System

Abstract

An object of a system according to an embodiment is to objectively evaluate the quality of a meeting and clarify points to be improved.SOLUTION: A system includes an image recording part, a sound recording part, an analysis part, an evaluation part, and a feedback part. The recording unit acquires a video of a meeting. The recording unit acquires sound of a meeting. The analysis unit analyzes the data acquired by the image recording unit and the sound recording unit. The evaluation unit scores the quality of the conference based on the data analyzed by the analysis unit. The feedback unit provides good points and improvements based on the result scored by the evaluation 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] Conventional technologies have had the problem of making it difficult to objectively evaluate the quality of a meeting and identify areas for improvement.

[0005] The system according to the embodiment aims to objectively evaluate the quality of a conference and clarify areas for improvement. [Means for solving the problem]

[0006] The system according to the embodiment includes a video recording unit, a sound recording unit, an analysis unit, an evaluation unit, and a feedback unit. The video recording unit captures video of the conference. The sound recording unit captures audio of the conference. The analysis unit analyzes the data acquired by the video recording unit and the sound recording unit. The evaluation unit scores the quality of the conference based on the data analyzed by the analysis unit. The feedback unit provides good points and areas for improvement based on the results of the scoring by the evaluation unit. [Effects of the Invention]

[0007] The system according to the embodiment can objectively evaluate the quality of a conference and clarify areas for improvement. [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 evaluation system according to an embodiment of the present invention is a system that records and records meetings, analyzes the data using a generation AI to score the quality of the meeting, and changes the mindset of all participants to make the meeting more fruitful. By scoring the quality of the meeting and providing feedback to participants, the meeting evaluation system can improve the efficiency and productivity of meetings.

[0029] A meeting evaluation system according to an embodiment includes a video recording unit, a sound recording unit, an analysis unit, an evaluation unit, and a feedback unit. The video recording unit captures video of the meeting. For example, it captures video of the entire conference room using a video camera. The video recording unit can also capture video of the online meeting using a webcam. The video recording unit can also record presentation materials using a screen sharing function. The sound recording unit captures audio of the meeting. For example, it records participants' remarks using a microphone. The sound recording unit can also record high-quality audio of the meeting using a recording device. The sound recording unit can also convert the remarks into text data using voice recognition technology. The analysis unit analyzes the data acquired by the video recording unit and the sound recording unit. For example, a generation AI performs voice analysis to analyze the remarks. The generation AI can also perform video analysis to analyze the participants' movements. The generation AI can also perform text analysis to extract key points from the remarks. The evaluation unit scores the quality of the meeting based on the data analyzed by the analysis unit. For example, it assigns scores based on the frequency and content of remarks. It can also assign scores based on the participants' eye movements and facial expressions. Furthermore, it is possible to assign scores based on the progress of the meeting and the degree to which the agenda items were achieved. The feedback section provides good points and areas for improvement based on the results scored by the evaluation section. For example, if comments are constructive and contribute to the progress of the meeting, a high score will be given. It is also possible to suggest areas for improvement if participants' eyes are not focused and they are not concentrating. Furthermore, it is possible to give a high score if the meeting progresses smoothly. In this way, the meeting evaluation system can improve the efficiency and productivity of meetings by scoring the quality of the meeting and providing feedback to participants.

[0030] The recording unit also records environmental and background sounds during a meeting, and the generation AI analyzes these sounds to evaluate the atmosphere and level of concentration of the meeting. For example, the recording unit records environmental and background sounds during a meeting in detail, and the generation AI analyzes these sounds to evaluate the atmosphere and level of concentration of participants. For example, it analyzes the sounds of keyboard typing and paper turning to understand the progress of the meeting. The recording unit also records noise and external sounds during the meeting, and the generation AI filters and analyzes these sounds. For example, it removes the sounds of external traffic and people talking to evaluate the level of concentration of the meeting. The recording unit also analyzes environmental sounds during the meeting in real time, and the generation AI evaluates the atmosphere of the meeting. For example, it analyzes participants' laughter and sighs to quantify the atmosphere of the meeting. This allows the quality of meetings to be further improved by evaluating the atmosphere and level of concentration of the meeting.

[0031] The recording unit also records participants' gestures and body movements during the meeting, and the generation AI can analyze these movements to evaluate the participants' proactiveness. For example, the recording unit records participants' gestures and body movements during the meeting in detail, and the generation AI analyzes these movements to evaluate the participants' proactiveness. For example, it analyzes the movements of raising a hand or taking notes to evaluate active participation. The recording unit also analyzes participants' body movements during the meeting in real time, and the generation AI evaluates these movements. For example, it analyzes a leaning-forward posture or nodding movements to quantify active participation. The recording unit also records participants' gestures during the meeting, and the generation AI analyzes these movements to evaluate their proactiveness. For example, it analyzes movements such as pointing and spreading one's hand to evaluate the degree of emphasis of speech. This can further improve the quality of meetings by evaluating participants' proactiveness.

[0032] The video and audio recording units can adjust the video and audio recording data of a meeting to accommodate different meeting formats. For example, the video and audio recording units analyze the video and audio recording data and make adjustments to accommodate online and hybrid meetings. For example, they adjust the clarity of the audio and the resolution of the video to accommodate different meeting formats. The video and audio recording units also convert the format of the video and audio recording data to accommodate different meeting formats. For example, they compress the audio data for online meetings and increase the resolution of the video data for hybrid meetings. The video and audio recording units also analyze the video and audio recording data and filter it to accommodate different meeting formats. For example, they remove unnecessary background noise in online meetings and highlight the faces of participants in hybrid meetings. This allows the quality of meetings to be improved by accommodating different meeting formats.

[0033] The video and audio recording department can compare video and audio data of meetings with other meeting data and use it as a benchmark. For example, the video and audio recording department can compare video and audio data of meetings with other meeting data and use it as a benchmark. For example, by comparing it with past meeting data, they can evaluate the frequency of comments and the quality of the content. The video and audio recording department can also compare video and audio data with other meeting data to benchmark the progress of the meeting and the contributions of participants. For example, by comparing it with meeting data on the same topic, they can evaluate the depth of discussion and the number of constructive opinions. The video and audio recording department can also build a system to compare video and audio data of meetings with other meeting data and use it as a benchmark. For example, they can compare meeting data from different teams or projects and extract best practices. This allows the quality of meetings to be benchmarked by comparing it with other meeting data.

[0034] The analysis unit uses the generation AI to analyze and score data, and can evaluate the relevance and importance of each statement based on the meeting's theme and agenda. For example, the analysis unit has the generation AI analyze the meeting's theme and agenda and evaluate the relevance and importance of each statement. For example, high scores are given to statements that are directly related to the agenda, and low scores are given to unrelated statements. The analysis unit also builds a system in which the generation AI evaluates the importance of each statement based on the meeting's theme and agenda. For example, high scores are given to statements that contribute to the progress of the agenda. The analysis unit also has the generation AI analyze the meeting's theme and agenda and evaluate the relevance and importance of each statement. For example, high scores are given to statements that include specific proposals or solutions to the agenda. This makes it possible to improve the quality of meetings by evaluating the relevance and importance of statements based on the meeting's theme and agenda.

[0035] The analysis unit uses the generation AI to analyze and score the data, and can analyze the progress of the meeting in real time to detect delays in progress or deviations from the agenda. For example, the analysis unit builds a system in which the generation AI analyzes the progress of the meeting in real time to detect delays in progress or deviations from the agenda. For example, it analyzes the time allocation for each agenda item and detects delays in progress. The analysis unit also analyzes the progress of the meeting in real time and the generation AI detects deviations from the agenda. For example, it displays a warning if topics unrelated to the agenda continue. The analysis unit also analyzes the progress of the meeting in real time and detects delays in progress or deviations from the agenda. For example, it monitors the progress of each agenda item and evaluates whether it is progressing as planned. In this way, the efficiency of meetings can be improved by analyzing the progress of the meeting in real time and detecting delays in progress or deviations from the agenda.

[0036] The analysis unit uses the generation AI to analyze and score data, and can analyze conference data from different industries and fields to create common evaluation criteria. For example, the analysis unit builds a system in which the generation AI analyzes conference data from different industries and fields to create common evaluation criteria. For example, it analyzes conference data from technical, design, and marketing fields to unify the evaluation criteria. The analysis unit also analyzes conference data from different industries and the generation AI creates common evaluation criteria. For example, it sets evaluation criteria based on the quality and frequency of comments. The analysis unit also analyzes conference data from different fields and creates common evaluation criteria. For example, it sets evaluation criteria based on the progress of agenda items and the contributions of participants. In this way, by analyzing conference data from different industries and creating common evaluation criteria, the quality of meetings can be uniformly evaluated.

[0037] The analysis unit uses the generation AI to analyze and score the data, and can compare the meeting data with meeting data from other organizations to perform a relative evaluation. For example, the analysis unit builds a system in which the generation AI compares the meeting data with meeting data from other organizations to perform a relative evaluation. For example, it compares it with meeting data from companies in the same industry to evaluate the quality and frequency of comments. The analysis unit also compares it with meeting data from other organizations, and the generation AI performs a relative evaluation. For example, it compares it with meeting data on the same topic to evaluate the depth of discussion and the number of constructive opinions. The analysis unit also compares the meeting data with meeting data from other organizations to perform a relative evaluation. For example, it compares meeting data from different teams or projects to extract best practices. This makes it possible to relatively evaluate the quality of meetings by comparing it with meeting data from other organizations.

[0038] The evaluation unit can analyze the content of statements and evaluate them based on technical terminology and details. For example, the evaluation unit constructs a system in which a generation AI analyzes the content of statements and evaluates them based on technical terminology and details. For example, scores are assigned based on the frequency of use of technical terminology and the depth of technical details. The evaluation unit also analyzes the content of statements and the generation AI evaluates them based on technical terminology and details. For example, statements with a lot of technical details are assigned higher scores. The evaluation unit also analyzes the content of statements and the generation AI evaluates them based on technical terminology and details. For example, scores are assigned based on the accurate use of technical terminology and the concreteness of the technical details. In this way, the quality of meetings can be improved by evaluating statements based on technical terminology and details.

[0039] The evaluation unit can analyze the logical structure of a statement and evaluate its logical consistency and persuasiveness. For example, the evaluation unit constructs a system in which a generation AI analyzes the logical structure of a statement and evaluates its logical consistency and persuasiveness. For example, a high score is given to a statement with high logical consistency. The evaluation unit also analyzes the logical structure of a statement and the generation AI evaluates its logical consistency and persuasiveness. For example, a high score is given to a statement with few logical contradictions. The evaluation unit also analyzes the logical structure of a statement and the generation AI evaluates its logical consistency and persuasiveness. For example, a high score is given to a statement that includes a persuasive logical development. In this way, the quality of meetings can be improved by evaluating the logical structure of statements.

[0040] The evaluation unit can translate the content of the utterances into different languages ​​and evaluate them from an international perspective. For example, the evaluation unit builds a system in which a generation AI translates the content of the utterances into different languages ​​and evaluates them from an international perspective. For example, translation into multiple languages ​​such as English, French, and Chinese. The evaluation unit also translates the content of the utterances into different languages ​​and the generation AI evaluates them from an international perspective. For example, evaluation is performed by incorporating perspectives from different cultural spheres. The evaluation unit also translates the content of the utterances into different languages ​​and evaluates them from an international perspective. For example, the quality of the utterances is evaluated based on international standards. In this way, the quality of meetings can be improved by translating the content of the utterances into different languages ​​and evaluating them from an international perspective.

[0041] The evaluation unit can convert the content of comments into visual notes or mind maps and visually evaluate them. For example, the evaluation unit constructs a system in which a generation AI converts the content of comments into visual notes and visually evaluates them. For example, important points are indicated with diagrams or icons. The evaluation unit also converts the content of comments into mind map format and the generation AI visually evaluates them. For example, related keywords and concepts are visually organized. The evaluation unit also converts the content of comments into visual notes or mind maps and visually evaluates them. For example, it provides a function to visualize summaries with drag and drop. This allows the quality of meetings to be improved by visually evaluating the content of comments.

[0042] The evaluation unit can analyze gaze movements and evaluate the degree of gaze concentration and gaze direction. For example, the evaluation unit constructs a system in which a generation AI analyzes gaze movements and evaluates the degree of gaze concentration and gaze direction. For example, if the gaze is focused on a specific object, a high score is given. The evaluation unit also analyzes gaze movements in real time, and the generation AI evaluates the degree of gaze concentration and gaze direction. For example, if the gaze moves frequently, a low score is given. The evaluation unit also analyzes gaze movements and evaluates the degree of gaze concentration and gaze direction. For example, if the gaze is focused on a specific object for a long period of time, a high score is given. In this way, the evaluation of gaze movements can improve the quality of meetings.

[0043] The evaluation unit can analyze changes in facial expressions and evaluate the intensity and type of emotion. The evaluation unit, for example, constructs a system in which a generation AI analyzes changes in facial expressions and evaluates the intensity and type of emotion. For example, smiling or surprised expressions are given high scores. The evaluation unit also analyzes changes in facial expressions in real time, and the generation AI evaluates the intensity and type of emotion. For example, a high score is given if the emotion is expressed strongly. The evaluation unit also analyzes changes in facial expressions and evaluates the intensity and type of emotion. For example, a high score is given to expressions that change emotions. In this way, the quality of meetings can be improved by evaluating changes in facial expressions.

[0044] The evaluation unit can compare the gaze movement and facial expression data with other meeting data and perform a relative evaluation. For example, the evaluation unit constructs a system in which the generation AI compares the gaze movement and facial expression data with other meeting data and performs a relative evaluation. For example, it compares it with meeting data from competing companies to evaluate the level of gaze concentration and changes in facial expression. The evaluation unit also compares the gaze movement and facial expression data with other meeting data and the generation AI performs a relative evaluation. For example, it compares it with meeting data on the same topic to evaluate gaze movement and changes in facial expression. The evaluation unit also compares the gaze movement and facial expression data with other meeting data and performs a relative evaluation. For example, it compares meeting data from different teams or projects and extracts best practices. This makes it possible to perform a relative evaluation of gaze movement and facial expressions by comparing it with other meeting data.

[0045] The evaluation unit can compare the gaze movement and facial expression data with data from different cultural spheres to evaluate cultural differences. For example, the evaluation unit constructs a system in which a generation AI compares gaze movement and facial expression data with data from different cultural spheres to evaluate cultural differences. For example, meeting data from Asia and Europe is compared to evaluate gaze movement and facial expression changes. The evaluation unit also compares gaze movement and facial expression data from different cultural spheres, and the generation AI evaluates cultural differences. For example, the generation AI evaluates gaze movement and facial expression changes based on cultural background. The evaluation unit also compares the gaze movement and facial expression data with data from different cultural spheres to evaluate cultural differences. For example, the generation AI evaluates gaze movement and facial expression changes based on meeting data from different cultural spheres. This makes it possible to evaluate cultural differences by comparing with data from different cultural spheres.

[0046] The feedback unit can individually customize the feedback provided by the generation AI and suggest specific areas for improvement based on each participant's characteristics and past data. For example, the feedback unit constructs a system in which the generation AI analyzes the characteristics and past data of each participant and provides individually customized feedback. For example, the feedback unit suggests specific areas for improvement based on the content of past comments and eye movements. The feedback unit also has the generation AI suggest specific areas for improvement based on each participant's characteristics. For example, it suggests areas for improvement based on the frequency and content of comments. The feedback unit also has the generation AI analyze past data and provide individually customized feedback to each participant. For example, it suggests specific areas for improvement based on changes in eye movements and facial expressions. This makes it possible to promote improvement by providing individually customized feedback to participants.

[0047] The feedback unit provides feedback from the generation AI in real time, encouraging immediate improvement during the meeting. The feedback unit, for example, builds a system in which the generation AI provides feedback in real time during the meeting and encourages immediate improvement. For example, it suggests areas for improvement in real time based on the content of comments and eye movements. The feedback unit also provides feedback in real time during the meeting from the generation AI, enabling participants to make immediate improvements. For example, it provides advice in real time based on the frequency and content of comments. The feedback unit also provides feedback in real time from the generation AI during the meeting and encourages immediate improvement. For example, it suggests areas for improvement in real time based on changes in eye movements and facial expressions. In this way, by providing feedback in real time, it is possible to encourage immediate improvement during the meeting.

[0048] The feedback unit can provide feedback from the generation AI in different formats (text, audio, video) and provide feedback according to the preferences of the participants. For example, the feedback unit builds a system in which the generation AI provides feedback in different formats (text, audio, video) and provides feedback according to the preferences of the participants. For example, it provides text to participants who request text feedback. The feedback unit also provides feedback in different formats and the generation AI provides feedback according to the preferences of the participants. For example, it provides audio to participants who request audio feedback. The feedback unit also provides feedback in different formats and provides feedback according to the preferences of the participants. For example, it provides video to participants who request video feedback. This makes it possible to provide feedback in different formats according to the preferences of the participants.

[0049] The feedback unit can compare the feedback provided by the generation AI with other meeting data and suggest best practices. The feedback unit, for example, builds a system in which the generation AI compares the feedback with other meeting data and suggests best practices. For example, it compares with meeting data from other companies in the same industry to provide optimal feedback. The feedback unit also compares the feedback with other meeting data and the generation AI suggests best practices. For example, it compares with meeting data on the same topic to provide optimal feedback. The feedback unit also compares the feedback with other meeting data and suggests best practices. For example, it compares meeting data from different teams or projects to provide optimal feedback. This makes it possible to suggest best practices by comparing with other meeting data.

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

[0051] The meeting evaluation system can further include a statement evaluation unit for evaluating the quality of participants' statements. The statement evaluation unit evaluates, for example, how specific the content of a statement is with respect to the agenda or whether it presents a solution. Specifically, a statement that includes a specific proposal for solving a problem can be given a high evaluation. The statement evaluation unit can also evaluate the logical consistency and persuasiveness of the statement. For example, a statement that has few logical contradictions and is persuasive can be given a high evaluation. Furthermore, the statement evaluation unit can evaluate the frequency of statements and the degree of contribution of participants. For example, a participant who actively speaks and contributes to the progress of the meeting can be given a high evaluation. In this way, by evaluating the quality of statements, the quality of the meeting can be further improved.

[0052] The conference evaluation system may further include a translation unit that translates participants' comments in real time to facilitate communication between participants who speak different languages. The translation unit may, for example, translate comments into text in real time and display the text as subtitles. The translation unit may also perform speech translation to provide simultaneous interpretation for participants who speak different languages. The translation unit may also translate comments into multiple languages ​​and display the translated text in the language selected by the participant. This may improve the quality of the conference by facilitating communication between participants who speak different languages.

[0053] The meeting evaluation system may further include a summarizing unit that summarizes the remarks made by participants and provides a summary report after the meeting. The summarizing unit may, for example, analyze the remarks and extract important points and conclusions. The summarizing unit may also evaluate the contribution of each participant based on the frequency and content of remarks. Furthermore, the summarizing unit may summarize the progress of the meeting and the degree to which the agenda items have been achieved, and create a report to grasp the overall picture of the meeting. In this way, providing a summary report after the meeting makes it easier for participants to reflect on the content of the meeting, thereby improving the quality of the meeting.

[0054] The meeting evaluation system can further include a visualization unit that visualizes the content of participants' comments to make them easier to understand visually. The visualization unit can, for example, display the content of comments in mind map format to visually organize related keywords and concepts. The visualization unit can also convert the content of comments into graphs or charts to visually show trends and patterns in the data. Furthermore, the visualization unit can display the content of comments in timeline format to allow the progress of the meeting to be grasped at a glance. This makes the content of comments easier to understand visually, thereby improving the quality of the meeting.

[0055] The meeting evaluation system can further include a comparative evaluation unit that compares the content of participants' comments with other meeting data and uses it as a benchmark. The comparative evaluation unit can, for example, compare it with past meeting data to evaluate the frequency of comments and the quality of the content. The comparative evaluation unit can also compare it with meeting data from other companies in the same industry to evaluate the quality and frequency of comments as a benchmark. Furthermore, the comparative evaluation unit can compare meeting data from different teams or projects to extract best practices. This allows the quality of meetings to be evaluated as a benchmark by comparing it with other meeting data.

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

[0057] Step 1: The recording unit captures video of the meeting. For example, a video camera can be used to capture the entire conference room. The recording unit can also capture video of online meetings using a webcam. Furthermore, the recording unit can also record presentation materials using the screen sharing function. Step 2: The recording unit captures the audio of the conference. For example, it uses a microphone to record what the participants say. The recording unit can also use a recording device to record the audio of the conference in high quality. Furthermore, the recording unit can convert the speech into text data using speech recognition technology. Step 3: The analysis unit analyzes the data acquired by the video recording unit and the audio recording unit. For example, the generation AI performs audio analysis to analyze what is being said. The generation AI can also perform video analysis to analyze the movements of participants. Furthermore, the generation AI can perform text analysis to extract the main points of what is being said. Step 4: The evaluation unit scores the quality of the meeting based on the data analyzed by the analysis unit. For example, the evaluation unit assigns scores based on the frequency and content of comments. It can also assign scores based on participants' eye movements and facial expressions. It can also assign scores based on the progress of the meeting and the degree to which the agenda was achieved. Step 5: The feedback department provides good points and areas for improvement based on the results scored by the evaluation department. For example, if the comments were constructive and contributed to the progress of the meeting, a high score is given. Also, if the participants' eyes were not focused and they were not concentrating, an area for improvement can be suggested. Furthermore, if the meeting proceeded smoothly, a high score can be given.

[0058] (Example 2) A meeting evaluation system according to an embodiment of the present invention is a system that records and records meetings, analyzes the data using a generation AI to score the quality of the meeting, and changes the mindset of all participants to make the meeting more fruitful. By scoring the quality of the meeting and providing feedback to participants, the meeting evaluation system can improve the efficiency and productivity of meetings.

[0059] A meeting evaluation system according to an embodiment includes a video recording unit, a sound recording unit, an analysis unit, an evaluation unit, and a feedback unit. The video recording unit captures video of the meeting. For example, it captures video of the entire conference room using a video camera. The video recording unit can also capture video of the online meeting using a webcam. The video recording unit can also record presentation materials using a screen sharing function. The sound recording unit captures audio of the meeting. For example, it records participants' remarks using a microphone. The sound recording unit can also record high-quality audio of the meeting using a recording device. The sound recording unit can also convert the remarks into text data using voice recognition technology. The analysis unit analyzes the data acquired by the video recording unit and the sound recording unit. For example, a generation AI performs voice analysis to analyze the remarks. The generation AI can also perform video analysis to analyze the participants' movements. The generation AI can also perform text analysis to extract key points from the remarks. The evaluation unit scores the quality of the meeting based on the data analyzed by the analysis unit. For example, it assigns scores based on the frequency and content of remarks. It can also assign scores based on the participants' eye movements and facial expressions. Furthermore, it is possible to assign scores based on the progress of the meeting and the degree to which the agenda items were achieved. The feedback section provides good points and areas for improvement based on the results scored by the evaluation section. For example, if comments are constructive and contribute to the progress of the meeting, a high score will be given. It is also possible to suggest areas for improvement if participants' eyes are not focused and they are not concentrating. Furthermore, it is possible to give a high score if the meeting progresses smoothly. In this way, the meeting evaluation system can improve the efficiency and productivity of meetings by scoring the quality of the meeting and providing feedback to participants.

[0060] The recording unit also records environmental and background sounds during a meeting, and the generation AI analyzes these sounds to evaluate the atmosphere and level of concentration of the meeting. For example, the recording unit records environmental and background sounds during a meeting in detail, and the generation AI analyzes these sounds to evaluate the atmosphere and level of concentration of participants. For example, it analyzes the sounds of keyboard typing and paper turning to understand the progress of the meeting. The recording unit also records noise and external sounds during the meeting, and the generation AI filters and analyzes these sounds. For example, it removes the sounds of external traffic and people talking to evaluate the level of concentration of the meeting. The recording unit also analyzes environmental sounds during the meeting in real time, and the generation AI evaluates the atmosphere of the meeting. For example, it analyzes participants' laughter and sighs to quantify the atmosphere of the meeting. This allows the quality of meetings to be further improved by evaluating the atmosphere and level of concentration of the meeting.

[0061] The recording unit also records participants' gestures and body movements during the meeting, and the generation AI can analyze these movements to evaluate the participants' proactiveness. For example, the recording unit records participants' gestures and body movements during the meeting in detail, and the generation AI analyzes these movements to evaluate the participants' proactiveness. For example, it analyzes the movements of raising a hand or taking notes to evaluate active participation. The recording unit also analyzes participants' body movements during the meeting in real time, and the generation AI evaluates these movements. For example, it analyzes a leaning-forward posture or nodding movements to quantify active participation. The recording unit also records participants' gestures during the meeting, and the generation AI analyzes these movements to evaluate their proactiveness. For example, it analyzes movements such as pointing and spreading one's hand to evaluate the degree of emphasis of speech. This can further improve the quality of meetings by evaluating participants' proactiveness.

[0062] The analysis unit uses the emotion estimation function to analyze changes in the emotions of participants during a meeting in real time and evaluate their emotional reactions to the progress of the meeting. The analysis unit, for example, analyzes the facial expressions and voices of participants during a meeting in real time and evaluates changes in emotion using the emotion estimation function. For example, it analyzes smiling and surprised expressions and quantifies their emotional reactions to the progress of the meeting. The analysis unit also analyzes the emotions of participants during a meeting in real time, and the generation AI evaluates those changes in emotion. For example, it analyzes changes in tone of voice and speaking style to evaluate the emotional reactions. The analysis unit also uses the emotion estimation function to analyze changes in the emotions of participants during a meeting in real time and evaluates their emotional reactions to the progress of the meeting. For example, it analyzes the facial expressions and body movements of participants and quantifies changes in emotion. This allows the progress of the meeting to be managed more effectively by evaluating emotional reactions.

[0063] The video and audio recording units can adjust the video and audio recording data of a meeting to accommodate different meeting formats. For example, the video and audio recording units analyze the video and audio recording data and make adjustments to accommodate online and hybrid meetings. For example, they adjust the clarity of the audio and the resolution of the video to accommodate different meeting formats. The video and audio recording units also convert the format of the video and audio recording data to accommodate different meeting formats. For example, they compress the audio data for online meetings and increase the resolution of the video data for hybrid meetings. The video and audio recording units also analyze the video and audio recording data and filter it to accommodate different meeting formats. For example, they remove unnecessary background noise in online meetings and highlight the faces of participants in hybrid meetings. This allows the quality of meetings to be improved by accommodating different meeting formats.

[0064] The video and audio recording department can compare video and audio data of meetings with other meeting data and use it as a benchmark. For example, the video and audio recording department can compare video and audio data of meetings with other meeting data and use it as a benchmark. For example, by comparing it with past meeting data, they can evaluate the frequency of comments and the quality of the content. The video and audio recording department can also compare video and audio data with other meeting data to benchmark the progress of the meeting and the contributions of participants. For example, by comparing it with meeting data on the same topic, they can evaluate the depth of discussion and the number of constructive opinions. The video and audio recording department can also build a system to compare video and audio data of meetings with other meeting data and use it as a benchmark. For example, they can compare meeting data from different teams or projects and extract best practices. This allows the quality of meetings to be benchmarked by comparing it with other meeting data.

[0065] The analysis unit uses the generation AI to analyze and score data, and can evaluate the relevance and importance of each statement based on the meeting's theme and agenda. For example, the analysis unit has the generation AI analyze the meeting's theme and agenda and evaluate the relevance and importance of each statement. For example, high scores are given to statements that are directly related to the agenda, and low scores are given to unrelated statements. The analysis unit also builds a system in which the generation AI evaluates the importance of each statement based on the meeting's theme and agenda. For example, high scores are given to statements that contribute to the progress of the agenda. The analysis unit also has the generation AI analyze the meeting's theme and agenda and evaluate the relevance and importance of each statement. For example, high scores are given to statements that include specific proposals or solutions to the agenda. This makes it possible to improve the quality of meetings by evaluating the relevance and importance of statements based on the meeting's theme and agenda.

[0066] The analysis unit uses the generation AI to analyze and score the data, and can analyze the progress of the meeting in real time to detect delays in progress or deviations from the agenda. For example, the analysis unit builds a system in which the generation AI analyzes the progress of the meeting in real time to detect delays in progress or deviations from the agenda. For example, it analyzes the time allocation for each agenda item and detects delays in progress. The analysis unit also analyzes the progress of the meeting in real time and the generation AI detects deviations from the agenda. For example, it displays a warning if topics unrelated to the agenda continue. The analysis unit also analyzes the progress of the meeting in real time and detects delays in progress or deviations from the agenda. For example, it monitors the progress of each agenda item and evaluates whether it is progressing as planned. In this way, the efficiency of meetings can be improved by analyzing the progress of the meeting in real time and detecting delays in progress or deviations from the agenda.

[0067] The analysis unit can use the emotion estimation function to analyze changes in the emotions of participants during a meeting and adjust scores based on their emotional responses. The analysis unit, for example, uses the emotion estimation function to analyze changes in the emotions of participants during a meeting and build a system that adjusts scores based on the results. For example, a high score is assigned to a statement that expresses a strong positive emotion. The analysis unit also analyzes the emotions of participants during a meeting in real time and adjusts scores based on their emotional responses. For example, a high score is assigned to a statement that expresses increasing emotion. The analysis unit also uses the emotion estimation function to analyze changes in the emotions of participants during a meeting and adjusts scores based on their emotional responses. For example, a low score is assigned to a statement that expresses decreasing emotion. In this way, by adjusting scores based on emotional responses, the quality of a meeting can be more accurately evaluated.

[0068] The analysis unit uses the generation AI to analyze and score data, and can analyze conference data from different industries and fields to create common evaluation criteria. For example, the analysis unit builds a system in which the generation AI analyzes conference data from different industries and fields to create common evaluation criteria. For example, it analyzes conference data from technical, design, and marketing fields to unify the evaluation criteria. The analysis unit also analyzes conference data from different industries and the generation AI creates common evaluation criteria. For example, it sets evaluation criteria based on the quality and frequency of comments. The analysis unit also analyzes conference data from different fields and creates common evaluation criteria. For example, it sets evaluation criteria based on the progress of agenda items and the contributions of participants. In this way, by analyzing conference data from different industries and creating common evaluation criteria, the quality of meetings can be uniformly evaluated.

[0069] The analysis unit uses the generation AI to analyze and score the data, and can compare the meeting data with meeting data from other organizations to perform a relative evaluation. For example, the analysis unit builds a system in which the generation AI compares the meeting data with meeting data from other organizations to perform a relative evaluation. For example, it compares it with meeting data from companies in the same industry to evaluate the quality and frequency of comments. The analysis unit also compares it with meeting data from other organizations, and the generation AI performs a relative evaluation. For example, it compares it with meeting data on the same topic to evaluate the depth of discussion and the number of constructive opinions. The analysis unit also compares the meeting data with meeting data from other organizations to perform a relative evaluation. For example, it compares meeting data from different teams or projects to extract best practices. This makes it possible to relatively evaluate the quality of meetings by comparing it with meeting data from other organizations.

[0070] The analysis unit can use the emotion estimation function to analyze the emotions of participants during a meeting and evaluate the quality of the meeting based on their emotional reactions. The analysis unit, for example, uses the emotion estimation function to analyze the emotions of participants during a meeting and builds a system to evaluate the quality of the meeting based on the results. For example, a meeting in which positive emotions are strong is given a high rating. The analysis unit also analyzes the emotions of participants during a meeting in real time and evaluates the quality of the meeting based on their emotional reactions. For example, a meeting in which emotions are rising is given a high rating. The analysis unit also uses the emotion estimation function to analyze the emotions of participants during a meeting and evaluate the quality of the meeting based on their emotional reactions. For example, a meeting in which emotions are falling is given a low rating. In this way, by evaluating the quality of a meeting based on emotional reactions, the quality of the meeting can be evaluated more accurately.

[0071] The evaluation unit can analyze the content of statements and evaluate them based on technical terminology and details. For example, the evaluation unit constructs a system in which a generation AI analyzes the content of statements and evaluates them based on technical terminology and details. For example, scores are assigned based on the frequency of use of technical terminology and the depth of technical details. The evaluation unit also analyzes the content of statements and the generation AI evaluates them based on technical terminology and details. For example, statements with a lot of technical details are assigned higher scores. The evaluation unit also analyzes the content of statements and the generation AI evaluates them based on technical terminology and details. For example, scores are assigned based on the accurate use of technical terminology and the concreteness of the technical details. In this way, the quality of meetings can be improved by evaluating statements based on technical terminology and details.

[0072] The evaluation unit can analyze the logical structure of a statement and evaluate its logical consistency and persuasiveness. For example, the evaluation unit constructs a system in which a generation AI analyzes the logical structure of a statement and evaluates its logical consistency and persuasiveness. For example, a high score is given to a statement with high logical consistency. The evaluation unit also analyzes the logical structure of a statement and the generation AI evaluates its logical consistency and persuasiveness. For example, a high score is given to a statement with few logical contradictions. The evaluation unit also analyzes the logical structure of a statement and the generation AI evaluates its logical consistency and persuasiveness. For example, a high score is given to a statement that includes a persuasive logical development. In this way, the quality of meetings can be improved by evaluating the logical structure of statements.

[0073] The evaluation unit can use the emotion estimation function to analyze changes in emotions during speech and evaluate emotional influence. The evaluation unit, for example, uses the emotion estimation function to analyze changes in emotions during speech and builds a system to evaluate emotional influence based on the results. For example, a high score is given to a statement that expresses strong emotions. The evaluation unit also analyzes emotions during speech in real time and evaluates emotional influence. For example, a high score is given to a statement that expresses strong emotions. The evaluation unit also uses the emotion estimation function to analyze changes in emotions during speech and evaluate emotional influence. For example, a high score is given to a statement that changes emotions. In this way, the quality of meetings can be improved by evaluating changes in emotions during speech.

[0074] The evaluation unit can translate the content of the utterances into different languages ​​and evaluate them from an international perspective. For example, the evaluation unit builds a system in which a generation AI translates the content of the utterances into different languages ​​and evaluates them from an international perspective. For example, translation into multiple languages ​​such as English, French, and Chinese. The evaluation unit also translates the content of the utterances into different languages ​​and the generation AI evaluates them from an international perspective. For example, evaluation is performed by incorporating perspectives from different cultural spheres. The evaluation unit also translates the content of the utterances into different languages ​​and evaluates them from an international perspective. For example, the quality of the utterances is evaluated based on international standards. In this way, the quality of meetings can be improved by translating the content of the utterances into different languages ​​and evaluating them from an international perspective.

[0075] The evaluation unit can convert the content of comments into visual notes or mind maps and visually evaluate them. For example, the evaluation unit constructs a system in which a generation AI converts the content of comments into visual notes and visually evaluates them. For example, important points are indicated with diagrams or icons. The evaluation unit also converts the content of comments into mind map format and the generation AI visually evaluates them. For example, related keywords and concepts are visually organized. The evaluation unit also converts the content of comments into visual notes or mind maps and visually evaluates them. For example, it provides a function to visualize summaries with drag and drop. This allows the quality of meetings to be improved by visually evaluating the content of comments.

[0076] The evaluation unit can use the emotion estimation function to analyze emotions during speech and evaluate emotional influence. The evaluation unit, for example, uses the emotion estimation function to analyze emotions during speech and builds a system to evaluate emotional influence based on the results. For example, a high score is given to a speech that expresses strong emotions. The evaluation unit also analyzes emotions during speech in real time and evaluates emotional influence. For example, a high score is given to a speech that expresses strong emotions. The evaluation unit also uses the emotion estimation function to analyze emotions during speech and evaluate emotional influence. For example, a high score is given to a speech that changes in emotion. In this way, the quality of the meeting can be improved by evaluating changes in emotions during speech.

[0077] The evaluation unit can analyze gaze movements and evaluate the degree of gaze concentration and gaze direction. For example, the evaluation unit constructs a system in which a generation AI analyzes gaze movements and evaluates the degree of gaze concentration and gaze direction. For example, if the gaze is focused on a specific object, a high score is given. The evaluation unit also analyzes gaze movements in real time, and the generation AI evaluates the degree of gaze concentration and gaze direction. For example, if the gaze moves frequently, a low score is given. The evaluation unit also analyzes gaze movements and evaluates the degree of gaze concentration and gaze direction. For example, if the gaze is focused on a specific object for a long period of time, a high score is given. In this way, the evaluation of gaze movements can improve the quality of meetings.

[0078] The evaluation unit can analyze changes in facial expressions and evaluate the intensity and type of emotion. The evaluation unit, for example, constructs a system in which a generation AI analyzes changes in facial expressions and evaluates the intensity and type of emotion. For example, smiling or surprised expressions are given high scores. The evaluation unit also analyzes changes in facial expressions in real time, and the generation AI evaluates the intensity and type of emotion. For example, a high score is given if the emotion is expressed strongly. The evaluation unit also analyzes changes in facial expressions and evaluates the intensity and type of emotion. For example, a high score is given to expressions that change emotions. In this way, the quality of meetings can be improved by evaluating changes in facial expressions.

[0079] The evaluation unit can use the emotion estimation function to analyze gaze movements and changes in facial expression to evaluate emotional responses. The evaluation unit, for example, uses the emotion estimation function to analyze gaze movements and changes in facial expression and builds a system to evaluate emotional responses based on the results. For example, a high score is given if emotions are heightened. The evaluation unit also analyzes gaze movements and changes in facial expression in real time to evaluate emotional responses. For example, a high score is given if emotions are expressed strongly. The evaluation unit also uses the emotion estimation function to analyze gaze movements and changes in facial expression to evaluate emotional responses. For example, a high score is given if emotions change. In this way, the quality of meetings can be improved by evaluating gaze movements and changes in facial expression.

[0080] The evaluation unit can compare the gaze movement and facial expression data with other meeting data and perform a relative evaluation. For example, the evaluation unit constructs a system in which the generation AI compares the gaze movement and facial expression data with other meeting data and performs a relative evaluation. For example, it compares it with meeting data from competing companies to evaluate the level of gaze concentration and changes in facial expression. The evaluation unit also compares the gaze movement and facial expression data with other meeting data and the generation AI performs a relative evaluation. For example, it compares it with meeting data on the same topic to evaluate gaze movement and changes in facial expression. The evaluation unit also compares the gaze movement and facial expression data with other meeting data and performs a relative evaluation. For example, it compares meeting data from different teams or projects and extracts best practices. This makes it possible to perform a relative evaluation of gaze movement and facial expressions by comparing it with other meeting data.

[0081] The evaluation unit can compare the gaze movement and facial expression data with data from different cultural spheres to evaluate cultural differences. For example, the evaluation unit constructs a system in which a generation AI compares gaze movement and facial expression data with data from different cultural spheres to evaluate cultural differences. For example, meeting data from Asia and Europe is compared to evaluate gaze movement and facial expression changes. The evaluation unit also compares gaze movement and facial expression data from different cultural spheres, and the generation AI evaluates cultural differences. For example, the generation AI evaluates gaze movement and facial expression changes based on cultural background. The evaluation unit also compares the gaze movement and facial expression data with data from different cultural spheres to evaluate cultural differences. For example, the generation AI evaluates gaze movement and facial expression changes based on meeting data from different cultural spheres. This makes it possible to evaluate cultural differences by comparing with data from different cultural spheres.

[0082] The evaluation unit can use the emotion estimation function to analyze gaze movements and changes in facial expression to evaluate emotional responses. The evaluation unit, for example, uses the emotion estimation function to analyze gaze movements and changes in facial expression and builds a system to evaluate emotional responses based on the results. For example, a high score is given if emotions are heightened. The evaluation unit also analyzes gaze movements and changes in facial expression in real time to evaluate emotional responses. For example, a high score is given if emotions are expressed strongly. The evaluation unit also uses the emotion estimation function to analyze gaze movements and changes in facial expression to evaluate emotional responses. For example, a high score is given if emotions change. In this way, the quality of meetings can be improved by evaluating gaze movements and changes in facial expression.

[0083] The feedback unit can individually customize the feedback provided by the generation AI and suggest specific areas for improvement based on each participant's characteristics and past data. For example, the feedback unit constructs a system in which the generation AI analyzes the characteristics and past data of each participant and provides individually customized feedback. For example, the feedback unit suggests specific areas for improvement based on the content of past comments and eye movements. The feedback unit also has the generation AI suggest specific areas for improvement based on each participant's characteristics. For example, it suggests areas for improvement based on the frequency and content of comments. The feedback unit also has the generation AI analyze past data and provide individually customized feedback to each participant. For example, it suggests specific areas for improvement based on changes in eye movements and facial expressions. This makes it possible to promote improvement by providing individually customized feedback to participants.

[0084] The feedback unit provides feedback from the generation AI in real time, encouraging immediate improvement during the meeting. The feedback unit, for example, builds a system in which the generation AI provides feedback in real time during the meeting and encourages immediate improvement. For example, it suggests areas for improvement in real time based on the content of comments and eye movements. The feedback unit also provides feedback in real time during the meeting from the generation AI, enabling participants to make immediate improvements. For example, it provides advice in real time based on the frequency and content of comments. The feedback unit also provides feedback in real time from the generation AI during the meeting and encourages immediate improvement. For example, it suggests areas for improvement in real time based on changes in eye movements and facial expressions. In this way, by providing feedback in real time, it is possible to encourage immediate improvement during the meeting.

[0085] The feedback unit can use the emotion estimation function to take emotional into consideration the content of the feedback and emphasize positive feedback. For example, the feedback unit uses the emotion estimation function to build a system that takes emotional into consideration the content of the feedback and emphasizes positive feedback. For example, it provides feedback with a strong positive emotion preferentially. The feedback unit also takes emotional into consideration the content of the feedback, and the generation AI emphasizes positive feedback. For example, it provides feedback with a high level of emotion preferentially. The feedback unit also uses the emotion estimation function to take emotional into consideration the content of the feedback and emphasizes positive feedback. For example, it provides feedback with a change in emotion preferentially. In this way, by providing feedback that takes emotional consideration into consideration, it is possible to improve the motivation of participants.

[0086] The feedback unit can provide feedback from the generation AI in different formats (text, audio, video) and provide feedback according to the preferences of the participants. For example, the feedback unit builds a system in which the generation AI provides feedback in different formats (text, audio, video) and provides feedback according to the preferences of the participants. For example, it provides text to participants who request text feedback. The feedback unit also provides feedback in different formats and the generation AI provides feedback according to the preferences of the participants. For example, it provides audio to participants who request audio feedback. The feedback unit also provides feedback in different formats and provides feedback according to the preferences of the participants. For example, it provides video to participants who request video feedback. This makes it possible to provide feedback in different formats according to the preferences of the participants.

[0087] The feedback unit can compare the feedback provided by the generation AI with other meeting data and suggest best practices. The feedback unit, for example, builds a system in which the generation AI compares the feedback with other meeting data and suggests best practices. For example, it compares with meeting data from other companies in the same industry to provide optimal feedback. The feedback unit also compares the feedback with other meeting data and the generation AI suggests best practices. For example, it compares with meeting data on the same topic to provide optimal feedback. The feedback unit also compares the feedback with other meeting data and suggests best practices. For example, it compares meeting data from different teams or projects to provide optimal feedback. This makes it possible to suggest best practices by comparing with other meeting data.

[0088] The feedback unit can use the emotion estimation function to take emotional into consideration the content of the feedback and emphasize positive feedback. For example, the feedback unit uses the emotion estimation function to build a system that takes emotional into consideration the content of the feedback and emphasizes positive feedback. For example, it provides feedback with a strong positive emotion preferentially. The feedback unit also takes emotional into consideration the content of the feedback, and the generation AI emphasizes positive feedback. For example, it provides feedback with a high level of emotion preferentially. The feedback unit also uses the emotion estimation function to take emotional into consideration the content of the feedback and emphasizes positive feedback. For example, it provides feedback with a change in emotion preferentially. In this way, by providing feedback that takes emotional consideration into consideration, it is possible to improve the motivation of participants.

[0089] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0090] The meeting evaluation system can further include a statement evaluation unit for evaluating the quality of participants' statements. The statement evaluation unit evaluates, for example, how specific the content of a statement is with respect to the agenda or whether it presents a solution. Specifically, a statement that includes a specific proposal for solving a problem can be given a high evaluation. The statement evaluation unit can also evaluate the logical consistency and persuasiveness of the statement. For example, a statement that has few logical contradictions and is persuasive can be given a high evaluation. Furthermore, the statement evaluation unit can evaluate the frequency of statements and the degree of contribution of participants. For example, a participant who actively speaks and contributes to the progress of the meeting can be given a high evaluation. In this way, by evaluating the quality of statements, the quality of the meeting can be further improved.

[0091] The meeting evaluation system can further include a progress adjustment unit that estimates the emotions of the participants and adjusts the progress of the meeting based on those emotions. For example, if the emotions of the participants are high, the progress adjustment unit can temporarily suspend the progress of the meeting and provide a refreshment time. Furthermore, if the emotions of the participants are low, the progress adjustment unit can accelerate the progress of the meeting and end it early. Furthermore, the progress adjustment unit can change the order of agenda items based on the emotions of the participants. For example, by prioritizing agenda items that participants are interested in, the meeting can be made more lively. In this way, the quality of the meeting can be improved by adjusting the progress of the meeting based on the emotions of the participants.

[0092] The conference evaluation system may further include a translation unit that translates participants' comments in real time to facilitate communication between participants who speak different languages. The translation unit may, for example, translate comments into text in real time and display the text as subtitles. The translation unit may also perform speech translation to provide simultaneous interpretation for participants who speak different languages. The translation unit may also translate comments into multiple languages ​​and display the translated text in the language selected by the participant. This may improve the quality of the conference by facilitating communication between participants who speak different languages.

[0093] The meeting evaluation system can further include a feedback customization unit that estimates the emotions of participants and customizes feedback based on those emotions. For example, if a participant has positive emotions, the feedback customization unit can emphasize positive feedback. Also, if a participant has negative emotions, the feedback customization unit can gently suggest areas for improvement to maintain the participant's motivation. Furthermore, the feedback customization unit can adjust the content and format of feedback based on the participant's emotions. For example, detailed feedback can be provided to participants whose emotions are high, and brief feedback can be provided to participants whose emotions are low. In this way, the quality of the meeting can be improved by providing feedback that takes into consideration the emotions of the participants.

[0094] The meeting evaluation system may further include a summarizing unit that summarizes the remarks made by participants and provides a summary report after the meeting. The summarizing unit may, for example, analyze the remarks and extract important points and conclusions. The summarizing unit may also evaluate the contribution of each participant based on the frequency and content of remarks. Furthermore, the summarizing unit may summarize the progress of the meeting and the degree to which the agenda items have been achieved, and create a report to grasp the overall picture of the meeting. In this way, providing a summary report after the meeting makes it easier for participants to reflect on the content of the meeting, thereby improving the quality of the meeting.

[0095] The meeting evaluation system can further include a progress guide unit that estimates the emotions of the participants and guides the progress of the meeting based on those emotions. For example, if the emotions of the participants are high, the progress guide unit can provide advice to ensure the smooth progress of the meeting. Also, if the emotions of the participants are low, the progress guide unit can make suggestions to improve the progress of the meeting. Furthermore, the progress guide unit can adjust the progress of the meeting in real time based on the emotions of the participants. For example, by prioritizing topics that evoke high emotions, the meeting can be made more lively. In this way, the quality of the meeting can be improved by guiding the progress of the meeting based on the emotions of the participants.

[0096] The meeting evaluation system can further include a visualization unit that visualizes the content of participants' comments to make them easier to understand visually. The visualization unit can, for example, display the content of comments in mind map format to visually organize related keywords and concepts. The visualization unit can also convert the content of comments into graphs or charts to visually show trends and patterns in the data. Furthermore, the visualization unit can display the content of comments in timeline format to allow the progress of the meeting to be grasped at a glance. This makes the content of comments easier to understand visually, thereby improving the quality of the meeting.

[0097] The meeting evaluation system can further include a progress optimization unit that estimates the emotions of the participants and optimizes the progress of the meeting based on those emotions. For example, if the emotions of the participants are rising, the progress optimization unit can accelerate the progress of the meeting and promote the achievement of the agenda. Also, if the emotions of the participants are falling, the progress of the meeting can be temporarily suspended to provide a refreshment time. Furthermore, the progress optimization unit can change the order of the agenda items based on the emotions of the participants. For example, by prioritizing the agenda items that the participants are interested in, the meeting can be made more lively. In this way, the quality of the meeting can be improved by optimizing the progress of the meeting based on the emotions of the participants.

[0098] The meeting evaluation system can further include a comparative evaluation unit that compares the content of participants' comments with other meeting data and uses it as a benchmark. The comparative evaluation unit can, for example, compare it with past meeting data to evaluate the frequency of comments and the quality of the content. The comparative evaluation unit can also compare it with meeting data from other companies in the same industry to evaluate the quality and frequency of comments as a benchmark. Furthermore, the comparative evaluation unit can compare meeting data from different teams or projects to extract best practices. This allows the quality of meetings to be evaluated as a benchmark by comparing it with other meeting data.

[0099] The meeting evaluation system can further include an emotion feedback unit that estimates the emotions of participants and provides feedback based on those emotions. For example, the emotion feedback unit can emphasize positive feedback when a participant's emotions are high. On the other hand, when a participant's emotions are low, the emotion feedback unit can gently advise the participant on areas for improvement, thereby maintaining the participant's motivation. Furthermore, the emotion feedback unit can adjust the content and format of the feedback based on the participants' emotions. For example, detailed feedback can be provided to participants who are high in emotion, and brief feedback can be provided to participants who are low in emotion. This makes it possible to improve the quality of the meeting by providing feedback that takes into consideration the emotions of the participants.

[0100] The processing flow of the second embodiment will be briefly explained below.

[0101] Step 1: The recording unit captures video of the meeting. For example, a video camera can be used to capture the entire conference room. The recording unit can also capture video of online meetings using a webcam. Furthermore, the recording unit can also record presentation materials using the screen sharing function. Step 2: The recording unit captures the audio of the conference. For example, it uses a microphone to record what the participants say. The recording unit can also use a recording device to record the audio of the conference in high quality. Furthermore, the recording unit can convert the speech into text data using speech recognition technology. Step 3: The analysis unit analyzes the data acquired by the video recording unit and the audio recording unit. For example, the generation AI performs audio analysis to analyze what is being said. The generation AI can also perform video analysis to analyze the movements of participants. Furthermore, the generation AI can perform text analysis to extract the main points of what is being said. Step 4: The evaluation unit scores the quality of the meeting based on the data analyzed by the analysis unit. For example, the evaluation unit assigns scores based on the frequency and content of comments. It can also assign scores based on participants' eye movements and facial expressions. It can also assign scores based on the progress of the meeting and the degree to which the agenda was achieved. Step 5: The feedback department provides good points and areas for improvement based on the results scored by the evaluation department. For example, if the comments were constructive and contributed to the progress of the meeting, a high score is given. Also, if the participants' eyes were not focused and they were not concentrating, an area for improvement can be suggested. Furthermore, if the meeting proceeded smoothly, a high score can be given.

[0102] 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.

[0103] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0104] 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.

[0105] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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).

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0121] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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).

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0136] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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).

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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).

[0155] 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.

[0156] 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."

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0169] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a recording unit that captures video of the meeting; a recording unit for capturing audio from the conference; an analysis unit that analyzes data acquired by the video recording unit and the audio recording unit; an evaluation unit that scores the quality of the conference based on the data analyzed by the analysis unit; a feedback unit that provides good points and points for improvement based on the results scored by the evaluation unit. A system characterized by:

2. The recording unit The environmental and background sounds during the meeting are also recorded, and the AI ​​analyzes these sounds to evaluate the atmosphere and concentration level of the meeting.

2. The system of claim 1.

3. The recording unit The gestures and body movements of the participants during the meeting are also recorded, and the generating AI analyzes these movements to evaluate the participants' proactiveness.

2. The system of claim 1.

4. The analysis unit Analyzing changes in the emotions of participants during the meeting in real time and evaluating their emotional reactions to the progress of the meeting 2. The system of claim 1.

5. The video recording unit and the audio recording unit are Adjusting recordings and audio data to accommodate different meeting formats 2. The system of claim 1.

6. The video recording unit and the audio recording unit are Compare video and audio data with other meeting data and use it as a benchmark 2. The system of claim 1.

Images