System

Abstract

An object of the system according to the embodiment is to eliminate emotions and biases during a meeting and realize a logical and constructive discussion.SOLUTION: A system includes an analysis unit, a conversion unit, a collation unit, and a proposal unit. The analysis unit analyzes the utterance in real time and detects an emotion or a bias. The conversion unit converts the emotion or the bias detected by the analysis unit into a neutral expression. The matching unit matches the statement content converted by the conversion unit with the database and provides related evidence. The proposal unit proposes a solution learned from the past discussion based on the evidence provided by the matching unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, emotions and biases can degrade the quality of discussion during meetings.

[0005] The system according to the embodiment aims to eliminate emotions and prejudices during meetings and to realize logical and constructive discussions. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, a conversion unit, a matching unit, and a suggestion unit. The analysis unit analyzes utterances in real time to detect emotions or prejudices. The conversion unit converts the emotions or prejudices detected by the analysis unit into neutral expressions. The matching unit compares the content of the utterances converted by the conversion unit with a database and provides relevant evidence. The suggestion unit learns from past discussions based on the evidence provided by the matching unit and proposes solutions. [Effects of the Invention]

[0007] The system according to the embodiment can eliminate emotions and prejudices during meetings and realize logical and constructive discussions. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A meeting support system according to an embodiment of the present invention supports meetings in real time and enables logical, constructive discussions based on evidence. This meeting support system analyzes comments in real time and filters them to eliminate emotions and biases. It then compares the comments with a database and provides relevant evidence. It also has a function of learning from past discussions and proposing solutions. For example, the meeting support system analyzes comments in real time during a meeting, detects comments containing emotional expressions or bias, and converts them into neutral expressions. This enables fair communication for all participants. The meeting support system then compares the comments with a database and provides relevant evidence. For example, it references past discussions, research results, statistical data, etc. in real time to support comments. This enables logical, constructive discussions. Furthermore, the meeting support system analyzes past meeting records and proposes solutions to similar problems. For example, it analyzes past meeting records and proposes solutions to similar problems. This facilitates smooth discussions and enables efficient decision-making. This allows the meeting support system to promote data-driven decision-making and achieve high-quality results. This allows the meeting support system to support meetings in real time and enable evidence-based, logical, and constructive discussions. For example, it can be used in a variety of situations, such as corporate management meetings and project team meetings, which is expected to improve the performance of the entire organization.

[0029] A conference support system according to an embodiment includes an analysis unit, a conversion unit, a matching unit, and a suggestion unit. The analysis unit analyzes utterances in real time to detect emotions or biases. The analysis unit analyzes utterances using, for example, natural language processing (NLP) or machine learning techniques to detect emotions or biases. The analysis unit can also improve the accuracy of emotion or bias detection by taking into account the context of the utterances. The analysis unit can also analyze the tone and speed of the utterances to help detect emotions and biases. For example, the analysis unit analyzes the tone of the utterances to estimate the intensity of the emotions. The analysis unit can also analyze the speed of the utterances to detect emotional fluctuations. The conversion unit converts the detected emotions or biases into neutral expressions. For example, the conversion unit converts the detected emotions or biases into neutral expressions. The conversion unit can also generate more appropriate neutral expressions by taking into account the context of the utterances. The conversion unit can also apply different conversion algorithms depending on the content of the utterances. For example, if the content of the utterances is emotional, the conversion unit applies a conversion algorithm that suppresses the emotions. In addition, if the content of the utterance is technical, the conversion unit can apply an algorithm that appropriately converts technical terms. The matching unit compares the content of the utterance converted by the conversion unit with a database and provides related evidence. For example, the matching unit compares the content of the utterance with a database and provides related evidence. The matching unit can also improve the accuracy of the related evidence by taking into account the context of the utterance. Furthermore, the matching unit can refer to different databases based on the content of the utterance. The suggestion unit learns from past discussions and proposes solutions based on the evidence provided by the matching unit. For example, the suggestion unit analyzes past discussion records and proposes solutions to similar problems. The suggestion unit can also propose a more appropriate solution by taking into account the context of the utterance. Furthermore, the suggestion unit can apply different suggestion algorithms based on the content of the utterance. As a result, the meeting support system according to the embodiment can support meetings in real time and realize evidence-based, logical, and constructive discussions.

[0030] The analysis unit can analyze utterances and detect emotions or biases using natural language processing or machine learning techniques. Natural language processing includes, but is not limited to, morphological analysis, grammatical analysis, and semantic analysis. For example, the analysis unit uses morphological analysis to segment words in utterances and grammatical analysis to analyze sentence structure. The analysis unit can also understand the meaning of utterances using semantic analysis. Machine learning includes, but is not limited to, supervised learning, unsupervised learning, and reinforcement learning. For example, the analysis unit trains an emotion or bias detection model using supervised learning. The analysis unit can also perform utterance clustering using unsupervised learning. Furthermore, the analysis unit can improve the accuracy of emotion or bias detection using reinforcement learning. Thus, the accuracy of emotion or bias detection is improved by using natural language processing or machine learning techniques. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input text data of utterances to a generation AI and cause the generation AI to detect emotions and biases.

[0031] The conversion unit can convert the detected emotion or prejudice into a neutral expression. Neutral expressions include, but are not limited to, paraphrasing methods to eliminate specific emotions or prejudices. For example, the conversion unit can convert emotional expressions into neutral expressions. The conversion unit can also convert prejudiced expressions into neutral expressions. Furthermore, the conversion unit can generate a more appropriate neutral expression by taking into account the context of the utterance. For example, the conversion unit can analyze the context before and after the utterance to generate an appropriate neutral expression. The conversion unit can also extract keywords related to the topic of the utterance and generate a neutral expression based on the context. This allows fair communication by converting emotion or prejudice into a neutral expression. Some or all of the above-described processing in the conversion unit can be performed using, or without, AI. For example, the conversion unit can input text data of utterances containing emotion or prejudice into a generation AI and have the generation AI convert the data into a neutral expression.

[0032] The matching unit can compare the content of a statement with a database and provide relevant evidence. Examples of databases include, but are not limited to, past discussion records and literature databases. For example, the matching unit can compare the content of a statement with past discussion records and provide relevant evidence. The matching unit can also compare the content of a statement with a literature database and provide relevant evidence. Furthermore, the matching unit can improve the accuracy of the relevant evidence by taking into account the context of the statement. For example, the matching unit can analyze the context before and after the statement to improve the accuracy of the relevant evidence. The matching unit can also extract keywords related to the topic of the statement and provide evidence based on the context. This enables evidence-based discussion by comparing with the database. Some or all of the above-mentioned processing in the matching unit may be performed using, for example, AI, or may be performed without using AI. For example, the matching unit can input text data of the content of a statement to a generation AI and cause the generation AI to provide relevant evidence.

[0033] The suggestion unit can analyze past discussion records and propose solutions to similar problems. Examples of past discussion records include, but are not limited to, minutes and audio recordings. The suggestion unit can, for example, analyze past discussion records and propose solutions to similar problems. The suggestion unit can also propose more appropriate solutions by taking into account the context of a comment. For example, the suggestion unit can analyze the context before and after a comment and propose an appropriate solution. The suggestion unit can also extract keywords related to the topic of a comment and propose a solution based on the context. This enables efficient decision-making by analyzing past discussion records. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input text data of past discussion records into a generation AI and have the generation AI execute a solution proposal.

[0034] The analysis unit can improve the accuracy of emotion and bias detection based on the context of the statement. For example, the analysis unit analyzes the context before and after the statement to improve the accuracy of emotion and bias detection. The analysis unit can also extract keywords related to the topic of the statement and detect emotion and bias based on the context. Furthermore, the analysis unit can analyze the flow of the statement and optimize the emotion and bias detection algorithm based on the context. This improves the accuracy of emotion and bias detection by taking the context into consideration. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input context data of the statement into the generation AI and cause the generation AI to detect emotion and bias.

[0035] The analysis unit can analyze the tone and speed of speech to help detect emotions and biases. For example, the analysis unit can analyze the tone of speech to estimate the strength of emotions. The analysis unit can also analyze the speed of speech to detect emotional fluctuations. Furthermore, the analysis unit can combine changes in speech tone and speed to improve the accuracy of emotion and bias detection. In this way, analyzing speech tone and speed improves the accuracy of emotion and bias detection. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input speech data of speech to a generation AI and have the generation AI detect emotions and biases.

[0036] The analysis unit can optimize the emotion and bias detection algorithm based on the speaker's past speech history. The analysis unit, for example, analyzes the speaker's past speech history and learns patterns of emotion and bias. The analysis unit can also customize the emotion and bias detection algorithm based on the past speech history. Furthermore, the analysis unit can refer to the speaker's past speech history in real time to improve the accuracy of emotion and bias detection. In this way, the emotion and bias detection algorithm is optimized by referring to the past speech history. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the speaker's past speech history data into the generation AI and cause the generation AI to optimize the emotion and bias detection algorithm.

[0037] The analysis unit can customize the emotion and bias detection algorithm based on the language or cultural background of the utterance. For example, the analysis unit can adjust the emotion and bias detection algorithm according to the language of the utterance. The analysis unit can also improve the accuracy of emotion and bias detection by taking into account the cultural background of the utterance. Furthermore, the analysis unit can optimize the emotion and bias detection algorithm by taking into account both the language and the cultural background. This improves the accuracy of emotion and bias detection by taking into account the language and cultural background. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the language and cultural background data of the utterance into the generation AI and cause the generation AI to customize the emotion and bias detection algorithm.

[0038] The analysis unit can highlight specific keywords and phrases based on the content of the utterance. For example, the analysis unit can automatically extract and highlight important keywords in the utterance. The analysis unit can also highlight specific phrases based on the content of the utterance to make them visually easier to understand. Furthermore, the analysis unit can highlight keywords related to the topic of the utterance to clarify the focus of the discussion. In this way, by highlighting important keywords and phrases, the focus of the discussion becomes clear. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input text data of the utterance into a generation AI and cause the generation AI to highlight specific keywords and phrases.

[0039] The analysis unit can visualize the utterance analysis results in real time and provide feedback to participants. For example, the analysis unit visualizes the utterance analysis results in real time as graphs or charts. The analysis unit can also display the utterance analysis results as text in real time and provide feedback to participants. Furthermore, the analysis unit can display the utterance analysis results on a dashboard in real time so that participants can easily understand them. This allows participants to easily understand the analysis results by visualizing them in real time. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input utterance analysis result data to a generation AI and cause the generation AI to perform real-time visualization.

[0040] The conversion unit can generate a more appropriate neutral expression based on the context of the utterance. For example, the conversion unit analyzes the context before and after the utterance to generate an appropriate neutral expression. The conversion unit can also extract keywords related to the topic of the utterance and generate a neutral expression based on the context. Furthermore, the conversion unit can analyze the flow of the utterance and optimize the neutral expression based on the context. In this way, a more appropriate neutral expression is generated by taking the context into consideration. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input context data of the utterance into a generation AI and cause the generation AI to generate a neutral expression.

[0041] The conversion unit can apply different conversion algorithms based on the content of the utterance. For example, if the content of the utterance is emotional, the conversion unit can apply a conversion algorithm that suppresses the emotion. Furthermore, if the content of the utterance is technical, the conversion unit can also apply an algorithm that appropriately converts technical terms. Furthermore, if the content of the utterance is ambiguous, the conversion unit can also apply an algorithm that converts it into a clear, neutral expression. By applying a conversion algorithm according to the content, a more appropriate neutral expression is generated. Examples of conversion algorithms include, but are not limited to, rule-based and machine learning-based algorithms. Some or all of the above-described processing in the conversion unit may be performed using, or without, AI. For example, the conversion unit can input content data of the utterance into a generation AI and cause the generation AI to apply a conversion algorithm.

[0042] The conversion unit can optimize the conversion algorithm based on the speaker's past speech history. The conversion unit, for example, analyzes the speaker's past speech history and customizes the conversion algorithm. The conversion unit can also optimize the algorithm that generates appropriate neutral expressions based on the past speech history. Furthermore, the conversion unit can refer to the speaker's past speech history in real time and dynamically adjust the conversion algorithm. In this way, the conversion algorithm is optimized by referring to the past speech history. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the speaker's past speech history data into a generation AI and cause the generation AI to optimize the conversion algorithm.

[0043] The conversion unit can determine the priority of converted expressions based on the content of the utterance. For example, if the content of the utterance is important, the conversion unit can preferentially convert it into a neutral expression. Furthermore, if the content of the utterance is technical, the conversion unit can also appropriately convert technical terms. Furthermore, if the content of the utterance is ambiguous, the conversion unit can convert it into a clear, neutral expression. In this way, by determining the priority based on the content, important expressions are preferentially converted. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the content data of the utterance into a generation AI and have the generation AI determine the priority of converted expressions.

[0044] The conversion unit can make the converted expression multilingual based on the content of the utterance. For example, the conversion unit translates the content of the utterance into multiple languages ​​and converts it into a neutral expression. Furthermore, if the content of the utterance is technical, the conversion unit can also appropriately translate technical terms and convert it into a neutral expression. Furthermore, if the content of the utterance is ambiguous, the conversion unit can translate it into a clear neutral expression. This makes it multilingual, allowing it to accommodate participants who speak different languages. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input content data of the utterance into a generation AI and have the generation AI convert it into a multilingual neutral expression.

[0045] The conversion unit can visualize the utterance conversion results in real time and provide feedback to participants. For example, the conversion unit visualizes the utterance conversion results in real time as a graph or chart. The conversion unit can also display the utterance conversion results as text in real time and provide feedback to participants. Furthermore, the conversion unit can display the utterance conversion results on a dashboard in real time so that participants can easily understand them. This allows participants to easily understand the conversion results by visualizing them in real time. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the utterance conversion result data to a generation AI and cause the generation AI to perform visualization in real time.

[0046] The matching unit can improve the accuracy of related evidence based on the context of the utterance. For example, the matching unit analyzes the context before and after the utterance to improve the accuracy of related evidence. The matching unit can also extract keywords related to the topic of the utterance and provide evidence based on the context. Furthermore, the matching unit can analyze the flow of the utterance and optimize the accuracy of the evidence based on the context. This improves the accuracy of the evidence by taking the context into consideration. Some or all of the above-mentioned processing in the matching unit may be performed using AI, for example, or may be performed without using AI. For example, the matching unit can input context data of the utterance to the generation AI and cause the generation AI to provide related evidence.

[0047] The matching unit can refer to different databases based on the content of the utterance. For example, if the content of the utterance is technical, the matching unit can refer to a technical database to provide evidence. Furthermore, if the content of the utterance is statistical, the matching unit can also refer to a statistical database to provide evidence. Furthermore, if the content of the utterance is historical, the matching unit can also refer to a historical database to provide evidence. In this way, more appropriate evidence can be provided by referencing a database based on the content. Some or all of the above-mentioned processing in the matching unit may be performed using, for example, AI, or may be performed without using AI. For example, the matching unit can input content data of the utterance into a generation AI and cause the generation AI to refer to different databases.

[0048] The matching unit can optimize the evidence provision algorithm based on the speaker's past speech history. The matching unit, for example, analyzes the speaker's past speech history and customizes the evidence provision algorithm. The matching unit can also optimize the algorithm that provides appropriate evidence based on the past speech history. Furthermore, the matching unit can refer to the speaker's past speech history in real time and dynamically adjust the evidence provision algorithm. In this way, the evidence provision algorithm is optimized by referring to the past speech history. Some or all of the above-mentioned processing in the matching unit may be performed using AI, for example, or may be performed without using AI. For example, the matching unit can input the speaker's past speech history data into the generation AI and cause the generation AI to optimize the evidence provision algorithm.

[0049] The matching unit can determine the priority of evidence based on the content of the utterance. For example, if the content of the utterance is important, the matching unit can provide evidence preferentially. Furthermore, if the content of the utterance is technical, the matching unit can also preferentially refer to a technical database. Furthermore, if the content of the utterance is ambiguous, the matching unit can also preferentially provide clear evidence. In this way, by determining the priority based on the content, important evidence is preferentially provided. Some or all of the above-mentioned processing in the matching unit may be performed using AI, for example, or may be performed without using AI. For example, the matching unit can input the content data of the utterance to a generation AI and have the generation AI determine the priority of the evidence.

[0050] The collation unit can make the evidence multilingual based on the content of the utterance. For example, the collation unit translates the content of the utterance into multiple languages ​​and provides the evidence. Furthermore, if the content of the utterance is technical, the collation unit can also provide evidence by appropriately translating technical terms. Furthermore, if the content of the utterance is ambiguous, the collation unit can provide clear evidence in multiple languages. This multilingual support can also accommodate participants who speak different languages. Some or all of the above-mentioned processing in the collation unit may be performed using, for example, AI, or may be performed without using AI. For example, the collation unit can input content data of the utterance into a generation AI and cause the generation AI to provide evidence in multiple languages.

[0051] The collation unit can visualize the evidence provision results in real time and provide feedback to the participants. For example, the collation unit visualizes the evidence provision results in real time as graphs or charts. The collation unit can also display the evidence provision results as text in real time and provide feedback to the participants. Furthermore, the collation unit can display the evidence provision results on a dashboard in real time so that the participants can easily understand them. This allows the participants to easily understand the evidence provision results by visualizing them in real time. Some or all of the above-mentioned processing in the collation unit may be performed using AI, for example, or may be performed without using AI. For example, the collation unit can input evidence provision result data to a generation AI and cause the generation AI to perform real-time visualization.

[0052] The suggestion unit can propose a more appropriate solution based on the context of the utterance. For example, the suggestion unit analyzes the context before and after the utterance and proposes an appropriate solution. The suggestion unit can also extract keywords related to the topic of the utterance and propose a solution based on the context. Furthermore, the suggestion unit can analyze the flow of the utterance and optimize the solution based on the context. In this way, a more appropriate solution is proposed by taking the context into consideration. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input context data of the utterance into a generation AI and have the generation AI execute a solution proposal.

[0053] The suggestion unit can apply different suggestion algorithms based on the content of the utterance. For example, if the content of the utterance is technical, the suggestion unit can apply an algorithm that proposes a technical solution. Furthermore, if the content of the utterance is statistical, the suggestion unit can also apply an algorithm that proposes a statistical solution. Furthermore, if the content of the utterance is ambiguous, the suggestion unit can apply an algorithm that proposes a clear solution. By applying a suggestion algorithm based on the content, a more appropriate solution is suggested. Examples of suggestion algorithms include, but are not limited to, rule-based and machine learning-based algorithms. Some or all of the above-described processing in the suggestion unit may be performed using, or without, AI. For example, the suggestion unit can input content data of the utterance into a generation AI and cause the generation AI to apply a suggestion algorithm.

[0054] The proposal unit can optimize the proposal algorithm based on the speaker's past speech history. The proposal unit, for example, analyzes the speaker's past speech history and customizes the proposal algorithm. The proposal unit can also optimize an algorithm that proposes an appropriate solution based on the past speech history. Furthermore, the proposal unit can refer to the speaker's past speech history in real time and dynamically adjust the proposal algorithm. In this way, the proposal algorithm is optimized by referring to the past speech history. Some or all of the above-mentioned processing in the proposal unit may be performed using, for example, AI, or may be performed without using AI. For example, the proposal unit can input the speaker's past speech history data into the generation AI and cause the generation AI to optimize the proposal algorithm.

[0055] The suggestion unit can adjust the display method of the suggestion based on the content of the comment. For example, if the content of the comment is important, the suggestion unit can prioritize displaying the suggestion. Furthermore, if the content of the comment is technical, the suggestion unit can also prioritize displaying technical suggestions. Furthermore, if the content of the comment is ambiguous, the suggestion unit can also prioritize displaying clear suggestions. By adjusting the display method based on the content, the suggestion becomes easier to understand. Some or all of the above-mentioned processing in the suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the suggestion unit can input content data of the comment into a generation AI and cause the generation AI to adjust the display method of the suggestion.

[0056] The suggestion unit can make proposals multilingual based on the content of the utterance. For example, the suggestion unit translates the content of the utterance into multiple languages ​​and provides the proposal. Furthermore, if the content of the utterance is technical, the suggestion unit can also provide a proposal by appropriately translating technical terms. Furthermore, if the content of the utterance is ambiguous, the suggestion unit can also provide clear proposals in multiple languages. This makes it possible to support multiple languages ​​and accommodate participants who speak different languages. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input content data of the utterance into a generation AI and have the generation AI execute a multilingual proposal.

[0057] The suggestion unit can visualize the results of the proposal in real time and provide feedback to the participants. For example, the suggestion unit visualizes the results of the proposal as a graph or chart in real time. The suggestion unit can also display the results of the proposal as text in real time and provide feedback to the participants. Furthermore, the suggestion unit can display the results of the proposal on a dashboard in real time so that the participants can easily understand them. This allows the participants to easily understand the results of the proposal by visualizing them in real time. Some or all of the above-mentioned processing in the suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the suggestion unit can input the result data of the proposal to a generation AI and cause the generation AI to perform visualization in real time.

[0058] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0059] The meeting support system can also be equipped with a function that monitors the frequency of participants' speech and provides other participants with opportunities to speak if a specific participant is speaking excessively. For example, the analysis unit can count the number of times each participant speaks and issue an alert if it exceeds a certain threshold. The suggestion unit can also display a message encouraging participants who speak less frequently to speak. Furthermore, the matching unit can evaluate the balance of the discussion based on the frequency of speech and suggest adjustments as necessary. This provides all participants with a fair opportunity to express their opinions, and more diverse perspectives are reflected in the discussion.

[0060] The meeting support system can also be equipped with a function to automatically classify the topics of comments and support the progress of discussions. For example, the analysis unit can classify comments by topic and display them in real time. The suggestion unit can also provide past discussions and evidence related to each topic. Furthermore, the matching unit can evaluate the progress of the discussion for each topic and suggest moving on to the next topic as necessary. This allows discussions to proceed efficiently and prevents important topics from being overlooked.

[0061] The meeting support system can also be equipped with a function that evaluates the content of comments taking into account the expertise of participants and provides appropriate feedback. For example, the analysis unit retrieves each participant's area of ​​expertise from a database and evaluates the content of comments based on that expertise. The suggestion unit can also provide feedback based on expertise to improve the quality of discussions. Furthermore, the matching unit can provide relevant evidence based on expertise to strengthen the support for comments. This enables high-quality discussions that utilize expertise.

[0062] The meeting support system can also be equipped with a function to summarize what participants have said and display it in real time. For example, the analysis unit automatically summarizes what has been said and extracts the key points. The proposal unit can also suggest the direction of the next discussion based on the summarized content. Furthermore, the comparison unit can compare the summarized content with a database and provide related evidence. This makes it easier for participants to grasp the overall picture of the discussion, enabling efficient decision-making.

[0063] The conference support system can also be equipped with a function to translate participants' comments and support multilingual discussions. For example, the analysis unit can translate comments in real time and provide them to participants speaking other languages. The proposal unit can also propose solutions based on the translated content. Furthermore, the comparison unit can compare the translated content with a database and provide related evidence. This allows participants speaking different languages ​​to communicate smoothly and enables global discussions.

[0064] The processing flow of the first embodiment will be briefly explained below.

[0065] Step 1: The analyzer analyzes speech in real time to detect sentiment or bias. The analyzer uses natural language processing (NLP) and machine learning techniques to analyze speech and detect sentiment or bias. It can also improve detection accuracy by taking into account the context of speech. It can also analyze the tone and speed of speech to help detect sentiment and bias. Step 2: The conversion unit converts the sentiment or bias detected by the analysis unit into a neutral expression. The conversion unit generates a more appropriate neutral expression by taking into account the context of the utterance, and can apply different conversion algorithms depending on the content of the utterance. Step 3: The matching unit matches the utterance content converted by the conversion unit with the database and provides related evidence. The matching unit matches the utterance content with the database and provides related evidence. The accuracy of the related evidence can also be improved by taking into account the context of the utterance. Step 4: The suggestion unit learns from past discussions and proposes solutions based on the evidence provided by the matching unit. The suggestion unit analyzes past discussion records and proposes solutions to similar problems. It can also propose more appropriate solutions by taking into account the context of the comments.

[0066] (Example 2) A meeting support system according to an embodiment of the present invention supports meetings in real time and enables logical, constructive discussions based on evidence. This meeting support system analyzes comments in real time and filters them to eliminate emotions and biases. It then compares the comments with a database and provides relevant evidence. It also has a function of learning from past discussions and proposing solutions. For example, the meeting support system analyzes comments in real time during a meeting, detects comments containing emotional expressions or bias, and converts them into neutral expressions. This enables fair communication for all participants. The meeting support system then compares the comments with a database and provides relevant evidence. For example, it references past discussions, research results, statistical data, etc. in real time to support comments. This enables logical, constructive discussions. Furthermore, the meeting support system analyzes past meeting records and proposes solutions to similar problems. For example, it analyzes past meeting records and proposes solutions to similar problems. This facilitates smooth discussions and enables efficient decision-making. This allows the meeting support system to promote data-driven decision-making and achieve high-quality results. This allows the meeting support system to support meetings in real time and enable evidence-based, logical, and constructive discussions. For example, it can be used in a variety of situations, such as corporate management meetings and project team meetings, which is expected to improve the performance of the entire organization.

[0067] A conference support system according to an embodiment includes an analysis unit, a conversion unit, a matching unit, and a suggestion unit. The analysis unit analyzes utterances in real time to detect emotions or biases. The analysis unit analyzes utterances using, for example, natural language processing (NLP) or machine learning techniques to detect emotions or biases. The analysis unit can also improve the accuracy of emotion or bias detection by taking into account the context of the utterances. The analysis unit can also analyze the tone and speed of the utterances to help detect emotions and biases. For example, the analysis unit analyzes the tone of the utterances to estimate the intensity of the emotions. The analysis unit can also analyze the speed of the utterances to detect emotional fluctuations. The conversion unit converts the detected emotions or biases into neutral expressions. For example, the conversion unit converts the detected emotions or biases into neutral expressions. The conversion unit can also generate more appropriate neutral expressions by taking into account the context of the utterances. The conversion unit can also apply different conversion algorithms depending on the content of the utterances. For example, if the content of the utterances is emotional, the conversion unit applies a conversion algorithm that suppresses the emotions. In addition, if the content of the utterance is technical, the conversion unit can apply an algorithm that appropriately converts technical terms. The matching unit compares the content of the utterance converted by the conversion unit with a database and provides related evidence. For example, the matching unit compares the content of the utterance with a database and provides related evidence. The matching unit can also improve the accuracy of the related evidence by taking into account the context of the utterance. Furthermore, the matching unit can refer to different databases based on the content of the utterance. The suggestion unit learns from past discussions and proposes solutions based on the evidence provided by the matching unit. For example, the suggestion unit analyzes past discussion records and proposes solutions to similar problems. The suggestion unit can also propose a more appropriate solution by taking into account the context of the utterance. Furthermore, the suggestion unit can apply different suggestion algorithms based on the content of the utterance. As a result, the meeting support system according to the embodiment can support meetings in real time and realize evidence-based, logical, and constructive discussions.

[0068] The analysis unit can analyze utterances and detect emotions or biases using natural language processing or machine learning techniques. Natural language processing includes, but is not limited to, morphological analysis, grammatical analysis, and semantic analysis. For example, the analysis unit uses morphological analysis to segment words in utterances and grammatical analysis to analyze sentence structure. The analysis unit can also understand the meaning of utterances using semantic analysis. Machine learning includes, but is not limited to, supervised learning, unsupervised learning, and reinforcement learning. For example, the analysis unit trains an emotion or bias detection model using supervised learning. The analysis unit can also perform utterance clustering using unsupervised learning. Furthermore, the analysis unit can improve the accuracy of emotion or bias detection using reinforcement learning. Thus, the accuracy of emotion or bias detection is improved by using natural language processing or machine learning techniques. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input text data of utterances to a generation AI and cause the generation AI to detect emotions and biases.

[0069] The conversion unit can convert the detected emotion or prejudice into a neutral expression. Neutral expressions include, but are not limited to, paraphrasing methods to eliminate specific emotions or prejudices. For example, the conversion unit can convert emotional expressions into neutral expressions. The conversion unit can also convert prejudiced expressions into neutral expressions. Furthermore, the conversion unit can generate a more appropriate neutral expression by taking into account the context of the utterance. For example, the conversion unit can analyze the context before and after the utterance to generate an appropriate neutral expression. The conversion unit can also extract keywords related to the topic of the utterance and generate a neutral expression based on the context. This allows fair communication by converting emotion or prejudice into a neutral expression. Some or all of the above-described processing in the conversion unit can be performed using, or without, AI. For example, the conversion unit can input text data of utterances containing emotion or prejudice into a generation AI and have the generation AI convert the data into a neutral expression.

[0070] The matching unit can compare the content of a statement with a database and provide relevant evidence. Examples of databases include, but are not limited to, past discussion records and literature databases. For example, the matching unit can compare the content of a statement with past discussion records and provide relevant evidence. The matching unit can also compare the content of a statement with a literature database and provide relevant evidence. Furthermore, the matching unit can improve the accuracy of the relevant evidence by taking into account the context of the statement. For example, the matching unit can analyze the context before and after the statement to improve the accuracy of the relevant evidence. The matching unit can also extract keywords related to the topic of the statement and provide evidence based on the context. This enables evidence-based discussion by comparing with the database. Some or all of the above-mentioned processing in the matching unit may be performed using, for example, AI, or may be performed without using AI. For example, the matching unit can input text data of the content of a statement to a generation AI and cause the generation AI to provide relevant evidence.

[0071] The suggestion unit can analyze past discussion records and propose solutions to similar problems. Examples of past discussion records include, but are not limited to, minutes and audio recordings. The suggestion unit can, for example, analyze past discussion records and propose solutions to similar problems. The suggestion unit can also propose more appropriate solutions by taking into account the context of a comment. For example, the suggestion unit can analyze the context before and after a comment and propose an appropriate solution. The suggestion unit can also extract keywords related to the topic of a comment and propose a solution based on the context. This enables efficient decision-making by analyzing past discussion records. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input text data of past discussion records into a generation AI and have the generation AI execute a solution proposal.

[0072] The analysis unit can estimate the speaker's emotions and adjust the analysis accuracy of the utterance based on the estimated emotions. For example, if the speaker is angry, the analysis unit increases the analysis accuracy by taking into account the strength of the emotion. Furthermore, if the speaker is relaxed, the analysis unit can minimize the influence of the emotion when performing analysis. Furthermore, if the speaker is nervous, the analysis unit can track emotional fluctuations in real time and dynamically adjust the analysis accuracy. This enables more accurate analysis by adjusting the analysis accuracy based on the speaker's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit can be performed using, for example, an AI, or without an AI. For example, the analysis unit can input the speaker's emotion data into the generation AI and have the generation AI adjust the analysis accuracy of the utterance.

[0073] The analysis unit can improve the accuracy of emotion and bias detection based on the context of the statement. For example, the analysis unit analyzes the context before and after the statement to improve the accuracy of emotion and bias detection. The analysis unit can also extract keywords related to the topic of the statement and detect emotion and bias based on the context. Furthermore, the analysis unit can analyze the flow of the statement and optimize the emotion and bias detection algorithm based on the context. This improves the accuracy of emotion and bias detection by taking the context into consideration. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input context data of the statement into the generation AI and cause the generation AI to detect emotion and bias.

[0074] The analysis unit can analyze the tone and speed of speech to help detect emotions and biases. For example, the analysis unit can analyze the tone of speech to estimate the strength of emotions. The analysis unit can also analyze the speed of speech to detect emotional fluctuations. Furthermore, the analysis unit can combine changes in speech tone and speed to improve the accuracy of emotion and bias detection. In this way, analyzing speech tone and speed improves the accuracy of emotion and bias detection. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input speech data of speech to a generation AI and have the generation AI detect emotions and biases.

[0075] The analysis unit can optimize the emotion and bias detection algorithm based on the speaker's past speech history. The analysis unit, for example, analyzes the speaker's past speech history and learns patterns of emotion and bias. The analysis unit can also customize the emotion and bias detection algorithm based on the past speech history. Furthermore, the analysis unit can refer to the speaker's past speech history in real time to improve the accuracy of emotion and bias detection. In this way, the emotion and bias detection algorithm is optimized by referring to the past speech history. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the speaker's past speech history data into the generation AI and cause the generation AI to optimize the emotion and bias detection algorithm.

[0076] The analysis unit can estimate the speaker's emotions and adjust the display method of the analysis results based on the estimated emotions. For example, if the speaker is angry, the analysis unit can display the analysis results simply to minimize the influence of the speaker's emotions. Furthermore, if the speaker is relaxed, the analysis unit can display detailed analysis results to take the influence of the speaker's emotions into consideration. Furthermore, if the speaker is nervous, the analysis unit can display the analysis results in a visually easy-to-understand manner to reflect the speaker's emotional fluctuations. This makes the analysis results easier to understand by adjusting the display method based on the speaker's emotions. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit can be performed using, for example, an AI, or without an AI. For example, the analysis unit can input the speaker's emotional data into the generation AI and have the generation AI adjust the display method of the analysis results.

[0077] The analysis unit can customize the emotion and bias detection algorithm based on the language or cultural background of the utterance. For example, the analysis unit can adjust the emotion and bias detection algorithm according to the language of the utterance. The analysis unit can also improve the accuracy of emotion and bias detection by taking into account the cultural background of the utterance. Furthermore, the analysis unit can optimize the emotion and bias detection algorithm by taking into account both the language and the cultural background. This improves the accuracy of emotion and bias detection by taking into account the language and cultural background. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the language and cultural background data of the utterance into the generation AI and cause the generation AI to customize the emotion and bias detection algorithm.

[0078] The analysis unit can highlight specific keywords and phrases based on the content of the utterance. For example, the analysis unit can automatically extract and highlight important keywords in the utterance. The analysis unit can also highlight specific phrases based on the content of the utterance to make them visually easier to understand. Furthermore, the analysis unit can highlight keywords related to the topic of the utterance to clarify the focus of the discussion. In this way, by highlighting important keywords and phrases, the focus of the discussion becomes clear. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input text data of the utterance into a generation AI and cause the generation AI to highlight specific keywords and phrases.

[0079] The analysis unit can visualize the utterance analysis results in real time and provide feedback to participants. For example, the analysis unit visualizes the utterance analysis results in real time as graphs or charts. The analysis unit can also display the utterance analysis results as text in real time and provide feedback to participants. Furthermore, the analysis unit can display the utterance analysis results on a dashboard in real time so that participants can easily understand them. This allows participants to easily understand the analysis results by visualizing them in real time. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input utterance analysis result data to a generation AI and cause the generation AI to perform real-time visualization.

[0080] The conversion unit can estimate the speaker's emotion and adjust the conversion method to a neutral expression based on the estimated emotion. For example, if the speaker is angry, the conversion unit converts the speaker's emotion into a neutral expression taking into account the intensity of the emotion. Furthermore, if the speaker is relaxed, the conversion unit can also convert the speaker's emotion into a neutral expression while minimizing the influence of the emotion. Furthermore, if the speaker is nervous, the conversion unit can track emotional fluctuations in real time and convert the speaker's emotion into a neutral expression. By adjusting the conversion method based on the emotion, a more appropriate neutral expression is generated. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the conversion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the conversion unit can input the speaker's emotion data into the generation AI and cause the generation AI to adjust the conversion method to a neutral expression.

[0081] The conversion unit can generate a more appropriate neutral expression based on the context of the utterance. For example, the conversion unit analyzes the context before and after the utterance to generate an appropriate neutral expression. The conversion unit can also extract keywords related to the topic of the utterance and generate a neutral expression based on the context. Furthermore, the conversion unit can analyze the flow of the utterance and optimize the neutral expression based on the context. In this way, a more appropriate neutral expression is generated by taking the context into consideration. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input context data of the utterance into a generation AI and cause the generation AI to generate a neutral expression.

[0082] The conversion unit can apply different conversion algorithms based on the content of the utterance. For example, if the content of the utterance is emotional, the conversion unit can apply a conversion algorithm that suppresses the emotion. Furthermore, if the content of the utterance is technical, the conversion unit can also apply an algorithm that appropriately converts technical terms. Furthermore, if the content of the utterance is ambiguous, the conversion unit can also apply an algorithm that converts it into a clear, neutral expression. By applying a conversion algorithm according to the content, a more appropriate neutral expression is generated. Examples of conversion algorithms include, but are not limited to, rule-based and machine learning-based algorithms. Some or all of the above-described processing in the conversion unit may be performed using, or without, AI. For example, the conversion unit can input content data of the utterance into a generation AI and cause the generation AI to apply a conversion algorithm.

[0083] The conversion unit can optimize the conversion algorithm based on the speaker's past speech history. The conversion unit, for example, analyzes the speaker's past speech history and customizes the conversion algorithm. The conversion unit can also optimize the algorithm that generates appropriate neutral expressions based on the past speech history. Furthermore, the conversion unit can refer to the speaker's past speech history in real time and dynamically adjust the conversion algorithm. In this way, the conversion algorithm is optimized by referring to the past speech history. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the speaker's past speech history data into a generation AI and cause the generation AI to optimize the conversion algorithm.

[0084] The conversion unit can estimate the speaker's emotion and adjust the length of the converted expression based on the estimated emotion. For example, if the speaker is angry, the conversion unit converts the expression into a short, to-the-point, neutral expression. Furthermore, if the speaker is relaxed, the conversion unit can convert the expression into a detailed, neutral expression. Furthermore, if the speaker is nervous, the conversion unit can convert the expression into a neutral expression of appropriate length, taking into account emotional fluctuations. By adjusting the length of the expression based on the emotion, a more appropriate neutral expression is generated. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the conversion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the conversion unit can input the speaker's emotion data into the generation AI and cause the generation AI to adjust the length of the converted expression.

[0085] The conversion unit can determine the priority of converted expressions based on the content of the utterance. For example, if the content of the utterance is important, the conversion unit can preferentially convert it into a neutral expression. Furthermore, if the content of the utterance is technical, the conversion unit can also appropriately convert technical terms. Furthermore, if the content of the utterance is ambiguous, the conversion unit can convert it into a clear, neutral expression. In this way, by determining the priority based on the content, important expressions are preferentially converted. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the content data of the utterance into a generation AI and have the generation AI determine the priority of converted expressions.

[0086] The conversion unit can make the converted expression multilingual based on the content of the utterance. For example, the conversion unit translates the content of the utterance into multiple languages ​​and converts it into a neutral expression. Furthermore, if the content of the utterance is technical, the conversion unit can also appropriately translate technical terms and convert it into a neutral expression. Furthermore, if the content of the utterance is ambiguous, the conversion unit can translate it into a clear neutral expression. This makes it multilingual, allowing it to accommodate participants who speak different languages. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input content data of the utterance into a generation AI and have the generation AI convert it into a multilingual neutral expression.

[0087] The conversion unit can visualize the utterance conversion results in real time and provide feedback to participants. For example, the conversion unit visualizes the utterance conversion results in real time as a graph or chart. The conversion unit can also display the utterance conversion results as text in real time and provide feedback to participants. Furthermore, the conversion unit can display the utterance conversion results on a dashboard in real time so that participants can easily understand them. This allows participants to easily understand the conversion results by visualizing them in real time. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the utterance conversion result data to a generation AI and cause the generation AI to perform visualization in real time.

[0088] The matching unit can estimate the speaker's emotions and adjust the evidence provision method based on the estimated emotions. For example, if the speaker is angry, the matching unit provides simple, highly visible evidence. Furthermore, if the speaker is relaxed, the matching unit can also provide detailed evidence. Furthermore, if the speaker is nervous, the matching unit can adjust the evidence provision method taking into account emotional fluctuations. This allows for more appropriate evidence to be provided by adjusting the evidence provision method based on emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the matching unit may be performed using, for example, AI, or may be performed without using AI. For example, the matching unit can input the speaker's emotion data into the generation AI and have the generation AI adjust the evidence provision method.

[0089] The matching unit can improve the accuracy of related evidence based on the context of the utterance. For example, the matching unit analyzes the context before and after the utterance to improve the accuracy of related evidence. The matching unit can also extract keywords related to the topic of the utterance and provide evidence based on the context. Furthermore, the matching unit can analyze the flow of the utterance and optimize the accuracy of the evidence based on the context. This improves the accuracy of the evidence by taking the context into consideration. Some or all of the above-mentioned processing in the matching unit may be performed using AI, for example, or may be performed without using AI. For example, the matching unit can input context data of the utterance to the generation AI and cause the generation AI to provide related evidence.

[0090] The matching unit can refer to different databases based on the content of the utterance. For example, if the content of the utterance is technical, the matching unit can refer to a technical database to provide evidence. Furthermore, if the content of the utterance is statistical, the matching unit can also refer to a statistical database to provide evidence. Furthermore, if the content of the utterance is historical, the matching unit can also refer to a historical database to provide evidence. In this way, more appropriate evidence can be provided by referencing a database based on the content. Some or all of the above-mentioned processing in the matching unit may be performed using, for example, AI, or may be performed without using AI. For example, the matching unit can input content data of the utterance into a generation AI and cause the generation AI to refer to different databases.

[0091] The matching unit can optimize the evidence provision algorithm based on the speaker's past speech history. The matching unit, for example, analyzes the speaker's past speech history and customizes the evidence provision algorithm. The matching unit can also optimize the algorithm that provides appropriate evidence based on the past speech history. Furthermore, the matching unit can refer to the speaker's past speech history in real time and dynamically adjust the evidence provision algorithm. In this way, the evidence provision algorithm is optimized by referring to the past speech history. Some or all of the above-mentioned processing in the matching unit may be performed using AI, for example, or may be performed without using AI. For example, the matching unit can input the speaker's past speech history data into the generation AI and cause the generation AI to optimize the evidence provision algorithm.

[0092] The matching unit can estimate the speaker's emotions and adjust the display method of evidence based on the estimated emotions. For example, if the speaker is angry, the matching unit provides simple, highly visible evidence. Furthermore, if the speaker is relaxed, the matching unit can also provide detailed evidence. Furthermore, if the speaker is nervous, the matching unit can adjust the display method of evidence taking into account emotional fluctuations. This makes the evidence easier to understand by adjusting the display method based on emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the matching unit may be performed using AI, or may be performed without AI. For example, the matching unit can input the speaker's emotion data into the generation AI and have the generation AI adjust the display method of the evidence.

[0093] The matching unit can determine the priority of evidence based on the content of the utterance. For example, if the content of the utterance is important, the matching unit can provide evidence preferentially. Furthermore, if the content of the utterance is technical, the matching unit can also preferentially refer to a technical database. Furthermore, if the content of the utterance is ambiguous, the matching unit can also preferentially provide clear evidence. In this way, by determining the priority based on the content, important evidence is preferentially provided. Some or all of the above-mentioned processing in the matching unit may be performed using AI, for example, or may be performed without using AI. For example, the matching unit can input the content data of the utterance to a generation AI and have the generation AI determine the priority of the evidence.

[0094] The collation unit can make the evidence multilingual based on the content of the utterance. For example, the collation unit translates the content of the utterance into multiple languages ​​and provides the evidence. Furthermore, if the content of the utterance is technical, the collation unit can also provide evidence by appropriately translating technical terms. Furthermore, if the content of the utterance is ambiguous, the collation unit can provide clear evidence in multiple languages. This multilingual support can also accommodate participants who speak different languages. Some or all of the above-mentioned processing in the collation unit may be performed using, for example, AI, or may be performed without using AI. For example, the collation unit can input content data of the utterance into a generation AI and cause the generation AI to provide evidence in multiple languages.

[0095] The collation unit can visualize the evidence provision results in real time and provide feedback to the participants. For example, the collation unit visualizes the evidence provision results in real time as graphs or charts. The collation unit can also display the evidence provision results as text in real time and provide feedback to the participants. Furthermore, the collation unit can display the evidence provision results on a dashboard in real time so that the participants can easily understand them. This allows the participants to easily understand the evidence provision results by visualizing them in real time. Some or all of the above-mentioned processing in the collation unit may be performed using AI, for example, or may be performed without using AI. For example, the collation unit can input evidence provision result data to a generation AI and cause the generation AI to perform real-time visualization.

[0096] The suggestion unit can estimate the speaker's emotions and adjust the solution proposal method based on the estimated emotions. For example, if the speaker is angry, the suggestion unit can propose a simple and highly visible solution. Furthermore, if the speaker is relaxed, the suggestion unit can also propose a detailed solution. Furthermore, if the speaker is nervous, the suggestion unit can adjust the solution proposal method taking into account emotional fluctuations. Thus, by adjusting the proposal method based on emotions, a more appropriate solution is proposed. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the suggestion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the suggestion unit can input the speaker's emotion data into the generation AI and cause the generation AI to adjust the solution proposal method.

[0097] The suggestion unit can propose a more appropriate solution based on the context of the utterance. For example, the suggestion unit analyzes the context before and after the utterance and proposes an appropriate solution. The suggestion unit can also extract keywords related to the topic of the utterance and propose a solution based on the context. Furthermore, the suggestion unit can analyze the flow of the utterance and optimize the solution based on the context. In this way, a more appropriate solution is proposed by taking the context into consideration. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input context data of the utterance into a generation AI and have the generation AI execute a solution proposal.

[0098] The suggestion unit can apply different suggestion algorithms based on the content of the utterance. For example, if the content of the utterance is technical, the suggestion unit can apply an algorithm that proposes a technical solution. Furthermore, if the content of the utterance is statistical, the suggestion unit can also apply an algorithm that proposes a statistical solution. Furthermore, if the content of the utterance is ambiguous, the suggestion unit can apply an algorithm that proposes a clear solution. By applying a suggestion algorithm based on the content, a more appropriate solution is suggested. Examples of suggestion algorithms include, but are not limited to, rule-based and machine learning-based algorithms. Some or all of the above-described processing in the suggestion unit may be performed using, or without, AI. For example, the suggestion unit can input content data of the utterance into a generation AI and cause the generation AI to apply a suggestion algorithm.

[0099] The proposal unit can optimize the proposal algorithm based on the speaker's past speech history. The proposal unit, for example, analyzes the speaker's past speech history and customizes the proposal algorithm. The proposal unit can also optimize an algorithm that proposes an appropriate solution based on the past speech history. Furthermore, the proposal unit can refer to the speaker's past speech history in real time and dynamically adjust the proposal algorithm. In this way, the proposal algorithm is optimized by referring to the past speech history. Some or all of the above-mentioned processing in the proposal unit may be performed using, for example, AI, or may be performed without using AI. For example, the proposal unit can input the speaker's past speech history data into the generation AI and cause the generation AI to optimize the proposal algorithm.

[0100] The suggestion unit can estimate the speaker's emotions and prioritize suggestions based on the estimated emotions. For example, if the speaker is angry, the suggestion unit can prioritize simple, highly visible suggestions. Furthermore, if the speaker is relaxed, the suggestion unit can prioritize detailed suggestions. Furthermore, if the speaker is nervous, the suggestion unit can prioritize suggestions taking into account emotional fluctuations. Thus, by determining priorities based on emotions, important suggestions are provided preferentially. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the suggestion unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the suggestion unit can input the speaker's emotion data into the generation AI and have the generation AI determine the priority of suggestions.

[0101] The suggestion unit can adjust the display method of the suggestion based on the content of the comment. For example, if the content of the comment is important, the suggestion unit can prioritize displaying the suggestion. Furthermore, if the content of the comment is technical, the suggestion unit can also prioritize displaying technical suggestions. Furthermore, if the content of the comment is ambiguous, the suggestion unit can also prioritize displaying clear suggestions. By adjusting the display method based on the content, the suggestion becomes easier to understand. Some or all of the above-mentioned processing in the suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the suggestion unit can input content data of the comment into a generation AI and cause the generation AI to adjust the display method of the suggestion.

[0102] The suggestion unit can make proposals multilingual based on the content of the utterance. For example, the suggestion unit translates the content of the utterance into multiple languages ​​and provides the proposal. Furthermore, if the content of the utterance is technical, the suggestion unit can also provide a proposal by appropriately translating technical terms. Furthermore, if the content of the utterance is ambiguous, the suggestion unit can also provide clear proposals in multiple languages. This makes it possible to support multiple languages ​​and accommodate participants who speak different languages. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input content data of the utterance into a generation AI and have the generation AI execute a multilingual proposal.

[0103] The suggestion unit can visualize the results of the proposal in real time and provide feedback to the participants. For example, the suggestion unit visualizes the results of the proposal as a graph or chart in real time. The suggestion unit can also display the results of the proposal as text in real time and provide feedback to the participants. Furthermore, the suggestion unit can display the results of the proposal on a dashboard in real time so that the participants can easily understand them. This allows the participants to easily understand the results of the proposal by visualizing them in real time. Some or all of the above-mentioned processing in the suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the suggestion unit can input the result data of the proposal to a generation AI and cause the generation AI to perform visualization in real time. === Hard Collateral 1-1 === Each of the multiple elements, including the above-mentioned analysis unit, conversion unit, matching unit, and suggestion unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the smart device 14 and analyzes utterances in real time to detect emotions and biases. The conversion unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and converts the detected emotions and biases into neutral expressions. The matching unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and compares the converted utterance content with the database 24 to provide related evidence. The suggestion unit is realized, for example, by the control unit 46A of the smart device 14 and learns from past discussions and suggests solutions. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned analysis unit, conversion unit, matching unit, and suggestion unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the smart glasses 214 and analyzes utterances in real time to detect emotions and biases. The conversion unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and converts the detected emotions and biases into neutral expressions. The matching unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and compares the converted utterance content with the database 24 to provide relevant evidence. The suggestion unit is realized, for example, by the control unit 46A of the smart glasses 214 and learns from past discussions and suggests solutions. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned analysis unit, conversion unit, matching unit, and suggestion unit is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the headset-type terminal 314 and analyzes utterances in real time to detect emotions and prejudices. The conversion unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and converts the detected emotions and prejudices into neutral expressions. The matching unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and compares the converted utterance content with the database 24 to provide related evidence. The suggestion unit is realized, for example, by the control unit 46A of the headset-type terminal 314 and learns from past discussions and suggests solutions. === Hard Collateral 1-4 === Each of the multiple elements, including the above-mentioned analysis unit, conversion unit, matching unit, and suggestion unit, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the robot 414 and analyzes utterances in real time to detect emotions and prejudices. The conversion unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and converts the detected emotions and prejudices into neutral expressions. The matching unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and compares the converted utterance content with the database 24 to provide related evidence. The suggestion unit is realized, for example, by the control unit 46A of the robot 414 and learns from past discussions and suggests solutions.

[0104] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0105] The meeting support system can also be equipped with a function that monitors the frequency of participants' speech and provides other participants with opportunities to speak if a specific participant is speaking excessively. For example, the analysis unit can count the number of times each participant speaks and issue an alert if it exceeds a certain threshold. The suggestion unit can also display a message encouraging participants who speak less frequently to speak. Furthermore, the matching unit can evaluate the balance of the discussion based on the frequency of speech and suggest adjustments as necessary. This provides all participants with a fair opportunity to express their opinions, and more diverse perspectives are reflected in the discussion.

[0106] The meeting support system can also be equipped with a function to automatically classify the topics of comments and support the progress of discussions. For example, the analysis unit can classify comments by topic and display them in real time. The suggestion unit can also provide past discussions and evidence related to each topic. Furthermore, the matching unit can evaluate the progress of the discussion for each topic and suggest moving on to the next topic as necessary. This allows discussions to proceed efficiently and prevents important topics from being overlooked.

[0107] The meeting support system can also be equipped with a function that evaluates the content of comments taking into account the expertise of participants and provides appropriate feedback. For example, the analysis unit retrieves each participant's area of ​​expertise from a database and evaluates the content of comments based on that expertise. The suggestion unit can also provide feedback based on expertise to improve the quality of discussions. Furthermore, the matching unit can provide relevant evidence based on expertise to strengthen the support for comments. This enables high-quality discussions that utilize expertise.

[0108] The meeting support system can also be equipped with a function to summarize what participants have said and display it in real time. For example, the analysis unit automatically summarizes what has been said and extracts the key points. The proposal unit can also suggest the direction of the next discussion based on the summarized content. Furthermore, the comparison unit can compare the summarized content with a database and provide related evidence. This makes it easier for participants to grasp the overall picture of the discussion, enabling efficient decision-making.

[0109] The conference support system can also be equipped with a function to translate participants' comments and support multilingual discussions. For example, the analysis unit can translate comments in real time and provide them to participants speaking other languages. The proposal unit can also propose solutions based on the translated content. Furthermore, the comparison unit can compare the translated content with a database and provide related evidence. This allows participants speaking different languages ​​to communicate smoothly and enables global discussions.

[0110] The meeting support system can also be equipped with a function to estimate the emotions of participants and adjust the progress of the discussion based on the estimated emotions. For example, the analysis unit can estimate the speaker's emotions in real time and monitor emotional fluctuations. The suggestion unit can also display a message to encourage calm discussion when emotions are running high. Furthermore, the matching unit can adjust the way evidence is provided based on emotional fluctuations and provide support to avoid emotional discussions. This enables smooth discussions that take emotions into consideration.

[0111] The meeting support system can also be equipped with a function to estimate participants' emotions and adjust feedback on speech content based on the estimated emotions. For example, the analysis unit can estimate the speaker's emotions in real time and evaluate the strength of their emotions. The suggestion unit can also provide calm feedback when emotions are high. Furthermore, the matching unit can adjust the way evidence is provided based on fluctuations in emotions and provide support to avoid emotional discussions. This provides appropriate feedback that takes emotions into consideration, improving the quality of discussions.

[0112] The meeting support system can also be equipped with a function to estimate the emotions of participants and adjust the display method of remarks based on the estimated emotions. For example, the analysis unit can estimate the speaker's emotions in real time and evaluate the strength of the emotions. The suggestion unit can also provide a simple display method when emotions are high. Furthermore, the matching unit can adjust the display method of evidence based on fluctuations in emotions and provide support to avoid emotional discussions. This provides an appropriate display method that takes emotions into consideration, deepening understanding of the discussion.

[0113] The meeting support system can also be equipped with a function to estimate the emotions of participants and adjust the method for summarizing speech content based on the estimated emotions. For example, the analysis unit can estimate the speaker's emotions in real time and evaluate the strength of their emotions. The suggestion unit can also provide a summary that focuses on the main points when emotions are high. Furthermore, the matching unit can adjust the method for summarizing evidence based on fluctuations in emotions and provide support to avoid emotional discussions. This provides an appropriate summary that takes emotions into consideration, deepening understanding of the discussion.

[0114] The meeting support system can also be equipped with a function to estimate participants' emotions and adjust the translation method of the speech content based on the estimated emotions. For example, the analysis unit estimates the speaker's emotions in real time and evaluates the strength of the emotion. The suggestion unit can also provide a simple translation when emotions are high. Furthermore, the matching unit can adjust the translation method of evidence based on fluctuations in emotion and provide support to avoid emotional discussions. This provides appropriate translations that take emotions into consideration, allowing participants speaking different languages ​​to communicate smoothly.

[0115] The processing flow of the second embodiment will be briefly explained below.

[0116] Step 1: The analyzer analyzes speech in real time to detect sentiment or bias. The analyzer uses natural language processing (NLP) and machine learning techniques to analyze speech and detect sentiment or bias. It can also improve detection accuracy by taking into account the context of speech. It can also analyze the tone and speed of speech to help detect sentiment and bias. Step 2: The conversion unit converts the sentiment or bias detected by the analysis unit into a neutral expression. The conversion unit generates a more appropriate neutral expression by taking into account the context of the utterance, and can apply different conversion algorithms depending on the content of the utterance. Step 3: The matching unit matches the utterance content converted by the conversion unit with the database and provides related evidence. The matching unit matches the utterance content with the database and provides related evidence. The accuracy of the related evidence can also be improved by taking into account the context of the utterance. Step 4: The suggestion unit learns from past discussions and proposes solutions based on the evidence provided by the matching unit. The suggestion unit analyzes past discussion records and proposes solutions to similar problems. It can also propose more appropriate solutions by taking into account the context of the comments.

[0117] 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.

[0118] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<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.

[0119] 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.

[0120] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0121] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0122] 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.

[0123] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0124] The 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.

[0125] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0126] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0127] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0128] Fig. 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.

[0129] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0130] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0131] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0132] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0133] The specific processing unit 290 transmits the result of the specific processing to the 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.

[0134] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes 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.

[0135] 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.

[0136] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0137] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0138] 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.

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

[0140] The 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.

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

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (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).

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

[0144] 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.

[0145] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0146] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0147] In the 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 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0148] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0149] The specific processing unit 290 transmits the result of the specific processing to the 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.

[0150] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes 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.

[0151] 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.

[0152] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0153] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0154] 7, a 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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).

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0164] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. 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 the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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).

[0174] 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.

[0175] 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."

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] [Explanation of symbols]

[0189] 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. an analysis unit that analyzes utterances in real time to detect emotions or biases; a conversion unit that converts the emotion or prejudice detected by the analysis unit into a neutral expression; a verification unit that compares the converted speech content with a database and provides relevant evidence; a suggestion unit that learns from past discussions and proposes solutions based on the evidence provided by the matching unit; Equipped with A system characterized by:

2. The analysis unit Use natural language processing or machine learning techniques to analyze speech and detect sentiment or bias The system of claim 1 .

3. The conversion unit Converting detected emotions or biases into neutral expressions The system of claim 1 .

4. The collation unit Cross-check statements against a database and provide relevant evidence The system of claim 1 .

5. The proposal unit Analyze past discussion records and propose solutions to similar problems The system of claim 1 .

6. The analysis unit Estimate the speaker's emotions and adjust the accuracy of speech analysis based on the estimated emotions. The system of claim 1 .

7. The analysis unit Improved sentiment and bias detection based on speech context The system of claim 1 .

8. The analysis unit Analyzing the tone or rate of speech to help detect emotion or bias The system of claim 1 .

Images