system

Abstract

The system according to the embodiment aims to provide feedback on what is said and how it is said in online meetings, and to promote improvement. [Solution] A system according to an embodiment includes a collection unit, an analysis unit, a provision unit, and a tracking unit. The collection unit collects recorded data. The analysis unit analyzes the data collected by the collection unit. The provision unit provides feedback based on the analysis results obtained by the analysis unit. The tracking unit tracks the progress of improvement due to user registration.

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 do not provide sufficient feedback on what is said and how it is said in online meetings, and there is room for improvement.

[0005] The system according to the embodiment aims to provide feedback on what is said and how it is said in online meetings, and to promote improvement. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, a provision unit, and a tracking unit. The collection unit collects recorded data. The analysis unit analyzes the data collected by the collection unit. The provision unit provides feedback based on the analysis results obtained by the analysis unit. The tracking unit tracks the progress of improvement due to user registration. [Effects of the Invention]

[0007] The system according to the embodiment can provide feedback on what is said and how it is said in an online conference, and promote 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 pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

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

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

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

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

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

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

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

[0028] (Example 1) The online conference evaluation system according to an embodiment of the present invention records conversations during online meetings and trains a generation AI to learn from the recordings. The system then provides feedback to speakers on communication aspects, such as the content and manner of speech. Once users register, the generation AI tracks progress toward improvement, contributing to organizational growth. First, online conference conversations are recorded. The recordings are then input into the generation AI. The generation AI analyzes the content of the conversation and the manner of speech to evaluate each speaker's communication skills. For example, evaluation criteria include clarity of speech, logical structure, and appropriate timing. Next, the generation AI provides feedback to each speaker based on the analysis results. This feedback includes specific areas for improvement and merit. For example, advice such as "Try to speak more slowly to improve the clarity of your speech" or "Your logical structure is excellent, so keep it up." Furthermore, once users register, the generation AI tracks progress toward improvement, allowing them to monitor their own communication skills. For example, improvements can be visually displayed compared to past feedback. This system is expected to improve communication skills within an organization and increase overall productivity. For example, it will increase the efficiency of meetings and lead to faster decision-making. Also, as individual speakers improve their skills, the performance of the entire team will improve. This allows the online meeting evaluation system to evaluate what is said and how it is said in meetings and provide feedback.

[0029] An online conference evaluation system according to an embodiment includes a collection unit, an analysis unit, a provision unit, and a tracking unit. The collection unit records conversations during an online conference. For example, the collection unit collects audio data from the conference and stores it digitally. The collection unit has a function for recording the audio data of the conference at high quality and removing noise. For example, the collection unit records the audio of the conference in real time and generates clear audio data using noise reduction technology. The collection unit can also collect video data of the conference. For example, the collection unit records a video of the conference at high resolution and synchronizes it with the audio data. The analysis unit uses a generation AI to analyze the data collected by the collection unit. For example, the analysis unit analyzes the audio data of the conference and evaluates the content and manner of speech. The analysis unit uses the generation AI to evaluate the clarity of speech, logical structure, appropriate timing of speech, etc. For example, the analysis unit inputs audio data into the generation AI and evaluates the clarity of speech. The generation AI analyzes the audio data and evaluates the accuracy of pronunciation and clarity of speech. The analysis unit also uses the generation AI to evaluate the logical structure of the statement. The generation AI analyzes the audio data and evaluates the logical consistency of the statement and the clarity of the argument. The analysis unit also uses the generation AI to evaluate the timing of the statement. The generation AI analyzes the audio data and evaluates appropriate pauses and timing of the statement. The provision unit provides feedback based on the analysis results obtained by the analysis unit. For example, the provision unit provides feedback on specific areas for improvement and merits based on the analysis results. The provision unit uses the generation AI to generate the content of the feedback. For example, the provision unit inputs the analysis results into the generation AI to generate the content of the feedback. The generation AI provides advice for improving the clarity of the statement and for maintaining a logical structure based on the analysis results. The tracking unit tracks the progress of improvements due to user registration. For example, the tracking unit references the user's past feedback history and visually displays the progress of improvements. The tracking unit uses the generation AI to track the progress of improvements. For example, the tracking unit inputs the user's feedback history into the generation AI and analyzes the progress of improvements. The generative AI evaluates and visually displays the user's communication skill growth based on feedback history.As a result, the online conference evaluation system according to the embodiment can evaluate the content and manner of statements made in a conference and provide feedback.

[0030] The online conference evaluation system includes a setting unit that sets evaluation criteria. The setting unit sets the evaluation criteria. For example, the setting unit sets evaluation criteria such as clarity of speech, logical structure, and appropriate timing of speech. The setting unit sets the evaluation criteria using a generation AI. For example, the setting unit inputs the evaluation criteria settings into the generation AI to generate the evaluation criteria. The generation AI sets criteria for evaluating clarity of speech and criteria for evaluating logical structure based on the evaluation criteria. In this way, setting the evaluation criteria improves the accuracy of feedback.

[0031] The online meeting evaluation system includes a generation unit that generates feedback content. The generation unit generates the feedback content. For example, the generation unit provides feedback on specific improvements and merits based on the analysis results obtained by the analysis unit. The generation unit generates the feedback content using a generation AI. For example, the generation unit inputs the analysis results into the generation AI to generate the feedback content. The generation AI provides advice on improving the clarity of speech and advice on maintaining a logical structure based on the analysis results. In this way, specific improvements and merits can be provided by generating feedback content using the generation AI.

[0032] The online meeting evaluation system includes a display unit that visually displays the progress of improvement. The display unit visually displays the progress of improvement. For example, the display unit references the user's past feedback history and displays the progress of improvement as a graph or chart. The display unit visually displays the progress of improvement using a generation AI. For example, the display unit inputs the user's feedback history into the generation AI and analyzes the progress of improvement. The generation AI evaluates the growth of the user's communication skills based on the feedback history and visually displays it. In this way, the progress of improvement is visually displayed, allowing the user to confirm their own growth.

[0033] The analysis unit can evaluate the clarity of the statement, its logical structure, and timing. For example, the analysis unit evaluates the clarity of the statement. The analysis unit uses the generation AI to evaluate the clarity of the statement. The generation AI analyzes the audio data and evaluates the accuracy of pronunciation and the clarity of the voice. The analysis unit also evaluates the logical structure of the statement. The generation AI analyzes the audio data and evaluates the logical consistency of the statement and the clarity of the points being made. Furthermore, the analysis unit evaluates the timing of the statement. The generation AI analyzes the audio data and evaluates the appropriate spacing and timing of the statement. This makes it possible to provide detailed feedback by evaluating the clarity of the statement, its logical structure, and the appropriate timing of the statement.

[0034] The providing unit can provide feedback on specific areas for improvement and meritorious points. For example, the providing unit provides feedback on specific areas for improvement and meritorious points based on the analysis results. The providing unit uses the generation AI to generate the content of the feedback. For example, the providing unit inputs the analysis results into the generation AI to generate the content of the feedback. The generation AI provides advice on improving the clarity of speech and advice on maintaining a logical structure based on the analysis results. In this way, by providing feedback on specific areas for improvement and meritorious points, the improvement of the user's communication skills is supported.

[0035] The collection unit can dynamically change the scope of data to be collected depending on the type and purpose of the meeting. For example, in a brainstorming meeting, the collection unit collects all comments. The collection unit uses the generation AI to determine the type and purpose of the meeting. The generation AI analyzes the content and agenda of the meeting to determine the type and purpose of the meeting. For example, the collection unit inputs the content of the meeting into the generation AI and determines the type and purpose of the meeting. The generation AI analyzes the content of the meeting and determines that it is a brainstorming meeting. Furthermore, in a project progress meeting, the collection unit prioritizes collecting comments related to important decisions and action items. The collection unit uses the generation AI to analyze the content of the meeting and identify important comments. For example, the collection unit inputs the content of the meeting into the generation AI and identifies important comments. The generation AI analyzes the content of the meeting and identifies comments related to important decisions and action items. Furthermore, in regular meetings, the collection unit sets the scope of data to be collected for each agenda item and collects only the necessary parts. The collection unit uses the generation AI to analyze the agenda of the meeting and set the scope of data to be collected. For example, the collection unit inputs the meeting agenda into the generation AI and sets the range of data to be collected. The generation AI then analyzes the meeting agenda and collects only the necessary parts. This allows the necessary data to be collected efficiently by dynamically changing the range of data depending on the type and purpose of the meeting.

[0036] The collection unit can analyze the speaker's voice characteristics and perform filtering to record with optimal sound quality. For example, if the speaker's voice is quiet, the collection unit performs noise reduction to make the voice clear. The collection unit uses the generation AI to analyze the speaker's voice characteristics. The generation AI analyzes the voice data and evaluates the speaker's voice characteristics. For example, the collection unit inputs the voice data into the generation AI and analyzes the speaker's voice characteristics. The generation AI analyzes the voice data and evaluates the volume of the speaker's voice. Furthermore, if the speaker's voice is high-pitched, the collection unit performs echo cancellation to improve the sound quality. The collection unit uses the generation AI to analyze the speaker's voice characteristics. The generation AI analyzes the voice data and evaluates the speaker's voice characteristics. For example, the collection unit inputs the voice data into the generation AI and analyzes the speaker's voice characteristics. The generation AI analyzes the voice data and evaluates the pitch of the speaker's voice. Furthermore, if the speaker's voice is low-pitched, the collection unit removes low-frequency noise to make the voice clear. The collection unit uses the generation AI to analyze the speaker's voice characteristics. The generation AI analyzes the voice data and evaluates the speaker's voice characteristics. For example, the collection unit inputs voice data into the generation AI and analyzes the speaker's voice characteristics. The generation AI analyzes the voice data and evaluates the lowness of the speaker's voice. This improves the quality of the recorded data by analyzing the speaker's voice characteristics and recording with optimal sound quality.

[0037] The collection unit can adjust the scope of data to be collected taking into account the geographic location information of meeting participants. For example, if participants are in different time zones, the collection unit prioritizes collection of important statements. The collection unit uses the generation AI to analyze the participants' geographic location information. The generation AI analyzes the participants' location data and determines their time zones. For example, the collection unit inputs location data into the generation AI and determines the participants' time zones. The generation AI analyzes the location data and determines that participants are in different time zones. Furthermore, if participants are in the same office, the collection unit collects all statements equally. The collection unit uses the generation AI to analyze the participants' geographic location information. The generation AI analyzes the participants' location data and determines that they are in the same office. For example, the collection unit inputs location data into the generation AI and determines the participants' locations. The generation AI analyzes the location data and determines that participants are in the same office. Furthermore, if participants are participating remotely, the collection unit adjusts the scope of data to be collected taking into account audio quality. The collection unit uses the generation AI to analyze the participants' geographic location information. The generation AI analyzes the location information data of participants and determines whether they are participating remotely. For example, the collection unit inputs location information data into the generation AI and determines the location of the participants. The generation AI analyzes the location information data and determines whether the participant is participating remotely. This enables appropriate data collection by taking into account the geographic location information of meeting participants.

[0038] The collection unit can prioritize collecting utterances containing specific keywords based on the content of the meeting. For example, the collection unit prioritizes collecting utterances containing keywords related to the meeting agenda. The collection unit uses the generation AI to analyze the content of the meeting and extract specific keywords. The generation AI analyzes the content of the meeting and identifies important keywords. For example, the collection unit inputs the content of the meeting into the generation AI and extracts specific keywords. The generation AI analyzes the content of the meeting and identifies keywords related to the agenda. Furthermore, the collection unit prioritizes collecting utterances containing keywords related to important decisions. The collection unit uses the generation AI to analyze the content of the meeting and extracts important keywords. The generation AI analyzes the content of the meeting and identifies keywords related to the important decisions. For example, the collection unit inputs the content of the meeting into the generation AI and extracts specific keywords. The generation AI analyzes the content of the meeting and identifies keywords related to the important decisions. Furthermore, the collection unit prioritizes collecting utterances containing keywords related to action items. The collection unit uses the generation AI to analyze the content of the meeting and extracts important keywords. The generation AI analyzes the content of the meeting and identifies keywords related to action items. For example, the collection unit inputs the content of the meeting into the generation AI and extracts specific keywords. The generation AI analyzes the content of the meeting and identifies keywords related to action items. This allows important information to be collected efficiently by preferentially collecting comments containing specific keywords based on the content of the meeting.

[0039] The analysis unit can apply different analysis methods based on the content of the utterance to perform a detailed evaluation. For example, the analysis unit uses speech recognition technology to evaluate the clarity of the utterance. The analysis unit uses a generation AI to analyze the content of the utterance. The generation AI analyzes the audio data to evaluate the clarity of the utterance. For example, the analysis unit inputs audio data into the generation AI and evaluates the clarity of the utterance. The generation AI analyzes the audio data to evaluate the accuracy of pronunciation and the clarity of the voice. The analysis unit also uses natural language processing technology to evaluate the logical structure of the utterance. The analysis unit uses a generation AI to analyze the content of the utterance. The generation AI analyzes the audio data to evaluate the logical consistency of the utterance and the clarity of the argument. For example, the analysis unit inputs audio data into the generation AI and evaluates the logical structure of the utterance. The generation AI analyzes the audio data to evaluate the logical consistency of the utterance and the clarity of the argument. Furthermore, the analysis unit analyzes the flow of the conversation to evaluate the appropriate timing of the utterance. The analysis unit uses a generation AI to analyze the content of the utterance. The generation AI analyzes the voice data and evaluates the timing of the speech. For example, the analysis unit inputs the voice data into the generation AI and evaluates the timing of the speech. The generation AI analyzes the voice data and evaluates the appropriate spacing and timing of the speech. This allows for a detailed evaluation by applying different analysis methods based on the content of the speech.

[0040] The analysis unit can update the analysis results in real time according to the progress of the meeting. For example, if an important comment is made during the meeting, the analysis unit updates the analysis results in real time. The analysis unit uses the generation AI to analyze the progress of the meeting. The generation AI analyzes the audio data and video data of the meeting to understand the progress of the meeting. For example, the analysis unit inputs the audio data of the meeting into the generation AI and analyzes the progress of the meeting. The generation AI analyzes the audio data and identifies important comments. The analysis unit also dynamically adjusts the evaluation criteria for comments as the meeting progresses. The analysis unit uses the generation AI to analyze the progress of the meeting. The generation AI analyzes the audio data and video data of the meeting to understand the progress of the meeting. For example, the analysis unit inputs the audio data of the meeting into the generation AI and analyzes the progress of the meeting. The generation AI analyzes the audio data and dynamically adjusts the evaluation criteria for comments. Furthermore, at the end of the meeting, the analysis unit comprehensively evaluates all comments and provides a final analysis result. The analysis unit uses the generation AI to analyze the progress of the meeting. The generation AI analyzes the audio and video data of the meeting to understand the progress of the meeting. For example, the analysis unit inputs the audio data of the meeting into the generation AI and analyzes the progress of the meeting. The generation AI analyzes the audio data and comprehensively evaluates all comments. This allows the analysis results to be updated in real time according to the progress of the meeting, making it possible to provide the latest information.

[0041] The analysis unit can improve the accuracy of the analysis results by referring to the speaker's past utterance history. The analysis unit, for example, analyzes utterance patterns based on the speaker's past utterance history. The analysis unit uses the generation AI to analyze the speaker's past utterance history. The generation AI analyzes the past utterance data and identifies utterance patterns. For example, the analysis unit inputs past utterance data into the generation AI and analyzes utterance patterns. The generation AI analyzes the past utterance data and identifies utterance patterns. The analysis unit also identifies areas for improvement in the utterances from the speaker's past utterance history. The analysis unit uses the generation AI to analyze the speaker's past utterance history. The generation AI analyzes the past utterance data and identifies areas for improvement in the utterances. For example, the analysis unit inputs past utterance data into the generation AI and identifies areas for improvement in the utterances. The generation AI analyzes the past utterance data and identifies areas for improvement in the utterances. Furthermore, the analysis unit refers to the speaker's past utterance history to adjust the evaluation criteria for the utterances. The analysis unit uses the generation AI to analyze the speaker's past utterance history. The generation AI analyzes past utterance data and adjusts the evaluation criteria for utterances. For example, the analysis unit inputs past utterance data into the generation AI and adjusts the evaluation criteria for utterances. The generation AI analyzes past utterance data and adjusts the evaluation criteria for utterances. This improves the accuracy of the analysis results by referencing the speaker's past utterance history.

[0042] The analysis unit can emphasize specific evaluation criteria based on the theme of the meeting. For example, if the theme of the meeting is project management, the analysis unit emphasizes clarity of progress reports. The analysis unit uses the generation AI to analyze the theme of the meeting. The generation AI analyzes the content of the meeting and identifies the theme. For example, the analysis unit inputs the content of the meeting into the generation AI and identifies the theme. The generation AI analyzes the content of the meeting and identifies that the theme is project management. Furthermore, if the theme of the meeting is brainstorming, the analysis unit emphasizes creativity and the proposal of new ideas. The analysis unit uses the generation AI to analyze the theme of the meeting. The generation AI analyzes the content of the meeting and identifies the theme. For example, the analysis unit inputs the content of the meeting into the generation AI and identifies the theme. The generation AI analyzes the content of the meeting and identifies that the theme is brainstorming. Furthermore, if the theme of the meeting is problem solving, the analysis unit emphasizes logical structure and the proposal of solutions. The analysis unit uses the generation AI to analyze the theme of the meeting. The generation AI analyzes the content of the meeting and identifies the theme. For example, the analysis unit inputs the content of the meeting into the generation AI and identifies the theme. The generation AI analyzes the content of the meeting and identifies that the theme is problem-solving. This enables appropriate evaluation by emphasizing specific evaluation criteria based on the theme of the meeting.

[0043] The provision department can customize the content of the feedback depending on the speaker's position and experience. For example, the provision department provides new employees with feedback regarding basic communication skills. The provision department uses the generation AI to analyze the speaker's position and experience. The generation AI analyzes the speaker's position and experience data and generates appropriate feedback. For example, the provision department inputs the speaker's position and experience data into the generation AI to generate feedback content. The generation AI analyzes the speaker's position and experience and generates feedback suitable for new employees. Furthermore, the provision department provides mid-level employees with feedback regarding leadership and teamwork. The provision department uses the generation AI to analyze the speaker's position and experience. The generation AI analyzes the speaker's position and experience data and generates appropriate feedback. For example, the provision department inputs the speaker's position and experience data into the generation AI to generate feedback content. The generation AI analyzes the speaker's position and experience and generates feedback suitable for mid-level employees. Furthermore, the provision department provides managers with feedback regarding strategic thinking and decision-making. The provision unit uses the generation AI to analyze the speaker's job title and experience. The generation AI analyzes the speaker's job title and experience data and generates appropriate feedback. For example, the provision unit inputs the speaker's job title and experience data into the generation AI and generates feedback content. The generation AI analyzes the speaker's job title and experience and generates feedback suitable for a managerial position. This makes it possible to provide appropriate feedback according to the speaker's job title and experience.

[0044] The providing unit can dynamically change the timing of providing feedback depending on the progress of the meeting. For example, the providing unit provides feedback immediately after the end of the meeting. The providing unit uses the generation AI to analyze the progress of the meeting. The generation AI analyzes audio data and video data of the meeting to understand the progress of the meeting. For example, the providing unit inputs the audio data of the meeting into the generation AI and analyzes the progress of the meeting. The generation AI analyzes the audio data and identifies the end of the meeting. Furthermore, the providing unit provides feedback immediately after an important statement is made during the meeting. The providing unit uses the generation AI to analyze the progress of the meeting. The generation AI analyzes the audio data and video data of the meeting to understand the progress of the meeting. For example, the providing unit inputs the audio data of the meeting into the generation AI and analyzes the progress of the meeting. The generation AI analyzes the audio data and identifies important statements. Furthermore, the providing unit provides feedback at appropriate timing as the meeting progresses. The providing unit uses the generation AI to analyze the progress of the meeting. The generation AI analyzes the audio and video data of the meeting to understand the progress of the meeting. For example, the providing unit inputs the audio data of the meeting into the generation AI and analyzes the progress of the meeting. The generation AI analyzes the audio data and provides feedback at the appropriate time. This allows feedback to be provided at the appropriate time depending on the progress of the meeting.

[0045] The providing unit can provide the feedback by comparing the content of the feedback with the speaker's past feedback history. For example, the providing unit identifies areas for improvement based on the speaker's past feedback history. The providing unit uses the generation AI to analyze the speaker's past feedback history. The generation AI analyzes the past feedback data and identifies areas for improvement. For example, the providing unit inputs past feedback data into the generation AI and identifies areas for improvement. The generation AI analyzes the past feedback data and identifies areas for improvement. The providing unit also highlights good points from the speaker's past feedback history. The providing unit uses the generation AI to analyze the speaker's past feedback history. The generation AI analyzes the past feedback data and identifies good points. For example, the providing unit inputs past feedback data into the generation AI and identifies good points. The generation AI analyzes the past feedback data and identifies good points. Furthermore, the providing unit refers to the speaker's past feedback history to provide specific areas for improvement. The providing unit uses the generation AI to analyze the speaker's past feedback history. The generation AI analyzes the past feedback data and identifies specific areas for improvement. For example, the providing unit inputs past feedback data into the generating AI and identifies specific areas for improvement. The generating AI then analyzes the past feedback data and identifies specific areas for improvement. This allows the AI ​​to provide specific areas for improvement by comparing the feedback data with the speaker's past feedback history.

[0046] The providing department can emphasize specific points in the feedback content based on the theme of the meeting. For example, if the theme of the meeting is project management, the providing department emphasizes clarity of the progress report. The providing department uses the generating AI to analyze the theme of the meeting. The generating AI analyzes the content of the meeting and identifies the theme. For example, the providing department inputs the content of the meeting into the generating AI and identifies the theme. The generating AI analyzes the content of the meeting and identifies that the theme is project management. Furthermore, if the theme of the meeting is brainstorming, the providing department emphasizes creativity and the proposal of new ideas. The providing department uses the generating AI to analyze the theme of the meeting. The generating AI analyzes the content of the meeting and identifies the theme. For example, the providing department inputs the content of the meeting into the generating AI and identifies the theme. The generating AI analyzes the content of the meeting and identifies that the theme is brainstorming. Furthermore, if the theme of the meeting is problem solving, the providing department emphasizes logical structure and the proposal of solutions. The providing department uses the generating AI to analyze the theme of the meeting. The generation AI analyzes the content of the meeting and identifies the theme. For example, the provider inputs the content of the meeting into the generation AI and identifies the theme. The generation AI analyzes the content of the meeting and identifies that the theme is problem solving. This allows appropriate feedback to be provided by emphasizing specific points based on the theme of the meeting.

[0047] The tracking unit can evaluate the progress of improvement using different indicators depending on the speaker's position and experience. For example, the tracking unit provides new employees with indicators that evaluate the improvement of basic communication skills. The tracking unit uses the generation AI to analyze the speaker's position and experience. The generation AI analyzes the speaker's position and experience data and generates appropriate evaluation indicators. For example, the tracking unit inputs the speaker's position and experience data into the generation AI and generates evaluation indicators. The generation AI analyzes the speaker's position and experience and generates evaluation indicators that are suitable for new employees. Furthermore, the tracking unit provides mid-level employees with indicators that evaluate the improvement of leadership and teamwork. The tracking unit uses the generation AI to analyze the speaker's position and experience. The generation AI analyzes the speaker's position and experience data and generates appropriate evaluation indicators. For example, the tracking unit inputs the speaker's position and experience data into the generation AI and generates evaluation indicators. The generation AI analyzes the speaker's position and experience and generates evaluation indicators that are suitable for mid-level employees. Furthermore, the tracking unit provides managers with indicators to evaluate improvements in strategic thinking and decision-making. The tracking unit uses the generation AI to analyze the speaker's position and experience. The generation AI analyzes the speaker's position and experience data and generates appropriate evaluation indicators. For example, the tracking unit inputs the speaker's position and experience data into the generation AI to generate evaluation indicators. The generation AI analyzes the speaker's position and experience and generates evaluation indicators suitable for managers. This makes it possible to evaluate the progress of improvement using indicators appropriate for the speaker's position and experience.

[0048] The tracking unit can analyze the progress of improvement from different perspectives depending on the type and purpose of the meeting. For example, in a brainstorming meeting, the tracking unit evaluates improvements in creativity and the proposal of new ideas. The tracking unit uses the generation AI to analyze the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies the type and purpose of the meeting. For example, the tracking unit inputs the content of the meeting into the generation AI and identifies the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies that it is a brainstorming meeting. In addition, in a project progress meeting, the tracking unit evaluates the clarity of the progress report and the degree to which action items are implemented. The tracking unit uses the generation AI to analyze the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies the type and purpose of the meeting. For example, the tracking unit inputs the content of the meeting into the generation AI and identifies the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies that it is a project progress meeting. In addition, in a regular meeting, the tracking unit evaluates the quality and timing of comments for each agenda item. The tracking unit uses the generation AI to analyze the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies the type and purpose of the meeting. For example, the tracking unit inputs the content of the meeting into the generation AI and identifies the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies that it is a regular meeting. This makes it possible to analyze the progress of improvement from an appropriate perspective according to the type and purpose of the meeting.

[0049] The tracking unit can evaluate the progress of improvement by comparing it with the speaker's past speech history. For example, the tracking unit identifies areas for improvement based on the speaker's past speech history. The tracking unit uses the generation AI to analyze the speaker's past speech history. The generation AI analyzes the past speech data and identifies areas for improvement. For example, the tracking unit inputs past speech data into the generation AI and identifies areas for improvement. The generation AI analyzes the past speech data and identifies areas for improvement. The tracking unit also highlights good points from the speaker's past speech history. The tracking unit uses the generation AI to analyze the speaker's past speech history. The generation AI analyzes the past speech data and identifies good points. For example, the tracking unit inputs past speech data into the generation AI and identifies good points. The generation AI analyzes the past speech data and identifies good points. The tracking unit also provides specific areas for improvement by referring to the speaker's past speech history. The tracking unit uses the generation AI to analyze the speaker's past speech history. The generation AI analyzes the past speech data and identifies specific areas for improvement. For example, the tracking unit inputs past speech data into the generation AI and identifies specific areas for improvement. The generation AI then analyzes the past speech data and identifies specific areas for improvement. This allows the AI ​​to provide specific areas for improvement by comparing the data with the speaker's past speech history.

[0050] The tracking unit can emphasize specific indicators of improvement progress based on the theme of the meeting. For example, if the theme of the meeting is project management, the tracking unit emphasizes clarity of the progress report. The tracking unit uses the generation AI to analyze the theme of the meeting. The generation AI analyzes the content of the meeting and identifies the theme. For example, the tracking unit inputs the content of the meeting into the generation AI and identifies the theme. The generation AI analyzes the content of the meeting and identifies that the theme is project management. Furthermore, if the theme of the meeting is brainstorming, the tracking unit emphasizes creativity and the proposal of new ideas. The tracking unit uses the generation AI to analyze the theme of the meeting. The generation AI analyzes the content of the meeting and identifies the theme. For example, the tracking unit inputs the content of the meeting into the generation AI and identifies the theme. The generation AI analyzes the content of the meeting and identifies that the theme is brainstorming. Furthermore, if the theme of the meeting is problem solving, the tracking unit emphasizes logical structure and the proposal of solutions. The tracking unit uses the generation AI to analyze the theme of the meeting. The generation AI analyzes the content of the meeting and identifies the theme. For example, the tracking unit inputs the content of the meeting into the generation AI and identifies the theme. The generation AI analyzes the content of the meeting and identifies that the theme is problem solving. This enables appropriate evaluation by emphasizing specific indicators based on the theme of the meeting.

[0051] The setting unit can customize the evaluation criteria according to the type and purpose of the meeting. For example, for a brainstorming meeting, the setting unit sets evaluation criteria that emphasize creativity and the proposal of new ideas. The setting unit uses the generation AI to analyze the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies the type and purpose of the meeting. For example, the setting unit inputs the content of the meeting into the generation AI and identifies the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies that it is a brainstorming meeting. Furthermore, for a project progress meeting, the setting unit sets evaluation criteria that emphasize the clarity of the progress report and the degree to which action items are implemented. The setting unit uses the generation AI to analyze the type and purpose of the meeting. The generation AI analyzes the content of the meeting. For example, the setting unit inputs the content of the meeting into the generation AI and identifies the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies that it is a project progress meeting. Furthermore, for regular meetings, the setting unit sets evaluation criteria that emphasize the quality and timing of comments for each agenda item. The setting unit uses the generation AI to analyze the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies the type and purpose of the meeting. For example, the setting unit inputs the content of the meeting into the generation AI and identifies the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies that it is a regular meeting. This makes it possible to set appropriate evaluation criteria according to the type and purpose of the meeting.

[0052] The setting unit can set different evaluation criteria depending on the speaker's position and experience. For example, for new employees, the setting unit sets evaluation criteria that emphasize basic communication skills. The setting unit uses the generation AI to analyze the speaker's position and experience. The generation AI analyzes the speaker's position and experience data and generates appropriate evaluation criteria. For example, the setting unit inputs the speaker's position and experience data into the generation AI and generates evaluation criteria. The generation AI analyzes the speaker's position and experience and generates evaluation criteria that are suitable for new employees. Furthermore, the setting unit sets evaluation criteria that emphasize leadership and teamwork for mid-level employees. The setting unit uses the generation AI to analyze the speaker's position and experience. The generation AI analyzes the speaker's position and experience data and generates appropriate evaluation criteria. For example, the setting unit inputs the speaker's position and experience data into the generation AI and generates evaluation criteria. The generation AI analyzes the speaker's position and experience and generates evaluation criteria that are suitable for mid-level employees. Furthermore, for managerial positions, the setting unit sets evaluation criteria that emphasize strategic thinking and decision-making. The setting unit uses the generation AI to analyze the speaker's job title and experience. The generation AI analyzes the speaker's job title and experience data and generates appropriate evaluation criteria. For example, the setting unit inputs the speaker's job title and experience data into the generation AI to generate evaluation criteria. The generation AI analyzes the speaker's job title and experience and generates evaluation criteria suitable for managerial positions. This makes it possible to set appropriate evaluation criteria according to the speaker's job title and experience.

[0053] The setting unit can set the evaluation criteria by comparing them with the speaker's past utterance history. For example, the setting unit sets the evaluation criteria based on the speaker's past utterance history. The setting unit uses the generation AI to analyze the speaker's past utterance history. The generation AI analyzes the past utterance data and identifies the evaluation criteria. For example, the setting unit inputs past utterance data into the generation AI and identifies the evaluation criteria. The generation AI analyzes the past utterance data and identifies the evaluation criteria. Furthermore, the setting unit sets evaluation criteria that emphasize good points from the speaker's past utterance history. The setting unit uses the generation AI to analyze the speaker's past utterance history. The generation AI analyzes the past utterance data and identifies good points. For example, the setting unit inputs past utterance data into the generation AI and identifies good points. The generation AI analyzes the past utterance data and identifies good points. Furthermore, the setting unit sets specific evaluation criteria by referring to the speaker's past utterance history. The setting unit uses the generation AI to analyze the speaker's past utterance history. The generation AI analyzes the past utterance data and identifies good points. For example, the setting unit inputs past utterance data into the generation AI and identifies specific evaluation criteria. The generation AI analyzes the past utterance data and identifies specific evaluation criteria. This allows the specific evaluation criteria to be set by comparing them with the speaker's past utterance history.

[0054] The generation unit can customize the content of the feedback depending on the speaker's position and experience. For example, the generation unit provides new employees with feedback regarding basic communication skills. The generation unit uses a generation AI to analyze the speaker's position and experience. The generation AI analyzes the speaker's position and experience data and generates appropriate feedback. For example, the generation unit inputs the speaker's position and experience data into the generation AI to generate feedback content. The generation AI analyzes the speaker's position and experience and generates feedback suitable for new employees. The generation unit also provides mid-level employees with feedback regarding leadership and teamwork. The generation unit uses a generation AI to analyze the speaker's position and experience. The generation AI analyzes the speaker's position and experience data and generates appropriate feedback. For example, the generation unit inputs the speaker's position and experience data into the generation AI to generate feedback content. The generation AI analyzes the speaker's position and experience and generates feedback suitable for mid-level employees. Furthermore, the generation unit provides managers with feedback regarding strategic thinking and decision-making. The generation unit uses the generation AI to analyze the speaker's job title and experience. The generation AI analyzes the speaker's job title and experience data and generates appropriate feedback. For example, the generation unit inputs the speaker's job title and experience data into the generation AI and generates feedback content. The generation AI analyzes the speaker's job title and experience and generates feedback suitable for a managerial position. This makes it possible to provide appropriate feedback according to the speaker's job title and experience.

[0055] The generation unit can generate the feedback content from different perspectives depending on the type and purpose of the meeting. For example, in a brainstorming meeting, the generation unit provides feedback regarding creativity and the proposal of new ideas. The generation unit uses the generation AI to analyze the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies the type and purpose of the meeting. For example, the generation unit inputs the content of the meeting into the generation AI and identifies the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies that it is a brainstorming meeting. Furthermore, in a project progress meeting, the generation unit provides feedback regarding the clarity of the progress report and the degree to which action items have been implemented. The generation unit uses the generation AI to analyze the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies the type and purpose of the meeting. For example, the generation unit inputs the content of the meeting into the generation AI and identifies the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies that it is a project progress meeting. Furthermore, in regular meetings, the generation unit provides feedback regarding the quality and timing of comments for each agenda item. The generation unit uses the generation AI to analyze the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies the type and purpose of the meeting. For example, the generation unit inputs the content of the meeting into the generation AI and identifies the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies that it is a regular meeting. This makes it possible to provide appropriate feedback according to the type and purpose of the meeting.

[0056] The generation unit can generate the feedback by comparing the content with the speaker's past speech history. For example, the generation unit identifies areas for improvement based on the speaker's past speech history. The generation unit uses a generation AI to analyze the speaker's past speech history. The generation AI analyzes the past speech data and identifies areas for improvement. For example, the generation unit inputs past speech data into the generation AI and identifies areas for improvement. The generation AI analyzes the past speech data and identifies areas for improvement. The generation unit also highlights good points from the speaker's past speech history. The generation unit uses a generation AI to analyze the speaker's past speech history. The generation AI analyzes the past speech data and identifies good points. For example, the generation unit inputs past speech data into the generation AI and identifies good points. The generation AI analyzes the past speech data and identifies good points. The generation unit also refers to the speaker's past speech history to provide specific areas for improvement. The generation unit uses a generation AI to analyze the speaker's past speech history. The generation AI analyzes the past speech data and identifies specific areas for improvement. For example, the generation unit inputs past utterance data into the generation AI and identifies specific areas for improvement. The generation AI then analyzes the past utterance data and identifies specific areas for improvement. This allows the AI ​​to provide specific areas for improvement by comparing the data with the speaker's past utterance history.

[0057] The display unit can customize the display content according to the speaker's position and experience. For example, the display unit provides new employees with display content related to basic communication skills. The display unit uses a generation AI to analyze the speaker's position and experience. The generation AI analyzes the speaker's position and experience data and generates appropriate display content. For example, the display unit inputs the speaker's position and experience data into the generation AI and generates display content. The generation AI analyzes the speaker's position and experience and generates display content suitable for new employees. Furthermore, the display unit provides mid-level employees with display content related to leadership and teamwork. The display unit uses a generation AI to analyze the speaker's position and experience. The generation AI analyzes the speaker's position and experience data and generates appropriate display content. For example, the display unit inputs the speaker's position and experience data into the generation AI and generates display content. The generation AI analyzes the speaker's position and experience and generates display content suitable for mid-level employees. Furthermore, the display unit provides managers with display content related to strategic thinking and decision-making. The display unit uses the generation AI to analyze the speaker's job title and experience. The generation AI analyzes the speaker's job title and experience data and generates appropriate display content. For example, the display unit inputs the speaker's job title and experience data into the generation AI and generates display content. The generation AI analyzes the speaker's job title and experience and generates display content suitable for a managerial position. This makes it possible to provide appropriate display content according to the speaker's job title and experience.

[0058] The display unit can display the display content from different perspectives depending on the type and purpose of the meeting. For example, in a brainstorming meeting, the display unit provides display content related to creativity and the proposal of new ideas. The display unit uses a generation AI to analyze the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies the type and purpose of the meeting. For example, the display unit inputs the content of the meeting into the generation AI and identifies the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies that it is a brainstorming meeting. Furthermore, in a project progress meeting, the display unit provides display content related to the clarity of the progress report and the degree of execution of action items. The display unit uses a generation AI to analyze the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies the type and purpose of the meeting. For example, the display unit inputs the content of the meeting into the generation AI and identifies the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies that it is a project progress meeting. Furthermore, in a regular meeting, the display unit provides display content related to the quality and timing of comments for each agenda item. The display unit uses the generation AI to analyze the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies the type and purpose of the meeting. For example, the display unit inputs the content of the meeting into the generation AI and identifies the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies that it is a regular meeting. This makes it possible to provide appropriate display content according to the type and purpose of the meeting.

[0059] The display unit can compare the display content with the speaker's past speech history and display it. The display unit, for example, identifies areas for improvement based on the speaker's past speech history. The display unit uses a generation AI to analyze the speaker's past speech history. The generation AI analyzes the past speech data and identifies areas for improvement. For example, the display unit inputs past speech data into the generation AI and identifies areas for improvement. The generation AI analyzes the past speech data and identifies areas for improvement. The display unit also highlights good points from the speaker's past speech history. The display unit uses a generation AI to analyze the speaker's past speech history. The generation AI analyzes the past speech data and identifies good points. For example, the display unit inputs past speech data into the generation AI and identifies good points. The generation AI analyzes the past speech data and identifies good points. The display unit also displays specific areas for improvement by referring to the speaker's past speech history. The display unit uses a generation AI to analyze the speaker's past speech history. The generation AI analyzes the past speech data and identifies specific areas for improvement. For example, the display unit inputs past speech data into the generation AI and identifies specific areas for improvement. The generation AI then analyzes the past speech data and identifies specific areas for improvement. This allows the specific areas for improvement to be displayed by comparing them with the speaker's past speech history.

[0060] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0061] The analysis unit can update the analysis results in real time according to the progress of the meeting. For example, if an important comment is made during the meeting, the analysis results are updated in real time. The analysis unit uses the generation AI to analyze the progress of the meeting. The generation AI analyzes the audio data and video data of the meeting to understand the progress of the meeting. For example, the analysis unit inputs the audio data of the meeting into the generation AI and analyzes the progress of the meeting. The generation AI analyzes the audio data and identifies important comments. The analysis unit also dynamically adjusts the evaluation criteria for comments as the meeting progresses. The analysis unit uses the generation AI to analyze the progress of the meeting. The generation AI analyzes the audio data and video data of the meeting to understand the progress of the meeting. For example, the analysis unit inputs the audio data of the meeting into the generation AI and analyzes the progress of the meeting. The generation AI analyzes the audio data and dynamically adjusts the evaluation criteria for comments. Furthermore, at the end of the meeting, the analysis unit comprehensively evaluates all comments and provides a final analysis result. The analysis unit uses the generation AI to analyze the progress of the meeting. The generation AI analyzes the audio and video data of the meeting to understand the progress of the meeting. For example, the analysis unit inputs the audio data of the meeting into the generation AI and analyzes the progress of the meeting. The generation AI analyzes the audio data and comprehensively evaluates all comments. This allows the analysis results to be updated in real time according to the progress of the meeting, making it possible to provide the latest information.

[0062] The feedback delivery department can customize the content of the feedback depending on the speaker's position and experience. For example, the feedback delivery department provides new employees with feedback regarding basic communication skills. The feedback delivery department uses a generation AI to analyze the speaker's position and experience. The generation AI analyzes the speaker's position and experience data and generates appropriate feedback. For example, the feedback delivery department inputs the speaker's position and experience data into the generation AI to generate feedback content. The generation AI analyzes the speaker's position and experience and generates feedback appropriate for new employees. The feedback delivery department also provides mid-level employees with feedback regarding leadership and teamwork. The feedback delivery department uses a generation AI to analyze the speaker's position and experience. The generation AI analyzes the speaker's position and experience data and generates appropriate feedback. For example, the feedback delivery department inputs the speaker's position and experience data into the generation AI to generate feedback content. The generation AI analyzes the speaker's position and experience and generates feedback appropriate for mid-level employees. The feedback delivery department also provides managers with feedback regarding strategic thinking and decision-making. The provision unit uses the generation AI to analyze the speaker's job title and experience. The generation AI analyzes the speaker's job title and experience data and generates appropriate feedback. For example, the provision unit inputs the speaker's job title and experience data into the generation AI and generates feedback content. The generation AI analyzes the speaker's job title and experience and generates feedback suitable for a managerial position. This makes it possible to provide appropriate feedback according to the speaker's job title and experience.

[0063] The collection unit can dynamically change the scope of data to be collected depending on the type and purpose of the meeting. For example, in a brainstorming meeting, the collection unit collects all comments. The collection unit uses the generation AI to determine the type and purpose of the meeting. The generation AI analyzes the content and agenda of the meeting to determine the type and purpose of the meeting. For example, the collection unit inputs the content of the meeting into the generation AI and determines the type and purpose of the meeting. The generation AI analyzes the content of the meeting and determines that it is a brainstorming meeting. In addition, in a project progress meeting, the collection unit prioritizes collecting comments related to important decisions and action items. The collection unit uses the generation AI to analyze the content of the meeting and identify important comments. For example, the collection unit inputs the content of the meeting into the generation AI and identifies important comments. The generation AI analyzes the content of the meeting and identifies comments related to important decisions and action items. In addition, in regular meetings, the collection unit sets the scope of data to be collected for each agenda item and collects only the necessary parts. The collection unit uses the generation AI to analyze the agenda of the meeting and set the scope of data to be collected. For example, the collection unit inputs the meeting agenda into the generation AI and sets the range of data to be collected. The generation AI then analyzes the meeting agenda and collects only the necessary parts. This allows the necessary data to be collected efficiently by dynamically changing the range of data depending on the type and purpose of the meeting.

[0064] The analysis unit can apply different analysis methods based on the content of the utterance to perform a detailed evaluation. For example, the analysis unit uses voice recognition technology to evaluate the clarity of the utterance. The analysis unit uses a generation AI to analyze the content of the utterance. The generation AI analyzes the audio data and evaluates the clarity of the utterance. For example, the analysis unit inputs audio data into the generation AI and evaluates the clarity of the utterance. The generation AI analyzes the audio data and evaluates the accuracy of pronunciation and the clarity of the voice. The analysis unit also uses natural language processing technology to evaluate the logical structure of the utterance. The analysis unit uses a generation AI to analyze the content of the utterance. The generation AI analyzes the audio data and evaluates the logical consistency of the utterance and the clarity of the argument. For example, the analysis unit inputs audio data into the generation AI and evaluates the logical structure of the utterance. The generation AI analyzes the audio data and evaluates the logical consistency of the utterance and the clarity of the argument. Furthermore, the analysis unit analyzes the flow of the conversation to evaluate the appropriate timing of the utterance. The analysis unit uses a generation AI to analyze the content of the utterance. The generation AI analyzes the voice data and evaluates the timing of the speech. For example, the analysis unit inputs the voice data into the generation AI and evaluates the timing of the speech. The generation AI analyzes the voice data and evaluates the appropriate spacing and timing of the speech. This allows for a detailed evaluation by applying different analysis methods based on the content of the speech.

[0065] The providing unit can dynamically change the timing of providing feedback depending on the progress of the meeting. For example, the providing unit provides feedback immediately after the end of the meeting. The providing unit uses the generation AI to analyze the progress of the meeting. The generation AI analyzes the audio data and video data of the meeting to understand the progress of the meeting. For example, the providing unit inputs the audio data of the meeting into the generation AI and analyzes the progress of the meeting. The generation AI analyzes the audio data and identifies the end of the meeting. Furthermore, the providing unit provides feedback immediately after an important comment is made during the meeting. The providing unit uses the generation AI to analyze the progress of the meeting. The generation AI analyzes the audio data and video data of the meeting to understand the progress of the meeting. For example, the providing unit inputs the audio data of the meeting into the generation AI and analyzes the progress of the meeting. The generation AI analyzes the audio data and identifies important comments. Furthermore, the providing unit provides feedback at appropriate times as the meeting progresses. The providing unit uses the generation AI to analyze the progress of the meeting. The generation AI analyzes the audio and video data of the meeting to understand the progress of the meeting. For example, the providing unit inputs the audio data of the meeting into the generation AI and analyzes the progress of the meeting. The generation AI analyzes the audio data and provides feedback at the appropriate time. This allows feedback to be provided at the appropriate time depending on the progress of the meeting.

[0066] The analysis unit can emphasize specific evaluation criteria based on the theme of the meeting. For example, if the theme of the meeting is project management, the analysis unit emphasizes the clarity of the progress report. The analysis unit uses the generation AI to analyze the theme of the meeting. The generation AI analyzes the content of the meeting and identifies the theme. For example, the analysis unit inputs the content of the meeting into the generation AI and identifies the theme. The generation AI analyzes the content of the meeting and identifies that the theme is project management. Furthermore, if the theme of the meeting is brainstorming, the analysis unit emphasizes creativity and the proposal of new ideas. The analysis unit uses the generation AI to analyze the theme of the meeting. The generation AI analyzes the content of the meeting and identifies the theme. For example, the analysis unit inputs the content of the meeting into the generation AI and identifies the theme. The generation AI analyzes the content of the meeting and identifies that the theme is brainstorming. Furthermore, if the theme of the meeting is problem solving, the analysis unit emphasizes logical structure and the proposal of solutions. The analysis unit uses the generation AI to analyze the theme of the meeting. The generation AI analyzes the content of the meeting and identifies the theme. For example, the analysis unit inputs the contents of a meeting into the generation AI and identifies the theme. The generation AI then analyzes the contents of the meeting and identifies that the theme is problem-solving. This enables appropriate evaluation by emphasizing specific evaluation criteria based on the theme of the meeting.

[0067] The processing flow of the first embodiment will be briefly explained below.

[0068] Step 1: The collection unit records conversations in online meetings. For example, the collection unit collects audio data of the meetings and stores it in a digital format. The collection unit has the function of recording the audio data of the meetings in high quality and removing noise. For example, the collection unit records the audio of the meetings in real time and uses noise reduction technology to generate clear audio data. The collection unit can also collect video data of the meetings. For example, the collection unit records the video of the meetings in high resolution and synchronizes it with the audio data. Step 2: The analysis unit uses the generation AI to analyze the data collected by the collection unit. For example, the analysis unit analyzes audio data from a meeting to evaluate the content of what is said and how it is spoken. The analysis unit uses the generation AI to evaluate the clarity of what is said, its logical structure, and the appropriate timing of what is said. For example, the analysis unit inputs audio data into the generation AI to evaluate the clarity of what is said. The generation AI analyzes the audio data to evaluate the accuracy of pronunciation and the clarity of the voice. The analysis unit also uses the generation AI to evaluate the logical structure of what is said. The generation AI analyzes the audio data to evaluate the logical consistency of what is said and the clarity of the points being made. Furthermore, the analysis unit uses the generation AI to evaluate the timing of what is said. The generation AI analyzes the audio data to evaluate the appropriate spacing and timing of what is said. Step 3: The providing unit provides feedback based on the analysis results obtained by the analyzing unit. For example, the providing unit provides feedback on specific areas for improvement or merits based on the analysis results. The providing unit uses the generating AI to generate the content of the feedback. For example, the providing unit inputs the analysis results into the generating AI to generate the content of the feedback. Based on the analysis results, the generating AI provides advice for improving the clarity of speech and advice for maintaining a logical structure. Step 4: The tracking unit tracks the progress of improvement due to user registration. For example, the tracking unit references the user's past feedback history and visually displays the progress of improvement. The tracking unit uses the generation AI to track the progress of improvement. For example, the tracking unit inputs the user's feedback history into the generation AI and analyzes the progress of improvement. The generation AI evaluates the growth of the user's communication skills based on the feedback history and visually displays it.

[0069] (Example 2) The online conference evaluation system according to an embodiment of the present invention records conversations during online meetings and trains a generation AI to learn from the recordings. The system then provides feedback to speakers on communication aspects, such as the content and manner of speech. Once users register, the generation AI tracks progress toward improvement, contributing to organizational growth. First, online conference conversations are recorded. The recordings are then input into the generation AI. The generation AI analyzes the content of the conversation and the manner of speech to evaluate each speaker's communication skills. For example, evaluation criteria include clarity of speech, logical structure, and appropriate timing. Next, the generation AI provides feedback to each speaker based on the analysis results. This feedback includes specific areas for improvement and merit. For example, advice such as "Try to speak more slowly to improve the clarity of your speech" or "Your logical structure is excellent, so keep it up." Furthermore, once users register, the generation AI tracks progress toward improvement, allowing them to monitor their own communication skills. For example, improvements can be visually displayed compared to past feedback. This system is expected to improve communication skills within an organization and increase overall productivity. For example, it will increase the efficiency of meetings and lead to faster decision-making. Also, as individual speakers improve their skills, the performance of the entire team will improve. This allows the online meeting evaluation system to evaluate what is said and how it is said in meetings and provide feedback.

[0070] An online conference evaluation system according to an embodiment includes a collection unit, an analysis unit, a provision unit, and a tracking unit. The collection unit records conversations during an online conference. For example, the collection unit collects audio data from the conference and stores it digitally. The collection unit has a function for recording the audio data of the conference at high quality and removing noise. For example, the collection unit records the audio of the conference in real time and generates clear audio data using noise reduction technology. The collection unit can also collect video data of the conference. For example, the collection unit records a video of the conference at high resolution and synchronizes it with the audio data. The analysis unit uses a generation AI to analyze the data collected by the collection unit. For example, the analysis unit analyzes the audio data of the conference and evaluates the content and manner of speech. The analysis unit uses the generation AI to evaluate the clarity of speech, logical structure, appropriate timing of speech, etc. For example, the analysis unit inputs audio data into the generation AI and evaluates the clarity of speech. The generation AI analyzes the audio data and evaluates the accuracy of pronunciation and clarity of speech. The analysis unit also uses the generation AI to evaluate the logical structure of the statement. The generation AI analyzes the audio data and evaluates the logical consistency of the statement and the clarity of the argument. The analysis unit also uses the generation AI to evaluate the timing of the statement. The generation AI analyzes the audio data and evaluates appropriate pauses and timing of the statement. The provision unit provides feedback based on the analysis results obtained by the analysis unit. For example, the provision unit provides feedback on specific areas for improvement and merits based on the analysis results. The provision unit uses the generation AI to generate the content of the feedback. For example, the provision unit inputs the analysis results into the generation AI to generate the content of the feedback. The generation AI provides advice for improving the clarity of the statement and for maintaining a logical structure based on the analysis results. The tracking unit tracks the progress of improvements due to user registration. For example, the tracking unit references the user's past feedback history and visually displays the progress of improvements. The tracking unit uses the generation AI to track the progress of improvements. For example, the tracking unit inputs the user's feedback history into the generation AI and analyzes the progress of improvements. The generative AI evaluates and visually displays the user's communication skill growth based on feedback history.As a result, the online conference evaluation system according to the embodiment can evaluate the content and manner of statements made in a conference and provide feedback.

[0071] The online conference evaluation system includes a setting unit that sets evaluation criteria. The setting unit sets the evaluation criteria. For example, the setting unit sets evaluation criteria such as clarity of speech, logical structure, and appropriate timing of speech. The setting unit sets the evaluation criteria using a generation AI. For example, the setting unit inputs the evaluation criteria settings into the generation AI to generate the evaluation criteria. The generation AI sets criteria for evaluating clarity of speech and criteria for evaluating logical structure based on the evaluation criteria. In this way, setting the evaluation criteria improves the accuracy of feedback.

[0072] The online meeting evaluation system includes a generation unit that generates feedback content. The generation unit generates the feedback content. For example, the generation unit provides feedback on specific improvements and merits based on the analysis results obtained by the analysis unit. The generation unit generates the feedback content using a generation AI. For example, the generation unit inputs the analysis results into the generation AI to generate the feedback content. The generation AI provides advice on improving the clarity of speech and advice on maintaining a logical structure based on the analysis results. In this way, specific improvements and merits can be provided by generating feedback content using the generation AI.

[0073] The online meeting evaluation system includes a display unit that visually displays the progress of improvement. The display unit visually displays the progress of improvement. For example, the display unit references the user's past feedback history and displays the progress of improvement as a graph or chart. The display unit visually displays the progress of improvement using a generation AI. For example, the display unit inputs the user's feedback history into the generation AI and analyzes the progress of improvement. The generation AI evaluates the growth of the user's communication skills based on the feedback history and visually displays it. In this way, the progress of improvement is visually displayed, allowing the user to confirm their own growth.

[0074] The analysis unit can evaluate the clarity of the statement, its logical structure, and timing. For example, the analysis unit evaluates the clarity of the statement. The analysis unit uses the generation AI to evaluate the clarity of the statement. The generation AI analyzes the audio data and evaluates the accuracy of pronunciation and the clarity of the voice. The analysis unit also evaluates the logical structure of the statement. The generation AI analyzes the audio data and evaluates the logical consistency of the statement and the clarity of the points being made. Furthermore, the analysis unit evaluates the timing of the statement. The generation AI analyzes the audio data and evaluates the appropriate spacing and timing of the statement. This makes it possible to provide detailed feedback by evaluating the clarity of the statement, its logical structure, and the appropriate timing of the statement.

[0075] The providing unit can provide feedback on specific areas for improvement and meritorious points. For example, the providing unit provides feedback on specific areas for improvement and meritorious points based on the analysis results. The providing unit uses the generation AI to generate the content of the feedback. For example, the providing unit inputs the analysis results into the generation AI to generate the content of the feedback. The generation AI provides advice on improving the clarity of speech and advice on maintaining a logical structure based on the analysis results. In this way, by providing feedback on specific areas for improvement and meritorious points, the improvement of the user's communication skills is supported.

[0076] The collection unit can estimate the user's emotions and adjust the timing of collecting recorded data based on the estimated user's emotions. For example, if the user is nervous, the collection unit starts recording when the user is relaxed, rather than immediately after the start of the meeting. The collection unit estimates the user's emotions using the generation AI. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the collection unit inputs voice data into the generation AI and estimates the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of tension. Furthermore, if the user is relaxed, the collection unit starts recording before an important topic in the meeting begins. The collection unit estimates the user's emotions using the generation AI. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the collection unit inputs voice data into the generation AI and estimates the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of relaxation. Furthermore, if the user is concentrating, the collection unit starts recording in the middle or end of the meeting. The collection unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the collection unit inputs voice data into the generation AI to estimate the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of concentration. This enables more appropriate data collection by adjusting the timing of collecting recorded data according to the user's emotions.

[0077] The collection unit can dynamically change the scope of data to be collected depending on the type and purpose of the meeting. For example, in a brainstorming meeting, the collection unit collects all comments. The collection unit uses the generation AI to determine the type and purpose of the meeting. The generation AI analyzes the content and agenda of the meeting to determine the type and purpose of the meeting. For example, the collection unit inputs the content of the meeting into the generation AI and determines the type and purpose of the meeting. The generation AI analyzes the content of the meeting and determines that it is a brainstorming meeting. Furthermore, in a project progress meeting, the collection unit prioritizes collecting comments related to important decisions and action items. The collection unit uses the generation AI to analyze the content of the meeting and identify important comments. For example, the collection unit inputs the content of the meeting into the generation AI and identifies important comments. The generation AI analyzes the content of the meeting and identifies comments related to important decisions and action items. Furthermore, in regular meetings, the collection unit sets the scope of data to be collected for each agenda item and collects only the necessary parts. The collection unit uses the generation AI to analyze the agenda of the meeting and set the scope of data to be collected. For example, the collection unit inputs the meeting agenda into the generation AI and sets the range of data to be collected. The generation AI then analyzes the meeting agenda and collects only the necessary parts. This allows the necessary data to be collected efficiently by dynamically changing the range of data depending on the type and purpose of the meeting.

[0078] The collection unit can analyze the speaker's voice characteristics and perform filtering to record with optimal sound quality. For example, if the speaker's voice is quiet, the collection unit performs noise reduction to make the voice clear. The collection unit uses the generation AI to analyze the speaker's voice characteristics. The generation AI analyzes the voice data and evaluates the speaker's voice characteristics. For example, the collection unit inputs the voice data into the generation AI and analyzes the speaker's voice characteristics. The generation AI analyzes the voice data and evaluates the volume of the speaker's voice. Furthermore, if the speaker's voice is high-pitched, the collection unit performs echo cancellation to improve the sound quality. The collection unit uses the generation AI to analyze the speaker's voice characteristics. The generation AI analyzes the voice data and evaluates the speaker's voice characteristics. For example, the collection unit inputs the voice data into the generation AI and analyzes the speaker's voice characteristics. The generation AI analyzes the voice data and evaluates the pitch of the speaker's voice. Furthermore, if the speaker's voice is low-pitched, the collection unit removes low-frequency noise to make the voice clear. The collection unit uses the generation AI to analyze the speaker's voice characteristics. The generation AI analyzes the voice data and evaluates the speaker's voice characteristics. For example, the collection unit inputs voice data into the generation AI and analyzes the speaker's voice characteristics. The generation AI analyzes the voice data and evaluates the lowness of the speaker's voice. This improves the quality of the recorded data by analyzing the speaker's voice characteristics and recording with optimal sound quality.

[0079] The collection unit can estimate the user's emotions and determine the priority of data to be collected based on the estimated user emotions. For example, if the user is nervous, the collection unit prioritizes collecting important utterances. The collection unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the collection unit inputs voice data into the generation AI and estimates the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of tension. Furthermore, if the user is relaxed, the collection unit collects all utterances equally. The collection unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the collection unit inputs voice data into the generation AI and estimates the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of relaxation. Furthermore, if the user is concentrating, the collection unit prioritizes collecting utterances related to the topic. The collection unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to infer the user's emotions. For example, the collection unit inputs voice data into the generation AI to infer the user's emotions. The generation AI then analyzes the voice data and evaluates the user's level of concentration. This allows the system to prioritize data according to the user's emotions, allowing important data to be collected preferentially.

[0080] The collection unit can adjust the scope of data to be collected taking into account the geographic location information of meeting participants. For example, if participants are in different time zones, the collection unit prioritizes collection of important statements. The collection unit uses the generation AI to analyze the participants' geographic location information. The generation AI analyzes the participants' location data and determines their time zones. For example, the collection unit inputs location data into the generation AI and determines the participants' time zones. The generation AI analyzes the location data and determines that participants are in different time zones. Furthermore, if participants are in the same office, the collection unit collects all statements equally. The collection unit uses the generation AI to analyze the participants' geographic location information. The generation AI analyzes the participants' location data and determines that they are in the same office. For example, the collection unit inputs location data into the generation AI and determines the participants' locations. The generation AI analyzes the location data and determines that participants are in the same office. Furthermore, if participants are participating remotely, the collection unit adjusts the scope of data to be collected taking into account audio quality. The collection unit uses the generation AI to analyze the participants' geographic location information. The generation AI analyzes the location information data of participants and determines whether they are participating remotely. For example, the collection unit inputs location information data into the generation AI and determines the location of the participants. The generation AI analyzes the location information data and determines whether the participant is participating remotely. This enables appropriate data collection by taking into account the geographic location information of meeting participants.

[0081] The collection unit can prioritize collecting utterances containing specific keywords based on the content of the meeting. For example, the collection unit prioritizes collecting utterances containing keywords related to the meeting agenda. The collection unit uses the generation AI to analyze the content of the meeting and extract specific keywords. The generation AI analyzes the content of the meeting and identifies important keywords. For example, the collection unit inputs the content of the meeting into the generation AI and extracts specific keywords. The generation AI analyzes the content of the meeting and identifies keywords related to the agenda. Furthermore, the collection unit prioritizes collecting utterances containing keywords related to important decisions. The collection unit uses the generation AI to analyze the content of the meeting and extracts important keywords. The generation AI analyzes the content of the meeting and identifies keywords related to the important decisions. For example, the collection unit inputs the content of the meeting into the generation AI and extracts specific keywords. The generation AI analyzes the content of the meeting and identifies keywords related to the important decisions. Furthermore, the collection unit prioritizes collecting utterances containing keywords related to action items. The collection unit uses the generation AI to analyze the content of the meeting and extracts important keywords. The generation AI analyzes the content of the meeting and identifies keywords related to action items. For example, the collection unit inputs the content of the meeting into the generation AI and extracts specific keywords. The generation AI analyzes the content of the meeting and identifies keywords related to action items. This allows important information to be collected efficiently by preferentially collecting comments containing specific keywords based on the content of the meeting.

[0082] The analysis unit can estimate the user's emotions and adjust the analysis algorithm based on the estimated user emotions. For example, if the user is nervous, the analysis unit performs an analysis that emphasizes changes in emotions. The analysis unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the analysis unit inputs voice data into the generation AI and estimates the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of tension. Furthermore, if the user is relaxed, the analysis unit performs an analysis that emphasizes the content of the utterances. The analysis unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the analysis unit inputs voice data into the generation AI and estimates the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of relaxation. Furthermore, if the user is concentrating, the analysis unit performs an analysis that emphasizes the logical structure of the utterances. The analysis unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to infer the user's emotions. For example, the analysis unit inputs voice data into the generation AI and infers the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of concentration. This allows for more appropriate analysis by adjusting the analysis algorithm according to the user's emotions.

[0083] The analysis unit can apply different analysis methods based on the content of the utterance to perform a detailed evaluation. For example, the analysis unit uses speech recognition technology to evaluate the clarity of the utterance. The analysis unit uses a generation AI to analyze the content of the utterance. The generation AI analyzes the audio data to evaluate the clarity of the utterance. For example, the analysis unit inputs audio data into the generation AI and evaluates the clarity of the utterance. The generation AI analyzes the audio data to evaluate the accuracy of pronunciation and the clarity of the voice. The analysis unit also uses natural language processing technology to evaluate the logical structure of the utterance. The analysis unit uses a generation AI to analyze the content of the utterance. The generation AI analyzes the audio data to evaluate the logical consistency of the utterance and the clarity of the argument. For example, the analysis unit inputs audio data into the generation AI and evaluates the logical structure of the utterance. The generation AI analyzes the audio data to evaluate the logical consistency of the utterance and the clarity of the argument. Furthermore, the analysis unit analyzes the flow of the conversation to evaluate the appropriate timing of the utterance. The analysis unit uses a generation AI to analyze the content of the utterance. The generation AI analyzes the voice data and evaluates the timing of the speech. For example, the analysis unit inputs the voice data into the generation AI and evaluates the timing of the speech. The generation AI analyzes the voice data and evaluates the appropriate spacing and timing of the speech. This allows for a detailed evaluation by applying different analysis methods based on the content of the speech.

[0084] The analysis unit can update the analysis results in real time according to the progress of the meeting. For example, if an important comment is made during the meeting, the analysis unit updates the analysis results in real time. The analysis unit uses the generation AI to analyze the progress of the meeting. The generation AI analyzes the audio data and video data of the meeting to understand the progress of the meeting. For example, the analysis unit inputs the audio data of the meeting into the generation AI and analyzes the progress of the meeting. The generation AI analyzes the audio data and identifies important comments. The analysis unit also dynamically adjusts the evaluation criteria for comments as the meeting progresses. The analysis unit uses the generation AI to analyze the progress of the meeting. The generation AI analyzes the audio data and video data of the meeting to understand the progress of the meeting. For example, the analysis unit inputs the audio data of the meeting into the generation AI and analyzes the progress of the meeting. The generation AI analyzes the audio data and dynamically adjusts the evaluation criteria for comments. Furthermore, at the end of the meeting, the analysis unit comprehensively evaluates all comments and provides a final analysis result. The analysis unit uses the generation AI to analyze the progress of the meeting. The generation AI analyzes the audio and video data of the meeting to understand the progress of the meeting. For example, the analysis unit inputs the audio data of the meeting into the generation AI and analyzes the progress of the meeting. The generation AI analyzes the audio data and comprehensively evaluates all comments. This allows the analysis results to be updated in real time according to the progress of the meeting, making it possible to provide the latest information.

[0085] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is nervous, the analysis unit provides a simple, highly visible display method. The analysis unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the analysis unit inputs voice data into the generation AI and estimates the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of tension. Furthermore, if the user is relaxed, the analysis unit provides a display method that includes detailed information. The analysis unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the analysis unit inputs voice data into the generation AI and estimates the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of relaxation. Furthermore, if the user is concentrating, the analysis unit provides a display method that focuses on the key points. The analysis unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to infer the user's emotions. For example, the analysis unit inputs voice data into the generation AI and infers the user's emotions. The generation AI then analyzes the voice data and evaluates the user's level of concentration. This allows for a highly visible display by adjusting the way the analysis results are displayed according to the user's emotions.

[0086] The analysis unit can improve the accuracy of the analysis results by referring to the speaker's past utterance history. The analysis unit, for example, analyzes utterance patterns based on the speaker's past utterance history. The analysis unit uses the generation AI to analyze the speaker's past utterance history. The generation AI analyzes the past utterance data and identifies utterance patterns. For example, the analysis unit inputs past utterance data into the generation AI and analyzes utterance patterns. The generation AI analyzes the past utterance data and identifies utterance patterns. The analysis unit also identifies areas for improvement in the utterances from the speaker's past utterance history. The analysis unit uses the generation AI to analyze the speaker's past utterance history. The generation AI analyzes the past utterance data and identifies areas for improvement in the utterances. For example, the analysis unit inputs past utterance data into the generation AI and identifies areas for improvement in the utterances. The generation AI analyzes the past utterance data and identifies areas for improvement in the utterances. Furthermore, the analysis unit refers to the speaker's past utterance history to adjust the evaluation criteria for the utterances. The analysis unit uses the generation AI to analyze the speaker's past utterance history. The generation AI analyzes past utterance data and adjusts the evaluation criteria for utterances. For example, the analysis unit inputs past utterance data into the generation AI and adjusts the evaluation criteria for utterances. The generation AI analyzes past utterance data and adjusts the evaluation criteria for utterances. This improves the accuracy of the analysis results by referencing the speaker's past utterance history.

[0087] The analysis unit can emphasize specific evaluation criteria based on the theme of the meeting. For example, if the theme of the meeting is project management, the analysis unit emphasizes clarity of progress reports. The analysis unit uses the generation AI to analyze the theme of the meeting. The generation AI analyzes the content of the meeting and identifies the theme. For example, the analysis unit inputs the content of the meeting into the generation AI and identifies the theme. The generation AI analyzes the content of the meeting and identifies that the theme is project management. Furthermore, if the theme of the meeting is brainstorming, the analysis unit emphasizes creativity and the proposal of new ideas. The analysis unit uses the generation AI to analyze the theme of the meeting. The generation AI analyzes the content of the meeting and identifies the theme. For example, the analysis unit inputs the content of the meeting into the generation AI and identifies the theme. The generation AI analyzes the content of the meeting and identifies that the theme is brainstorming. Furthermore, if the theme of the meeting is problem solving, the analysis unit emphasizes logical structure and the proposal of solutions. The analysis unit uses the generation AI to analyze the theme of the meeting. The generation AI analyzes the content of the meeting and identifies the theme. For example, the analysis unit inputs the content of the meeting into the generation AI and identifies the theme. The generation AI analyzes the content of the meeting and identifies that the theme is problem-solving. This enables appropriate evaluation by emphasizing specific evaluation criteria based on the theme of the meeting.

[0088] The providing unit can estimate the user's emotions and adjust the way feedback is expressed based on the estimated user's emotions. For example, if the user is nervous, the providing unit provides feedback in gentle words. The providing unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the providing unit inputs voice data into the generation AI to estimate the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of tension. Furthermore, if the user is relaxed, the providing unit provides detailed feedback. The providing unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the providing unit inputs voice data into the generation AI to estimate the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of relaxation. Furthermore, if the user is concentrating, the providing unit provides feedback that highlights specific areas for improvement. The providing unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the providing unit inputs voice data into the generation AI and estimates the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of concentration. This allows the system to provide more appropriate feedback by adjusting the way feedback is expressed according to the user's emotions.

[0089] The provision department can customize the content of the feedback depending on the speaker's position and experience. For example, the provision department provides new employees with feedback regarding basic communication skills. The provision department uses the generation AI to analyze the speaker's position and experience. The generation AI analyzes the speaker's position and experience data and generates appropriate feedback. For example, the provision department inputs the speaker's position and experience data into the generation AI to generate feedback content. The generation AI analyzes the speaker's position and experience and generates feedback suitable for new employees. Furthermore, the provision department provides mid-level employees with feedback regarding leadership and teamwork. The provision department uses the generation AI to analyze the speaker's position and experience. The generation AI analyzes the speaker's position and experience data and generates appropriate feedback. For example, the provision department inputs the speaker's position and experience data into the generation AI to generate feedback content. The generation AI analyzes the speaker's position and experience and generates feedback suitable for mid-level employees. Furthermore, the provision department provides managers with feedback regarding strategic thinking and decision-making. The provision unit uses the generation AI to analyze the speaker's job title and experience. The generation AI analyzes the speaker's job title and experience data and generates appropriate feedback. For example, the provision unit inputs the speaker's job title and experience data into the generation AI and generates feedback content. The generation AI analyzes the speaker's job title and experience and generates feedback suitable for a managerial position. This makes it possible to provide appropriate feedback according to the speaker's job title and experience.

[0090] The providing unit can dynamically change the timing of providing feedback depending on the progress of the meeting. For example, the providing unit provides feedback immediately after the end of the meeting. The providing unit uses the generation AI to analyze the progress of the meeting. The generation AI analyzes audio data and video data of the meeting to understand the progress of the meeting. For example, the providing unit inputs the audio data of the meeting into the generation AI and analyzes the progress of the meeting. The generation AI analyzes the audio data and identifies the end of the meeting. Furthermore, the providing unit provides feedback immediately after an important statement is made during the meeting. The providing unit uses the generation AI to analyze the progress of the meeting. The generation AI analyzes the audio data and video data of the meeting to understand the progress of the meeting. For example, the providing unit inputs the audio data of the meeting into the generation AI and analyzes the progress of the meeting. The generation AI analyzes the audio data and identifies important statements. Furthermore, the providing unit provides feedback at appropriate timing as the meeting progresses. The providing unit uses the generation AI to analyze the progress of the meeting. The generation AI analyzes the audio and video data of the meeting to understand the progress of the meeting. For example, the providing unit inputs the audio data of the meeting into the generation AI and analyzes the progress of the meeting. The generation AI analyzes the audio data and provides feedback at the appropriate time. This allows feedback to be provided at the appropriate time depending on the progress of the meeting.

[0091] The providing unit can estimate the user's emotions and determine the priority of feedback based on the estimated user's emotions. For example, if the user is nervous, the providing unit prioritizes feedback on important areas for improvement. The providing unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the providing unit inputs voice data into the generation AI to estimate the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of tension. Furthermore, if the user is relaxed, the providing unit provides all feedback equally. The providing unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the providing unit inputs voice data into the generation AI to estimate the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of relaxation. Furthermore, if the user is concentrating, the providing unit prioritizes feedback on specific areas for improvement. The providing unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to infer the user's emotions. For example, the provision unit inputs voice data into the generation AI to infer the user's emotions. The generation AI then analyzes the voice data and evaluates the user's level of concentration. This allows the system to prioritize feedback according to the user's emotions, allowing it to provide important improvements first.

[0092] The providing unit can provide the feedback by comparing the content of the feedback with the speaker's past feedback history. For example, the providing unit identifies areas for improvement based on the speaker's past feedback history. The providing unit uses the generation AI to analyze the speaker's past feedback history. The generation AI analyzes the past feedback data and identifies areas for improvement. For example, the providing unit inputs past feedback data into the generation AI and identifies areas for improvement. The generation AI analyzes the past feedback data and identifies areas for improvement. The providing unit also highlights good points from the speaker's past feedback history. The providing unit uses the generation AI to analyze the speaker's past feedback history. The generation AI analyzes the past feedback data and identifies good points. For example, the providing unit inputs past feedback data into the generation AI and identifies good points. The generation AI analyzes the past feedback data and identifies good points. Furthermore, the providing unit refers to the speaker's past feedback history to provide specific areas for improvement. The providing unit uses the generation AI to analyze the speaker's past feedback history. The generation AI analyzes the past feedback data and identifies specific areas for improvement. For example, the providing unit inputs past feedback data into the generating AI and identifies specific areas for improvement. The generating AI then analyzes the past feedback data and identifies specific areas for improvement. This allows the AI ​​to provide specific areas for improvement by comparing the feedback data with the speaker's past feedback history.

[0093] The providing department can emphasize specific points in the feedback content based on the theme of the meeting. For example, if the theme of the meeting is project management, the providing department emphasizes clarity of the progress report. The providing department uses the generating AI to analyze the theme of the meeting. The generating AI analyzes the content of the meeting and identifies the theme. For example, the providing department inputs the content of the meeting into the generating AI and identifies the theme. The generating AI analyzes the content of the meeting and identifies that the theme is project management. Furthermore, if the theme of the meeting is brainstorming, the providing department emphasizes creativity and the proposal of new ideas. The providing department uses the generating AI to analyze the theme of the meeting. The generating AI analyzes the content of the meeting and identifies the theme. For example, the providing department inputs the content of the meeting into the generating AI and identifies the theme. The generating AI analyzes the content of the meeting and identifies that the theme is brainstorming. Furthermore, if the theme of the meeting is problem solving, the providing department emphasizes logical structure and the proposal of solutions. The providing department uses the generating AI to analyze the theme of the meeting. The generation AI analyzes the content of the meeting and identifies the theme. For example, the provider inputs the content of the meeting into the generation AI and identifies the theme. The generation AI analyzes the content of the meeting and identifies that the theme is problem solving. This allows appropriate feedback to be provided by emphasizing specific points based on the theme of the meeting.

[0094] The tracking unit can estimate the user's emotions and adjust the method for tracking the progress of improvement based on the estimated user emotions. For example, when the user is nervous, the tracking unit provides a simple and highly visible tracking method. The tracking unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the tracking unit inputs voice data into the generation AI to estimate the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of tension. Furthermore, when the user is relaxed, the tracking unit provides a tracking method that includes detailed information. The tracking unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the tracking unit inputs voice data into the generation AI to estimate the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of relaxation. Furthermore, when the user is concentrating, the tracking unit provides a tracking method that focuses on the key points. The tracking unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the tracking unit inputs voice data into the generation AI and estimates the user's emotions. The generation AI then analyzes the voice data and evaluates the user's level of concentration. This enables highly visible tracking by adjusting the method for tracking the progress of improvement according to the user's emotions.

[0095] The tracking unit can evaluate the progress of improvement using different indicators depending on the speaker's position and experience. For example, the tracking unit provides new employees with indicators that evaluate the improvement of basic communication skills. The tracking unit uses the generation AI to analyze the speaker's position and experience. The generation AI analyzes the speaker's position and experience data and generates appropriate evaluation indicators. For example, the tracking unit inputs the speaker's position and experience data into the generation AI and generates evaluation indicators. The generation AI analyzes the speaker's position and experience and generates evaluation indicators that are suitable for new employees. Furthermore, the tracking unit provides mid-level employees with indicators that evaluate the improvement of leadership and teamwork. The tracking unit uses the generation AI to analyze the speaker's position and experience. The generation AI analyzes the speaker's position and experience data and generates appropriate evaluation indicators. For example, the tracking unit inputs the speaker's position and experience data into the generation AI and generates evaluation indicators. The generation AI analyzes the speaker's position and experience and generates evaluation indicators that are suitable for mid-level employees. Furthermore, the tracking unit provides managers with indicators to evaluate improvements in strategic thinking and decision-making. The tracking unit uses the generation AI to analyze the speaker's position and experience. The generation AI analyzes the speaker's position and experience data and generates appropriate evaluation indicators. For example, the tracking unit inputs the speaker's position and experience data into the generation AI to generate evaluation indicators. The generation AI analyzes the speaker's position and experience and generates evaluation indicators suitable for managers. This makes it possible to evaluate the progress of improvement using indicators appropriate for the speaker's position and experience.

[0096] The tracking unit can analyze the progress of improvement from different perspectives depending on the type and purpose of the meeting. For example, in a brainstorming meeting, the tracking unit evaluates improvements in creativity and the proposal of new ideas. The tracking unit uses the generation AI to analyze the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies the type and purpose of the meeting. For example, the tracking unit inputs the content of the meeting into the generation AI and identifies the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies that it is a brainstorming meeting. In addition, in a project progress meeting, the tracking unit evaluates the clarity of the progress report and the degree to which action items are implemented. The tracking unit uses the generation AI to analyze the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies the type and purpose of the meeting. For example, the tracking unit inputs the content of the meeting into the generation AI and identifies the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies that it is a project progress meeting. In addition, in a regular meeting, the tracking unit evaluates the quality and timing of comments for each agenda item. The tracking unit uses the generation AI to analyze the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies the type and purpose of the meeting. For example, the tracking unit inputs the content of the meeting into the generation AI and identifies the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies that it is a regular meeting. This makes it possible to analyze the progress of improvement from an appropriate perspective according to the type and purpose of the meeting.

[0097] The tracking unit can estimate the user's emotions and adjust the display method for the progress of improvement based on the estimated user emotions. For example, if the user is nervous, the tracking unit provides a simple, highly visible display method. The tracking unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the tracking unit inputs voice data into the generation AI to estimate the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of tension. Furthermore, if the user is relaxed, the tracking unit provides a display method that includes detailed information. The tracking unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the tracking unit inputs voice data into the generation AI to estimate the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of relaxation. Furthermore, if the user is concentrating, the tracking unit provides a display method that focuses on the key points. The tracking unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the tracking unit inputs voice data into the generation AI to estimate the user's emotions. The generation AI then analyzes the voice data and evaluates the user's level of concentration. This allows for a highly visible display by adjusting the way the progress of improvement is displayed according to the user's emotions.

[0098] The tracking unit can evaluate the progress of improvement by comparing it with the speaker's past speech history. For example, the tracking unit identifies areas for improvement based on the speaker's past speech history. The tracking unit uses the generation AI to analyze the speaker's past speech history. The generation AI analyzes the past speech data and identifies areas for improvement. For example, the tracking unit inputs past speech data into the generation AI and identifies areas for improvement. The generation AI analyzes the past speech data and identifies areas for improvement. The tracking unit also highlights good points from the speaker's past speech history. The tracking unit uses the generation AI to analyze the speaker's past speech history. The generation AI analyzes the past speech data and identifies good points. For example, the tracking unit inputs past speech data into the generation AI and identifies good points. The generation AI analyzes the past speech data and identifies good points. The tracking unit also provides specific areas for improvement by referring to the speaker's past speech history. The tracking unit uses the generation AI to analyze the speaker's past speech history. The generation AI analyzes the past speech data and identifies specific areas for improvement. For example, the tracking unit inputs past speech data into the generation AI and identifies specific areas for improvement. The generation AI then analyzes the past speech data and identifies specific areas for improvement. This allows the AI ​​to provide specific areas for improvement by comparing the data with the speaker's past speech history.

[0099] The tracking unit can emphasize specific indicators of improvement progress based on the theme of the meeting. For example, if the theme of the meeting is project management, the tracking unit emphasizes clarity of the progress report. The tracking unit uses the generation AI to analyze the theme of the meeting. The generation AI analyzes the content of the meeting and identifies the theme. For example, the tracking unit inputs the content of the meeting into the generation AI and identifies the theme. The generation AI analyzes the content of the meeting and identifies that the theme is project management. Furthermore, if the theme of the meeting is brainstorming, the tracking unit emphasizes creativity and the proposal of new ideas. The tracking unit uses the generation AI to analyze the theme of the meeting. The generation AI analyzes the content of the meeting and identifies the theme. For example, the tracking unit inputs the content of the meeting into the generation AI and identifies the theme. The generation AI analyzes the content of the meeting and identifies that the theme is brainstorming. Furthermore, if the theme of the meeting is problem solving, the tracking unit emphasizes logical structure and the proposal of solutions. The tracking unit uses the generation AI to analyze the theme of the meeting. The generation AI analyzes the content of the meeting and identifies the theme. For example, the tracking unit inputs the content of the meeting into the generation AI and identifies the theme. The generation AI analyzes the content of the meeting and identifies that the theme is problem solving. This enables appropriate evaluation by emphasizing specific indicators based on the theme of the meeting.

[0100] The setting unit can estimate the user's emotions and dynamically adjust the evaluation criteria based on the estimated user's emotions. For example, when the user is nervous, the setting unit provides simple, highly visible evaluation criteria. The setting unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the setting unit inputs voice data into the generation AI to estimate the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of tension. Furthermore, when the user is relaxed, the setting unit provides evaluation criteria that include detailed information. The setting unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the setting unit inputs voice data into the generation AI to estimate the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of relaxation. Furthermore, when the user is concentrating, the setting unit provides evaluation criteria that focus on the key points. The setting unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the setting unit inputs voice data into the generation AI to estimate the user's emotions. The generation AI then analyzes the voice data and evaluates the user's level of concentration. This allows for appropriate evaluation by dynamically adjusting the evaluation criteria according to the user's emotions.

[0101] The setting unit can customize the evaluation criteria according to the type and purpose of the meeting. For example, for a brainstorming meeting, the setting unit sets evaluation criteria that emphasize creativity and the proposal of new ideas. The setting unit uses the generation AI to analyze the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies the type and purpose of the meeting. For example, the setting unit inputs the content of the meeting into the generation AI and identifies the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies that it is a brainstorming meeting. Furthermore, for a project progress meeting, the setting unit sets evaluation criteria that emphasize the clarity of the progress report and the degree to which action items are implemented. The setting unit uses the generation AI to analyze the type and purpose of the meeting. The generation AI analyzes the content of the meeting. For example, the setting unit inputs the content of the meeting into the generation AI and identifies the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies that it is a project progress meeting. Furthermore, for regular meetings, the setting unit sets evaluation criteria that emphasize the quality and timing of comments for each agenda item. The setting unit uses the generation AI to analyze the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies the type and purpose of the meeting. For example, the setting unit inputs the content of the meeting into the generation AI and identifies the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies that it is a regular meeting. This makes it possible to set appropriate evaluation criteria according to the type and purpose of the meeting.

[0102] The setting unit can set different evaluation criteria depending on the speaker's position and experience. For example, for new employees, the setting unit sets evaluation criteria that emphasize basic communication skills. The setting unit uses the generation AI to analyze the speaker's position and experience. The generation AI analyzes the speaker's position and experience data and generates appropriate evaluation criteria. For example, the setting unit inputs the speaker's position and experience data into the generation AI and generates evaluation criteria. The generation AI analyzes the speaker's position and experience and generates evaluation criteria that are suitable for new employees. Furthermore, the setting unit sets evaluation criteria that emphasize leadership and teamwork for mid-level employees. The setting unit uses the generation AI to analyze the speaker's position and experience. The generation AI analyzes the speaker's position and experience data and generates appropriate evaluation criteria. For example, the setting unit inputs the speaker's position and experience data into the generation AI and generates evaluation criteria. The generation AI analyzes the speaker's position and experience and generates evaluation criteria that are suitable for mid-level employees. Furthermore, for managerial positions, the setting unit sets evaluation criteria that emphasize strategic thinking and decision-making. The setting unit uses the generation AI to analyze the speaker's job title and experience. The generation AI analyzes the speaker's job title and experience data and generates appropriate evaluation criteria. For example, the setting unit inputs the speaker's job title and experience data into the generation AI to generate evaluation criteria. The generation AI analyzes the speaker's job title and experience and generates evaluation criteria suitable for managerial positions. This makes it possible to set appropriate evaluation criteria according to the speaker's job title and experience.

[0103] The setting unit can estimate the user's emotions and determine the priority of the evaluation criteria based on the estimated user's emotions. For example, when the user is nervous, the setting unit prioritizes providing important evaluation criteria. The setting unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the setting unit inputs voice data into the generation AI to estimate the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of tension. Furthermore, when the user is relaxed, the setting unit provides all evaluation criteria equally. The setting unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the setting unit inputs voice data into the generation AI to estimate the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of relaxation. Furthermore, when the user is concentrating, the setting unit prioritizes providing specific evaluation criteria. The setting unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the setting unit inputs voice data into the generation AI to estimate the user's emotions. The generation AI then analyzes the voice data and evaluates the user's level of concentration. This allows the system to prioritize evaluation criteria according to the user's emotions, allowing important evaluation criteria to be provided preferentially.

[0104] The setting unit can set the evaluation criteria by comparing them with the speaker's past utterance history. For example, the setting unit sets the evaluation criteria based on the speaker's past utterance history. The setting unit uses the generation AI to analyze the speaker's past utterance history. The generation AI analyzes the past utterance data and identifies the evaluation criteria. For example, the setting unit inputs past utterance data into the generation AI and identifies the evaluation criteria. The generation AI analyzes the past utterance data and identifies the evaluation criteria. Furthermore, the setting unit sets evaluation criteria that emphasize good points from the speaker's past utterance history. The setting unit uses the generation AI to analyze the speaker's past utterance history. The generation AI analyzes the past utterance data and identifies good points. For example, the setting unit inputs past utterance data into the generation AI and identifies good points. The generation AI analyzes the past utterance data and identifies good points. Furthermore, the setting unit sets specific evaluation criteria by referring to the speaker's past utterance history. The setting unit uses the generation AI to analyze the speaker's past utterance history. The generation AI analyzes the past utterance data and identifies good points. For example, the setting unit inputs past utterance data into the generation AI and identifies specific evaluation criteria. The generation AI analyzes the past utterance data and identifies specific evaluation criteria. This allows the specific evaluation criteria to be set by comparing them with the speaker's past utterance history.

[0105] The generation unit can estimate the user's emotions and generate feedback content based on the estimated user's emotions. For example, if the user is nervous, the generation unit provides feedback in gentle words. The generation unit uses a generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the generation unit inputs voice data into the generation AI and estimates the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of tension. Furthermore, if the user is relaxed, the generation unit provides detailed feedback. The generation unit uses a generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the generation unit inputs voice data into the generation AI and estimates the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of relaxation. Furthermore, if the user is concentrating, the generation unit provides feedback that highlights specific areas for improvement. The generation unit uses a generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the generation unit inputs voice data into the generation AI and estimates the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of concentration. This allows the content of the feedback to be generated according to the user's emotions, making it possible to provide more appropriate feedback.

[0106] The generation unit can customize the content of the feedback depending on the speaker's position and experience. For example, the generation unit provides new employees with feedback regarding basic communication skills. The generation unit uses a generation AI to analyze the speaker's position and experience. The generation AI analyzes the speaker's position and experience data and generates appropriate feedback. For example, the generation unit inputs the speaker's position and experience data into the generation AI to generate feedback content. The generation AI analyzes the speaker's position and experience and generates feedback suitable for new employees. The generation unit also provides mid-level employees with feedback regarding leadership and teamwork. The generation unit uses a generation AI to analyze the speaker's position and experience. The generation AI analyzes the speaker's position and experience data and generates appropriate feedback. For example, the generation unit inputs the speaker's position and experience data into the generation AI to generate feedback content. The generation AI analyzes the speaker's position and experience and generates feedback suitable for mid-level employees. Furthermore, the generation unit provides managers with feedback regarding strategic thinking and decision-making. The generation unit uses the generation AI to analyze the speaker's job title and experience. The generation AI analyzes the speaker's job title and experience data and generates appropriate feedback. For example, the generation unit inputs the speaker's job title and experience data into the generation AI and generates feedback content. The generation AI analyzes the speaker's job title and experience and generates feedback suitable for a managerial position. This makes it possible to provide appropriate feedback according to the speaker's job title and experience.

[0107] The generation unit can generate the feedback content from different perspectives depending on the type and purpose of the meeting. For example, in a brainstorming meeting, the generation unit provides feedback regarding creativity and the proposal of new ideas. The generation unit uses the generation AI to analyze the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies the type and purpose of the meeting. For example, the generation unit inputs the content of the meeting into the generation AI and identifies the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies that it is a brainstorming meeting. Furthermore, in a project progress meeting, the generation unit provides feedback regarding the clarity of the progress report and the degree to which action items have been implemented. The generation unit uses the generation AI to analyze the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies the type and purpose of the meeting. For example, the generation unit inputs the content of the meeting into the generation AI and identifies the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies that it is a project progress meeting. Furthermore, in regular meetings, the generation unit provides feedback regarding the quality and timing of comments for each agenda item. The generation unit uses the generation AI to analyze the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies the type and purpose of the meeting. For example, the generation unit inputs the content of the meeting into the generation AI and identifies the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies that it is a regular meeting. This makes it possible to provide appropriate feedback according to the type and purpose of the meeting.

[0108] The generation unit can estimate the user's emotions and determine the priority of feedback based on the estimated user emotions. For example, if the user is nervous, the generation unit prioritizes feedback on important areas for improvement. The generation unit uses a generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the generation unit inputs voice data into the generation AI and estimates the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of tension. Furthermore, if the user is relaxed, the generation unit provides all feedback equally. The generation unit uses a generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the generation unit inputs voice data into the generation AI and estimates the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of relaxation. Furthermore, if the user is concentrating, the generation unit prioritizes feedback on specific areas for improvement. The generation unit uses a generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the generation unit inputs voice data into the generation AI to estimate the user's emotions. The generation AI then analyzes the voice data and evaluates the user's level of concentration. This allows the system to prioritize feedback according to the user's emotions, allowing it to provide important improvements first.

[0109] The generation unit can generate the feedback by comparing the content with the speaker's past speech history. For example, the generation unit identifies areas for improvement based on the speaker's past speech history. The generation unit uses a generation AI to analyze the speaker's past speech history. The generation AI analyzes the past speech data and identifies areas for improvement. For example, the generation unit inputs past speech data into the generation AI and identifies areas for improvement. The generation AI analyzes the past speech data and identifies areas for improvement. The generation unit also highlights good points from the speaker's past speech history. The generation unit uses a generation AI to analyze the speaker's past speech history. The generation AI analyzes the past speech data and identifies good points. For example, the generation unit inputs past speech data into the generation AI and identifies good points. The generation AI analyzes the past speech data and identifies good points. The generation unit also refers to the speaker's past speech history to provide specific areas for improvement. The generation unit uses a generation AI to analyze the speaker's past speech history. The generation AI analyzes the past speech data and identifies specific areas for improvement. For example, the generation unit inputs past utterance data into the generation AI and identifies specific areas for improvement. The generation AI then analyzes the past utterance data and identifies specific areas for improvement. This allows the AI ​​to provide specific areas for improvement by comparing the data with the speaker's past utterance history.

[0110] The display unit can estimate the user's emotions and adjust the display method based on the estimated user emotions. For example, when the user is nervous, the display unit provides a simple, highly visible display method. The display unit uses a generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the display unit inputs voice data into the generation AI and estimates the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of tension. Furthermore, when the user is relaxed, the display unit provides a display method that includes detailed information. The display unit uses a generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the display unit inputs voice data into the generation AI and estimates the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of relaxation. Furthermore, when the user is concentrating, the display unit provides a display method that focuses on the main points. The display unit uses a generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the display unit inputs voice data into the generation AI and estimates the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of concentration. This allows the display method to be adjusted according to the user's emotions, enabling a highly visible display.

[0111] The display unit can customize the display content according to the speaker's position and experience. For example, the display unit provides new employees with display content related to basic communication skills. The display unit uses a generation AI to analyze the speaker's position and experience. The generation AI analyzes the speaker's position and experience data and generates appropriate display content. For example, the display unit inputs the speaker's position and experience data into the generation AI and generates display content. The generation AI analyzes the speaker's position and experience and generates display content suitable for new employees. Furthermore, the display unit provides mid-level employees with display content related to leadership and teamwork. The display unit uses a generation AI to analyze the speaker's position and experience. The generation AI analyzes the speaker's position and experience data and generates appropriate display content. For example, the display unit inputs the speaker's position and experience data into the generation AI and generates display content. The generation AI analyzes the speaker's position and experience and generates display content suitable for mid-level employees. Furthermore, the display unit provides managers with display content related to strategic thinking and decision-making. The display unit uses the generation AI to analyze the speaker's job title and experience. The generation AI analyzes the speaker's job title and experience data and generates appropriate display content. For example, the display unit inputs the speaker's job title and experience data into the generation AI and generates display content. The generation AI analyzes the speaker's job title and experience and generates display content suitable for a managerial position. This makes it possible to provide appropriate display content according to the speaker's job title and experience.

[0112] The display unit can display the display content from different perspectives depending on the type and purpose of the meeting. For example, in a brainstorming meeting, the display unit provides display content related to creativity and the proposal of new ideas. The display unit uses a generation AI to analyze the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies the type and purpose of the meeting. For example, the display unit inputs the content of the meeting into the generation AI and identifies the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies that it is a brainstorming meeting. Furthermore, in a project progress meeting, the display unit provides display content related to the clarity of the progress report and the degree of execution of action items. The display unit uses a generation AI to analyze the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies the type and purpose of the meeting. For example, the display unit inputs the content of the meeting into the generation AI and identifies the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies that it is a project progress meeting. Furthermore, in a regular meeting, the display unit provides display content related to the quality and timing of comments for each agenda item. The display unit uses the generation AI to analyze the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies the type and purpose of the meeting. For example, the display unit inputs the content of the meeting into the generation AI and identifies the type and purpose of the meeting. The generation AI analyzes the content of the meeting and identifies that it is a regular meeting. This makes it possible to provide appropriate display content according to the type and purpose of the meeting.

[0113] The display unit can estimate the user's emotions and determine display priorities based on the estimated user emotions. For example, when the user is nervous, the display unit prioritizes displaying important information. The display unit estimates the user's emotions using a generation AI. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the display unit inputs voice data into the generation AI and estimates the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of tension. Furthermore, when the user is relaxed, the display unit displays all information equally. The display unit estimates the user's emotions using a generation AI. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the display unit inputs voice data into the generation AI and estimates the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of relaxation. Furthermore, when the user is concentrating, the display unit prioritizes displaying specific information. The display unit estimates the user's emotions using a generation AI. The generation AI analyzes voice data and facial expression data to infer the user's emotions. For example, the display unit inputs voice data into the generation AI and infers the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of concentration. This allows important information to be displayed first by determining display priorities according to the user's emotions.

[0114] The display unit can compare the display content with the speaker's past speech history and display it. The display unit, for example, identifies areas for improvement based on the speaker's past speech history. The display unit uses a generation AI to analyze the speaker's past speech history. The generation AI analyzes the past speech data and identifies areas for improvement. For example, the display unit inputs past speech data into the generation AI and identifies areas for improvement. The generation AI analyzes the past speech data and identifies areas for improvement. The display unit also highlights good points from the speaker's past speech history. The display unit uses a generation AI to analyze the speaker's past speech history. The generation AI analyzes the past speech data and identifies good points. For example, the display unit inputs past speech data into the generation AI and identifies good points. The generation AI analyzes the past speech data and identifies good points. The display unit also displays specific areas for improvement by referring to the speaker's past speech history. The display unit uses a generation AI to analyze the speaker's past speech history. The generation AI analyzes the past speech data and identifies specific areas for improvement. For example, the display unit inputs past speech data into the generation AI and identifies specific areas for improvement. The generation AI then analyzes the past speech data and identifies specific areas for improvement. This allows the specific areas for improvement to be displayed by comparing them with the speaker's past speech history. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, analysis unit, provision unit, tracking unit, setting unit, generation unit, and display unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects audio and video data of a meeting using the camera 42 and microphone 38B of the smart device 14, and the collected data is analyzed by the specific processing unit 290 of the data processing device 12. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and evaluates the content and manner of speech using a generation AI. The provision unit generates feedback based on the analysis results using the specific processing unit 290 of the data processing device 12 and provides the feedback to the user via the output device 40 of the smart device 14. The tracking unit tracks the progress of the user's improvement using the specific processing unit 290 of the data processing device 12 and visually displays it. The setting unit sets evaluation criteria using the specific processing unit 290 of the data processing device 12, and the generation unit generates the content of the feedback using a generation AI. The display unit visually displays the progress of improvement using the display 40A of the smart device 14. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, analysis unit, provision unit, tracking unit, setting unit, generation unit, and display unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects audio and video data of a meeting using the camera 42 and microphone 238 of the smart glasses 214, which is analyzed by the specific processing unit 290 of the data processing device 12. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and evaluates the content of statements and the manner of statements using a generation AI. The provision unit generates feedback based on the analysis results using the specific processing unit 290 of the data processing device 12 and provides it to the user through the speaker 240 of the smart glasses 214. The tracking unit tracks the progress of the user's improvement using the specific processing unit 290 of the data processing device 12 and visually displays it. The setting unit sets evaluation criteria using the specific processing unit 290 of the data processing device 12, and the generation unit generates the content of the feedback using a generation AI. The display unit visually displays the progress of improvement using the display of the smart glasses 214. === Hard Collateral 1-3 === Each of the multiple elements, including the collection unit, analysis unit, provision unit, tracking unit, setting unit, generation unit, and display unit, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the collection unit collects audio and video data of the conference using the camera 42 and microphone 238 of the headset-type terminal 314, and the collected data is analyzed by the specific processing unit 290 of the data processing device 12. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and evaluates the content of comments and the manner of comments using a generation AI. The provision unit generates feedback based on the analysis results using the specific processing unit 290 of the data processing device 12 and provides the feedback to the user through the speaker 240 of the headset-type terminal 314. The tracking unit tracks the progress of the user's improvement using the specific processing unit 290 of the data processing device 12 and visually displays it. The setting unit sets evaluation criteria using the specific processing unit 290 of the data processing device 12, and the generation unit generates the content of the feedback using a generation AI. The display unit visually displays the progress of improvement using the display 343 of the headset terminal 314. === Hard Collateral 1-4 === Each of the multiple elements, including the collection unit, analysis unit, provision unit, tracking unit, setting unit, generation unit, and display unit, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects audio and video data of the meeting using the camera 42 and microphone 238 of the robot 414, and the collected data is analyzed by the specific processing unit 290 of the data processing device 12. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and evaluates the content of comments and the manner of comments using a generation AI. The provision unit generates feedback based on the analysis results using the specific processing unit 290 of the data processing device 12 and provides the feedback to the user through the speaker 240 of the robot 414. The tracking unit tracks the progress of the user's improvement using the specific processing unit 290 of the data processing device 12 and visually displays it. The setting unit sets evaluation criteria using the specific processing unit 290 of the data processing device 12, and the generation unit generates the content of the feedback using a generation AI. The display unit visually displays the progress of improvement using the display of the robot 414.

[0115] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0116] The analysis unit can update the analysis results in real time according to the progress of the meeting. For example, if an important comment is made during the meeting, the analysis results are updated in real time. The analysis unit uses the generation AI to analyze the progress of the meeting. The generation AI analyzes the audio data and video data of the meeting to understand the progress of the meeting. For example, the analysis unit inputs the audio data of the meeting into the generation AI and analyzes the progress of the meeting. The generation AI analyzes the audio data and identifies important comments. The analysis unit also dynamically adjusts the evaluation criteria for comments as the meeting progresses. The analysis unit uses the generation AI to analyze the progress of the meeting. The generation AI analyzes the audio data and video data of the meeting to understand the progress of the meeting. For example, the analysis unit inputs the audio data of the meeting into the generation AI and analyzes the progress of the meeting. The generation AI analyzes the audio data and dynamically adjusts the evaluation criteria for comments. Furthermore, at the end of the meeting, the analysis unit comprehensively evaluates all comments and provides a final analysis result. The analysis unit uses the generation AI to analyze the progress of the meeting. The generation AI analyzes the audio and video data of the meeting to understand the progress of the meeting. For example, the analysis unit inputs the audio data of the meeting into the generation AI and analyzes the progress of the meeting. The generation AI analyzes the audio data and comprehensively evaluates all comments. This allows the analysis results to be updated in real time according to the progress of the meeting, making it possible to provide the latest information.

[0117] The feedback delivery department can customize the content of the feedback depending on the speaker's position and experience. For example, the feedback delivery department provides new employees with feedback regarding basic communication skills. The feedback delivery department uses a generation AI to analyze the speaker's position and experience. The generation AI analyzes the speaker's position and experience data and generates appropriate feedback. For example, the feedback delivery department inputs the speaker's position and experience data into the generation AI to generate feedback content. The generation AI analyzes the speaker's position and experience and generates feedback appropriate for new employees. The feedback delivery department also provides mid-level employees with feedback regarding leadership and teamwork. The feedback delivery department uses a generation AI to analyze the speaker's position and experience. The generation AI analyzes the speaker's position and experience data and generates appropriate feedback. For example, the feedback delivery department inputs the speaker's position and experience data into the generation AI to generate feedback content. The generation AI analyzes the speaker's position and experience and generates feedback appropriate for mid-level employees. The feedback delivery department also provides managers with feedback regarding strategic thinking and decision-making. The provision unit uses the generation AI to analyze the speaker's job title and experience. The generation AI analyzes the speaker's job title and experience data and generates appropriate feedback. For example, the provision unit inputs the speaker's job title and experience data into the generation AI and generates feedback content. The generation AI analyzes the speaker's job title and experience and generates feedback suitable for a managerial position. This makes it possible to provide appropriate feedback according to the speaker's job title and experience.

[0118] The collection unit can dynamically change the scope of data to be collected depending on the type and purpose of the meeting. For example, in a brainstorming meeting, the collection unit collects all comments. The collection unit uses the generation AI to determine the type and purpose of the meeting. The generation AI analyzes the content and agenda of the meeting to determine the type and purpose of the meeting. For example, the collection unit inputs the content of the meeting into the generation AI and determines the type and purpose of the meeting. The generation AI analyzes the content of the meeting and determines that it is a brainstorming meeting. In addition, in a project progress meeting, the collection unit prioritizes collecting comments related to important decisions and action items. The collection unit uses the generation AI to analyze the content of the meeting and identify important comments. For example, the collection unit inputs the content of the meeting into the generation AI and identifies important comments. The generation AI analyzes the content of the meeting and identifies comments related to important decisions and action items. In addition, in regular meetings, the collection unit sets the scope of data to be collected for each agenda item and collects only the necessary parts. The collection unit uses the generation AI to analyze the agenda of the meeting and set the scope of data to be collected. For example, the collection unit inputs the meeting agenda into the generation AI and sets the range of data to be collected. The generation AI then analyzes the meeting agenda and collects only the necessary parts. This allows the necessary data to be collected efficiently by dynamically changing the range of data depending on the type and purpose of the meeting.

[0119] The analysis unit can estimate the user's emotions and adjust the analysis algorithm based on the estimated user emotions. For example, if the user is nervous, the analysis will focus on changes in emotions. The analysis unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the analysis unit inputs voice data into the generation AI to estimate the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of tension. Furthermore, if the user is relaxed, the analysis will focus on the content of the utterances. The analysis unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the analysis unit inputs voice data into the generation AI to estimate the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of relaxation. Furthermore, if the user is concentrating, the analysis will focus on the logical structure of the utterances. The analysis unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to infer the user's emotions. For example, the analysis unit inputs voice data into the generation AI and infers the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of concentration. This allows for more appropriate analysis by adjusting the analysis algorithm according to the user's emotions.

[0120] The providing unit can estimate the user's emotions and adjust the way feedback is expressed based on the estimated user's emotions. For example, if the user is nervous, the providing unit provides feedback in gentler terms. The providing unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the providing unit inputs voice data into the generation AI to estimate the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of tension. Furthermore, if the user is relaxed, the providing unit provides detailed feedback. The providing unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the providing unit inputs voice data into the generation AI to estimate the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of relaxation. Furthermore, if the user is concentrating, the providing unit provides feedback that highlights specific areas for improvement. The providing unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the providing unit inputs voice data into the generation AI and estimates the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of concentration. This allows the system to provide more appropriate feedback by adjusting the way feedback is expressed according to the user's emotions.

[0121] The collection unit can estimate the user's emotions and adjust the timing of collecting recorded data based on the estimated user's emotions. For example, if the user is nervous, the collection unit starts recording when the user is relaxed, rather than immediately after the start of the meeting. The collection unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the collection unit inputs voice data into the generation AI and estimates the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of tension. Furthermore, if the user is relaxed, the collection unit starts recording before an important topic in the meeting begins. The collection unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the collection unit inputs voice data into the generation AI and estimates the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of relaxation. Furthermore, if the user is concentrating, the collection unit starts recording in the middle or end of the meeting. The collection unit uses the generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the collection unit inputs voice data into the generation AI and estimates the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of concentration. This allows for more appropriate data collection by adjusting the timing of collecting recorded data according to the user's emotions.

[0122] The analysis unit can apply different analysis methods based on the content of the utterance to perform a detailed evaluation. For example, the analysis unit uses voice recognition technology to evaluate the clarity of the utterance. The analysis unit uses a generation AI to analyze the content of the utterance. The generation AI analyzes the audio data and evaluates the clarity of the utterance. For example, the analysis unit inputs audio data into the generation AI and evaluates the clarity of the utterance. The generation AI analyzes the audio data and evaluates the accuracy of pronunciation and the clarity of the voice. The analysis unit also uses natural language processing technology to evaluate the logical structure of the utterance. The analysis unit uses a generation AI to analyze the content of the utterance. The generation AI analyzes the audio data and evaluates the logical consistency of the utterance and the clarity of the argument. For example, the analysis unit inputs audio data into the generation AI and evaluates the logical structure of the utterance. The generation AI analyzes the audio data and evaluates the logical consistency of the utterance and the clarity of the argument. Furthermore, the analysis unit analyzes the flow of the conversation to evaluate the appropriate timing of the utterance. The analysis unit uses a generation AI to analyze the content of the utterance. The generation AI analyzes the voice data and evaluates the timing of the speech. For example, the analysis unit inputs the voice data into the generation AI and evaluates the timing of the speech. The generation AI analyzes the voice data and evaluates the appropriate spacing and timing of the speech. This allows for a detailed evaluation by applying different analysis methods based on the content of the speech.

[0123] The providing unit can dynamically change the timing of providing feedback depending on the progress of the meeting. For example, the providing unit provides feedback immediately after the end of the meeting. The providing unit uses the generation AI to analyze the progress of the meeting. The generation AI analyzes the audio data and video data of the meeting to understand the progress of the meeting. For example, the providing unit inputs the audio data of the meeting into the generation AI and analyzes the progress of the meeting. The generation AI analyzes the audio data and identifies the end of the meeting. Furthermore, the providing unit provides feedback immediately after an important comment is made during the meeting. The providing unit uses the generation AI to analyze the progress of the meeting. The generation AI analyzes the audio data and video data of the meeting to understand the progress of the meeting. For example, the providing unit inputs the audio data of the meeting into the generation AI and analyzes the progress of the meeting. The generation AI analyzes the audio data and identifies important comments. Furthermore, the providing unit provides feedback at appropriate times as the meeting progresses. The providing unit uses the generation AI to analyze the progress of the meeting. The generation AI analyzes the audio and video data of the meeting to understand the progress of the meeting. For example, the providing unit inputs the audio data of the meeting into the generation AI and analyzes the progress of the meeting. The generation AI analyzes the audio data and provides feedback at the appropriate time. This allows feedback to be provided at the appropriate time depending on the progress of the meeting.

[0124] The tracking unit can estimate the user's emotions and adjust the method for tracking the progress of improvement based on the estimated user emotions. For example, if the user is tense, a simple and highly visible tracking method is provided. The tracking unit uses a generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the tracking unit inputs voice data into the generation AI to estimate the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of tension. Furthermore, if the user is relaxed, a tracking method that includes detailed information is provided. The tracking unit uses a generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the tracking unit inputs voice data into the generation AI to estimate the user's emotions. The generation AI analyzes the voice data and evaluates the user's level of relaxation. Furthermore, if the user is concentrating, a tracking method that focuses on the key points is provided. The tracking unit uses a generation AI to estimate the user's emotions. The generation AI analyzes voice data and facial expression data to estimate the user's emotions. For example, the tracking unit inputs voice data into the generation AI and estimates the user's emotions. The generation AI then analyzes the voice data and evaluates the user's level of concentration. This enables highly visible tracking by adjusting the method for tracking the progress of improvement according to the user's emotions.

[0125] The analysis unit can emphasize specific evaluation criteria based on the theme of the meeting. For example, if the theme of the meeting is project management, the analysis unit emphasizes the clarity of the progress report. The analysis unit uses the generation AI to analyze the theme of the meeting. The generation AI analyzes the content of the meeting and identifies the theme. For example, the analysis unit inputs the content of the meeting into the generation AI and identifies the theme. The generation AI analyzes the content of the meeting and identifies that the theme is project management. Furthermore, if the theme of the meeting is brainstorming, the analysis unit emphasizes creativity and the proposal of new ideas. The analysis unit uses the generation AI to analyze the theme of the meeting. The generation AI analyzes the content of the meeting and identifies the theme. For example, the analysis unit inputs the content of the meeting into the generation AI and identifies the theme. The generation AI analyzes the content of the meeting and identifies that the theme is brainstorming. Furthermore, if the theme of the meeting is problem solving, the analysis unit emphasizes logical structure and the proposal of solutions. The analysis unit uses the generation AI to analyze the theme of the meeting. The generation AI analyzes the content of the meeting and identifies the theme. For example, the analysis unit inputs the contents of a meeting into the generation AI and identifies the theme. The generation AI then analyzes the contents of the meeting and identifies that the theme is problem-solving. This enables appropriate evaluation by emphasizing specific evaluation criteria based on the theme of the meeting.

[0126] The processing flow of the second embodiment will be briefly explained below.

[0127] Step 1: The collection unit records conversations in online meetings. For example, the collection unit collects audio data of the meetings and stores it in a digital format. The collection unit has the function of recording the audio data of the meetings in high quality and removing noise. For example, the collection unit records the audio of the meetings in real time and uses noise reduction technology to generate clear audio data. The collection unit can also collect video data of the meetings. For example, the collection unit records the video of the meetings in high resolution and synchronizes it with the audio data. Step 2: The analysis unit uses the generation AI to analyze the data collected by the collection unit. For example, the analysis unit analyzes audio data from a meeting to evaluate the content of what is said and how it is spoken. The analysis unit uses the generation AI to evaluate the clarity of what is said, its logical structure, and the appropriate timing of what is said. For example, the analysis unit inputs audio data into the generation AI to evaluate the clarity of what is said. The generation AI analyzes the audio data to evaluate the accuracy of pronunciation and the clarity of the voice. The analysis unit also uses the generation AI to evaluate the logical structure of what is said. The generation AI analyzes the audio data to evaluate the logical consistency of what is said and the clarity of the points being made. Furthermore, the analysis unit uses the generation AI to evaluate the timing of what is said. The generation AI analyzes the audio data to evaluate the appropriate spacing and timing of what is said. Step 3: The providing unit provides feedback based on the analysis results obtained by the analyzing unit. For example, the providing unit provides feedback on specific areas for improvement or merits based on the analysis results. The providing unit uses the generating AI to generate the content of the feedback. For example, the providing unit inputs the analysis results into the generating AI to generate the content of the feedback. Based on the analysis results, the generating AI provides advice for improving the clarity of speech and advice for maintaining a logical structure. Step 4: The tracking unit tracks the progress of improvement due to user registration. For example, the tracking unit references the user's past feedback history and visually displays the progress of improvement. The tracking unit uses the generation AI to track the progress of improvement. For example, the tracking unit inputs the user's feedback history into the generation AI and analyzes the progress of improvement. The generation AI evaluates the growth of the user's communication skills based on the feedback history and visually displays it.

[0128] 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.

[0129] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). 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 (e.g., still image data or video data). 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 one or more data formats of voice data, text data, image data, etc. 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 may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0130] 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.

[0131] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0132] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0133] 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.

[0134] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0135] The 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.

[0136] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0137] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (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).

[0138] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0146] 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.

[0147] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0148] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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).

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0159] 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.

[0160] 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.

[0161] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0162] 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.

[0163] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0164] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0165] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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).

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0176] 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.

[0177] 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.

[0178] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0179] 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.

[0180] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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).

[0185] 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.

[0186] 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."

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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, in order to avoid confusion and to 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.

[0198] 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.

[0199] [Explanation of symbols]

[0200] 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 collection unit that collects recording data; an analysis unit that analyzes the data collected by the collection unit; a providing unit that provides feedback based on the analysis result obtained by the analyzing unit; A tracking unit that tracks the progress of improvements due to user registration. A system characterized by:

2. Equipped with a setting unit for setting evaluation criteria 2. The system of claim 1.

3. A generator for generating feedback content is provided.

2. The system of claim 1.

4. Equipped with a display that visually shows the progress of improvements 2. The system of claim 1.

5. The analysis unit Evaluate the clarity, logical structure, and timing of your speech.

2. The system of claim 1.

6. The providing unit Give specific feedback on areas for improvement and excellence 2. The system of claim 1.

7. The collecting unit The system estimates the user's emotions and adjusts the timing of collecting audio recording data based on the estimated user emotions.

2. The system of claim 1.

8. The collecting unit Dynamically change the scope of data collected depending on the type and purpose of the meeting 2. The system of claim 1.

Images