.In addition, by utilizing data from past discussions, solutions can be found smoothly even when a deadlock occurs.

[0030] The diagramming unit can automatically recognize technical terms and jargon used in discussions and add annotations that concisely explain them in real time. For example, the diagramming unit uses a generative AI to automatically recognize technical terms and jargon used in discussions and add annotations that concisely explain their meaning and background in real time. For example, it recognizes technical terms used in discussions in the medical field and displays their definitions and related information. The diagramming unit can also recognize technical terms used in discussions in technology fields and add their explanations. For example, it recognizes programming terms and engineering terms and displays their meanings. The diagramming unit can also recognize industry-specific terms and add their annotations. For example, it recognizes financial industry terms and marketing terms and displays their explanations. This makes it easier for participants to understand the discussion by explaining the technical terms and jargon used in discussions in real time.

[0031] The diagramming unit can automatically refer to related past discussions and literature as the discussion progresses and add that information to the diagram in real time. For example, the generation AI can automatically refer to related past discussions and literature as the discussion progresses and add that information to the diagram in real time. For example, it can refer to past meeting records and related research papers to provide background information for the discussion. The diagramming unit can also analyze data from past discussions, extract relevant information, and add it to the diagram. For example, it can refer to evidence and data presented in past discussions and reflect that in the diagram. Furthermore, the diagramming unit can automatically search for related literature and add that information to the diagram. For example, it can search for related academic papers and technical reports and reflect their contents in the diagram. In this way, by referring to related past discussions and literature in real time as the discussion progresses, it is possible to provide background information for the discussion and deepen the discussion.

[0032] The diagramming unit can display the diagram of the argument as a 3D model or in a virtual reality environment, allowing participants to understand it more intuitively. For example, the diagramming unit uses a generative AI to display the logical structure of the argument as a 3D model, allowing participants to understand it more intuitively. For example, the arguments and counterarguments of the argument can be displayed as 3D objects to visually show the logical flow. The diagramming unit can also use a virtual reality (VR) environment to diagram the argument. For example, a VR headset can be used to display the content of the argument in a virtual space, allowing participants to experience the flow of the argument within it. Furthermore, the diagramming unit can use the 3D model or VR environment to allow participants to interactively manipulate the content of the argument. For example, participants can manipulate the 3D objects to change the flow of the argument or display additional information. Thus, displaying the diagram of the argument as a 3D model or in a virtual reality (VR) environment allows participants to understand the argument more intuitively.

[0033] The diagramming unit can promote multilingual communication by translating and diagramming discussions in different languages ​​in real time. The diagramming unit, for example, provides a function whereby a generative AI translates discussions in different languages ​​in real time and diagrams their contents. For example, it can translate a discussion in English into Japanese and diagram the logical structure. The diagramming unit can also translate discussions in multiple languages ​​simultaneously and diagram them in each language. For example, it can translate a discussion in English and French simultaneously and diagram them in each language. Furthermore, the diagramming unit can integrate discussions in different languages ​​and summarize them into a common diagram. For example, it can integrate discussions in English and Japanese and reflect them in a common diagram. In this way, it can promote multilingual communication by translating discussions in different languages ​​in real time and diagramming them.

[0034] The logical structure analysis unit can automatically detect logical fallacies used in arguments and present specific examples. For example, the logical structure analysis unit can automatically detect logical fallacies used in arguments using generative AI and present specific examples. For example, it can detect straw man arguments and ad hominem attacks and display specific examples. The logical structure analysis unit can also classify types of logical fallacies and present specific examples of each. For example, it can detect incorrect causal relationships and circular reasoning and display specific examples. Furthermore, the logical structure analysis unit can evaluate the impact of logical fallacies and visually show that impact. For example, it can evaluate the impact of logical fallacies on the entire argument and reflect that impact in a diagram. This improves the quality of arguments by automatically detecting logical fallacies and presenting specific examples.

[0035] When detecting illogical statements, the logical structure analysis unit can generate reasons from a global perspective, taking into account biases based on different cultures and values. For example, when a generative AI detects illogical statements, the logical structure analysis unit can generate reasons from a global perspective, taking into account biases based on different cultures and values. For example, it can present reasons taking into account differences in cultural background and values. The logical structure analysis unit can also evaluate biases based on different cultures and values ​​and visually show their impact. For example, it can evaluate the impact of cultural bias on a discussion and reflect that impact in a diagram. Furthermore, the logical structure analysis unit can suggest methods for removing biases based on different cultures and values. For example, it can suggest methods for promoting intercultural communication. This improves the quality of discussions by generating reasons from a global perspective, taking into account biases based on different cultures and values.

[0036] The logical structure analysis unit can refer to the opinions of experts in different fields and present reasons from multiple perspectives to detect logical flaws. For example, in order for generative AI to detect logical flaws, the logical structure analysis unit can refer to the opinions of experts in different fields and present reasons from multiple perspectives. For example, it can refer to the opinions of experts in the medical and legal fields to present reasons. The logical structure analysis unit can also classify expert opinions and present reasons from each perspective. For example, it can present reasons from a technical perspective or an economic perspective. Furthermore, the logical structure analysis unit can evaluate expert opinions and visually indicate their reliability. For example, it can evaluate the reliability of expert opinions and reflect the evaluation results in a diagram. This improves the quality of discussions by referring to the opinions of experts in different fields and presenting reasons from multiple perspectives.

[0037] The bias removal unit can analyze the language and expressions used in a discussion and automatically correct parts that contain emotional bias. For example, the bias removal unit uses a generative AI to analyze the language and expressions used in a discussion and automatically correct parts that contain emotional bias. For example, it replaces emotional expressions with neutral expressions. The bias removal unit can also classify types of emotional bias and make corrections based on each bias. For example, it can distinguish between emotions such as anger and sadness and make corrections based on each emotion. Furthermore, the bias removal unit can evaluate the strength of emotional bias and change the correction method depending on that strength. For example, if the intensity of the emotion is high, it will change to a more neutral expression. This improves the quality of the discussion by automatically correcting parts that contain emotional bias.

[0038] The bias removal unit can anonymize the identities and background information of discussion participants, minimizing the influence of bias. For example, the generative AI can anonymize the identities and background information of discussion participants to minimize the influence of bias. For example, it can hide the names and occupations of participants and display only the content of their opinions. The bias removal unit can also set criteria for anonymizing participants' background information and perform anonymization based on those criteria. For example, it can delete specific personal information and use pseudonyms. Furthermore, the bias removal unit can evaluate the anonymized information and visually display the evaluation results. For example, it can evaluate the degree of anonymization and reflect the evaluation results in a diagram. In this way, the influence of bias can be minimized by anonymizing the identities and background information of participants.

[0039] The bias removal unit can take into account biases based on different cultures and values ​​and make corrections from a global perspective to remove biases based on emotions and status. For example, in order for the generative AI to remove biases based on emotions and status, the bias removal unit can take into account biases based on different cultures and values ​​and make corrections from a global perspective. For example, it makes corrections taking into account differences in cultural background and values. The bias removal unit can also evaluate biases based on different cultures and values ​​and visually show their impact. For example, it can evaluate the impact of cultural bias on a discussion and reflect that impact in a diagram. Furthermore, the bias removal unit can suggest methods to remove biases based on different cultures and values. For example, it can suggest methods to promote intercultural communication. This improves the quality of discussions by taking into account biases based on different cultures and values ​​and making corrections from a global perspective.

[0040] The bias removal unit can add an automatic translation function to adapt the language and expressions used in a discussion to different languages ​​and cultures. For example, the bias removal unit provides an automatic translation function that enables the generative AI to adapt the language and expressions used in a discussion to different languages ​​and cultures. For example, it translates a discussion in English into Japanese and adjusts the expressions taking cultural background into consideration. The bias removal unit can also translate discussions in multiple languages ​​simultaneously and adapt them in each language. For example, it can translate discussions in English and French simultaneously and adapt them to each culture. Furthermore, the bias removal unit can set standards for adaptation to different languages ​​and cultures and perform translation based on those standards. For example, it performs translation taking specific cultural background into consideration. This improves the quality of discussions by adding an automatic translation function to adapt the language and expressions used in a discussion to different languages ​​and cultures.

[0041] The solution presentation unit can analyze data from past discussions, learn not only successful solutions but also unsuccessful cases, and present the reasons for their success. For example, the generation AI can analyze data from past discussions, learn not only successful solutions but also unsuccessful cases, and present the reasons for their success. For example, it can analyze the factors behind successful cases and the causes of unsuccessful cases and use this as reference for discussions. The solution presentation unit can also classify data from past discussions and present solutions based on each case. For example, it can present solutions based on a specific topic or theme. Furthermore, the solution presentation unit can compare successful cases with unsuccessful cases and present a solution based on the comparison results. For example, it can analyze the differences between successful and unsuccessful cases and present a solution based on those differences. In this way, the system can learn not only successful solutions but also unsuccessful cases and present the reasons for their success, thereby improving the quality of discussions.

[0042] The solution presentation unit can analyze past discussion data in chronological order to clarify discussion progression patterns and trends. For example, the solution presentation unit uses a generation AI to analyze past discussion data in chronological order to clarify discussion progression patterns and trends. For example, it displays the discussion progression patterns and trends in graphs and charts. The solution presentation unit can also analyze past discussion data to clarify progression patterns and trends based on a specific period or topic. For example, it can analyze the progression patterns of discussions on a specific theme and show the trends. Furthermore, the solution presentation unit can predict future discussions based on the discussion progression patterns and trends. For example, it can predict future discussion progression patterns based on past data and present the prediction results. In this way, the quality of discussions can be improved by analyzing past discussion data in chronological order to clarify discussion progression patterns and trends.

[0043] The solution presentation unit can compare data from past discussions with different industries or fields and apply solutions that have been successful in other fields. For example, the generative AI can compare data from past discussions with different industries or fields and apply solutions that have been successful in other fields. For example, it can apply successful cases from the medical field to the technology field. The solution presentation unit can also classify data from different industries or fields and present solutions based on each data. For example, it can present solutions based on a specific industry or field. Furthermore, the solution presentation unit can integrate data from different industries or fields and present solutions based on the integrated data. For example, it can integrate data from the medical field and the technology field and present solutions based on the integrated data. This improves the quality of discussions by comparing data from different industries or fields and applying solutions that have been successful in other fields.

[0044] The solution presentation unit can translate past discussion data into different languages ​​and present solutions from an international perspective. For example, the solution presentation unit uses a generation AI to translate past discussion data into different languages ​​and present solutions from an international perspective. For example, it translates English discussion data into Japanese and presents solutions from an international perspective. The solution presentation unit can also translate discussion data in multiple languages ​​simultaneously and present solutions in each language. For example, it can translate discussion data into English and French simultaneously and present solutions in each language. Furthermore, the solution presentation unit can integrate discussion data in different languages ​​and present solutions based on the integrated data. For example, it can integrate English and Japanese discussion data and present solutions based on the integrated data. In this way, the quality of discussions is improved by translating past discussion data into different languages ​​and presenting solutions from an international perspective.

[0045] The solution presentation unit can analyze the data and evidence presented during a discussion and evaluate its reliability and relevance. For example, the solution presentation unit can analyze the data and evidence presented during a discussion by a generation AI and evaluate its reliability and relevance. For example, it can point out problems with the source of the data or sample size. The solution presentation unit can also evaluate the relevance of the presented data and evidence and, if the relevance is low, can present the reasons. For example, if the data is not directly related to the topic of the discussion, it can present the reasons. Furthermore, the solution presentation unit can set criteria for evaluating the reliability and relevance of data and evidence and perform evaluations based on those criteria. For example, it can evaluate based on the reproducibility of the data and verification results. In this way, the quality of discussions can be improved by evaluating the reliability and relevance of data and evidence.

[0046] The solution presentation unit can analyze discussion data in real time and generate a dashboard to support data-based decision-making. For example, the solution presentation unit uses a generation AI to analyze discussion data in real time and generate a dashboard to support data-based decision-making. For example, the progress of the discussion and the reliability of the data are visually displayed. The solution presentation unit can also update data in real time and generate a dashboard based on the updated data. For example, the solution presentation unit can update data according to the progress of the discussion and display a dashboard that reflects the updated data. Furthermore, the solution presentation unit can customize the dashboard display method and display it according to the user's needs. For example, specific data can be highlighted or an interactive UI can be provided. This improves the quality of discussions by generating a dashboard to support data-based decision-making.

[0047] The solution presentation unit can compare data from different industries and fields to support data-driven decision-making and derive optimal conclusions. For example, the solution presentation unit compares data from different industries and fields to derive optimal conclusions for generative AI to support data-driven decision-making. For example, it compares data from the medical field and data from the technology field to derive optimal conclusions. The solution presentation unit can also classify data from different industries and fields and derive conclusions based on each data. For example, it can classify data based on a specific industry or field and derive conclusions based on the classified data. Furthermore, the solution presentation unit can apply an optimization algorithm based on the compared data and present the optimization results. For example, it can compare data from different industries and fields and derive optimal conclusions based on the comparison results. This supports data-driven decision-making by comparing data from different industries and fields and deriving optimal conclusions.

[0048] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0049] The logical structure analysis unit can automatically detect metaphors and analogies used in discussions and present specific examples. For example, it can detect metaphorical expressions and explain their specific meanings. The logical structure analysis unit can also classify types of metaphors and analogies and present specific examples of each. For example, it can classify expressions that use analogies to animals or natural phenomena and display specific examples. Furthermore, the logical structure analysis unit can evaluate the impact of metaphors and analogies and visually show that impact. For example, it can evaluate the impact of metaphors on the entire discussion and reflect that impact in a diagram. In this way, the quality of discussions can be improved by automatically detecting metaphors and analogies and presenting specific examples.

[0050] The diagramming unit can automatically recognize technical terms and jargon used in discussions and add annotations that concisely explain them in real time. For example, it can recognize technical terms used in discussions in the medical field and display their definitions and related information. The diagramming unit can also recognize technical terms used in discussions in technical fields and add their explanations. For example, it can recognize programming terms and engineering terms and display their meanings. The diagramming unit can also recognize industry-specific terms and add their annotations. For example, it can recognize financial industry terms and marketing terms and display their explanations. This makes it easier for participants to understand the discussion by explaining technical terms and jargon used in discussions in real time.

[0051] The diagramming unit can automatically refer to related past discussions and literature as the discussion progresses and add them to the diagram in real time. For example, it can refer to past meeting records and related research papers to provide background information for the discussion. The diagramming unit can also analyze data from past discussions, extract relevant information, and add it to the diagram. For example, it can refer to evidence and data presented in past discussions and reflect that information in the diagram. The diagramming unit can also automatically search for related literature and add that information to the diagram. For example, it can search for related academic papers and technical reports and reflect their contents in the diagram. In this way, by referring to related past discussions and literature in real time as the discussion progresses, background information for the discussion can be provided and the discussion can be deepened.

[0052] The diagramming unit can display the diagram of the argument as a 3D model or in a virtual reality environment, allowing participants to understand it more intuitively. For example, the arguments and counterarguments of the argument can be displayed as 3D objects to visually show the logical flow. The diagramming unit can also use a virtual reality (VR) environment to diagram the argument. For example, a VR headset can be used to display the content of the argument in a virtual space, allowing participants to experience the flow of the argument within it. The diagramming unit can also use the 3D model or VR environment to allow participants to interactively manipulate the content of the argument. For example, participants can manipulate the 3D objects to change the flow of the argument or display additional information. Thus, displaying the diagram of the argument as a 3D model or in a virtual reality (VR) environment allows participants to understand the argument more intuitively.

[0053] The logical structure analysis unit can automatically detect logical fallacies used in arguments and present specific examples. For example, it can detect straw man arguments and ad hominem attacks and display specific examples. The logical structure analysis unit can also classify types of logical fallacies and present specific examples of each. For example, it can detect incorrect causal relationships and circular reasoning and display specific examples. Furthermore, the logical structure analysis unit can evaluate the impact of logical fallacies and visually show that impact. For example, it can evaluate the impact of logical fallacies on the entire argument and reflect that impact in a diagram. In this way, the quality of arguments can be improved by automatically detecting logical fallacies and presenting specific examples.

[0054] When detecting illogical discourse, the logical structure analysis unit can generate reasons from a global perspective, taking into account biases based on different cultures and values. For example, it can present reasons taking into account differences in cultural backgrounds and values. The logical structure analysis unit can also evaluate biases based on different cultures and values ​​and visually show their impact. For example, it can evaluate the impact of cultural bias on a discussion and reflect that impact in a diagram. Furthermore, the logical structure analysis unit can suggest methods for removing biases based on different cultures and values. For example, it can suggest methods for promoting intercultural communication. This improves the quality of discussions by generating reasons from a global perspective, taking into account biases based on different cultures and values.

[0055] The processing flow of the first embodiment will be briefly explained below.

[0056] Step 1: The logical structure analysis unit analyzes the content of the argument. For example, it uses natural language processing technology to analyze the content of the argument and extract arguments, counterarguments, and evidence. It also uses sentiment analysis technology to analyze the emotional aspects of the argument and calculates an emotional score to evaluate the emotional tone of the argument. It also uses a logical structure analysis algorithm to detect logical errors and contradictions. Step 2: The diagramming section diagrams the content analyzed by the logical structure analysis section. For example, a flowchart can be used to visually show the flow of the discussion, a mind map can be used to organize the structure of the discussion, or a concept diagram can be used to show the conceptual relationships of the discussion. Step 3: The bias removal unit removes emotional and status-based biases from the schematized content, for example, by converting emotional expressions into neutral ones and detecting and correcting social and cultural biases. Step 4: The solution presentation part learns from past discussions and proposes solutions when a problem arises. For example, it analyzes data from similar past discussions and presents successful solutions and causes of failure. It also analyzes the progress patterns and trends of the discussion and proposes solutions based on that.

[0057] (Example 2) The AI-based solution according to an embodiment of the present invention is a system that diagrams the logical structure of a conversation in real time and generates illogical statements and the reasons for them, thereby promoting clear and fair communication and deriving high-quality conclusions.

[0058] The AI-based solution according to the embodiment includes a logical structure analysis unit, a diagramming unit, a bias removal unit, and a solution presentation unit. The logical structure analysis unit analyzes the content of an argument. For example, it analyzes the content of the argument using natural language processing technology and extracts arguments, counterarguments, evidence, etc. The logical structure analysis unit can also analyze the emotional aspects of the argument using sentiment analysis technology. For example, it calculates a sentiment score and evaluates the emotional tone of the argument. The logical structure analysis unit can also analyze the logical flow of the argument using a logical structure analysis algorithm. For example, it can detect logical errors and contradictions. The diagramming unit diagrams the content analyzed by the logical structure analysis unit. For example, it can visually show the flow of the argument using a flowchart. The diagramming unit can also organize the structure of the argument using a mind map. For example, it can arrange arguments, counterarguments, and evidence as nodes and connect them with links. The diagramming unit can also show the conceptual relationships of the argument using a concept diagram. For example, it can show the relationships between concepts using arrows. The bias removal unit removes biases based on emotions and status from the content schematized by the schematization unit. For example, it converts emotional expressions into neutral expressions. The bias removal unit can also detect and remove social biases. For example, it identifies and corrects biases based on specific status or background. The bias removal unit can also detect and remove cultural biases. For example, it considers and corrects biases based on different cultures. The solution presentation unit learns from past discussions and presents solutions when a problem arises. For example, it analyzes data from similar past discussions and proposes successful solutions. The solution presentation unit can also learn from unsuccessful cases and present the reasons for failure. For example, it analyzes the causes of failure and proposes areas for improvement. The solution presentation unit can also analyze discussion progression patterns and trends and present solutions based on the results. For example, it can analyze discussion progression patterns over time to identify trends. As a result, the AI-based solution according to the embodiment can promote clear and fair communication and derive high-quality conclusions. For example, in meetings and discussions, all participants can exchange opinions logically and fairly and make optimal decisions.In addition, by utilizing data from past discussions, solutions can be found smoothly even when a deadlock occurs.

[0059] The diagramming unit can automatically recognize technical terms and jargon used in discussions and add annotations that concisely explain them in real time. For example, the diagramming unit uses a generative AI to automatically recognize technical terms and jargon used in discussions and add annotations that concisely explain their meaning and background in real time. For example, it recognizes technical terms used in discussions in the medical field and displays their definitions and related information. The diagramming unit can also recognize technical terms used in discussions in technology fields and add their explanations. For example, it recognizes programming terms and engineering terms and displays their meanings. The diagramming unit can also recognize industry-specific terms and add their annotations. For example, it recognizes financial industry terms and marketing terms and displays their explanations. This makes it easier for participants to understand the discussion by explaining the technical terms and jargon used in discussions in real time.

[0060] The diagramming unit can automatically refer to related past discussions and literature as the discussion progresses and add that information to the diagram in real time. For example, the generation AI can automatically refer to related past discussions and literature as the discussion progresses and add that information to the diagram in real time. For example, it can refer to past meeting records and related research papers to provide background information for the discussion. The diagramming unit can also analyze data from past discussions, extract relevant information, and add it to the diagram. For example, it can refer to evidence and data presented in past discussions and reflect that in the diagram. Furthermore, the diagramming unit can automatically search for related literature and add that information to the diagram. For example, it can search for related academic papers and technical reports and reflect their contents in the diagram. In this way, by referring to related past discussions and literature in real time as the discussion progresses, it is possible to provide background information for the discussion and deepen the discussion.

[0061] The diagramming unit can use the emotion estimation function to highlight emotional statements made during a discussion, visually displaying the impact of those emotions. For example, the diagramming unit provides a function in which the generative AI detects emotional statements during a discussion and highlights those parts. For example, when an emotional statement is made, the part is displayed in a different color to visually indicate the impact of the emotion. The diagramming unit can also use an emotion estimation algorithm to evaluate the intensity of the emotional statement and change the display method depending on that intensity. For example, if the emotional intensity is high, it will be displayed more emphasized. Furthermore, the diagramming unit can classify the type of emotional statement and change the display method depending on that type. For example, it can distinguish between positive and negative emotions and display them in different colors. In this way, highlighting emotional statements visually shows the impact of emotions during a discussion, making it easier for participants to understand that impact.

[0062] The diagramming unit can display the diagram of the argument as a 3D model or in a virtual reality environment, allowing participants to understand it more intuitively. For example, the diagramming unit uses a generative AI to display the logical structure of the argument as a 3D model, allowing participants to understand it more intuitively. For example, the arguments and counterarguments of the argument can be displayed as 3D objects to visually show the logical flow. The diagramming unit can also use a virtual reality (VR) environment to diagram the argument. For example, a VR headset can be used to display the content of the argument in a virtual space, allowing participants to experience the flow of the argument within it. Furthermore, the diagramming unit can use the 3D model or VR environment to allow participants to interactively manipulate the content of the argument. For example, participants can manipulate the 3D objects to change the flow of the argument or display additional information. Thus, displaying the diagram of the argument as a 3D model or in a virtual reality (VR) environment allows participants to understand the argument more intuitively.

[0063] The diagramming unit can promote multilingual communication by translating and diagramming discussions in different languages ​​in real time. The diagramming unit, for example, provides a function whereby a generative AI translates discussions in different languages ​​in real time and diagrams their contents. For example, it can translate a discussion in English into Japanese and diagram the logical structure. The diagramming unit can also translate discussions in multiple languages ​​simultaneously and diagram them in each language. For example, it can translate a discussion in English and French simultaneously and diagram them in each language. Furthermore, the diagramming unit can integrate discussions in different languages ​​and summarize them into a common diagram. For example, it can integrate discussions in English and Japanese and reflect them in a common diagram. In this way, it can promote multilingual communication by translating discussions in different languages ​​in real time and diagramming them.

[0064] The diagramming unit uses the emotion estimation function to emphasize parts of a discussion where positive emotions are strong, making it easier for participants to focus on those parts. For example, the diagramming unit provides a function where the generative AI detects parts of a discussion where positive emotions are strong and highlights those parts. For example, when a positive comment is made, that part is displayed in a different color, making it easier for participants to focus on it. The diagramming unit can also use an emotion estimation algorithm to evaluate the intensity of positive emotions and change the display method depending on that intensity. For example, if the intensity of positive emotions is high, they are displayed more emphasized. Furthermore, the diagramming unit can classify types of positive emotions and change the display method depending on that type. For example, emotions such as joy and gratitude can be distinguished and displayed in different colors. This allows parts with strong positive emotions to be highlighted, making it easier for participants to focus on them.

[0065] The logical structure analysis unit can automatically detect logical fallacies used in arguments and present specific examples. For example, the logical structure analysis unit can automatically detect logical fallacies used in arguments using generative AI and present specific examples. For example, it can detect straw man arguments and ad hominem attacks and display specific examples. The logical structure analysis unit can also classify types of logical fallacies and present specific examples of each. For example, it can detect incorrect causal relationships and circular reasoning and display specific examples. Furthermore, the logical structure analysis unit can evaluate the impact of logical fallacies and visually show that impact. For example, it can evaluate the impact of logical fallacies on the entire argument and reflect that impact in a diagram. This improves the quality of arguments by automatically detecting logical fallacies and presenting specific examples.

[0066] The logical structure analysis unit can use the emotion estimation function to detect statements that contain emotional bias and visually display their impact. For example, the logical structure analysis unit uses the emotion estimation function to detect statements that contain emotional bias and visually display their impact. For example, if an emotional statement is made, it will be displayed in a different color. The logical structure analysis unit can also evaluate the strength of the emotional bias and change the display method depending on the strength. For example, if the emotion is highly intense, it will be displayed more emphatically. Furthermore, the logical structure analysis unit can classify the type of emotional bias and change the display method depending on the type. For example, it can distinguish between emotions such as anger and sadness and display them in different colors. This improves the quality of discussions by detecting statements that contain emotional bias and visually displaying their impact.

[0067] When detecting illogical statements, the logical structure analysis unit can generate reasons from a global perspective, taking into account biases based on different cultures and values. For example, when a generative AI detects illogical statements, the logical structure analysis unit can generate reasons from a global perspective, taking into account biases based on different cultures and values. For example, it can present reasons taking into account differences in cultural background and values. The logical structure analysis unit can also evaluate biases based on different cultures and values ​​and visually show their impact. For example, it can evaluate the impact of cultural bias on a discussion and reflect that impact in a diagram. Furthermore, the logical structure analysis unit can suggest methods for removing biases based on different cultures and values. For example, it can suggest methods for promoting intercultural communication. This improves the quality of discussions by generating reasons from a global perspective, taking into account biases based on different cultures and values.

[0068] The logical structure analysis unit can refer to the opinions of experts in different fields and present reasons from multiple perspectives to detect logical flaws. For example, in order for generative AI to detect logical flaws, the logical structure analysis unit can refer to the opinions of experts in different fields and present reasons from multiple perspectives. For example, it can refer to the opinions of experts in the medical and legal fields to present reasons. The logical structure analysis unit can also classify expert opinions and present reasons from each perspective. For example, it can present reasons from a technical perspective or an economic perspective. Furthermore, the logical structure analysis unit can evaluate expert opinions and visually indicate their reliability. For example, it can evaluate the reliability of expert opinions and reflect the evaluation results in a diagram. This improves the quality of discussions by referring to the opinions of experts in different fields and presenting reasons from multiple perspectives.

[0069] The logical structure analysis unit can use the emotion estimation function to collect users' emotional reactions to illogical statements and generate reasons based on those reactions. For example, the generation AI can use the emotion estimation function to collect users' emotional reactions to illogical statements and generate reasons based on those reactions. For example, it can highlight the parts to which the user reacted emotionally and present the reasons. The logical structure analysis unit can also classify types of emotional reactions and generate reasons based on each reaction. For example, it can distinguish between positive and negative emotions and present reasons based on each emotion. Furthermore, the logical structure analysis unit can evaluate the intensity of the emotional reaction and generate reasons based on that intensity. For example, if the intensity of the emotion is high, it can present more detailed reasons. In this way, by collecting users' emotional reactions and generating reasons based on those reactions, the quality of discussions is improved.

[0070] The bias removal unit can analyze the language and expressions used in a discussion and automatically correct parts that contain emotional bias. For example, the bias removal unit uses a generative AI to analyze the language and expressions used in a discussion and automatically correct parts that contain emotional bias. For example, it replaces emotional expressions with neutral expressions. The bias removal unit can also classify types of emotional bias and make corrections based on each bias. For example, it can distinguish between emotions such as anger and sadness and make corrections based on each emotion. Furthermore, the bias removal unit can evaluate the strength of emotional bias and change the correction method depending on that strength. For example, if the intensity of the emotion is high, it will change to a more neutral expression. This improves the quality of the discussion by automatically correcting parts that contain emotional bias.

[0071] The bias removal unit can anonymize the identities and background information of discussion participants, minimizing the influence of bias. For example, the generative AI can anonymize the identities and background information of discussion participants to minimize the influence of bias. For example, it can hide the names and occupations of participants and display only the content of their opinions. The bias removal unit can also set criteria for anonymizing participants' background information and perform anonymization based on those criteria. For example, it can delete specific personal information and use pseudonyms. Furthermore, the bias removal unit can evaluate the anonymized information and visually display the evaluation results. For example, it can evaluate the degree of anonymization and reflect the evaluation results in a diagram. In this way, the influence of bias can be minimized by anonymizing the identities and background information of participants.

[0072] The bias removal unit can use the emotion estimation function to detect statements with strong emotional bias and convert them into neutral expressions. For example, the generative AI can use the emotion estimation function to detect statements with strong emotional bias and convert them into neutral expressions. For example, it can remove emotional emphasis and change them to fact-based expressions. The bias removal unit can also classify types of emotional bias and make corrections based on each bias. For example, it can distinguish between emotions such as anger and sadness and make corrections based on each emotion. Furthermore, the bias removal unit can evaluate the strength of emotional bias and change the correction method depending on the strength. For example, if the intensity of the emotion is high, it can change it to a more neutral expression. This improves the quality of discussion by converting statements with strong emotional bias into neutral expressions.

[0073] The bias removal unit can take into account biases based on different cultures and values ​​and make corrections from a global perspective to remove biases based on emotions and status. For example, in order for the generative AI to remove biases based on emotions and status, the bias removal unit can take into account biases based on different cultures and values ​​and make corrections from a global perspective. For example, it makes corrections taking into account differences in cultural background and values. The bias removal unit can also evaluate biases based on different cultures and values ​​and visually show their impact. For example, it can evaluate the impact of cultural bias on a discussion and reflect that impact in a diagram. Furthermore, the bias removal unit can suggest methods to remove biases based on different cultures and values. For example, it can suggest methods to promote intercultural communication. This improves the quality of discussions by taking into account biases based on different cultures and values ​​and making corrections from a global perspective.

[0074] The bias removal unit can add an automatic translation function to adapt the language and expressions used in a discussion to different languages ​​and cultures. For example, the bias removal unit provides an automatic translation function that enables the generative AI to adapt the language and expressions used in a discussion to different languages ​​and cultures. For example, it translates a discussion in English into Japanese and adjusts the expressions taking cultural background into consideration. The bias removal unit can also translate discussions in multiple languages ​​simultaneously and adapt them in each language. For example, it can translate discussions in English and French simultaneously and adapt them to each culture. Furthermore, the bias removal unit can set standards for adaptation to different languages ​​and cultures and perform translation based on those standards. For example, it performs translation taking specific cultural background into consideration. This improves the quality of discussions by adding an automatic translation function to adapt the language and expressions used in a discussion to different languages ​​and cultures.

[0075] The solution presentation unit can analyze data from past discussions, learn not only successful solutions but also unsuccessful cases, and present the reasons for their success. For example, the generation AI can analyze data from past discussions, learn not only successful solutions but also unsuccessful cases, and present the reasons for their success. For example, it can analyze the factors behind successful cases and the causes of unsuccessful cases and use this as reference for discussions. The solution presentation unit can also classify data from past discussions and present solutions based on each case. For example, it can present solutions based on a specific topic or theme. Furthermore, the solution presentation unit can compare successful cases with unsuccessful cases and present a solution based on the comparison results. For example, it can analyze the differences between successful and unsuccessful cases and present a solution based on those differences. In this way, the system can learn not only successful solutions but also unsuccessful cases and present the reasons for their success, thereby improving the quality of discussions.

[0076] The solution presentation unit can analyze past discussion data in chronological order to clarify discussion progression patterns and trends. For example, the solution presentation unit uses a generation AI to analyze past discussion data in chronological order to clarify discussion progression patterns and trends. For example, it displays the discussion progression patterns and trends in graphs and charts. The solution presentation unit can also analyze past discussion data to clarify progression patterns and trends based on a specific period or topic. For example, it can analyze the progression patterns of discussions on a specific theme and show the trends. Furthermore, the solution presentation unit can predict future discussions based on the discussion progression patterns and trends. For example, it can predict future discussion progression patterns based on past data and present the prediction results. In this way, the quality of discussions can be improved by analyzing past discussion data in chronological order to clarify discussion progression patterns and trends.

[0077] The solution presentation unit can use the emotion estimation function to detect parts of past discussions where emotional bias is strong and present solutions that take that influence into account. For example, the generation AI uses the emotion estimation function to detect parts of past discussions where emotional bias is strong and presents solutions that take that influence into account. For example, it may color-code parts with strong emotional bias and present solutions that take that influence into account. The solution presentation unit can also evaluate the strength of emotional bias and present solutions based on that strength. For example, if the intensity of the emotion is high, it may present more detailed solutions. Furthermore, the solution presentation unit can classify types of emotional bias and present solutions based on each bias. For example, it may distinguish between emotions such as anger and sadness and present solutions based on each emotion. This improves the quality of discussions by detecting parts with strong emotional bias and presenting solutions that take that influence into account.

[0078] The solution presentation unit can compare data from past discussions with different industries or fields and apply solutions that have been successful in other fields. For example, the generative AI can compare data from past discussions with different industries or fields and apply solutions that have been successful in other fields. For example, it can apply successful cases from the medical field to the technology field. The solution presentation unit can also classify data from different industries or fields and present solutions based on each data. For example, it can present solutions based on a specific industry or field. Furthermore, the solution presentation unit can integrate data from different industries or fields and present solutions based on the integrated data. For example, it can integrate data from the medical field and the technology field and present solutions based on the integrated data. This improves the quality of discussions by comparing data from different industries or fields and applying solutions that have been successful in other fields.

[0079] The solution presentation unit can translate past discussion data into different languages ​​and present solutions from an international perspective. For example, the solution presentation unit uses a generation AI to translate past discussion data into different languages ​​and present solutions from an international perspective. For example, it translates English discussion data into Japanese and presents solutions from an international perspective. The solution presentation unit can also translate discussion data in multiple languages ​​simultaneously and present solutions in each language. For example, it can translate discussion data into English and French simultaneously and present solutions in each language. Furthermore, the solution presentation unit can integrate discussion data in different languages ​​and present solutions based on the integrated data. For example, it can integrate English and Japanese discussion data and present solutions based on the integrated data. In this way, the quality of discussions is improved by translating past discussion data into different languages ​​and presenting solutions from an international perspective.

[0080] The solution presentation unit can use the emotion estimation function to highlight parts of past discussions where positive emotions were strong and present solutions that take those parts into consideration. For example, the solution presentation unit provides a function in which the generation AI uses the emotion estimation function to detect parts of past discussions where positive emotions were strong and highlight those parts. For example, parts where positive comments were made can be displayed in different colors and solutions that take those parts into consideration can be presented. The solution presentation unit can also evaluate the intensity of positive emotions and present solutions based on that intensity. For example, if the intensity of positive emotions is high, more detailed solutions can be presented. Furthermore, the solution presentation unit can classify types of positive emotions and present solutions based on each emotion. For example, it can distinguish between emotions such as joy and gratitude and present solutions based on each emotion. This improves the quality of discussions by highlighting parts where positive emotions were strong and presenting solutions that take those parts into consideration.

[0081] The solution presentation unit can analyze the data and evidence presented during a discussion and evaluate its reliability and relevance. For example, the solution presentation unit can analyze the data and evidence presented during a discussion by a generation AI and evaluate its reliability and relevance. For example, it can point out problems with the source of the data or sample size. The solution presentation unit can also evaluate the relevance of the presented data and evidence and, if the relevance is low, can present the reasons. For example, if the data is not directly related to the topic of the discussion, it can present the reasons. Furthermore, the solution presentation unit can set criteria for evaluating the reliability and relevance of data and evidence and perform evaluations based on those criteria. For example, it can evaluate based on the reproducibility of the data and verification results. In this way, the quality of discussions can be improved by evaluating the reliability and relevance of data and evidence.

[0082] The solution presentation unit can analyze discussion data in real time and generate a dashboard to support data-based decision-making. For example, the solution presentation unit uses a generation AI to analyze discussion data in real time and generate a dashboard to support data-based decision-making. For example, the progress of the discussion and the reliability of the data are visually displayed. The solution presentation unit can also update data in real time and generate a dashboard based on the updated data. For example, the solution presentation unit can update data according to the progress of the discussion and display a dashboard that reflects the updated data. Furthermore, the solution presentation unit can customize the dashboard display method and display it according to the user's needs. For example, specific data can be highlighted or an interactive UI can be provided. This improves the quality of discussions by generating a dashboard to support data-based decision-making.

[0083] The solution presentation unit can use the emotion estimation function to detect parts of a discussion where emotional bias is strong and support decision-making that takes its impact into account. For example, the generation AI can use the emotion estimation function to detect parts of a discussion where emotional bias is strong and support decision-making that takes its impact into account. For example, parts with strong emotional bias can be displayed in different colors to support decision-making that takes their impact into account. The solution presentation unit can also evaluate the strength of emotional bias and support decision-making based on that strength. For example, if the intensity of the emotion is high, more detailed decision-making support can be provided. Furthermore, the solution presentation unit can classify types of emotional bias and support decision-making based on each bias. For example, it can distinguish between emotions such as anger and sadness and support decision-making based on each emotion. This improves the quality of discussions by detecting parts with strong emotional bias and supporting decision-making that takes their impact into account.

[0084] The solution presentation unit can compare data from different industries and fields to support data-driven decision-making and derive optimal conclusions. For example, the solution presentation unit compares data from different industries and fields to derive optimal conclusions for generative AI to support data-driven decision-making. For example, it compares data from the medical field and data from the technology field to derive optimal conclusions. The solution presentation unit can also classify data from different industries and fields and derive conclusions based on each data. For example, it can classify data based on a specific industry or field and derive conclusions based on the classified data. Furthermore, the solution presentation unit can apply an optimization algorithm based on the compared data and present the optimization results. For example, it can compare data from different industries and fields and derive optimal conclusions based on the comparison results. This supports data-driven decision-making by comparing data from different industries and fields and deriving optimal conclusions.

[0085] The solution presentation unit can use the emotion estimation function to highlight parts of a discussion where positive emotions are strong and support decision-making by taking those parts into consideration. For example, the solution presentation unit provides a function in which the generation AI uses the emotion estimation function to detect parts of a discussion where positive emotions are strong and highlight those parts. For example, parts where positive comments were made can be displayed in different colors to support decision-making by taking those parts into consideration. The solution presentation unit can also evaluate the intensity of positive emotions and support decision-making based on that intensity. For example, if the intensity of positive emotions is high, more detailed decision-making support can be provided. Furthermore, the solution presentation unit can classify types of positive emotions and support decision-making based on each emotion. For example, it can distinguish between emotions such as joy and gratitude and support decision-making based on each emotion. This improves the quality of discussions by highlighting parts where positive emotions are strong and supporting decision-making by taking those parts into consideration.

[0086] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0087] The logical structure analysis unit can automatically detect metaphors and analogies used in discussions and present specific examples. For example, it can detect metaphorical expressions and explain their specific meanings. The logical structure analysis unit can also classify types of metaphors and analogies and present specific examples of each. For example, it can classify expressions that use analogies to animals or natural phenomena and display specific examples. Furthermore, the logical structure analysis unit can evaluate the impact of metaphors and analogies and visually show that impact. For example, it can evaluate the impact of metaphors on the entire discussion and reflect that impact in a diagram. In this way, the quality of discussions can be improved by automatically detecting metaphors and analogies and presenting specific examples.

[0088] The diagramming unit can automatically detect humor or jokes used in a discussion and highlight those parts. For example, if humor or jokes are present, they can be displayed in different colors, making it easier for participants to focus on them. The diagramming unit can also classify types of humor or jokes and change the way they are displayed depending on their type. For example, it can distinguish between sarcasm and satire and display them in different colors. Furthermore, the diagramming unit can evaluate the impact of humor or jokes and visually show that impact. For example, it can evaluate the impact that humor has on the atmosphere of the discussion and reflect that impact in the diagram. In this way, highlighting humor or jokes visually shows the emotional impact in the discussion, making it easier for participants to understand that impact.

[0089] The diagramming unit can automatically recognize technical terms and jargon used in discussions and add annotations that concisely explain them in real time. For example, it can recognize technical terms used in discussions in the medical field and display their definitions and related information. The diagramming unit can also recognize technical terms used in discussions in technical fields and add their explanations. For example, it can recognize programming terms and engineering terms and display their meanings. The diagramming unit can also recognize industry-specific terms and add their annotations. For example, it can recognize financial industry terms and marketing terms and display their explanations. This makes it easier for participants to understand the discussion by explaining technical terms and jargon used in discussions in real time.

[0090] The diagramming unit can automatically refer to related past discussions and literature as the discussion progresses and add them to the diagram in real time. For example, it can refer to past meeting records and related research papers to provide background information for the discussion. The diagramming unit can also analyze data from past discussions, extract relevant information, and add it to the diagram. For example, it can refer to evidence and data presented in past discussions and reflect that information in the diagram. The diagramming unit can also automatically search for related literature and add that information to the diagram. For example, it can search for related academic papers and technical reports and reflect their contents in the diagram. In this way, by referring to related past discussions and literature in real time as the discussion progresses, background information for the discussion can be provided and the discussion can be deepened.

[0091] The diagramming unit can use the emotion estimation function to highlight emotional comments made during a discussion and visually display the impact of the emotion. For example, if an emotional comment is made, the comment can be displayed in a different color to visually indicate the impact of the emotion. The diagramming unit can also use an emotion estimation algorithm to evaluate the intensity of the emotional comment and change the display method depending on the intensity. For example, if the intensity of the emotion is high, it can be displayed more emphasized. Furthermore, the diagramming unit can classify the type of emotional comment and change the display method depending on the type. For example, it can distinguish between positive and negative emotions and display them in different colors. In this way, by highlighting emotional comments, the impact of emotions in a discussion can be visually indicated, making it easier for participants to understand that impact.

[0092] The diagramming unit can display the diagram of the argument as a 3D model or in a virtual reality environment, allowing participants to understand it more intuitively. For example, the arguments and counterarguments of the argument can be displayed as 3D objects to visually show the logical flow. The diagramming unit can also use a virtual reality (VR) environment to diagram the argument. For example, a VR headset can be used to display the content of the argument in a virtual space, allowing participants to experience the flow of the argument within it. The diagramming unit can also use the 3D model or VR environment to allow participants to interactively manipulate the content of the argument. For example, participants can manipulate the 3D objects to change the flow of the argument or display additional information. Thus, displaying the diagram of the argument as a 3D model or in a virtual reality (VR) environment allows participants to understand the argument more intuitively.

[0093] The diagramming unit can use its emotion estimation function to highlight parts of a discussion where positive emotions are strong, making it easier for participants to focus on those parts. For example, if a positive comment is made, that part can be displayed in a different color, making it easier for participants to focus on it. The diagramming unit can also use an emotion estimation algorithm to evaluate the strength of positive emotions and change the display method depending on that strength. For example, if the strength of positive emotions is high, they will be displayed more emphasized. Furthermore, the diagramming unit can classify types of positive emotions and change the display method depending on that type. For example, emotions such as joy and gratitude can be distinguished and displayed in different colors. This allows parts with strong positive emotions to be highlighted, making it easier for participants to focus on those parts.

[0094] The logical structure analysis unit can automatically detect logical fallacies used in arguments and present specific examples. For example, it can detect straw man arguments and ad hominem attacks and display specific examples. The logical structure analysis unit can also classify types of logical fallacies and present specific examples of each. For example, it can detect incorrect causal relationships and circular reasoning and display specific examples. Furthermore, the logical structure analysis unit can evaluate the impact of logical fallacies and visually show that impact. For example, it can evaluate the impact of logical fallacies on the entire argument and reflect that impact in a diagram. In this way, the quality of arguments can be improved by automatically detecting logical fallacies and presenting specific examples.

[0095] The logical structure analysis unit uses the emotion estimation function to detect statements that contain emotional bias and visually display their impact. For example, if an emotional statement is made, it will be displayed in a different color. The logical structure analysis unit can also evaluate the strength of the emotional bias and change the display method depending on that strength. For example, if the emotional strength is high, it will be displayed more emphasized. Furthermore, the logical structure analysis unit can classify the type of emotional bias and change the display method depending on that type. For example, it can distinguish between emotions such as anger and sadness and display them in different colors. This improves the quality of discussions by detecting statements that contain emotional bias and visually showing their impact.

[0096] When detecting illogical discourse, the logical structure analysis unit can generate reasons from a global perspective, taking into account biases based on different cultures and values. For example, it can present reasons taking into account differences in cultural backgrounds and values. The logical structure analysis unit can also evaluate biases based on different cultures and values ​​and visually show their impact. For example, it can evaluate the impact of cultural bias on a discussion and reflect that impact in a diagram. Furthermore, the logical structure analysis unit can suggest methods for removing biases based on different cultures and values. For example, it can suggest methods for promoting intercultural communication. This improves the quality of discussions by generating reasons from a global perspective, taking into account biases based on different cultures and values.

[0097] The processing flow of the second embodiment will be briefly explained below.

[0098] Step 1: The logical structure analysis unit analyzes the content of the argument. For example, it uses natural language processing technology to analyze the content of the argument and extract arguments, counterarguments, and evidence. It also uses sentiment analysis technology to analyze the emotional aspects of the argument and calculates an emotional score to evaluate the emotional tone of the argument. It also uses a logical structure analysis algorithm to detect logical errors and contradictions. Step 2: The diagramming section diagrams the content analyzed by the logical structure analysis section. For example, a flowchart can be used to visually show the flow of the discussion, a mind map can be used to organize the structure of the discussion, or a concept diagram can be used to show the conceptual relationships of the discussion. Step 3: The bias removal unit removes emotional and status-based biases from the schematized content, for example, by converting emotional expressions into neutral ones and detecting and correcting social and cultural biases. Step 4: The solution presentation part learns from past discussions and proposes solutions when a problem arises. For example, it analyzes data from similar past discussions and presents successful solutions and causes of failure. It also analyzes the progress patterns and trends of the discussion and proposes solutions based on that.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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).

[0108] 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.

[0109] 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.

[0110] 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.

[0111] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0112] 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. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0113] 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.

[0114] 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.

[0115] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0116] 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.

[0117] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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).

[0123] 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.

[0124] 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.

[0125] 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.

[0126] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0127] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0128] 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.

[0129] 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.

[0130] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0131] 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.

[0132] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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).

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0143] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0144] 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.

[0145] 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.

[0146] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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).

[0152] 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.

[0153] 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."

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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]

[0166] 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 logical structure analysis unit that analyzes the content of the discussion; a diagramming unit that diagrams the content analyzed by the logical structure analysis unit; a bias removal unit that removes bias based on emotion or status from the content schematized by the schematization unit; A solution presentation unit that learns from past discussions and presents solutions when an impasse occurs. A system characterized by:

2. The diagramming unit As the discussion progresses, relevant past discussions and literature are automatically referenced and added to the diagram in real time.

2. The system of claim 1.

3. The logical structure analysis unit Automatically detects logical fallacies used in arguments and provides examples 2. The system of claim 1.

4. The bias removal unit Analyzing the language and expressions used in discussions and automatically correcting any parts that contain emotional bias 2. The system of claim 1.

5. The solution presentation unit Analyze the data from the past discussions, learn from not only successful solutions but also unsuccessful cases, and present the reasons for them.

2. The system of claim 1.

6. The diagramming unit Highlight emotional statements in discussions to visually display the impact of emotions 2. The system of claim 1.

Images