System

Abstract

A system is provided.SOLUTION: A system comprising: means for capturing and transmitting video and audio of a meeting from terminals; means for storing the received video and audio at a server; means for analyzing the stored video and audio and generating feedback according to a generation AI; and means for transmitting the generated feedback to the terminals.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] A facilitator is essential for effectively conducting a meeting, but facilitators rarely have the opportunity to receive objective feedback on their facilitation, making it difficult for them to improve their skills. Furthermore, whether online or offline, manually recording and analyzing meetings is time-consuming and labor-intensive, making it inefficient. This invention aims to solve these problems and provide facilitators with quick, objective feedback. [Means for solving the problem]

[0005] The present invention is a system that includes a means for capturing and transmitting video and audio data of a conference from a terminal, a means for storing the received data on a server, a means for analyzing the stored data and generating feedback using a generation AI, and a means for transmitting the generated feedback to the terminal. When the server analyzes the conference data, it evaluates each participant's frequency of speech and question-and-answer patterns to provide specific feedback on the progress of the conference. Furthermore, by capturing conference data in real time on the terminal and transmitting the data to the server at regular intervals, it becomes possible to grasp the strengths and areas for improvement of facilitation in real time or at a later time. This allows facilitators to objectively evaluate their own skills and improve them efficiently.

[0006] A "terminal" is an electronic device that has the function of capturing video and audio data of a conference and transmitting it to a server.

[0007] The "server" is a computer system that stores the meeting data received from the terminal, analyzes the data, and generates feedback using a generation AI.

[0008] "Generative AI" is an artificial intelligence technology that analyzes stored meeting data and generates specific feedback.

[0009] "Feedback" is information that specifically identifies strengths and areas for improvement regarding the progress of the meeting.

[0010] "Analysis" is the process of evaluating meeting data and extracting patterns of participant speech frequency and question and answer sessions.

[0011] "Real time" means that processing or reaction occurs immediately in real time.

[0012] "Regular intervals" refers to the timing at which data is transmitted at equal intervals.

[0013] "Speech frequency" refers to the number of times each participant spoke during the conference.

[0014] "Question and answer patterns" refer to the tendency and format of questions and answers exchanged during a meeting. [Brief explanation of the drawings]

[0015] [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. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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, a 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), and an APU (Accelerated Processing Unit).

[0019] 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.

[0020] 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.

[0021] 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), Bluetooth (registered trademark), etc.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the 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).

[0027] 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.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. 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 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] This invention is a system that allows facilitators to receive objective and prompt feedback during or after a meeting. This system works effectively by combining terminals, a server, and a generative AI.

[0037] Device behavior

[0038] At the start of a meeting, the device activates its camera and microphone and captures video and audio data of the meeting in real time. This data includes video information, audio information, and metadata (e.g., who is speaking, the progress of the meeting, etc.) for each frame. The device transmits this data to the server at regular intervals.

[0039] For example, the device can be a PC or smartphone, and when a meeting starts, it automatically activates the camera and microphone to start capturing data. The captured data is periodically analyzed and sent to a server along with metadata.

[0040] Server Operation

[0041] The server receives the meeting data sent from the devices and temporarily stores it in local storage or a database. The stored data is then analyzed by the generative AI, which analyzes the meeting content from multiple angles and generates feedback to specifically identify the facilitator's strengths and areas for improvement. The feedback includes the frequency with which each participant spoke, patterns of question and answer sessions, best practices for the proceedings, and areas for improvement.

[0042] For example, after receiving the meeting data, the server analyzes each frame to extract and analyze information such as who spoke how much, how questions were asked, etc. Based on the analysis results, it generates feedback such as "Participant A spoke frequently" or "The facilitator is giving everyone a chance to speak, but one participant is talking too much."

[0043] User Use

[0044] Users can receive the feedback sent from the server on their devices and view the specific details. Based on the feedback they receive, users can identify areas for improvement and strengths in their facilitation skills and reflect these in their next meeting.

[0045] For example, after a meeting, users can receive feedback such as "Many participants were given the opportunity to speak" or "Time allocation was unbalanced due to too much focus on a particular topic." This allows users to incorporate improvements to ensure everyone has a balanced opportunity to speak in the next meeting.

[0046] System Features

[0047] The system's features include real-time data capture and analysis, advanced feedback generation using generative AI, and rapid feedback provision, allowing facilitators to receive immediate feedback on the spot or after the meeting, enabling them to make timely improvements.

[0048] ---

[0049] The system of the present invention supports the effective progress of meetings and the improvement of facilitation skills through the cooperation of hardware and software, which is expected to lead to efficient and productive meeting management.

[0050] The processing flow will be explained below.

[0051] Step 1:

[0052] Device: At the start of a meeting, start the camera and microphone to capture video and audio data of the meeting. This prepares the device to obtain real-time information about the progress of the meeting. For example, start the camera using cv2.VideoCapture(0).

[0053] Step 2:

[0054] Device: Analyzes captured video and audio data frame by frame to generate important metadata (e.g., which participants are speaking, and what is happening in the meeting). This includes image and audio analysis of each frame.

[0055] Step 3:

[0056] Terminal: Analyzed data is sent to the server at regular intervals (e.g., every minute). This allows data to be accumulated on the server in real time. For example, data is sent using an HTTP request.

[0057] Step 4:

[0058] Server: Receives the meeting data sent from the devices and temporarily stores it in local storage or a database, ensuring the data necessary for subsequent analysis.

[0059] Step 5:

[0060] Server: Passes the saved data to the generation AI and begins analyzing the meeting data. The generation AI evaluates the frequency of each participant's comments, question and answer patterns, and the progress of the meeting from various angles.

[0061] Step 6:

[0062] Server: Creates feedback based on the analysis results of the generative AI. This feedback includes the facilitator's strengths and areas for improvement. Specifically, it lists specific points such as "certain participants speak too much" or "the facilitator gives everyone an opportunity to speak."

[0063] Step 7:

[0064] Server: Sends the created feedback to the device, allowing users to receive feedback in real time or after the meeting ends.

[0065] Step 8:

[0066] User: Receive and review the feedback sent by the server, identify specific areas for improvement and strengths, and improve your skills for the next meeting.

[0067] Step 9:

[0068] Users: Based on the feedback they receive, they can take practical steps to improve their facilitation skills, leading to more effective meetings in the future.

[0069] Through these steps, the meeting facilitation feedback system utilizing generative AI completes a series of operations.

[0070] Example 1

[0071] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0072] It is difficult to objectively evaluate whether a meeting is being conducted properly and receive prompt feedback. Facilitators face the challenge of having to spend a lot of time and effort tracking who spoke and how much, and how questions were asked. This can also lead to a decline in the quality of the meeting.

[0073] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0074] In this invention, the server includes means for capturing and transmitting video and audio data of the conference from the terminal, means for storing the data received by the server, means for analyzing the stored data using a generative AI model to generate feedback, and means for transmitting the generated feedback to the terminal. This allows the facilitator to receive prompt and objective feedback during and after the conference, enabling efficient conference management and skill improvement.

[0075] "Terminals" refer to electronic devices that capture video and audio data of meetings in real time and send them to a server. Specifically, these devices include PCs and smartphones.

[0076] "Server" refers to a central processing unit that receives, stores, and analyzes meeting data sent from devices. The server may be installed in a cloud service or an on-premise data center.

[0077] A "generative AI model" is an artificial intelligence model that analyzes audio and video data from meetings and generates feedback. Specifically, it uses natural language processing and image recognition technology to perform the analysis.

[0078] "Feedback" refers to information generated based on the analysis results that provides specific evaluations and areas for improvement for the facilitator and meeting participants, and suggests specific actions to improve the quality of the meeting.

[0079] "Video data" refers to video information captured by a camera during a meeting that can be electronically stored and transmitted. Video data includes visual information such as the movements and facial expressions of participants.

[0080] "Audio Data" means audio information recorded by microphone during a meeting in a format that can be stored and transmitted electronically. Audio Data includes the voices of the speakers and the content of the conversation.

[0081] "Metadata" refers to information that accompanies video and audio data, such as who is speaking, the progress of the conversation, and timestamps of what is being said.

[0082] "Analysis" refers to the process of extracting characteristics and patterns from collected video and audio data using certain algorithms and AI models to provide specific evaluations and feedback.

[0083] "Storage" refers to storing received conference data in local storage or a database so that it can be analyzed or referenced later. Storing data enables sustainable management of data.

[0084] "Capture" refers to the process of capturing and electronically recording video and audio data using cameras and microphones while a meeting is in progress, allowing for real-time data collection.

[0085] The present invention is a system that allows facilitators to receive objective and prompt feedback during and after a meeting. The system works effectively by combining devices, servers, and generative AI models.

[0086] Device behavior

[0087] At the start of a meeting, the device activates its camera and microphone and captures video and audio data of the meeting in real time. This data includes video information, audio information, and metadata (e.g., who is speaking, the progress of the meeting, etc.) for each frame. The device transmits this data to the server at regular intervals.

[0088] Specific examples

[0089] For example, if the device is a PC or smartphone, when the meeting starts, it will automatically activate the camera and microphone to start capturing data. The captured data is periodically sent to the server, which receives and stores it.

[0090] Server Operation

[0091] The server receives the meeting data sent from the devices and temporarily stores it in local storage or a database. The stored data is then analyzed by a generative AI model. The generative AI model analyzes the meeting content from multiple angles and generates feedback to specifically identify the facilitator's strengths and areas for improvement. The feedback includes each participant's frequency of speech, question and answer patterns, best practices for the proceedings, and areas for improvement.

[0092] Specific examples

[0093] For example, after receiving the meeting data, the server analyzes each frame to extract and analyze information such as who spoke how much, how questions were asked, etc. Based on the analysis results, it generates feedback such as "Participant A spoke frequently" or "The facilitator is giving everyone a chance to speak, but one participant is talking too much."

[0094] User Use

[0095] Users can receive the feedback sent from the server on their devices and view the specific details. Based on the feedback they receive, users can identify areas for improvement and strengths in their facilitation skills and reflect these in their next meeting.

[0096] Specific examples

[0097] For example, users can receive feedback after a meeting, such as "We gave many participants the opportunity to speak" or "We focused too much on a particular topic and the time allocation was unbalanced." This allows them to incorporate improvements in the next meeting to ensure everyone has a balanced opportunity to speak.

[0098] Prompt Sentence Examples

[0099] "Analyze who spoke and how much during the meeting, and provide feedback on participants' speaking frequency and question-and-answer patterns."

[0100] This allows users to quickly and objectively identify areas for improvement during meetings, and is expected to lead to more efficient meeting management and improved facilitation skills.Specific hardware and software used include PCs and smartphones as terminals, cloud servers and databases as servers, and natural language processing models as generative AI models.

[0101] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0102] Step 1:

[0103] The device will automatically activate its camera and microphone at the start of the meeting, allowing it to begin capturing video and audio data in real time.

[0104] Requirement as input: Trigger to start a conference (user starts a conference).

[0105] Specific operation: When the PC or smartphone receives the "Start" button for the meeting, the camera and microphone are activated.

[0106] Output: A stream of real-time video and audio data is captured.

[0107] Step 2:

[0108] The device adds metadata (such as who is speaking and the progress of the conference) to the captured video and audio data, and sends this to the server at regular intervals.

[0109] Input requirements: Captured video and audio data.

[0110] Specific operation: Adds speaker recognition and timestamps to video and audio data.

[0111] Output: Packs of video and audio data with metadata are generated.

[0112] Step 3:

[0113] The server receives the conference data (video, audio, metadata) sent from the terminals and stores it in local storage or a database.

[0114] Input requirements: Meeting data with metadata.

[0115] Specific operation: After the server receives the data, it stores it in cloud storage such as AWS S3 or RDS.

[0116] Output: Saved meeting data.

[0117] Step 4:

[0118] The server inputs the saved meeting data into the generative AI model, analyzes the data, and uses the generative AI model to generate feedback.

[0119] Requirements as input: Saved meeting data.

[0120] Specific operation: Input the saved meeting data into a generative AI model (e.g., a natural language processing model) and analyze the frequency of comments and question and answer patterns.

[0121] Output: Feedback information based on the analysis results.

[0122] Step 5:

[0123] The server compiles the feedback generated by the generative AI model and sends it to the device.

[0124] Requirements as input: Feedback generated by a generative AI model.

[0125] Specific operation: The feedback information is formatted based on a template and sent to the terminal.

[0126] Output: The formatted feedback data is sent to the terminal.

[0127] Step 6:

[0128] The user can view the feedback received through the device and check the specific content.

[0129] Requirement as input: Feedback data sent by the server.

[0130] Specific operation: The user logs in to the feedback email or dedicated web portal on the device to view the feedback.

[0131] Output: User reviews the feedback and gets specific improvements for the next meeting.

[0132] (Application example 1)

[0133] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0134] Conventional meeting progress and feedback systems do not adequately capture real-time data or provide prompt feedback, resulting in limited improvements in meeting efficiency and facilitation skills. Furthermore, efficient communication is required for meetings and work instructions at production sites and factories, but current systems do not provide sufficient support. Therefore, a new system is needed to improve the quality of meetings.

[0135] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0136] In this invention, the server includes a means for capturing and transmitting video and audio data of the conference from the terminal, a means for storing the received data, a means for analyzing the stored data and generating feedback using a generation AI, a means for providing prompt feedback to the facilitator during or after the conference, a means for supporting the efficiency of meetings and work instructions within the factory, and a means for transmitting the generated feedback to the terminal. This enables the capture and analysis of conference data in real time, realizing the provision of prompt and effective feedback. Furthermore, it supports efficient communication and work instructions within the factory, improving the quality of meetings at the production site.

[0137] A "terminal" is a computing device used to capture and transmit video and audio data to a server.

[0138] "Video data" refers to video information that visually records the progress of the conference and the appearance of each participant.

[0139] "Audio data" refers to acoustic information used to record statements and conversations made during a meeting.

[0140] "Capture" is the process of collecting video and audio data and storing it in digital form.

[0141] "Send" is the operation of moving data from a terminal to a server via a network.

[0142] A "server" is a multi-computing device for storing and analyzing received video and audio data.

[0143] "Storage" is the process of storing data in storage for later use.

[0144] "Analysis" refers to data processing operations that process stored data and extract useful information.

[0145] "Generative AI" is a system that uses artificial intelligence technology to generate feedback and advice based on various data.

[0146] "Feedback" is a response that provides participants and facilitators with information about the meeting's evaluation, areas for improvement, strengths, etc.

[0147] A "facilitator" is a person whose role is to manage the progress of a meeting and promote dialogue among participants.

[0148] "Fast" refers to the property of reacting or processing within a short period of time.

[0149] A "factory" is a facility for manufacturing products.

[0150] "Work instructions" are instructions that clearly state the work content and procedures within a factory.

[0151] "Efficiency" means achieving maximum results while minimizing the use of resources and time.

[0152] The present invention is a system that streamlines meetings and provides prompt and objective feedback to facilitators. This system functions effectively by combining a terminal, a server, and a generative AI model. Specific embodiments are described below.

[0153] Hardware Configuration

[0154] Terminal: A device used to capture video and audio data from a meeting. Examples include a PC or smartphone. A camera and microphone are connected to the terminal, and data is collected using these devices.

[0155] Server: A computer that stores and analyzes received video and audio data. The server includes local storage or a database.

[0156] Software Configuration

[0157] Data capture module: Executed by the device, it activates the camera and microphone at the start of the meeting and captures data in real time. The captured data is sent to the server at regular intervals.

[0158] Data storage module: Runs on the server, receives data sent from the device, and stores it in local storage or a database.

[0159] Data analysis module: A program for analyzing data stored on the server. This module uses a generative AI model (e.g., GPT-3) to analyze the meeting content from multiple angles.

[0160] Feedback generation module: Based on the information obtained from the data analysis module, feedback is generated to specifically identify the facilitator's strengths and areas for improvement. The generated feedback is sent to the device.

[0161] User interface: Runs on the device and allows the user to view the generated feedback. Specific feedback is displayed as text information.

[0162] Data Flow and Processing

[0163] Terminal: When the meeting starts, the data capture module activates the camera and microphone to capture video and audio in real time. The captured data includes metadata such as video information for each frame, audio information, and the progress of the meeting. This data is sent to the server at regular intervals.

[0164] Server: Stores the received meeting data and analyzes it using a generative AI model. The analysis evaluates each participant's frequency of speech, patterns of Q&A, and best practices and areas for improvement in the proceedings. For example, the server may extract information such as "Participant A speaks frequently" or "Participant A is too focused on a particular topic."

[0165] Feedback generation module: Based on the analysis results, specific feedback is generated for the facilitator, such as "You gave many participants the opportunity to speak" or "The time allocation was unbalanced."

[0166] User reception: The generated feedback is sent to the device, and the user can view it and use it to improve the next meeting. Specifically, the user can incorporate improvement measures such as "giving everyone a chance to speak in the next meeting."

[0167] Specific examples and generative AI model prompts

[0168] As a concrete example, consider a work instruction meeting in a factory. Using this system, data from the meeting is captured and analyzed. The generating AI provides feedback such as "points where the order of work instructions should be improved" and "points where communication went smoothly."

[0169] Example prompts for generative AI models:

[0170] Analyze the following data and generate feedback on the facilitators' strengths and areas for improvement:

[0171] Meeting data: [Audio and video data of the meeting]

[0172] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0173] Step 1:

[0174] Device-based data capture

[0175] When a meeting starts, the device activates its camera and microphone and captures the video and audio data of the meeting in real time. The video and audio of the meeting are given as input, and this is collected as digital data. Specifically, the device obtains video information, audio information, and metadata (such as who is speaking and the progress of the meeting) for each frame. This records the progress of the meeting. The output is the captured data.

[0176] Step 2:

[0177] Sending data from the device to the server

[0178] The device sends the captured video and audio data to the server at regular intervals. The data captured in step 1 is given as input, and this data is sent to the server via the network. Specifically, the data is sent using a protocol such as HTTP, which allows the server to receive the data. The output is the sent data.

[0179] Step 3:

[0180] Data storage by server

[0181] The server stores the video and audio data received from the device in local storage or a database. The input is the data sent from the device, and this data is stored for efficient management. Specifically, the data is stored using a database management system (e.g., MySQL or PostgreSQL). This ensures that the data is available for subsequent analysis processes. The output is the stored data.

[0182] Step 4:

[0183] Data analysis

[0184] The server analyzes the stored data and uses a generative AI model to analyze the meeting content from multiple angles. The input is the stored data, and based on this data, it evaluates the frequency of each participant's comments, question and answer patterns, and best practices and areas for improvement in the proceedings. Specifically, it uses machine learning libraries such as TensorFlow and PyTorch to build models and perform analysis. This provides detailed evaluation information for the meeting. The output is the analysis results.

[0185] Step 5:

[0186] Feedback Generation

[0187] Based on the analysis results, the server uses a generative AI model to generate feedback that specifically identifies the facilitator's strengths and areas for improvement. The input is the analysis results, and based on these results, feedback is generated using a natural language processing model (e.g., GPT-3). Specifically, specific prompts are provided to the AI ​​model, which generates feedback in response. This results in declarative and useful feedback. The output is the generated feedback.

[0188] Step 6:

[0189] Sending and Viewing Feedback

[0190] The server sends the generated feedback to the terminal, which then displays it to the user. The input is the generated feedback, which is sent to the terminal. Specifically, the feedback content is processed as text and displayed on the user interface. This allows the user to receive feedback quickly and easily. The output is the displayed feedback.

[0191] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0192] This invention combines a feedback system for meeting facilitation with an emotion engine that recognizes the user's emotions. The main features of this system are the capture and analysis of meeting data, the generation of feedback using a generative AI, and the recognition and evaluation of the user's emotional state using an emotion engine. The operation of the terminal, server, and user is described in detail below.

[0193] Device behavior

[0194] At the start of a meeting, the device activates its camera and microphone to capture video and audio data of the meeting in real time. This data includes video and audio information for each frame, as well as metadata such as participants' facial expressions and tone of voice. The device is equipped with an emotion engine that uses the captured data to recognize the user's emotions in real time. This analysis data is then sent to a server at regular intervals.

[0195] For example, the device can be a PC or smartphone, and the camera and microphone will automatically start up when the meeting begins. The captured data is analyzed in real time by the emotion engine, and the analysis results are sent to the server. For example, it can recognize participants' emotional states, such as "tensed" or "relaxed," from their facial expressions.

[0196] Server Operation

[0197] The server receives the meeting data sent from the devices and stores it in local storage or a database. The stored data is then analyzed using a generative AI and emotion engine. The generative AI analyzes the meeting content from multiple angles and generates feedback on the facilitator's strengths and areas for improvement. The emotion engine also recognizes emotions based on participants' facial expressions and tone of voice and incorporates them into the analysis results.

[0198] For example, after receiving the meeting data, the server uses an emotion engine to analyze the emotional state of the participants for each frame. Next, the generation AI generates specific feedback based on the analysis results, such as "Participant A is nervous while speaking" or "The facilitator is helping Participant B relax."

[0199] User Use

[0200] The user receives the feedback sent from the server on their device and can view the specific details. The feedback includes not only the strengths and areas for improvement of the facilitator's progress, but also information about the emotional state of each participant. This allows the user to take measures to improve the session based on their emotional state.

[0201] For example, after a meeting, the user can review feedback such as "Many participants were given the opportunity to speak" or "Participant A is nervous because he or she is concentrating too much on a particular topic." At the next meeting, the user can refer to the analysis results of the emotion engine and develop measures to improve the emotional state of the participants.

[0202] System Features

[0203] The system's features include real-time data capture and analysis, advanced feedback generation using generative AI, and user emotional recognition using an emotion engine. Facilitators can adjust the progress of the meeting while understanding the emotional state of the participants, and after the meeting, they can take advantage of detailed feedback to make improvements for the next meeting.

[0204] ---

[0205] The system of the present invention integrates hardware and software to support the effective progress of meetings and the improvement of facilitation skills, which is expected to lead to efficient and productive meeting management.

[0206] The processing flow will be explained below.

[0207] Step 1:

[0208] Device: When a meeting starts, the camera and microphone are activated to capture video and audio data of the meeting in real time. For example, when a meeting starts, the camera and microphone are automatically activated, so that the device is ready to capture the entire meeting.

[0209] Step 2:

[0210] Device: Analyzes video and audio data in real time and recognizes participants' emotions through an emotion engine. Specifically, it identifies emotions such as "joy," "anger," "sadness," and "relaxation" based on information such as participants' facial expressions, tone of voice, and volume.

[0211] Step 3:

[0212] Device: Captured video and audio data, along with associated emotional data, is sent to the server at regular intervals (e.g., every minute). This allows the data to be accumulated on the server in real time. For example, the data is sent via an HTTP request.

[0213] Step 4:

[0214] Server: Receives the meeting data sent from the devices and stores it in local storage or a database, allowing the data required for analysis to be saved and used for subsequent processing.

[0215] Step 5:

[0216] Server: The received data is passed to the generation AI and emotion engine and analysis begins. The data is evaluated from multiple angles, including the frequency of each participant's speech, the content of the conversation, facial expressions, and tone of voice.

[0217] Step 6:

[0218] Server: Creates feedback based on the analysis results. The feedback includes the facilitator's strengths and areas for improvement in the process, as well as the emotional state of each participant. For example, the server lists specific points such as "Participant A seemed nervous while speaking" or "Participant B seemed relaxed."

[0219] Step 7:

[0220] Server: Sends the created feedback to the device, allowing users to receive feedback in real time or after the meeting ends.

[0221] Step 8:

[0222] User: Receives and reviews feedback sent from the server, identifies specific areas for improvement, strengths, and participants' emotional state, and considers measures for the next meeting.

[0223] Step 9:

[0224] Users: Based on the feedback they receive, they can take practical steps to improve their facilitation skills, leading to more effective meetings in the future.

[0225] Through these steps, the meeting facilitation feedback system, which combines generative AI and an emotion engine, completes a series of operations.

[0226] Example 2

[0227] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0228] Conventional online meeting systems have the problem of making it difficult to grasp the progress of the meeting and the emotional state of participants in real time. As a result, facilitators are unable to receive appropriate feedback, which can lead to a decline in the quality and efficiency of the meeting. Furthermore, there is a lack of information to identify specific areas for improvement after the meeting, which can lead to the same issues recurring in the next meeting.

[0229] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0230] In this invention, the server includes means for capturing and transmitting video and audio data of the conference from the terminals, means for analyzing the captured data in real time using an emotion engine and recognizing the user's emotion, means for saving the data received by the server, means for analyzing the saved data using a generative AI model and the emotion engine and generating feedback, and means for sending the generated feedback to the terminals, thereby enabling the facilitator to receive specific and real-time feedback during and after the conference.

[0231] A "terminal" is a computing device for capturing and analyzing video and audio data of a conference in real time.

[0232] The "emotion engine" is a software module that analyzes captured video and audio data to recognize the user's emotional state.

[0233] A "server" is a high-performance computing system that receives and stores data sent from a terminal and performs further analytical processing.

[0234] The "generative AI model" is an artificial intelligence algorithm that analyzes the content of a meeting from multiple perspectives and generates feedback that includes the facilitator's strengths and areas for improvement.

[0235] "Feedback" is the analysis result of the generative AI model and emotion engine, including an evaluation of the meeting's progress and areas for improvement.

[0236] "Data capture" is the process of capturing video and audio of a meeting in real time.

[0237] "Data transmission" is the process of sending captured video and audio data and analysis results from the terminal to the server.

[0238] "Data storage" is the process by which the server records the received data in local storage or a database.

[0239] This invention combines a feedback system for meeting facilitation with an emotion engine that recognizes the user's emotions. The main features of this system are the capture and analysis of meeting data, the generation of feedback using a generative AI, and the recognition and evaluation of the user's emotional state using an emotion engine. This system performs specific operations on the terminal, server, and user. Each operation is explained in detail below.

[0240] Device behavior

[0241] The device automatically activates its camera and microphone as soon as the meeting begins, preparing to capture the meeting's video and audio data in real time. The device is equipped with an emotion engine that uses the captured data to recognize participants' emotions in real time. This recognized emotion data is sent to the server at regular intervals.

[0242] Example: When a user opens a conference app on their PC or smartphone and presses the "Start Conference" button, the camera and microphone are automatically activated. As the conference progresses, the device's emotion engine captures the video and audio data of the participants, recognizes their emotional states in real time, such as "Participant A is nervous while speaking" or "Participant B is relaxed," and sends this data to the server.

[0243] Server Operation

[0244] The server receives the emotion data and video / audio data sent from the device and first stores it in local storage or a database. The stored data is then analyzed using a generative AI model and emotion engine. The generative AI model analyzes the text data of the meeting content from multiple angles and generates feedback based on the facilitator's strengths and areas for improvement. At the same time, the emotion engine analyzes the emotion data and incorporates the results into the analysis results of the generative AI model.

[0245] Example: The server receives the meeting data and uses an emotion engine to analyze the participants' emotional states for each frame. Based on this, the generative AI model generates specific feedback, such as "Participant A was feeling tense while speaking" or "The facilitator is creating a relaxed atmosphere for Participant B."

[0246] User Use

[0247] After the meeting, users receive feedback sent from the server on their devices and check the content. The feedback includes not only the facilitator's strengths and areas for improvement in the meeting's progress, but also information about the participants' emotional states. This allows users to take measures to improve the meeting based on their emotional states.

[0248] Example: After a meeting, a user opens a feedback report in the meeting app and sees detailed feedback such as "Many participants were given the opportunity to speak" and "Participant A was nervous because he was too focused on a particular topic." In the next meeting, the user can refer to this feedback and take measures to improve the emotional state of the participants.

[0249] Prompt Sentence Examples

[0250] "Please explain in detail the processing flow of a system that allows the facilitator to recognize participants' emotions during a meeting and provide feedback on specific areas for improvement. Please also clearly explain the roles of the terminal and server in this system."

[0251] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0252] Step 1:

[0253] As soon as the conference starts, the device automatically activates its camera and microphone to capture the conference video and audio data. At this stage, the conference video information and audio data are the input. Specifically, when the user presses the "Start Conference" button, the device's camera and microphone activate, and video and audio are captured in real time. The output is the captured video and audio data.

[0254] Step 2:

[0255] The device passes the captured data to the emotion engine for real-time analysis. The input is the captured video and audio data. The emotion engine analyzes this data and recognizes the emotional state of the participants. Specifically, the emotion engine analyzes facial expressions from the video data and tone of voice from the audio data. The output is the analyzed emotion data.

[0256] Step 3:

[0257] The device sends the analyzed emotion data to the server at regular intervals. The input is the emotion data generated by the emotion engine. Specifically, the device sets a timer and collects the emotion data into packets at regular intervals and sends them to the server. The output is the emotion data sent to the server.

[0258] Step 4:

[0259] The server receives data sent from the device and stores it in local storage or a database. The input is the emotion data sent from the device. Specifically, the server's data receiving module detects new data packets and writes them to the storage or database. The output is the stored data.

[0260] Step 5:

[0261] The server uses the stored data to perform analysis using a generative AI model and emotion engine. The input is the stored emotion data. Specifically, the emotion engine reanalyzes the emotion data, and the generative AI model analyzes the meeting content from multiple angles to generate feedback. The output is the feedback generated by the generative AI model and emotion engine.

[0262] Step 6:

[0263] The server sends the generated feedback to the terminal. The input is the generated feedback. In concrete terms, the server packs the feedback data into packets and sends them to the terminal. The output is the feedback sent to the terminal.

[0264] Step 7:

[0265] After the meeting ends, the user receives and checks the feedback on their device. The input is the feedback sent from the server. Specifically, the user opens the meeting app and presses the "View Feedback" button to display the received feedback. The output is the feedback displayed on the device.

[0266] Example prompt sentence:

[0267] "Please explain in detail the processing flow of a system that allows the facilitator to recognize participants' emotions during a meeting and provide feedback on specific areas for improvement. Please also clearly explain the roles of the terminal and server in this system."

[0268] (Application example 2)

[0269] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0270] There is a need to accurately grasp the emotional state of factory workers and provide specific feedback in real time to improve work efficiency and safety. However, currently, there is a lack of means to recognize changes in workers' mental state and stress in real time and provide appropriate feedback based on that. As a result, work efficiency can decrease and safety issues can arise. Furthermore, conventional systems do not properly evaluate workers' emotional state, making it difficult to take appropriate improvement measures.

[0271] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing and transmitting video and audio data from the terminal, means for saving the data received by the server, means for analyzing the saved data and generating feedback using a generation AI, means for sending the generated feedback to the terminal, an emotion engine for recognizing the emotions of workers based on the analyzed data, means for generating feedback regarding work efficiency and safety based on the recognized emotion data, and means for notifying on-site workers and managers of the generated feedback. This makes it possible to grasp the emotional state of workers in real time and provide specific feedback based on that.

[0272] A "terminal" is a device that has the function of capturing video and audio data and transmitting it to a server.

[0273] A "server" is a device or system that can store and analyze received data.

[0274] "Generative AI" refers to artificial intelligence technology that analyzes stored data and automatically generates feedback.

[0275] "Emotion engine" refers to technology that recognizes a person's emotional state from video and audio data.

[0276] "Work efficiency" is an indicator that shows the efficiency and productivity of workers' work.

[0277] "Safety" refers to the ability to minimize hazards in the work environment and prevent accidents and injuries.

[0278] "Feedback" refers to specific information and improvement measures generated based on analyzed data and emotional state.

[0279] "Notification" refers to the means by which generated feedback is communicated to field workers and managers in real time.

[0280] The system for implementing this invention can grasp the emotional state of workers in a factory in real time and provide specific feedback to improve work efficiency and safety. Each component of the system and its operation will be described in detail below.

[0281] Device behavior

[0282] The system's terminal is a device capable of capturing video and audio data and sending it to a server. Specifically, it has a built-in camera and microphone, which captures video and audio from the factory work area in real time. The terminal is equipped with a function to preprocess the captured data using OpenCV. Furthermore, an emotion engine is implemented using TensorFlow to recognize the emotional state of the worker from the captured data. The recognized emotion data is sent to the server at regular intervals.

[0283] Server Operation

[0284] The server receives the data sent from the terminal and stores it in a database. The stored data is analyzed by a generative AI using TensorFlow. The generative AI performs multifaceted analysis of the worker's emotional state, work efficiency, and safety, and generates specific feedback. Once the feedback is generated, it is immediately notified to the worker and manager on-site. This notification is sent via digital signage and a smartphone app.

[0285] User Use

[0286] The user receives the generated feedback on their device and views its contents. The feedback includes information on the worker's emotional state, as well as measures to improve work efficiency and safety. This allows the user to take appropriate improvement measures based on the worker's emotional state. For example, if the system recognizes that a worker is "tense," it will provide feedback such as "shorten work time" or "encourage them to take a break."

[0287] Hardware and software used

[0288] Hardware: Cameras, microphones, servers, digital signage, smartphones

[0289] Software: OpenCV, TensorFlow, database (e.g. MySQL)

[0290] Prompt Sentence Examples

[0291] Here are some examples of prompts for generative AI models:

[0292] Generate feedback based on a worker's emotional state. For example, if a worker is "tense," provide a recommended action.

[0293] Emotional state: Tense

[0294] Recommended actions: Reduce work time and encourage breaks

[0295] In this way, the system for implementing this invention can grasp the emotional state of workers in the field in real time and provide appropriate feedback immediately, which will greatly contribute to improving work efficiency and ensuring safety.

[0296] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0297] Step 1:

[0298] The terminal activates the camera and microphone to capture video and audio data of the factory work area in real time. The input is raw video and audio data from the camera and microphone. The output is the captured video and audio data. Specifically, the camera captures several frames per second, and the microphone picks up surrounding audio.

[0299] Step 2:

[0300] The device preprocesses the captured video and audio data. The input is the raw data obtained in step 1. OpenCV is used to convert the video data to grayscale, detect faces, and resize them. Preprocessing such as noise removal is performed on the audio data. The output is the preprocessed video and audio data.

[0301] Step 3:

[0302] The device inputs preprocessed video and audio data into an emotion engine using TensorFlow to recognize the worker's emotional state. The input is the preprocessed data. The emotion engine analyzes this data and identifies the emotional state (e.g., nervous, relaxed, stressed, etc.). The output is a label for the emotional state. Specifically, the emotion recognition model analyzes facial expressions and tone of voice to classify emotions.

[0303] Step 4:

[0304] The device sends the recognized emotion data to the server at regular intervals. The input is the emotional state label obtained in step 3. As an output, the emotion data is sent to the server. This involves transferring the data to the server using a communication protocol.

[0305] Step 5:

[0306] The server stores emotion data and other video and audio data received from the device. The input is the data sent from the device. The output is the received data stored in a database. Specifically, the server stores the data using a database system (e.g., MySQL).

[0307] Step 6:

[0308] The server analyzes the stored data and generates feedback using a generation AI. The inputs are the video, audio, and emotional data stored in the database. The generation AI evaluates the emotional state, work efficiency, and safety based on this data, and generates specific feedback. The generated feedback is obtained as the output.

[0309] Step 7:

[0310] The server notifies the generated feedback to the workers and managers on-site. The input is the feedback obtained in step 6. As an output, a notification is sent to the workers' terminals and digital signage. Specifically, the server sends a notification message via the network, conveying the feedback to the workers and managers in real time.

[0311] Through these steps, the system grasps the worker's emotional state in real time and provides specific feedback that contributes to improving work efficiency and safety.

[0312] 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.

[0313] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0314] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0315] [Second embodiment]

[0316] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0317] 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.

[0318] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the 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).

[0319] 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.

[0320] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0321] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0322] 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.

[0323] 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.

[0324] 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 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.

[0325] 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.

[0326] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0327] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0328] This invention is a system that allows facilitators to receive objective and prompt feedback during or after a meeting. This system works effectively by combining terminals, a server, and a generative AI.

[0329] Device behavior

[0330] At the start of a meeting, the device activates its camera and microphone and captures video and audio data of the meeting in real time. This data includes video information, audio information, and metadata (e.g., who is speaking, the progress of the meeting, etc.) for each frame. The device transmits this data to the server at regular intervals.

[0331] For example, the device can be a PC or smartphone, and when a meeting starts, it automatically activates the camera and microphone to start capturing data. The captured data is periodically analyzed and sent to a server along with metadata.

[0332] Server Operation

[0333] The server receives the meeting data sent from the devices and temporarily stores it in local storage or a database. The stored data is then analyzed by the generative AI, which analyzes the meeting content from multiple angles and generates feedback to specifically identify the facilitator's strengths and areas for improvement. The feedback includes the frequency with which each participant spoke, patterns of question and answer sessions, best practices for the proceedings, and areas for improvement.

[0334] For example, after receiving the meeting data, the server analyzes each frame to extract and analyze information such as who spoke how much, how questions were asked, etc. Based on the analysis results, it generates feedback such as "Participant A spoke frequently" or "The facilitator is giving everyone a chance to speak, but one participant is talking too much."

[0335] User Use

[0336] Users can receive the feedback sent from the server on their devices and view the specific details. Based on the feedback they receive, users can identify areas for improvement and strengths in their facilitation skills and reflect these in their next meeting.

[0337] For example, after a meeting, users can receive feedback such as "Many participants were given the opportunity to speak" or "Time allocation was unbalanced due to too much focus on a particular topic." This allows users to incorporate improvements to ensure everyone has a balanced opportunity to speak in the next meeting.

[0338] System Features

[0339] The system's features include real-time data capture and analysis, advanced feedback generation using generative AI, and rapid feedback provision, allowing facilitators to receive immediate feedback on the spot or after the meeting, enabling them to make timely improvements.

[0340] ---

[0341] The system of the present invention supports the effective progress of meetings and the improvement of facilitation skills through the cooperation of hardware and software, which is expected to lead to efficient and productive meeting management.

[0342] The processing flow will be explained below.

[0343] Step 1:

[0344] Device: At the start of a meeting, start the camera and microphone to capture video and audio data of the meeting. This prepares the device to obtain real-time information about the progress of the meeting. For example, start the camera using cv2.VideoCapture(0).

[0345] Step 2:

[0346] Device: Analyzes captured video and audio data frame by frame to generate important metadata (e.g., which participants are speaking, and what is happening in the meeting). This includes image and audio analysis of each frame.

[0347] Step 3:

[0348] Terminal: Analyzed data is sent to the server at regular intervals (e.g., every minute). This allows data to be accumulated on the server in real time. For example, data is sent using an HTTP request.

[0349] Step 4:

[0350] Server: Receives the meeting data sent from the devices and temporarily stores it in local storage or a database, ensuring the data necessary for subsequent analysis.

[0351] Step 5:

[0352] Server: Passes the saved data to the generation AI and begins analyzing the meeting data. The generation AI evaluates the frequency of each participant's comments, question and answer patterns, and the progress of the meeting from various angles.

[0353] Step 6:

[0354] Server: Creates feedback based on the analysis results of the generative AI. This feedback includes the facilitator's strengths and areas for improvement. Specifically, it lists specific points such as "certain participants speak too much" or "the facilitator gives everyone an opportunity to speak."

[0355] Step 7:

[0356] Server: Sends the created feedback to the device, allowing users to receive feedback in real time or after the meeting ends.

[0357] Step 8:

[0358] User: Receive and review the feedback sent by the server, identify specific areas for improvement and strengths, and improve your skills for the next meeting.

[0359] Step 9:

[0360] Users: Based on the feedback they receive, they can take practical steps to improve their facilitation skills, leading to more effective meetings in the future.

[0361] Through these steps, the meeting facilitation feedback system utilizing generative AI completes a series of operations.

[0362] Example 1

[0363] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0364] It is difficult to objectively evaluate whether a meeting is being conducted properly and receive prompt feedback. Facilitators face the challenge of having to spend a lot of time and effort tracking who spoke and how much, and how questions were asked. This can also lead to a decline in the quality of the meeting.

[0365] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0366] In this invention, the server includes means for capturing and transmitting video and audio data of the conference from the terminal, means for storing the data received by the server, means for analyzing the stored data using a generative AI model to generate feedback, and means for transmitting the generated feedback to the terminal. This allows the facilitator to receive prompt and objective feedback during and after the conference, enabling efficient conference management and skill improvement.

[0367] "Terminals" refer to electronic devices that capture video and audio data of meetings in real time and send them to a server. Specifically, these devices include PCs and smartphones.

[0368] "Server" refers to a central processing unit that receives, stores, and analyzes meeting data sent from devices. The server may be installed in a cloud service or an on-premise data center.

[0369] A "generative AI model" is an artificial intelligence model that analyzes audio and video data from meetings and generates feedback. Specifically, it uses natural language processing and image recognition technology to perform the analysis.

[0370] "Feedback" refers to information generated based on the analysis results that provides specific evaluations and areas for improvement for the facilitator and meeting participants, and suggests specific actions to improve the quality of the meeting.

[0371] "Video data" refers to video information captured by a camera during a meeting that can be electronically stored and transmitted. Video data includes visual information such as the movements and facial expressions of participants.

[0372] "Audio Data" means audio information recorded by microphone during a meeting in a format that can be stored and transmitted electronically. Audio Data includes the voices of the speakers and the content of the conversation.

[0373] "Metadata" refers to information that accompanies video and audio data, such as who is speaking, the progress of the conversation, and timestamps of what is being said.

[0374] "Analysis" refers to the process of extracting characteristics and patterns from collected video and audio data using certain algorithms and AI models to provide specific evaluations and feedback.

[0375] "Storage" refers to storing received conference data in local storage or a database so that it can be analyzed or referenced later. Storing data enables sustainable management of data.

[0376] "Capture" refers to the process of capturing and electronically recording video and audio data using cameras and microphones while a meeting is in progress, allowing for real-time data collection.

[0377] The present invention is a system that allows facilitators to receive objective and prompt feedback during and after a meeting. The system works effectively by combining devices, servers, and generative AI models.

[0378] Device behavior

[0379] At the start of a meeting, the device activates its camera and microphone and captures video and audio data of the meeting in real time. This data includes video information, audio information, and metadata (e.g., who is speaking, the progress of the meeting, etc.) for each frame. The device transmits this data to the server at regular intervals.

[0380] Specific examples

[0381] For example, if the device is a PC or smartphone, when the meeting starts, it will automatically activate the camera and microphone to start capturing data. The captured data is periodically sent to the server, which receives and stores it.

[0382] Server Operation

[0383] The server receives the meeting data sent from the devices and temporarily stores it in local storage or a database. The stored data is then analyzed by a generative AI model. The generative AI model analyzes the meeting content from multiple angles and generates feedback to specifically identify the facilitator's strengths and areas for improvement. The feedback includes each participant's frequency of speech, question and answer patterns, best practices for the proceedings, and areas for improvement.

[0384] Specific examples

[0385] For example, after receiving the meeting data, the server analyzes each frame to extract and analyze information such as who spoke how much, how questions were asked, etc. Based on the analysis results, it generates feedback such as "Participant A spoke frequently" or "The facilitator is giving everyone a chance to speak, but one participant is talking too much."

[0386] User Use

[0387] Users can receive the feedback sent from the server on their devices and view the specific details. Based on the feedback they receive, users can identify areas for improvement and strengths in their facilitation skills and reflect these in their next meeting.

[0388] Specific examples

[0389] For example, users can receive feedback after a meeting, such as "We gave many participants the opportunity to speak" or "We focused too much on a particular topic and the time allocation was unbalanced." This allows them to incorporate improvements in the next meeting to ensure everyone has a balanced opportunity to speak.

[0390] Prompt Sentence Examples

[0391] "Analyze who spoke and how much during the meeting, and provide feedback on participants' speaking frequency and question-and-answer patterns."

[0392] This allows users to quickly and objectively identify areas for improvement during meetings, and is expected to lead to more efficient meeting management and improved facilitation skills.Specific hardware and software used include PCs and smartphones as terminals, cloud servers and databases as servers, and natural language processing models as generative AI models.

[0393] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0394] Step 1:

[0395] The device will automatically activate its camera and microphone at the start of the meeting, allowing it to begin capturing video and audio data in real time.

[0396] Requirement as input: Trigger to start a conference (user starts a conference).

[0397] Specific operation: When the PC or smartphone receives the "Start" button for the meeting, the camera and microphone are activated.

[0398] Output: A stream of real-time video and audio data is captured.

[0399] Step 2:

[0400] The device adds metadata (such as who is speaking and the progress of the conference) to the captured video and audio data, and sends this to the server at regular intervals.

[0401] Input requirements: Captured video and audio data.

[0402] Specific operation: Adds speaker recognition and timestamps to video and audio data.

[0403] Output: Packs of video and audio data with metadata are generated.

[0404] Step 3:

[0405] The server receives the conference data (video, audio, metadata) sent from the terminals and stores it in local storage or a database.

[0406] Input requirements: Meeting data with metadata.

[0407] Specific operation: After the server receives the data, it stores it in cloud storage such as AWS S3 or RDS.

[0408] Output: Saved meeting data.

[0409] Step 4:

[0410] The server inputs the saved meeting data into the generative AI model, analyzes the data, and uses the generative AI model to generate feedback.

[0411] Requirements as input: Saved meeting data.

[0412] Specific operation: Input the saved meeting data into a generative AI model (e.g., a natural language processing model) and analyze the frequency of comments and question and answer patterns.

[0413] Output: Feedback information based on the analysis results.

[0414] Step 5:

[0415] The server compiles the feedback generated by the generative AI model and sends it to the device.

[0416] Requirements as input: Feedback generated by a generative AI model.

[0417] Specific operation: The feedback information is formatted based on a template and sent to the terminal.

[0418] Output: The formatted feedback data is sent to the terminal.

[0419] Step 6:

[0420] The user can view the feedback received through the device and check the specific content.

[0421] Requirement as input: Feedback data sent by the server.

[0422] Specific operation: The user logs in to the feedback email or dedicated web portal on the device to view the feedback.

[0423] Output: User reviews the feedback and gets specific improvements for the next meeting.

[0424] (Application example 1)

[0425] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0426] Conventional meeting progress and feedback systems do not adequately capture real-time data or provide prompt feedback, resulting in limited improvements in meeting efficiency and facilitation skills. Furthermore, efficient communication is required for meetings and work instructions at production sites and factories, but current systems do not provide sufficient support. Therefore, a new system is needed to improve the quality of meetings.

[0427] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0428] In this invention, the server includes a means for capturing and transmitting video and audio data of the conference from the terminal, a means for storing the received data, a means for analyzing the stored data and generating feedback using a generation AI, a means for providing prompt feedback to the facilitator during or after the conference, a means for supporting the efficiency of meetings and work instructions within the factory, and a means for transmitting the generated feedback to the terminal. This enables the capture and analysis of conference data in real time, realizing the provision of prompt and effective feedback. Furthermore, it supports efficient communication and work instructions within the factory, improving the quality of meetings at the production site.

[0429] A "terminal" is a computing device used to capture and transmit video and audio data to a server.

[0430] "Video data" refers to video information that visually records the progress of the conference and the appearance of each participant.

[0431] "Audio data" refers to acoustic information used to record statements and conversations made during a meeting.

[0432] "Capture" is the process of collecting video and audio data and storing it in digital form.

[0433] "Send" is the operation of moving data from a terminal to a server via a network.

[0434] A "server" is a multi-computing device for storing and analyzing received video and audio data.

[0435] "Storage" is the process of storing data in storage for later use.

[0436] "Analysis" refers to data processing operations that process stored data and extract useful information.

[0437] "Generative AI" is a system that uses artificial intelligence technology to generate feedback and advice based on various data.

[0438] "Feedback" is a response that provides participants and facilitators with information about the meeting's evaluation, areas for improvement, strengths, etc.

[0439] A "facilitator" is a person whose role is to manage the progress of a meeting and promote dialogue among participants.

[0440] "Fast" refers to the property of reacting or processing within a short period of time.

[0441] A "factory" is a facility for manufacturing products.

[0442] "Work instructions" are instructions that clearly state the work content and procedures within a factory.

[0443] "Efficiency" means achieving maximum results while minimizing the use of resources and time.

[0444] The present invention is a system that streamlines meetings and provides prompt and objective feedback to facilitators. This system functions effectively by combining a terminal, a server, and a generative AI model. Specific embodiments are described below.

[0445] Hardware Configuration

[0446] Terminal: A device used to capture video and audio data from a meeting. Examples include a PC or smartphone. A camera and microphone are connected to the terminal, and data is collected using these devices.

[0447] Server: A computer that stores and analyzes received video and audio data. The server includes local storage or a database.

[0448] Software Configuration

[0449] Data capture module: Executed by the device, it activates the camera and microphone at the start of the meeting and captures data in real time. The captured data is sent to the server at regular intervals.

[0450] Data storage module: Runs on the server, receives data sent from the device, and stores it in local storage or a database.

[0451] Data analysis module: A program for analyzing data stored on the server. This module uses a generative AI model (e.g., GPT-3) to analyze the meeting content from multiple angles.

[0452] Feedback generation module: Based on the information obtained from the data analysis module, feedback is generated to specifically identify the facilitator's strengths and areas for improvement. The generated feedback is sent to the device.

[0453] User interface: Runs on the device and allows the user to view the generated feedback. Specific feedback is displayed as text information.

[0454] Data Flow and Processing

[0455] Terminal: When the meeting starts, the data capture module activates the camera and microphone to capture video and audio in real time. The captured data includes metadata such as video information for each frame, audio information, and the progress of the meeting. This data is sent to the server at regular intervals.

[0456] Server: Stores the received meeting data and analyzes it using a generative AI model. The analysis evaluates each participant's frequency of speech, patterns of Q&A, and best practices and areas for improvement in the proceedings. For example, the server may extract information such as "Participant A speaks frequently" or "Participant A is too focused on a particular topic."

[0457] Feedback generation module: Based on the analysis results, specific feedback is generated for the facilitator, such as "You gave many participants the opportunity to speak" or "The time allocation was unbalanced."

[0458] User reception: The generated feedback is sent to the device, and the user can view it and use it to improve the next meeting. Specifically, the user can incorporate improvement measures such as "giving everyone a chance to speak in the next meeting."

[0459] Specific examples and generative AI model prompts

[0460] As a concrete example, consider a work instruction meeting in a factory. Using this system, data from the meeting is captured and analyzed. The generating AI provides feedback such as "points where the order of work instructions should be improved" and "points where communication went smoothly."

[0461] Example prompts for generative AI models:

[0462] Analyze the following data and generate feedback on the facilitators' strengths and areas for improvement:

[0463] Meeting data: [Audio and video data of the meeting]

[0464] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0465] Step 1:

[0466] Device-based data capture

[0467] When a meeting starts, the device activates its camera and microphone and captures the video and audio data of the meeting in real time. The video and audio of the meeting are given as input, and this is collected as digital data. Specifically, the device obtains video information, audio information, and metadata (such as who is speaking and the progress of the meeting) for each frame. This records the progress of the meeting. The output is the captured data.

[0468] Step 2:

[0469] Sending data from the device to the server

[0470] The device sends the captured video and audio data to the server at regular intervals. The data captured in step 1 is given as input, and this data is sent to the server via the network. Specifically, the data is sent using a protocol such as HTTP, which allows the server to receive the data. The output is the sent data.

[0471] Step 3:

[0472] Data storage by server

[0473] The server stores the video and audio data received from the device in local storage or a database. The input is the data sent from the device, and this data is stored for efficient management. Specifically, the data is stored using a database management system (e.g., MySQL or PostgreSQL). This ensures that the data is available for subsequent analysis processes. The output is the stored data.

[0474] Step 4:

[0475] Data analysis

[0476] The server analyzes the stored data and uses a generative AI model to analyze the meeting content from multiple angles. The input is the stored data, and based on this data, it evaluates the frequency of each participant's comments, question and answer patterns, and best practices and areas for improvement in the proceedings. Specifically, it uses machine learning libraries such as TensorFlow and PyTorch to build models and perform analysis. This provides detailed evaluation information for the meeting. The output is the analysis results.

[0477] Step 5:

[0478] Feedback Generation

[0479] Based on the analysis results, the server uses a generative AI model to generate feedback that specifically identifies the facilitator's strengths and areas for improvement. The input is the analysis results, and based on these results, feedback is generated using a natural language processing model (e.g., GPT-3). Specifically, specific prompts are provided to the AI ​​model, which generates feedback in response. This results in declarative and useful feedback. The output is the generated feedback.

[0480] Step 6:

[0481] Sending and Viewing Feedback

[0482] The server sends the generated feedback to the terminal, which then displays it to the user. The input is the generated feedback, which is sent to the terminal. Specifically, the feedback content is processed as text and displayed on the user interface. This allows the user to receive feedback quickly and easily. The output is the displayed feedback.

[0483] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0484] This invention combines a feedback system for meeting facilitation with an emotion engine that recognizes the user's emotions. The main features of this system are the capture and analysis of meeting data, the generation of feedback using a generative AI, and the recognition and evaluation of the user's emotional state using an emotion engine. The operation of the terminal, server, and user is described in detail below.

[0485] Device behavior

[0486] At the start of a meeting, the device activates its camera and microphone to capture video and audio data of the meeting in real time. This data includes video and audio information for each frame, as well as metadata such as participants' facial expressions and tone of voice. The device is equipped with an emotion engine that uses the captured data to recognize the user's emotions in real time. This analysis data is then sent to a server at regular intervals.

[0487] For example, the device can be a PC or smartphone, and the camera and microphone will automatically start up when the meeting begins. The captured data is analyzed in real time by the emotion engine, and the analysis results are sent to the server. For example, it can recognize participants' emotional states, such as "tensed" or "relaxed," from their facial expressions.

[0488] Server Operation

[0489] The server receives the meeting data sent from the devices and stores it in local storage or a database. The stored data is then analyzed using a generative AI and emotion engine. The generative AI analyzes the meeting content from multiple angles and generates feedback on the facilitator's strengths and areas for improvement. The emotion engine also recognizes emotions based on participants' facial expressions and tone of voice and incorporates them into the analysis results.

[0490] For example, after receiving the meeting data, the server uses an emotion engine to analyze the emotional state of the participants for each frame. Next, the generation AI generates specific feedback based on the analysis results, such as "Participant A is nervous while speaking" or "The facilitator is helping Participant B relax."

[0491] User Use

[0492] The user receives the feedback sent from the server on their device and can view the specific details. The feedback includes not only the strengths and areas for improvement of the facilitator's progress, but also information about the emotional state of each participant. This allows the user to take measures to improve the session based on their emotional state.

[0493] For example, after a meeting, the user can review feedback such as "Many participants were given the opportunity to speak" or "Participant A is nervous because he or she is concentrating too much on a particular topic." At the next meeting, the user can refer to the analysis results of the emotion engine and develop measures to improve the emotional state of the participants.

[0494] System Features

[0495] The system's features include real-time data capture and analysis, advanced feedback generation using generative AI, and user emotional recognition using an emotion engine. Facilitators can adjust the progress of the meeting while understanding the emotional state of the participants, and after the meeting, they can take advantage of detailed feedback to make improvements for the next meeting.

[0496] ---

[0497] The system of the present invention integrates hardware and software to support the effective progress of meetings and the improvement of facilitation skills, which is expected to lead to efficient and productive meeting management.

[0498] The processing flow will be explained below.

[0499] Step 1:

[0500] Device: When a meeting starts, the camera and microphone are activated to capture video and audio data of the meeting in real time. For example, when a meeting starts, the camera and microphone are automatically activated, so that the device is ready to capture the entire meeting.

[0501] Step 2:

[0502] Device: Analyzes video and audio data in real time and recognizes participants' emotions through an emotion engine. Specifically, it identifies emotions such as "joy," "anger," "sadness," and "relaxation" based on information such as participants' facial expressions, tone of voice, and volume.

[0503] Step 3:

[0504] Device: Captured video and audio data, along with associated emotional data, is sent to the server at regular intervals (e.g., every minute). This allows the data to be accumulated on the server in real time. For example, the data is sent via an HTTP request.

[0505] Step 4:

[0506] Server: Receives the meeting data sent from the devices and stores it in local storage or a database, allowing the data required for analysis to be saved and used for subsequent processing.

[0507] Step 5:

[0508] Server: The received data is passed to the generation AI and emotion engine and analysis begins. The data is evaluated from multiple angles, including the frequency of each participant's speech, the content of the conversation, facial expressions, and tone of voice.

[0509] Step 6:

[0510] Server: Creates feedback based on the analysis results. The feedback includes the facilitator's strengths and areas for improvement in the process, as well as the emotional state of each participant. For example, the server lists specific points such as "Participant A seemed nervous while speaking" or "Participant B seemed relaxed."

[0511] Step 7:

[0512] Server: Sends the created feedback to the device, allowing users to receive feedback in real time or after the meeting ends.

[0513] Step 8:

[0514] User: Receives and reviews feedback sent from the server, identifies specific areas for improvement, strengths, and participants' emotional state, and considers measures for the next meeting.

[0515] Step 9:

[0516] Users: Based on the feedback they receive, they can take practical steps to improve their facilitation skills, leading to more effective meetings in the future.

[0517] Through these steps, the meeting facilitation feedback system, which combines generative AI and an emotion engine, completes a series of operations.

[0518] Example 2

[0519] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0520] Conventional online meeting systems have the problem of making it difficult to grasp the progress of the meeting and the emotional state of participants in real time. As a result, facilitators are unable to receive appropriate feedback, which can lead to a decline in the quality and efficiency of the meeting. Furthermore, there is a lack of information to identify specific areas for improvement after the meeting, which can lead to the same issues recurring in the next meeting.

[0521] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0522] In this invention, the server includes means for capturing and transmitting video and audio data of the conference from the terminals, means for analyzing the captured data in real time using an emotion engine and recognizing the user's emotion, means for saving the data received by the server, means for analyzing the saved data using a generative AI model and the emotion engine and generating feedback, and means for sending the generated feedback to the terminals, thereby enabling the facilitator to receive specific and real-time feedback during and after the conference.

[0523] A "terminal" is a computing device for capturing and analyzing video and audio data of a conference in real time.

[0524] The "emotion engine" is a software module that analyzes captured video and audio data to recognize the user's emotional state.

[0525] A "server" is a high-performance computing system that receives and stores data sent from a terminal and performs further analytical processing.

[0526] The "generative AI model" is an artificial intelligence algorithm that analyzes the content of a meeting from multiple perspectives and generates feedback that includes the facilitator's strengths and areas for improvement.

[0527] "Feedback" is the analysis result of the generative AI model and emotion engine, including an evaluation of the meeting's progress and areas for improvement.

[0528] "Data capture" is the process of capturing video and audio of a meeting in real time.

[0529] "Data transmission" is the process of sending captured video and audio data and analysis results from the terminal to the server.

[0530] "Data storage" is the process by which the server records the received data in local storage or a database.

[0531] This invention combines a feedback system for meeting facilitation with an emotion engine that recognizes the user's emotions. The main features of this system are the capture and analysis of meeting data, the generation of feedback using a generative AI, and the recognition and evaluation of the user's emotional state using an emotion engine. This system performs specific operations on the terminal, server, and user. Each operation is explained in detail below.

[0532] Device behavior

[0533] The device automatically activates its camera and microphone as soon as the meeting begins, preparing to capture the meeting's video and audio data in real time. The device is equipped with an emotion engine that uses the captured data to recognize participants' emotions in real time. This recognized emotion data is sent to the server at regular intervals.

[0534] Example: When a user opens a conference app on their PC or smartphone and presses the "Start Conference" button, the camera and microphone are automatically activated. As the conference progresses, the device's emotion engine captures the video and audio data of the participants, recognizes their emotional states in real time, such as "Participant A is nervous while speaking" or "Participant B is relaxed," and sends this data to the server.

[0535] Server Operation

[0536] The server receives the emotion data and video / audio data sent from the device and first stores it in local storage or a database. The stored data is then analyzed using a generative AI model and emotion engine. The generative AI model analyzes the text data of the meeting content from multiple angles and generates feedback based on the facilitator's strengths and areas for improvement. At the same time, the emotion engine analyzes the emotion data and incorporates the results into the analysis results of the generative AI model.

[0537] Example: The server receives the meeting data and uses an emotion engine to analyze the participants' emotional states for each frame. Based on this, the generative AI model generates specific feedback, such as "Participant A was feeling tense while speaking" or "The facilitator is creating a relaxed atmosphere for Participant B."

[0538] User Use

[0539] After the meeting, users receive feedback sent from the server on their devices and check the content. The feedback includes not only the facilitator's strengths and areas for improvement in the meeting's progress, but also information about the participants' emotional states. This allows users to take measures to improve the meeting based on their emotional states.

[0540] Example: After a meeting, a user opens a feedback report in the meeting app and sees detailed feedback such as "Many participants were given the opportunity to speak" and "Participant A was nervous because he was too focused on a particular topic." In the next meeting, the user can refer to this feedback and take measures to improve the emotional state of the participants.

[0541] Prompt Sentence Examples

[0542] "Please explain in detail the processing flow of a system that allows the facilitator to recognize participants' emotions during a meeting and provide feedback on specific areas for improvement. Please also clearly explain the roles of the terminal and server in this system."

[0543] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0544] Step 1:

[0545] As soon as the conference starts, the device automatically activates its camera and microphone to capture the conference video and audio data. At this stage, the conference video information and audio data are the input. Specifically, when the user presses the "Start Conference" button, the device's camera and microphone activate, and video and audio are captured in real time. The output is the captured video and audio data.

[0546] Step 2:

[0547] The device passes the captured data to the emotion engine for real-time analysis. The input is the captured video and audio data. The emotion engine analyzes this data and recognizes the emotional state of the participants. Specifically, the emotion engine analyzes facial expressions from the video data and tone of voice from the audio data. The output is the analyzed emotion data.

[0548] Step 3:

[0549] The device sends the analyzed emotion data to the server at regular intervals. The input is the emotion data generated by the emotion engine. Specifically, the device sets a timer and collects the emotion data into packets at regular intervals and sends them to the server. The output is the emotion data sent to the server.

[0550] Step 4:

[0551] The server receives data sent from the device and stores it in local storage or a database. The input is the emotion data sent from the device. Specifically, the server's data receiving module detects new data packets and writes them to the storage or database. The output is the stored data.

[0552] Step 5:

[0553] The server uses the stored data to perform analysis using a generative AI model and emotion engine. The input is the stored emotion data. Specifically, the emotion engine reanalyzes the emotion data, and the generative AI model analyzes the meeting content from multiple angles to generate feedback. The output is the feedback generated by the generative AI model and emotion engine.

[0554] Step 6:

[0555] The server sends the generated feedback to the terminal. The input is the generated feedback. In concrete terms, the server packs the feedback data into packets and sends them to the terminal. The output is the feedback sent to the terminal.

[0556] Step 7:

[0557] After the meeting ends, the user receives and checks the feedback on their device. The input is the feedback sent from the server. Specifically, the user opens the meeting app and presses the "View Feedback" button to display the received feedback. The output is the feedback displayed on the device.

[0558] Example prompt sentence:

[0559] "Please explain in detail the processing flow of a system that allows the facilitator to recognize participants' emotions during a meeting and provide feedback on specific areas for improvement. Please also clearly explain the roles of the terminal and server in this system."

[0560] (Application example 2)

[0561] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0562] There is a need to accurately grasp the emotional state of factory workers and provide specific feedback in real time to improve work efficiency and safety. However, currently, there is a lack of means to recognize changes in workers' mental state and stress in real time and provide appropriate feedback based on that. As a result, work efficiency can decrease and safety issues can arise. Furthermore, conventional systems do not properly evaluate workers' emotional state, making it difficult to take appropriate improvement measures.

[0563] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing and transmitting video and audio data from the terminal, means for saving the data received by the server, means for analyzing the saved data and generating feedback using a generation AI, means for sending the generated feedback to the terminal, an emotion engine for recognizing the emotions of workers based on the analyzed data, means for generating feedback regarding work efficiency and safety based on the recognized emotion data, and means for notifying on-site workers and managers of the generated feedback. This makes it possible to grasp the emotional state of workers in real time and provide specific feedback based on that.

[0564] A "terminal" is a device that has the function of capturing video and audio data and transmitting it to a server.

[0565] A "server" is a device or system that can store and analyze received data.

[0566] "Generative AI" refers to artificial intelligence technology that analyzes stored data and automatically generates feedback.

[0567] "Emotion engine" refers to technology that recognizes a person's emotional state from video and audio data.

[0568] "Work efficiency" is an indicator that shows the efficiency and productivity of workers' work.

[0569] "Safety" refers to the ability to minimize hazards in the work environment and prevent accidents and injuries.

[0570] "Feedback" refers to specific information and improvement measures generated based on analyzed data and emotional state.

[0571] "Notification" refers to the means by which generated feedback is communicated to field workers and managers in real time.

[0572] The system for implementing this invention can grasp the emotional state of workers in a factory in real time and provide specific feedback to improve work efficiency and safety. Each component of the system and its operation will be described in detail below.

[0573] Device behavior

[0574] The system's terminal is a device capable of capturing video and audio data and sending it to a server. Specifically, it has a built-in camera and microphone, which captures video and audio from the factory work area in real time. The terminal is equipped with a function to preprocess the captured data using OpenCV. Furthermore, an emotion engine is implemented using TensorFlow to recognize the emotional state of the worker from the captured data. The recognized emotion data is sent to the server at regular intervals.

[0575] Server Operation

[0576] The server receives the data sent from the terminal and stores it in a database. The stored data is analyzed by a generative AI using TensorFlow. The generative AI performs multifaceted analysis of the worker's emotional state, work efficiency, and safety, and generates specific feedback. Once the feedback is generated, it is immediately notified to the worker and manager on-site. This notification is sent via digital signage and a smartphone app.

[0577] User Use

[0578] The user receives the generated feedback on their device and views its contents. The feedback includes information on the worker's emotional state, as well as measures to improve work efficiency and safety. This allows the user to take appropriate improvement measures based on the worker's emotional state. For example, if the system recognizes that a worker is "tense," it will provide feedback such as "shorten work time" or "encourage them to take a break."

[0579] Hardware and software used

[0580] Hardware: Cameras, microphones, servers, digital signage, smartphones

[0581] Software: OpenCV, TensorFlow, database (e.g. MySQL)

[0582] Prompt Sentence Examples

[0583] Here are some examples of prompts for generative AI models:

[0584] Generate feedback based on a worker's emotional state. For example, if a worker is "tense," provide a recommended action.

[0585] Emotional state: Tense

[0586] Recommended actions: Reduce work time and encourage breaks

[0587] In this way, the system for implementing this invention can grasp the emotional state of workers in the field in real time and provide appropriate feedback immediately, which will greatly contribute to improving work efficiency and ensuring safety.

[0588] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0589] Step 1:

[0590] The terminal activates the camera and microphone to capture video and audio data of the factory work area in real time. The input is raw video and audio data from the camera and microphone. The output is the captured video and audio data. Specifically, the camera captures several frames per second, and the microphone picks up surrounding audio.

[0591] Step 2:

[0592] The device preprocesses the captured video and audio data. The input is the raw data obtained in step 1. OpenCV is used to convert the video data to grayscale, detect faces, and resize them. Preprocessing such as noise removal is performed on the audio data. The output is the preprocessed video and audio data.

[0593] Step 3:

[0594] The device inputs preprocessed video and audio data into an emotion engine using TensorFlow to recognize the worker's emotional state. The input is the preprocessed data. The emotion engine analyzes this data and identifies the emotional state (e.g., nervous, relaxed, stressed, etc.). The output is a label for the emotional state. Specifically, the emotion recognition model analyzes facial expressions and tone of voice to classify emotions.

[0595] Step 4:

[0596] The device sends the recognized emotion data to the server at regular intervals. The input is the emotional state label obtained in step 3. As an output, the emotion data is sent to the server. This involves transferring the data to the server using a communication protocol.

[0597] Step 5:

[0598] The server stores emotion data and other video and audio data received from the device. The input is the data sent from the device. The output is the received data stored in a database. Specifically, the server stores the data using a database system (e.g., MySQL).

[0599] Step 6:

[0600] The server analyzes the stored data and generates feedback using a generation AI. The inputs are the video, audio, and emotional data stored in the database. The generation AI evaluates the emotional state, work efficiency, and safety based on this data, and generates specific feedback. The generated feedback is obtained as the output.

[0601] Step 7:

[0602] The server notifies the generated feedback to the workers and managers on-site. The input is the feedback obtained in step 6. As an output, a notification is sent to the workers' terminals and digital signage. Specifically, the server sends a notification message via the network, conveying the feedback to the workers and managers in real time.

[0603] Through these steps, the system grasps the worker's emotional state in real time and provides specific feedback that contributes to improving work efficiency and safety.

[0604] 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.

[0605] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0606] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0607] [Third embodiment]

[0608] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0609] 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.

[0610] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the 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).

[0611] 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.

[0612] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0613] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0614] 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.

[0615] 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.

[0616] 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 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.

[0617] 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.

[0618] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0619] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0620] This invention is a system that allows facilitators to receive objective and prompt feedback during or after a meeting. This system works effectively by combining terminals, a server, and a generative AI.

[0621] Device behavior

[0622] At the start of a meeting, the device activates its camera and microphone and captures video and audio data of the meeting in real time. This data includes video information, audio information, and metadata (e.g., who is speaking, the progress of the meeting, etc.) for each frame. The device transmits this data to the server at regular intervals.

[0623] For example, the device can be a PC or smartphone, and when a meeting starts, it automatically activates the camera and microphone to start capturing data. The captured data is periodically analyzed and sent to a server along with metadata.

[0624] Server Operation

[0625] The server receives the meeting data sent from the devices and temporarily stores it in local storage or a database. The stored data is then analyzed by the generative AI, which analyzes the meeting content from multiple angles and generates feedback to specifically identify the facilitator's strengths and areas for improvement. The feedback includes the frequency with which each participant spoke, patterns of question and answer sessions, best practices for the proceedings, and areas for improvement.

[0626] For example, after receiving the meeting data, the server analyzes each frame to extract and analyze information such as who spoke how much, how questions were asked, etc. Based on the analysis results, it generates feedback such as "Participant A spoke frequently" or "The facilitator is giving everyone a chance to speak, but one participant is talking too much."

[0627] User Use

[0628] Users can receive the feedback sent from the server on their devices and view the specific details. Based on the feedback they receive, users can identify areas for improvement and strengths in their facilitation skills and reflect these in their next meeting.

[0629] For example, after a meeting, users can receive feedback such as "Many participants were given the opportunity to speak" or "Time allocation was unbalanced due to too much focus on a particular topic." This allows users to incorporate improvements to ensure everyone has a balanced opportunity to speak in the next meeting.

[0630] System Features

[0631] The system's features include real-time data capture and analysis, advanced feedback generation using generative AI, and rapid feedback provision, allowing facilitators to receive immediate feedback on the spot or after the meeting, enabling them to make timely improvements.

[0632] ---

[0633] The system of the present invention supports the effective progress of meetings and the improvement of facilitation skills through the cooperation of hardware and software, which is expected to lead to efficient and productive meeting management.

[0634] The processing flow will be explained below.

[0635] Step 1:

[0636] Device: At the start of a meeting, start the camera and microphone to capture video and audio data of the meeting. This prepares the device to obtain real-time information about the progress of the meeting. For example, start the camera using cv2.VideoCapture(0).

[0637] Step 2:

[0638] Device: Analyzes captured video and audio data frame by frame to generate important metadata (e.g., which participants are speaking, and what is happening in the meeting). This includes image and audio analysis of each frame.

[0639] Step 3:

[0640] Terminal: Analyzed data is sent to the server at regular intervals (e.g., every minute). This allows data to be accumulated on the server in real time. For example, data is sent using an HTTP request.

[0641] Step 4:

[0642] Server: Receives the meeting data sent from the devices and temporarily stores it in local storage or a database, ensuring the data necessary for subsequent analysis.

[0643] Step 5:

[0644] Server: Passes the saved data to the generation AI and begins analyzing the meeting data. The generation AI evaluates the frequency of each participant's comments, question and answer patterns, and the progress of the meeting from various angles.

[0645] Step 6:

[0646] Server: Creates feedback based on the analysis results of the generative AI. This feedback includes the facilitator's strengths and areas for improvement. Specifically, it lists specific points such as "certain participants speak too much" or "the facilitator gives everyone an opportunity to speak."

[0647] Step 7:

[0648] Server: Sends the created feedback to the device, allowing users to receive feedback in real time or after the meeting ends.

[0649] Step 8:

[0650] User: Receive and review the feedback sent by the server, identify specific areas for improvement and strengths, and improve your skills for the next meeting.

[0651] Step 9:

[0652] Users: Based on the feedback they receive, they can take practical steps to improve their facilitation skills, leading to more effective meetings in the future.

[0653] Through these steps, the meeting facilitation feedback system utilizing generative AI completes a series of operations.

[0654] Example 1

[0655] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0656] It is difficult to objectively evaluate whether a meeting is being conducted properly and receive prompt feedback. Facilitators face the challenge of having to spend a lot of time and effort tracking who spoke and how much, and how questions were asked. This can also lead to a decline in the quality of the meeting.

[0657] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0658] In this invention, the server includes means for capturing and transmitting video and audio data of the conference from the terminal, means for storing the data received by the server, means for analyzing the stored data using a generative AI model to generate feedback, and means for transmitting the generated feedback to the terminal. This allows the facilitator to receive prompt and objective feedback during and after the conference, enabling efficient conference management and skill improvement.

[0659] "Terminals" refer to electronic devices that capture video and audio data of meetings in real time and send them to a server. Specifically, these devices include PCs and smartphones.

[0660] "Server" refers to a central processing unit that receives, stores, and analyzes meeting data sent from devices. The server may be installed in a cloud service or an on-premise data center.

[0661] A "generative AI model" is an artificial intelligence model that analyzes audio and video data from meetings and generates feedback. Specifically, it uses natural language processing and image recognition technology to perform the analysis.

[0662] "Feedback" refers to information generated based on the analysis results that provides specific evaluations and areas for improvement for the facilitator and meeting participants, and suggests specific actions to improve the quality of the meeting.

[0663] "Video data" refers to video information captured by a camera during a meeting that can be electronically stored and transmitted. Video data includes visual information such as the movements and facial expressions of participants.

[0664] "Audio Data" means audio information recorded by microphone during a meeting in a format that can be stored and transmitted electronically. Audio Data includes the voices of the speakers and the content of the conversation.

[0665] "Metadata" refers to information that accompanies video and audio data, such as who is speaking, the progress of the conversation, and timestamps of what is being said.

[0666] "Analysis" refers to the process of extracting characteristics and patterns from collected video and audio data using certain algorithms and AI models to provide specific evaluations and feedback.

[0667] "Storage" refers to storing received conference data in local storage or a database so that it can be analyzed or referenced later. Storing data enables sustainable management of data.

[0668] "Capture" refers to the process of capturing and electronically recording video and audio data using cameras and microphones while a meeting is in progress, allowing for real-time data collection.

[0669] The present invention is a system that allows facilitators to receive objective and prompt feedback during and after a meeting. The system works effectively by combining devices, servers, and generative AI models.

[0670] Device behavior

[0671] At the start of a meeting, the device activates its camera and microphone and captures video and audio data of the meeting in real time. This data includes video information, audio information, and metadata (e.g., who is speaking, the progress of the meeting, etc.) for each frame. The device transmits this data to the server at regular intervals.

[0672] Specific examples

[0673] For example, if the device is a PC or smartphone, when the meeting starts, it will automatically activate the camera and microphone to start capturing data. The captured data is periodically sent to the server, which receives and stores it.

[0674] Server Operation

[0675] The server receives the meeting data sent from the devices and temporarily stores it in local storage or a database. The stored data is then analyzed by a generative AI model. The generative AI model analyzes the meeting content from multiple angles and generates feedback to specifically identify the facilitator's strengths and areas for improvement. The feedback includes each participant's frequency of speech, question and answer patterns, best practices for the proceedings, and areas for improvement.

[0676] Specific examples

[0677] For example, after receiving the meeting data, the server analyzes each frame to extract and analyze information such as who spoke how much, how questions were asked, etc. Based on the analysis results, it generates feedback such as "Participant A spoke frequently" or "The facilitator is giving everyone a chance to speak, but one participant is talking too much."

[0678] User Use

[0679] Users can receive the feedback sent from the server on their devices and view the specific details. Based on the feedback they receive, users can identify areas for improvement and strengths in their facilitation skills and reflect these in their next meeting.

[0680] Specific examples

[0681] For example, users can receive feedback after a meeting, such as "We gave many participants the opportunity to speak" or "We focused too much on a particular topic and the time allocation was unbalanced." This allows them to incorporate improvements in the next meeting to ensure everyone has a balanced opportunity to speak.

[0682] Prompt Sentence Examples

[0683] "Analyze who spoke and how much during the meeting, and provide feedback on participants' speaking frequency and question-and-answer patterns."

[0684] This allows users to quickly and objectively identify areas for improvement during meetings, and is expected to lead to more efficient meeting management and improved facilitation skills.Specific hardware and software used include PCs and smartphones as terminals, cloud servers and databases as servers, and natural language processing models as generative AI models.

[0685] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0686] Step 1:

[0687] The device will automatically activate its camera and microphone at the start of the meeting, allowing it to begin capturing video and audio data in real time.

[0688] Requirement as input: Trigger to start a conference (user starts a conference).

[0689] Specific operation: When the PC or smartphone receives the "Start" button for the meeting, the camera and microphone are activated.

[0690] Output: A stream of real-time video and audio data is captured.

[0691] Step 2:

[0692] The device adds metadata (such as who is speaking and the progress of the conference) to the captured video and audio data, and sends this to the server at regular intervals.

[0693] Input requirements: Captured video and audio data.

[0694] Specific operation: Adds speaker recognition and timestamps to video and audio data.

[0695] Output: Packs of video and audio data with metadata are generated.

[0696] Step 3:

[0697] The server receives the conference data (video, audio, metadata) sent from the terminals and stores it in local storage or a database.

[0698] Input requirements: Meeting data with metadata.

[0699] Specific operation: After the server receives the data, it stores it in cloud storage such as AWS S3 or RDS.

[0700] Output: Saved meeting data.

[0701] Step 4:

[0702] The server inputs the saved meeting data into the generative AI model, analyzes the data, and uses the generative AI model to generate feedback.

[0703] Requirements as input: Saved meeting data.

[0704] Specific operation: Input the saved meeting data into a generative AI model (e.g., a natural language processing model) and analyze the frequency of comments and question and answer patterns.

[0705] Output: Feedback information based on the analysis results.

[0706] Step 5:

[0707] The server compiles the feedback generated by the generative AI model and sends it to the device.

[0708] Requirements as input: Feedback generated by a generative AI model.

[0709] Specific operation: The feedback information is formatted based on a template and sent to the terminal.

[0710] Output: The formatted feedback data is sent to the terminal.

[0711] Step 6:

[0712] The user can view the feedback received through the device and check the specific content.

[0713] Requirement as input: Feedback data sent by the server.

[0714] Specific operation: The user logs in to the feedback email or dedicated web portal on the device to view the feedback.

[0715] Output: User reviews the feedback and gets specific improvements for the next meeting.

[0716] (Application example 1)

[0717] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0718] Conventional meeting progress and feedback systems do not adequately capture real-time data or provide prompt feedback, resulting in limited improvements in meeting efficiency and facilitation skills. Furthermore, efficient communication is required for meetings and work instructions at production sites and factories, but current systems do not provide sufficient support. Therefore, a new system is needed to improve the quality of meetings.

[0719] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0720] In this invention, the server includes a means for capturing and transmitting video and audio data of the conference from the terminal, a means for storing the received data, a means for analyzing the stored data and generating feedback using a generation AI, a means for providing prompt feedback to the facilitator during or after the conference, a means for supporting the efficiency of meetings and work instructions within the factory, and a means for transmitting the generated feedback to the terminal. This enables the capture and analysis of conference data in real time, realizing the provision of prompt and effective feedback. Furthermore, it supports efficient communication and work instructions within the factory, improving the quality of meetings at the production site.

[0721] A "terminal" is a computing device used to capture and transmit video and audio data to a server.

[0722] "Video data" refers to video information that visually records the progress of the conference and the appearance of each participant.

[0723] "Audio data" refers to acoustic information used to record statements and conversations made during a meeting.

[0724] "Capture" is the process of collecting video and audio data and storing it in digital form.

[0725] "Send" is the operation of moving data from a terminal to a server via a network.

[0726] A "server" is a multi-computing device for storing and analyzing received video and audio data.

[0727] "Storage" is the process of storing data in storage for later use.

[0728] "Analysis" refers to data processing operations that process stored data and extract useful information.

[0729] "Generative AI" is a system that uses artificial intelligence technology to generate feedback and advice based on various data.

[0730] "Feedback" is a response that provides participants and facilitators with information about the meeting's evaluation, areas for improvement, strengths, etc.

[0731] A "facilitator" is a person whose role is to manage the progress of a meeting and promote dialogue among participants.

[0732] "Fast" refers to the property of reacting or processing within a short period of time.

[0733] A "factory" is a facility for manufacturing products.

[0734] "Work instructions" are instructions that clearly state the work content and procedures within a factory.

[0735] "Efficiency" means achieving maximum results while minimizing the use of resources and time.

[0736] The present invention is a system that streamlines meetings and provides prompt and objective feedback to facilitators. This system functions effectively by combining a terminal, a server, and a generative AI model. Specific embodiments are described below.

[0737] Hardware Configuration

[0738] Terminal: A device used to capture video and audio data from a meeting. Examples include a PC or smartphone. A camera and microphone are connected to the terminal, and data is collected using these devices.

[0739] Server: A computer that stores and analyzes received video and audio data. The server includes local storage or a database.

[0740] Software Configuration

[0741] Data capture module: Executed by the device, it activates the camera and microphone at the start of the meeting and captures data in real time. The captured data is sent to the server at regular intervals.

[0742] Data storage module: Runs on the server, receives data sent from the device, and stores it in local storage or a database.

[0743] Data analysis module: A program for analyzing data stored on the server. This module uses a generative AI model (e.g., GPT-3) to analyze the meeting content from multiple angles.

[0744] Feedback generation module: Based on the information obtained from the data analysis module, feedback is generated to specifically identify the facilitator's strengths and areas for improvement. The generated feedback is sent to the device.

[0745] User interface: Runs on the device and allows the user to view the generated feedback. Specific feedback is displayed as text information.

[0746] Data Flow and Processing

[0747] Terminal: When the meeting starts, the data capture module activates the camera and microphone to capture video and audio in real time. The captured data includes metadata such as video information for each frame, audio information, and the progress of the meeting. This data is sent to the server at regular intervals.

[0748] Server: Stores the received meeting data and analyzes it using a generative AI model. The analysis evaluates each participant's frequency of speech, patterns of Q&A, and best practices and areas for improvement in the proceedings. For example, the server may extract information such as "Participant A speaks frequently" or "Participant A is too focused on a particular topic."

[0749] Feedback generation module: Based on the analysis results, specific feedback is generated for the facilitator, such as "You gave many participants the opportunity to speak" or "The time allocation was unbalanced."

[0750] User reception: The generated feedback is sent to the device, and the user can view it and use it to improve the next meeting. Specifically, the user can incorporate improvement measures such as "giving everyone a chance to speak in the next meeting."

[0751] Specific examples and generative AI model prompts

[0752] As a concrete example, consider a work instruction meeting in a factory. Using this system, data from the meeting is captured and analyzed. The generating AI provides feedback such as "points where the order of work instructions should be improved" and "points where communication went smoothly."

[0753] Example prompts for generative AI models:

[0754] Analyze the following data and generate feedback on the facilitators' strengths and areas for improvement:

[0755] Meeting data: [Audio and video data of the meeting]

[0756] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0757] Step 1:

[0758] Device-based data capture

[0759] When a meeting starts, the device activates its camera and microphone and captures the video and audio data of the meeting in real time. The video and audio of the meeting are given as input, and this is collected as digital data. Specifically, the device obtains video information, audio information, and metadata (such as who is speaking and the progress of the meeting) for each frame. This records the progress of the meeting. The output is the captured data.

[0760] Step 2:

[0761] Sending data from the device to the server

[0762] The device sends the captured video and audio data to the server at regular intervals. The data captured in step 1 is given as input, and this data is sent to the server via the network. Specifically, the data is sent using a protocol such as HTTP, which allows the server to receive the data. The output is the sent data.

[0763] Step 3:

[0764] Data storage by server

[0765] The server stores the video and audio data received from the device in local storage or a database. The input is the data sent from the device, and this data is stored for efficient management. Specifically, the data is stored using a database management system (e.g., MySQL or PostgreSQL). This ensures that the data is available for subsequent analysis processes. The output is the stored data.

[0766] Step 4:

[0767] Data analysis

[0768] The server analyzes the stored data and uses a generative AI model to analyze the meeting content from multiple angles. The input is the stored data, and based on this data, it evaluates the frequency of each participant's comments, question and answer patterns, and best practices and areas for improvement in the proceedings. Specifically, it uses machine learning libraries such as TensorFlow and PyTorch to build models and perform analysis. This provides detailed evaluation information for the meeting. The output is the analysis results.

[0769] Step 5:

[0770] Feedback Generation

[0771] Based on the analysis results, the server uses a generative AI model to generate feedback that specifically identifies the facilitator's strengths and areas for improvement. The input is the analysis results, and based on these results, feedback is generated using a natural language processing model (e.g., GPT-3). Specifically, specific prompts are provided to the AI ​​model, which generates feedback in response. This results in declarative and useful feedback. The output is the generated feedback.

[0772] Step 6:

[0773] Sending and Viewing Feedback

[0774] The server sends the generated feedback to the terminal, which then displays it to the user. The input is the generated feedback, which is sent to the terminal. Specifically, the feedback content is processed as text and displayed on the user interface. This allows the user to receive feedback quickly and easily. The output is the displayed feedback.

[0775] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0776] This invention combines a feedback system for meeting facilitation with an emotion engine that recognizes the user's emotions. The main features of this system are the capture and analysis of meeting data, the generation of feedback using a generative AI, and the recognition and evaluation of the user's emotional state using an emotion engine. The operation of the terminal, server, and user is described in detail below.

[0777] Device behavior

[0778] At the start of a meeting, the device activates its camera and microphone to capture video and audio data of the meeting in real time. This data includes video and audio information for each frame, as well as metadata such as participants' facial expressions and tone of voice. The device is equipped with an emotion engine that uses the captured data to recognize the user's emotions in real time. This analysis data is then sent to a server at regular intervals.

[0779] For example, the device can be a PC or smartphone, and the camera and microphone will automatically start up when the meeting begins. The captured data is analyzed in real time by the emotion engine, and the analysis results are sent to the server. For example, it can recognize participants' emotional states, such as "tensed" or "relaxed," from their facial expressions.

[0780] Server Operation

[0781] The server receives the meeting data sent from the devices and stores it in local storage or a database. The stored data is then analyzed using a generative AI and emotion engine. The generative AI analyzes the meeting content from multiple angles and generates feedback on the facilitator's strengths and areas for improvement. The emotion engine also recognizes emotions based on participants' facial expressions and tone of voice and incorporates them into the analysis results.

[0782] For example, after receiving the meeting data, the server uses an emotion engine to analyze the emotional state of the participants for each frame. Next, the generation AI generates specific feedback based on the analysis results, such as "Participant A is nervous while speaking" or "The facilitator is helping Participant B relax."

[0783] User Use

[0784] The user receives the feedback sent from the server on their device and can view the specific details. The feedback includes not only the strengths and areas for improvement of the facilitator's progress, but also information about the emotional state of each participant. This allows the user to take measures to improve the session based on their emotional state.

[0785] For example, after a meeting, the user can review feedback such as "Many participants were given the opportunity to speak" or "Participant A is nervous because he or she is concentrating too much on a particular topic." At the next meeting, the user can refer to the analysis results of the emotion engine and develop measures to improve the emotional state of the participants.

[0786] System Features

[0787] The system's features include real-time data capture and analysis, advanced feedback generation using generative AI, and user emotional recognition using an emotion engine. Facilitators can adjust the progress of the meeting while understanding the emotional state of the participants, and after the meeting, they can take advantage of detailed feedback to make improvements for the next meeting.

[0788] ---

[0789] The system of the present invention integrates hardware and software to support the effective progress of meetings and the improvement of facilitation skills, which is expected to lead to efficient and productive meeting management.

[0790] The processing flow will be explained below.

[0791] Step 1:

[0792] Device: When a meeting starts, the camera and microphone are activated to capture video and audio data of the meeting in real time. For example, when a meeting starts, the camera and microphone are automatically activated, so that the device is ready to capture the entire meeting.

[0793] Step 2:

[0794] Device: Analyzes video and audio data in real time and recognizes participants' emotions through an emotion engine. Specifically, it identifies emotions such as "joy," "anger," "sadness," and "relaxation" based on information such as participants' facial expressions, tone of voice, and volume.

[0795] Step 3:

[0796] Device: Captured video and audio data, along with associated emotional data, is sent to the server at regular intervals (e.g., every minute). This allows the data to be accumulated on the server in real time. For example, the data is sent via an HTTP request.

[0797] Step 4:

[0798] Server: Receives the meeting data sent from the devices and stores it in local storage or a database, allowing the data required for analysis to be saved and used for subsequent processing.

[0799] Step 5:

[0800] Server: The received data is passed to the generation AI and emotion engine and analysis begins. The data is evaluated from multiple angles, including the frequency of each participant's speech, the content of the conversation, facial expressions, and tone of voice.

[0801] Step 6:

[0802] Server: Creates feedback based on the analysis results. The feedback includes the facilitator's strengths and areas for improvement in the process, as well as the emotional state of each participant. For example, the server lists specific points such as "Participant A seemed nervous while speaking" or "Participant B seemed relaxed."

[0803] Step 7:

[0804] Server: Sends the created feedback to the device, allowing users to receive feedback in real time or after the meeting ends.

[0805] Step 8:

[0806] User: Receives and reviews feedback sent from the server, identifies specific areas for improvement, strengths, and participants' emotional state, and considers measures for the next meeting.

[0807] Step 9:

[0808] Users: Based on the feedback they receive, they can take practical steps to improve their facilitation skills, leading to more effective meetings in the future.

[0809] Through these steps, the meeting facilitation feedback system, which combines generative AI and an emotion engine, completes a series of operations.

[0810] Example 2

[0811] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0812] Conventional online meeting systems have the problem of making it difficult to grasp the progress of the meeting and the emotional state of participants in real time. As a result, facilitators are unable to receive appropriate feedback, which can lead to a decline in the quality and efficiency of the meeting. Furthermore, there is a lack of information to identify specific areas for improvement after the meeting, which can lead to the same issues recurring in the next meeting.

[0813] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0814] In this invention, the server includes means for capturing and transmitting video and audio data of the conference from the terminals, means for analyzing the captured data in real time using an emotion engine and recognizing the user's emotion, means for saving the data received by the server, means for analyzing the saved data using a generative AI model and the emotion engine and generating feedback, and means for sending the generated feedback to the terminals, thereby enabling the facilitator to receive specific and real-time feedback during and after the conference.

[0815] A "terminal" is a computing device for capturing and analyzing video and audio data of a conference in real time.

[0816] The "emotion engine" is a software module that analyzes captured video and audio data to recognize the user's emotional state.

[0817] A "server" is a high-performance computing system that receives and stores data sent from a terminal and performs further analytical processing.

[0818] The "generative AI model" is an artificial intelligence algorithm that analyzes the content of a meeting from multiple perspectives and generates feedback that includes the facilitator's strengths and areas for improvement.

[0819] "Feedback" is the analysis result of the generative AI model and emotion engine, including an evaluation of the meeting's progress and areas for improvement.

[0820] "Data capture" is the process of capturing video and audio of a meeting in real time.

[0821] "Data transmission" is the process of sending captured video and audio data and analysis results from the terminal to the server.

[0822] "Data storage" is the process by which the server records the received data in local storage or a database.

[0823] This invention combines a feedback system for meeting facilitation with an emotion engine that recognizes the user's emotions. The main features of this system are the capture and analysis of meeting data, the generation of feedback using a generative AI, and the recognition and evaluation of the user's emotional state using an emotion engine. This system performs specific operations on the terminal, server, and user. Each operation is explained in detail below.

[0824] Device behavior

[0825] The device automatically activates its camera and microphone as soon as the meeting begins, preparing to capture the meeting's video and audio data in real time. The device is equipped with an emotion engine that uses the captured data to recognize participants' emotions in real time. This recognized emotion data is sent to the server at regular intervals.

[0826] Example: When a user opens a conference app on their PC or smartphone and presses the "Start Conference" button, the camera and microphone are automatically activated. As the conference progresses, the device's emotion engine captures the video and audio data of the participants, recognizes their emotional states in real time, such as "Participant A is nervous while speaking" or "Participant B is relaxed," and sends this data to the server.

[0827] Server Operation

[0828] The server receives the emotion data and video / audio data sent from the device and first stores it in local storage or a database. The stored data is then analyzed using a generative AI model and emotion engine. The generative AI model analyzes the text data of the meeting content from multiple angles and generates feedback based on the facilitator's strengths and areas for improvement. At the same time, the emotion engine analyzes the emotion data and incorporates the results into the analysis results of the generative AI model.

[0829] Example: The server receives the meeting data and uses an emotion engine to analyze the participants' emotional states for each frame. Based on this, the generative AI model generates specific feedback, such as "Participant A was feeling tense while speaking" or "The facilitator is creating a relaxed atmosphere for Participant B."

[0830] User Use

[0831] After the meeting, users receive feedback sent from the server on their devices and check the content. The feedback includes not only the facilitator's strengths and areas for improvement in the meeting's progress, but also information about the participants' emotional states. This allows users to take measures to improve the meeting based on their emotional states.

[0832] Example: After a meeting, a user opens a feedback report in the meeting app and sees detailed feedback such as "Many participants were given the opportunity to speak" and "Participant A was nervous because he was too focused on a particular topic." In the next meeting, the user can refer to this feedback and take measures to improve the emotional state of the participants.

[0833] Prompt Sentence Examples

[0834] "Please explain in detail the processing flow of a system that allows the facilitator to recognize participants' emotions during a meeting and provide feedback on specific areas for improvement. Please also clearly explain the roles of the terminal and server in this system."

[0835] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0836] Step 1:

[0837] As soon as the conference starts, the device automatically activates its camera and microphone to capture the conference video and audio data. At this stage, the conference video information and audio data are the input. Specifically, when the user presses the "Start Conference" button, the device's camera and microphone activate, and video and audio are captured in real time. The output is the captured video and audio data.

[0838] Step 2:

[0839] The device passes the captured data to the emotion engine for real-time analysis. The input is the captured video and audio data. The emotion engine analyzes this data and recognizes the emotional state of the participants. Specifically, the emotion engine analyzes facial expressions from the video data and tone of voice from the audio data. The output is the analyzed emotion data.

[0840] Step 3:

[0841] The device sends the analyzed emotion data to the server at regular intervals. The input is the emotion data generated by the emotion engine. Specifically, the device sets a timer and collects the emotion data into packets at regular intervals and sends them to the server. The output is the emotion data sent to the server.

[0842] Step 4:

[0843] The server receives data sent from the device and stores it in local storage or a database. The input is the emotion data sent from the device. Specifically, the server's data receiving module detects new data packets and writes them to the storage or database. The output is the stored data.

[0844] Step 5:

[0845] The server uses the stored data to perform analysis using a generative AI model and emotion engine. The input is the stored emotion data. Specifically, the emotion engine reanalyzes the emotion data, and the generative AI model analyzes the meeting content from multiple angles to generate feedback. The output is the feedback generated by the generative AI model and emotion engine.

[0846] Step 6:

[0847] The server sends the generated feedback to the terminal. The input is the generated feedback. In concrete terms, the server packs the feedback data into packets and sends them to the terminal. The output is the feedback sent to the terminal.

[0848] Step 7:

[0849] After the meeting ends, the user receives and checks the feedback on their device. The input is the feedback sent from the server. Specifically, the user opens the meeting app and presses the "View Feedback" button to display the received feedback. The output is the feedback displayed on the device.

[0850] Example prompt sentence:

[0851] "Please explain in detail the processing flow of a system that allows the facilitator to recognize participants' emotions during a meeting and provide feedback on specific areas for improvement. Please also clearly explain the roles of the terminal and server in this system."

[0852] (Application example 2)

[0853] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0854] There is a need to accurately grasp the emotional state of factory workers and provide specific feedback in real time to improve work efficiency and safety. However, currently, there is a lack of means to recognize changes in workers' mental state and stress in real time and provide appropriate feedback based on that. As a result, work efficiency can decrease and safety issues can arise. Furthermore, conventional systems do not properly evaluate workers' emotional state, making it difficult to take appropriate improvement measures.

[0855] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing and transmitting video and audio data from the terminal, means for saving the data received by the server, means for analyzing the saved data and generating feedback using a generation AI, means for sending the generated feedback to the terminal, an emotion engine for recognizing the emotions of workers based on the analyzed data, means for generating feedback regarding work efficiency and safety based on the recognized emotion data, and means for notifying on-site workers and managers of the generated feedback. This makes it possible to grasp the emotional state of workers in real time and provide specific feedback based on that.

[0856] A "terminal" is a device that has the function of capturing video and audio data and transmitting it to a server.

[0857] A "server" is a device or system that can store and analyze received data.

[0858] "Generative AI" refers to artificial intelligence technology that analyzes stored data and automatically generates feedback.

[0859] "Emotion engine" refers to technology that recognizes a person's emotional state from video and audio data.

[0860] "Work efficiency" is an indicator that shows the efficiency and productivity of workers' work.

[0861] "Safety" refers to the ability to minimize hazards in the work environment and prevent accidents and injuries.

[0862] "Feedback" refers to specific information and improvement measures generated based on analyzed data and emotional state.

[0863] "Notification" refers to the means by which generated feedback is communicated to field workers and managers in real time.

[0864] The system for implementing this invention can grasp the emotional state of workers in a factory in real time and provide specific feedback to improve work efficiency and safety. Each component of the system and its operation will be described in detail below.

[0865] Device behavior

[0866] The system's terminal is a device capable of capturing video and audio data and sending it to a server. Specifically, it has a built-in camera and microphone, which captures video and audio from the factory work area in real time. The terminal is equipped with a function to preprocess the captured data using OpenCV. Furthermore, an emotion engine is implemented using TensorFlow to recognize the emotional state of the worker from the captured data. The recognized emotion data is sent to the server at regular intervals.

[0867] Server Operation

[0868] The server receives the data sent from the terminal and stores it in a database. The stored data is analyzed by a generative AI using TensorFlow. The generative AI performs multifaceted analysis of the worker's emotional state, work efficiency, and safety, and generates specific feedback. Once the feedback is generated, it is immediately notified to the worker and manager on-site. This notification is sent via digital signage and a smartphone app.

[0869] User Use

[0870] The user receives the generated feedback on their device and views its contents. The feedback includes information on the worker's emotional state, as well as measures to improve work efficiency and safety. This allows the user to take appropriate improvement measures based on the worker's emotional state. For example, if the system recognizes that a worker is "tense," it will provide feedback such as "shorten work time" or "encourage them to take a break."

[0871] Hardware and software used

[0872] Hardware: Cameras, microphones, servers, digital signage, smartphones

[0873] Software: OpenCV, TensorFlow, database (e.g. MySQL)

[0874] Prompt Sentence Examples

[0875] Here are some examples of prompts for generative AI models:

[0876] Generate feedback based on a worker's emotional state. For example, if a worker is "tense," provide a recommended action.

[0877] Emotional state: Tense

[0878] Recommended actions: Reduce work time and encourage breaks

[0879] In this way, the system for implementing this invention can grasp the emotional state of workers in the field in real time and provide appropriate feedback immediately, which will greatly contribute to improving work efficiency and ensuring safety.

[0880] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0881] Step 1:

[0882] The terminal activates the camera and microphone to capture video and audio data of the factory work area in real time. The input is raw video and audio data from the camera and microphone. The output is the captured video and audio data. Specifically, the camera captures several frames per second, and the microphone picks up surrounding audio.

[0883] Step 2:

[0884] The device preprocesses the captured video and audio data. The input is the raw data obtained in step 1. OpenCV is used to convert the video data to grayscale, detect faces, and resize them. Preprocessing such as noise removal is performed on the audio data. The output is the preprocessed video and audio data.

[0885] Step 3:

[0886] The device inputs preprocessed video and audio data into an emotion engine using TensorFlow to recognize the worker's emotional state. The input is the preprocessed data. The emotion engine analyzes this data and identifies the emotional state (e.g., nervous, relaxed, stressed, etc.). The output is a label for the emotional state. Specifically, the emotion recognition model analyzes facial expressions and tone of voice to classify emotions.

[0887] Step 4:

[0888] The device sends the recognized emotion data to the server at regular intervals. The input is the emotional state label obtained in step 3. As an output, the emotion data is sent to the server. This involves transferring the data to the server using a communication protocol.

[0889] Step 5:

[0890] The server stores emotion data and other video and audio data received from the device. The input is the data sent from the device. The output is the received data stored in a database. Specifically, the server stores the data using a database system (e.g., MySQL).

[0891] Step 6:

[0892] The server analyzes the stored data and generates feedback using a generation AI. The inputs are the video, audio, and emotional data stored in the database. The generation AI evaluates the emotional state, work efficiency, and safety based on this data, and generates specific feedback. The generated feedback is obtained as the output.

[0893] Step 7:

[0894] The server notifies the generated feedback to the workers and managers on-site. The input is the feedback obtained in step 6. As an output, a notification is sent to the workers' terminals and digital signage. Specifically, the server sends a notification message via the network, conveying the feedback to the workers and managers in real time.

[0895] Through these steps, the system grasps the worker's emotional state in real time and provides specific feedback that contributes to improving work efficiency and safety.

[0896] 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.

[0897] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0898] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0899] [Fourth embodiment]

[0900] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0901] 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.

[0902] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the 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).

[0903] 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.

[0904] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0905] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0906] 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.

[0907] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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.

[0908] 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.

[0909] 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 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.

[0910] 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.

[0911] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0912] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0913] This invention is a system that allows facilitators to receive objective and prompt feedback during or after a meeting. This system works effectively by combining terminals, a server, and a generative AI.

[0914] Device behavior

[0915] At the start of a meeting, the device activates its camera and microphone and captures video and audio data of the meeting in real time. This data includes video information, audio information, and metadata (e.g., who is speaking, the progress of the meeting, etc.) for each frame. The device transmits this data to the server at regular intervals.

[0916] For example, the device can be a PC or smartphone, and when a meeting starts, it automatically activates the camera and microphone to start capturing data. The captured data is periodically analyzed and sent to a server along with metadata.

[0917] Server Operation

[0918] The server receives the meeting data sent from the devices and temporarily stores it in local storage or a database. The stored data is then analyzed by the generative AI, which analyzes the meeting content from multiple angles and generates feedback to specifically identify the facilitator's strengths and areas for improvement. The feedback includes the frequency with which each participant spoke, patterns of question and answer sessions, best practices for the proceedings, and areas for improvement.

[0919] For example, after receiving the meeting data, the server analyzes each frame to extract and analyze information such as who spoke how much, how questions were asked, etc. Based on the analysis results, it generates feedback such as "Participant A spoke frequently" or "The facilitator is giving everyone a chance to speak, but one participant is talking too much."

[0920] User Use

[0921] Users can receive the feedback sent from the server on their devices and view the specific details. Based on the feedback they receive, users can identify areas for improvement and strengths in their facilitation skills and reflect these in their next meeting.

[0922] For example, after a meeting, users can receive feedback such as "Many participants were given the opportunity to speak" or "Time allocation was unbalanced due to too much focus on a particular topic." This allows users to incorporate improvements to ensure everyone has a balanced opportunity to speak in the next meeting.

[0923] System Features

[0924] The system's features include real-time data capture and analysis, advanced feedback generation using generative AI, and rapid feedback provision, allowing facilitators to receive immediate feedback on the spot or after the meeting, enabling them to make timely improvements.

[0925] ---

[0926] The system of the present invention supports the effective progress of meetings and the improvement of facilitation skills through the cooperation of hardware and software, which is expected to lead to efficient and productive meeting management.

[0927] The processing flow will be explained below.

[0928] Step 1:

[0929] Device: At the start of a meeting, start the camera and microphone to capture video and audio data of the meeting. This prepares the device to obtain real-time information about the progress of the meeting. For example, start the camera using cv2.VideoCapture(0).

[0930] Step 2:

[0931] Device: Analyzes captured video and audio data frame by frame to generate important metadata (e.g., which participants are speaking, and what is happening in the meeting). This includes image and audio analysis of each frame.

[0932] Step 3:

[0933] Terminal: Analyzed data is sent to the server at regular intervals (e.g., every minute). This allows data to be accumulated on the server in real time. For example, data is sent using an HTTP request.

[0934] Step 4:

[0935] Server: Receives the meeting data sent from the devices and temporarily stores it in local storage or a database, ensuring the data necessary for subsequent analysis.

[0936] Step 5:

[0937] Server: Passes the saved data to the generation AI and begins analyzing the meeting data. The generation AI evaluates the frequency of each participant's comments, question and answer patterns, and the progress of the meeting from various angles.

[0938] Step 6:

[0939] Server: Creates feedback based on the analysis results of the generative AI. This feedback includes the facilitator's strengths and areas for improvement. Specifically, it lists specific points such as "certain participants speak too much" or "the facilitator gives everyone an opportunity to speak."

[0940] Step 7:

[0941] Server: Sends the created feedback to the device, allowing users to receive feedback in real time or after the meeting ends.

[0942] Step 8:

[0943] User: Receive and review the feedback sent by the server, identify specific areas for improvement and strengths, and improve your skills for the next meeting.

[0944] Step 9:

[0945] Users: Based on the feedback they receive, they can take practical steps to improve their facilitation skills, leading to more effective meetings in the future.

[0946] Through these steps, the meeting facilitation feedback system utilizing generative AI completes a series of operations.

[0947] Example 1

[0948] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0949] It is difficult to objectively evaluate whether a meeting is being conducted properly and receive prompt feedback. Facilitators face the challenge of having to spend a lot of time and effort tracking who spoke and how much, and how questions were asked. This can also lead to a decline in the quality of the meeting.

[0950] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0951] In this invention, the server includes means for capturing and transmitting video and audio data of the conference from the terminal, means for storing the data received by the server, means for analyzing the stored data using a generative AI model to generate feedback, and means for transmitting the generated feedback to the terminal. This allows the facilitator to receive prompt and objective feedback during and after the conference, enabling efficient conference management and skill improvement.

[0952] "Terminals" refer to electronic devices that capture video and audio data of meetings in real time and send them to a server. Specifically, these devices include PCs and smartphones.

[0953] "Server" refers to a central processing unit that receives, stores, and analyzes meeting data sent from devices. The server may be installed in a cloud service or an on-premise data center.

[0954] A "generative AI model" is an artificial intelligence model that analyzes audio and video data from meetings and generates feedback. Specifically, it uses natural language processing and image recognition technology to perform the analysis.

[0955] "Feedback" refers to information generated based on the analysis results that provides specific evaluations and areas for improvement for the facilitator and meeting participants, and suggests specific actions to improve the quality of the meeting.

[0956] "Video data" refers to video information captured by a camera during a meeting that can be electronically stored and transmitted. Video data includes visual information such as the movements and facial expressions of participants.

[0957] "Audio Data" means audio information recorded by microphone during a meeting in a format that can be stored and transmitted electronically. Audio Data includes the voices of the speakers and the content of the conversation.

[0958] "Metadata" refers to information that accompanies video and audio data, such as who is speaking, the progress of the conversation, and timestamps of what is being said.

[0959] "Analysis" refers to the process of extracting characteristics and patterns from collected video and audio data using certain algorithms and AI models to provide specific evaluations and feedback.

[0960] "Storage" refers to storing received conference data in local storage or a database so that it can be analyzed or referenced later. Storing data enables sustainable management of data.

[0961] "Capture" refers to the process of capturing and electronically recording video and audio data using cameras and microphones while a meeting is in progress, allowing for real-time data collection.

[0962] The present invention is a system that allows facilitators to receive objective and prompt feedback during and after a meeting. The system works effectively by combining devices, servers, and generative AI models.

[0963] Device behavior

[0964] At the start of a meeting, the device activates its camera and microphone and captures video and audio data of the meeting in real time. This data includes video information, audio information, and metadata (e.g., who is speaking, the progress of the meeting, etc.) for each frame. The device transmits this data to the server at regular intervals.

[0965] Specific examples

[0966] For example, if the device is a PC or smartphone, when the meeting starts, it will automatically activate the camera and microphone to start capturing data. The captured data is periodically sent to the server, which receives and stores it.

[0967] Server Operation

[0968] The server receives the meeting data sent from the devices and temporarily stores it in local storage or a database. The stored data is then analyzed by a generative AI model. The generative AI model analyzes the meeting content from multiple angles and generates feedback to specifically identify the facilitator's strengths and areas for improvement. The feedback includes each participant's frequency of speech, question and answer patterns, best practices for the proceedings, and areas for improvement.

[0969] Specific examples

[0970] For example, after receiving the meeting data, the server analyzes each frame to extract and analyze information such as who spoke how much, how questions were asked, etc. Based on the analysis results, it generates feedback such as "Participant A spoke frequently" or "The facilitator is giving everyone a chance to speak, but one participant is talking too much."

[0971] User Use

[0972] Users can receive the feedback sent from the server on their devices and view the specific details. Based on the feedback they receive, users can identify areas for improvement and strengths in their facilitation skills and reflect these in their next meeting.

[0973] Specific examples

[0974] For example, users can receive feedback after a meeting, such as "We gave many participants the opportunity to speak" or "We focused too much on a particular topic and the time allocation was unbalanced." This allows them to incorporate improvements in the next meeting to ensure everyone has a balanced opportunity to speak.

[0975] Prompt Sentence Examples

[0976] "Analyze who spoke and how much during the meeting, and provide feedback on participants' speaking frequency and question-and-answer patterns."

[0977] This allows users to quickly and objectively identify areas for improvement during meetings, and is expected to lead to more efficient meeting management and improved facilitation skills.Specific hardware and software used include PCs and smartphones as terminals, cloud servers and databases as servers, and natural language processing models as generative AI models.

[0978] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0979] Step 1:

[0980] The device will automatically activate its camera and microphone at the start of the meeting, allowing it to begin capturing video and audio data in real time.

[0981] Requirement as input: Trigger to start a conference (user starts a conference).

[0982] Specific operation: When the PC or smartphone receives the "Start" button for the meeting, the camera and microphone are activated.

[0983] Output: A stream of real-time video and audio data is captured.

[0984] Step 2:

[0985] The device adds metadata (such as who is speaking and the progress of the conference) to the captured video and audio data, and sends this to the server at regular intervals.

[0986] Input requirements: Captured video and audio data.

[0987] Specific operation: Adds speaker recognition and timestamps to video and audio data.

[0988] Output: Packs of video and audio data with metadata are generated.

[0989] Step 3:

[0990] The server receives the conference data (video, audio, metadata) sent from the terminals and stores it in local storage or a database.

[0991] Input requirements: Meeting data with metadata.

[0992] Specific operation: After the server receives the data, it stores it in cloud storage such as AWS S3 or RDS.

[0993] Output: Saved meeting data.

[0994] Step 4:

[0995] The server inputs the saved meeting data into the generative AI model, analyzes the data, and uses the generative AI model to generate feedback.

[0996] Requirements as input: Saved meeting data.

[0997] Specific operation: Input the saved meeting data into a generative AI model (e.g., a natural language processing model) and analyze the frequency of comments and question and answer patterns.

[0998] Output: Feedback information based on the analysis results.

[0999] Step 5:

[1000] The server compiles the feedback generated by the generative AI model and sends it to the device.

[1001] Requirements as input: Feedback generated by a generative AI model.

[1002] Specific operation: The feedback information is formatted based on a template and sent to the terminal.

[1003] Output: The formatted feedback data is sent to the terminal.

[1004] Step 6:

[1005] The user can view the feedback received through the device and check the specific content.

[1006] Requirement as input: Feedback data sent by the server.

[1007] Specific operation: The user logs in to the feedback email or dedicated web portal on the device to view the feedback.

[1008] Output: User reviews the feedback and gets specific improvements for the next meeting.

[1009] (Application example 1)

[1010] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1011] Conventional meeting progress and feedback systems do not adequately capture real-time data or provide prompt feedback, resulting in limited improvements in meeting efficiency and facilitation skills. Furthermore, efficient communication is required for meetings and work instructions at production sites and factories, but current systems do not provide sufficient support. Therefore, a new system is needed to improve the quality of meetings.

[1012] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1013] In this invention, the server includes a means for capturing and transmitting video and audio data of the conference from the terminal, a means for storing the received data, a means for analyzing the stored data and generating feedback using a generation AI, a means for providing prompt feedback to the facilitator during or after the conference, a means for supporting the efficiency of meetings and work instructions within the factory, and a means for transmitting the generated feedback to the terminal. This enables the capture and analysis of conference data in real time, realizing the provision of prompt and effective feedback. Furthermore, it supports efficient communication and work instructions within the factory, improving the quality of meetings at the production site.

[1014] A "terminal" is a computing device used to capture and transmit video and audio data to a server.

[1015] "Video data" refers to video information that visually records the progress of the conference and the appearance of each participant.

[1016] "Audio data" refers to acoustic information used to record statements and conversations made during a meeting.

[1017] "Capture" is the process of collecting video and audio data and storing it in digital form.

[1018] "Send" is the operation of moving data from a terminal to a server via a network.

[1019] A "server" is a multi-computing device for storing and analyzing received video and audio data.

[1020] "Storage" is the process of storing data in storage for later use.

[1021] "Analysis" refers to data processing operations that process stored data and extract useful information.

[1022] "Generative AI" is a system that uses artificial intelligence technology to generate feedback and advice based on various data.

[1023] "Feedback" is a response that provides participants and facilitators with information about the meeting's evaluation, areas for improvement, strengths, etc.

[1024] A "facilitator" is a person whose role is to manage the progress of a meeting and promote dialogue among participants.

[1025] "Fast" refers to the property of reacting or processing within a short period of time.

[1026] A "factory" is a facility for manufacturing products.

[1027] "Work instructions" are instructions that clearly state the work content and procedures within a factory.

[1028] "Efficiency" means achieving maximum results while minimizing the use of resources and time.

[1029] The present invention is a system that streamlines meetings and provides prompt and objective feedback to facilitators. This system functions effectively by combining a terminal, a server, and a generative AI model. Specific embodiments are described below.

[1030] Hardware Configuration

[1031] Terminal: A device used to capture video and audio data from a meeting. Examples include a PC or smartphone. A camera and microphone are connected to the terminal, and data is collected using these devices.

[1032] Server: A computer that stores and analyzes received video and audio data. The server includes local storage or a database.

[1033] Software Configuration

[1034] Data capture module: Executed by the device, it activates the camera and microphone at the start of the meeting and captures data in real time. The captured data is sent to the server at regular intervals.

[1035] Data storage module: Runs on the server, receives data sent from the device, and stores it in local storage or a database.

[1036] Data analysis module: A program for analyzing data stored on the server. This module uses a generative AI model (e.g., GPT-3) to analyze the meeting content from multiple angles.

[1037] Feedback generation module: Based on the information obtained from the data analysis module, feedback is generated to specifically identify the facilitator's strengths and areas for improvement. The generated feedback is sent to the device.

[1038] User interface: Runs on the device and allows the user to view the generated feedback. Specific feedback is displayed as text information.

[1039] Data Flow and Processing

[1040] Terminal: When the meeting starts, the data capture module activates the camera and microphone to capture video and audio in real time. The captured data includes metadata such as video information for each frame, audio information, and the progress of the meeting. This data is sent to the server at regular intervals.

[1041] Server: Stores the received meeting data and analyzes it using a generative AI model. The analysis evaluates each participant's frequency of speech, patterns of Q&A, and best practices and areas for improvement in the proceedings. For example, the server may extract information such as "Participant A speaks frequently" or "Participant A is too focused on a particular topic."

[1042] Feedback generation module: Based on the analysis results, specific feedback is generated for the facilitator, such as "You gave many participants the opportunity to speak" or "The time allocation was unbalanced."

[1043] User reception: The generated feedback is sent to the device, and the user can view it and use it to improve the next meeting. Specifically, the user can incorporate improvement measures such as "giving everyone a chance to speak in the next meeting."

[1044] Specific examples and generative AI model prompts

[1045] As a concrete example, consider a work instruction meeting in a factory. Using this system, data from the meeting is captured and analyzed. The generating AI provides feedback such as "points where the order of work instructions should be improved" and "points where communication went smoothly."

[1046] Example prompts for generative AI models:

[1047] Analyze the following data and generate feedback on the facilitators' strengths and areas for improvement:

[1048] Meeting data: [Audio and video data of the meeting]

[1049] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1050] Step 1:

[1051] Device-based data capture

[1052] When a meeting starts, the device activates its camera and microphone and captures the video and audio data of the meeting in real time. The video and audio of the meeting are given as input, and this is collected as digital data. Specifically, the device obtains video information, audio information, and metadata (such as who is speaking and the progress of the meeting) for each frame. This records the progress of the meeting. The output is the captured data.

[1053] Step 2:

[1054] Sending data from the device to the server

[1055] The device sends the captured video and audio data to the server at regular intervals. The data captured in step 1 is given as input, and this data is sent to the server via the network. Specifically, the data is sent using a protocol such as HTTP, which allows the server to receive the data. The output is the sent data.

[1056] Step 3:

[1057] Data storage by server

[1058] The server stores the video and audio data received from the device in local storage or a database. The input is the data sent from the device, and this data is stored for efficient management. Specifically, the data is stored using a database management system (e.g., MySQL or PostgreSQL). This ensures that the data is available for subsequent analysis processes. The output is the stored data.

[1059] Step 4:

[1060] Data analysis

[1061] The server analyzes the stored data and uses a generative AI model to analyze the meeting content from multiple angles. The input is the stored data, and based on this data, it evaluates the frequency of each participant's comments, question and answer patterns, and best practices and areas for improvement in the proceedings. Specifically, it uses machine learning libraries such as TensorFlow and PyTorch to build models and perform analysis. This provides detailed evaluation information for the meeting. The output is the analysis results.

[1062] Step 5:

[1063] Feedback Generation

[1064] Based on the analysis results, the server uses a generative AI model to generate feedback that specifically identifies the facilitator's strengths and areas for improvement. The input is the analysis results, and based on these results, feedback is generated using a natural language processing model (e.g., GPT-3). Specifically, specific prompts are provided to the AI ​​model, which generates feedback in response. This results in declarative and useful feedback. The output is the generated feedback.

[1065] Step 6:

[1066] Sending and Viewing Feedback

[1067] The server sends the generated feedback to the terminal, which then displays it to the user. The input is the generated feedback, which is sent to the terminal. Specifically, the feedback content is processed as text and displayed on the user interface. This allows the user to receive feedback quickly and easily. The output is the displayed feedback.

[1068] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1069] This invention combines a feedback system for meeting facilitation with an emotion engine that recognizes the user's emotions. The main features of this system are the capture and analysis of meeting data, the generation of feedback using a generative AI, and the recognition and evaluation of the user's emotional state using an emotion engine. The operation of the terminal, server, and user is described in detail below.

[1070] Device behavior

[1071] At the start of a meeting, the device activates its camera and microphone to capture video and audio data of the meeting in real time. This data includes video and audio information for each frame, as well as metadata such as participants' facial expressions and tone of voice. The device is equipped with an emotion engine that uses the captured data to recognize the user's emotions in real time. This analysis data is then sent to a server at regular intervals.

[1072] For example, the device can be a PC or smartphone, and the camera and microphone will automatically start up when the meeting begins. The captured data is analyzed in real time by the emotion engine, and the analysis results are sent to the server. For example, it can recognize participants' emotional states, such as "tensed" or "relaxed," from their facial expressions.

[1073] Server Operation

[1074] The server receives the meeting data sent from the devices and stores it in local storage or a database. The stored data is then analyzed using a generative AI and emotion engine. The generative AI analyzes the meeting content from multiple angles and generates feedback on the facilitator's strengths and areas for improvement. The emotion engine also recognizes emotions based on participants' facial expressions and tone of voice and incorporates them into the analysis results.

[1075] For example, after receiving the meeting data, the server uses an emotion engine to analyze the emotional state of the participants for each frame. Next, the generation AI generates specific feedback based on the analysis results, such as "Participant A is nervous while speaking" or "The facilitator is helping Participant B relax."

[1076] User Use

[1077] The user receives the feedback sent from the server on their device and can view the specific details. The feedback includes not only the strengths and areas for improvement of the facilitator's progress, but also information about the emotional state of each participant. This allows the user to take measures to improve the session based on their emotional state.

[1078] For example, after a meeting, the user can review feedback such as "Many participants were given the opportunity to speak" or "Participant A is nervous because he or she is concentrating too much on a particular topic." At the next meeting, the user can refer to the analysis results of the emotion engine and develop measures to improve the emotional state of the participants.

[1079] System Features

[1080] The system's features include real-time data capture and analysis, advanced feedback generation using generative AI, and user emotional recognition using an emotion engine. Facilitators can adjust the progress of the meeting while understanding the emotional state of the participants, and after the meeting, they can take advantage of detailed feedback to make improvements for the next meeting.

[1081] ---

[1082] The system of the present invention integrates hardware and software to support the effective progress of meetings and the improvement of facilitation skills, which is expected to lead to efficient and productive meeting management.

[1083] The processing flow will be explained below.

[1084] Step 1:

[1085] Device: When a meeting starts, the camera and microphone are activated to capture video and audio data of the meeting in real time. For example, when a meeting starts, the camera and microphone are automatically activated, so that the device is ready to capture the entire meeting.

[1086] Step 2:

[1087] Device: Analyzes video and audio data in real time and recognizes participants' emotions through an emotion engine. Specifically, it identifies emotions such as "joy," "anger," "sadness," and "relaxation" based on information such as participants' facial expressions, tone of voice, and volume.

[1088] Step 3:

[1089] Device: Captured video and audio data, along with associated emotional data, is sent to the server at regular intervals (e.g., every minute). This allows the data to be accumulated on the server in real time. For example, the data is sent via an HTTP request.

[1090] Step 4:

[1091] Server: Receives the meeting data sent from the devices and stores it in local storage or a database, allowing the data required for analysis to be saved and used for subsequent processing.

[1092] Step 5:

[1093] Server: The received data is passed to the generation AI and emotion engine and analysis begins. The data is evaluated from multiple angles, including the frequency of each participant's speech, the content of the conversation, facial expressions, and tone of voice.

[1094] Step 6:

[1095] Server: Creates feedback based on the analysis results. The feedback includes the facilitator's strengths and areas for improvement in the process, as well as the emotional state of each participant. For example, the server lists specific points such as "Participant A seemed nervous while speaking" or "Participant B seemed relaxed."

[1096] Step 7:

[1097] Server: Sends the created feedback to the device, allowing users to receive feedback in real time or after the meeting ends.

[1098] Step 8:

[1099] User: Receives and reviews feedback sent from the server, identifies specific areas for improvement, strengths, and participants' emotional state, and considers measures for the next meeting.

[1100] Step 9:

[1101] Users: Based on the feedback they receive, they can take practical steps to improve their facilitation skills, leading to more effective meetings in the future.

[1102] Through these steps, the meeting facilitation feedback system, which combines generative AI and an emotion engine, completes a series of operations.

[1103] Example 2

[1104] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1105] Conventional online meeting systems have the problem of making it difficult to grasp the progress of the meeting and the emotional state of participants in real time. As a result, facilitators are unable to receive appropriate feedback, which can lead to a decline in the quality and efficiency of the meeting. Furthermore, there is a lack of information to identify specific areas for improvement after the meeting, which can lead to the same issues recurring in the next meeting.

[1106] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1107] In this invention, the server includes means for capturing and transmitting video and audio data of the conference from the terminals, means for analyzing the captured data in real time using an emotion engine and recognizing the user's emotion, means for saving the data received by the server, means for analyzing the saved data using a generative AI model and the emotion engine and generating feedback, and means for sending the generated feedback to the terminals, thereby enabling the facilitator to receive specific and real-time feedback during and after the conference.

[1108] A "terminal" is a computing device for capturing and analyzing video and audio data of a conference in real time.

[1109] The "emotion engine" is a software module that analyzes captured video and audio data to recognize the user's emotional state.

[1110] A "server" is a high-performance computing system that receives and stores data sent from a terminal and performs further analytical processing.

[1111] The "generative AI model" is an artificial intelligence algorithm that analyzes the content of a meeting from multiple perspectives and generates feedback that includes the facilitator's strengths and areas for improvement.

[1112] "Feedback" is the analysis result of the generative AI model and emotion engine, including an evaluation of the meeting's progress and areas for improvement.

[1113] "Data capture" is the process of capturing video and audio of a meeting in real time.

[1114] "Data transmission" is the process of sending captured video and audio data and analysis results from the terminal to the server.

[1115] "Data storage" is the process by which the server records the received data in local storage or a database.

[1116] This invention combines a feedback system for meeting facilitation with an emotion engine that recognizes the user's emotions. The main features of this system are the capture and analysis of meeting data, the generation of feedback using a generative AI, and the recognition and evaluation of the user's emotional state using an emotion engine. This system performs specific operations on the terminal, server, and user. Each operation is explained in detail below.

[1117] Device behavior

[1118] The device automatically activates its camera and microphone as soon as the meeting begins, preparing to capture the meeting's video and audio data in real time. The device is equipped with an emotion engine that uses the captured data to recognize participants' emotions in real time. This recognized emotion data is sent to the server at regular intervals.

[1119] Example: When a user opens a conference app on their PC or smartphone and presses the "Start Conference" button, the camera and microphone are automatically activated. As the conference progresses, the device's emotion engine captures the video and audio data of the participants, recognizes their emotional states in real time, such as "Participant A is nervous while speaking" or "Participant B is relaxed," and sends this data to the server.

[1120] Server Operation

[1121] The server receives the emotion data and video / audio data sent from the device and first stores it in local storage or a database. The stored data is then analyzed using a generative AI model and emotion engine. The generative AI model analyzes the text data of the meeting content from multiple angles and generates feedback based on the facilitator's strengths and areas for improvement. At the same time, the emotion engine analyzes the emotion data and incorporates the results into the analysis results of the generative AI model.

[1122] Example: The server receives the meeting data and uses an emotion engine to analyze the participants' emotional states for each frame. Based on this, the generative AI model generates specific feedback, such as "Participant A was feeling tense while speaking" or "The facilitator is creating a relaxed atmosphere for Participant B."

[1123] User Use

[1124] After the meeting, users receive feedback sent from the server on their devices and check the content. The feedback includes not only the facilitator's strengths and areas for improvement in the meeting's progress, but also information about the participants' emotional states. This allows users to take measures to improve the meeting based on their emotional states.

[1125] Example: After a meeting, a user opens a feedback report in the meeting app and sees detailed feedback such as "Many participants were given the opportunity to speak" and "Participant A was nervous because he was too focused on a particular topic." In the next meeting, the user can refer to this feedback and take measures to improve the emotional state of the participants.

[1126] Prompt Sentence Examples

[1127] "Please explain in detail the processing flow of a system that allows the facilitator to recognize participants' emotions during a meeting and provide feedback on specific areas for improvement. Please also clearly explain the roles of the terminal and server in this system."

[1128] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1129] Step 1:

[1130] As soon as the conference starts, the device automatically activates its camera and microphone to capture the conference video and audio data. At this stage, the conference video information and audio data are the input. Specifically, when the user presses the "Start Conference" button, the device's camera and microphone activate, and video and audio are captured in real time. The output is the captured video and audio data.

[1131] Step 2:

[1132] The device passes the captured data to the emotion engine for real-time analysis. The input is the captured video and audio data. The emotion engine analyzes this data and recognizes the emotional state of the participants. Specifically, the emotion engine analyzes facial expressions from the video data and tone of voice from the audio data. The output is the analyzed emotion data.

[1133] Step 3:

[1134] The device sends the analyzed emotion data to the server at regular intervals. The input is the emotion data generated by the emotion engine. Specifically, the device sets a timer and collects the emotion data into packets at regular intervals and sends them to the server. The output is the emotion data sent to the server.

[1135] Step 4:

[1136] The server receives data sent from the device and stores it in local storage or a database. The input is the emotion data sent from the device. Specifically, the server's data receiving module detects new data packets and writes them to the storage or database. The output is the stored data.

[1137] Step 5:

[1138] The server uses the stored data to perform analysis using a generative AI model and emotion engine. The input is the stored emotion data. Specifically, the emotion engine reanalyzes the emotion data, and the generative AI model analyzes the meeting content from multiple angles to generate feedback. The output is the feedback generated by the generative AI model and emotion engine.

[1139] Step 6:

[1140] The server sends the generated feedback to the terminal. The input is the generated feedback. In concrete terms, the server packs the feedback data into packets and sends them to the terminal. The output is the feedback sent to the terminal.

[1141] Step 7:

[1142] After the meeting ends, the user receives and checks the feedback on their device. The input is the feedback sent from the server. Specifically, the user opens the meeting app and presses the "View Feedback" button to display the received feedback. The output is the feedback displayed on the device.

[1143] Example prompt sentence:

[1144] "Please explain in detail the processing flow of a system that allows the facilitator to recognize participants' emotions during a meeting and provide feedback on specific areas for improvement. Please also clearly explain the roles of the terminal and server in this system."

[1145] (Application example 2)

[1146] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1147] There is a need to accurately grasp the emotional state of factory workers and provide specific feedback in real time to improve work efficiency and safety. However, currently, there is a lack of means to recognize changes in workers' mental state and stress in real time and provide appropriate feedback based on that. As a result, work efficiency can decrease and safety issues can arise. Furthermore, conventional systems do not properly evaluate workers' emotional state, making it difficult to take appropriate improvement measures.

[1148] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing and transmitting video and audio data from the terminal, means for saving the data received by the server, means for analyzing the saved data and generating feedback using a generation AI, means for sending the generated feedback to the terminal, an emotion engine for recognizing the emotions of workers based on the analyzed data, means for generating feedback regarding work efficiency and safety based on the recognized emotion data, and means for notifying on-site workers and managers of the generated feedback. This makes it possible to grasp the emotional state of workers in real time and provide specific feedback based on that.

[1149] A "terminal" is a device that has the function of capturing video and audio data and transmitting it to a server.

[1150] A "server" is a device or system that can store and analyze received data.

[1151] "Generative AI" refers to artificial intelligence technology that analyzes stored data and automatically generates feedback.

[1152] "Emotion engine" refers to technology that recognizes a person's emotional state from video and audio data.

[1153] "Work efficiency" is an indicator that shows the efficiency and productivity of workers' work.

[1154] "Safety" refers to the ability to minimize hazards in the work environment and prevent accidents and injuries.

[1155] "Feedback" refers to specific information and improvement measures generated based on analyzed data and emotional state.

[1156] "Notification" refers to the means by which generated feedback is communicated to field workers and managers in real time.

[1157] The system for implementing this invention can grasp the emotional state of workers in a factory in real time and provide specific feedback to improve work efficiency and safety. Each component of the system and its operation will be described in detail below.

[1158] Device behavior

[1159] The system's terminal is a device capable of capturing video and audio data and sending it to a server. Specifically, it has a built-in camera and microphone, which captures video and audio from the factory work area in real time. The terminal is equipped with a function to preprocess the captured data using OpenCV. Furthermore, an emotion engine is implemented using TensorFlow to recognize the emotional state of the worker from the captured data. The recognized emotion data is sent to the server at regular intervals.

[1160] Server Operation

[1161] The server receives the data sent from the terminal and stores it in a database. The stored data is analyzed by a generative AI using TensorFlow. The generative AI performs multifaceted analysis of the worker's emotional state, work efficiency, and safety, and generates specific feedback. Once the feedback is generated, it is immediately notified to the worker and manager on-site. This notification is sent via digital signage and a smartphone app.

[1162] User Use

[1163] The user receives the generated feedback on their device and views its contents. The feedback includes information on the worker's emotional state, as well as measures to improve work efficiency and safety. This allows the user to take appropriate improvement measures based on the worker's emotional state. For example, if the system recognizes that a worker is "tense," it will provide feedback such as "shorten work time" or "encourage them to take a break."

[1164] Hardware and software used

[1165] Hardware: Cameras, microphones, servers, digital signage, smartphones

[1166] Software: OpenCV, TensorFlow, database (e.g. MySQL)

[1167] Prompt Sentence Examples

[1168] Here are some examples of prompts for generative AI models:

[1169] Generate feedback based on a worker's emotional state. For example, if a worker is "tense," provide a recommended action.

[1170] Emotional state: Tense

[1171] Recommended actions: Reduce work time and encourage breaks

[1172] In this way, the system for implementing this invention can grasp the emotional state of workers in the field in real time and provide appropriate feedback immediately, which will greatly contribute to improving work efficiency and ensuring safety.

[1173] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1174] Step 1:

[1175] The terminal activates the camera and microphone to capture video and audio data of the factory work area in real time. The input is raw video and audio data from the camera and microphone. The output is the captured video and audio data. Specifically, the camera captures several frames per second, and the microphone picks up surrounding audio.

[1176] Step 2:

[1177] The device preprocesses the captured video and audio data. The input is the raw data obtained in step 1. OpenCV is used to convert the video data to grayscale, detect faces, and resize them. Preprocessing such as noise removal is performed on the audio data. The output is the preprocessed video and audio data.

[1178] Step 3:

[1179] The device inputs preprocessed video and audio data into an emotion engine using TensorFlow to recognize the worker's emotional state. The input is the preprocessed data. The emotion engine analyzes this data and identifies the emotional state (e.g., nervous, relaxed, stressed, etc.). The output is a label for the emotional state. Specifically, the emotion recognition model analyzes facial expressions and tone of voice to classify emotions.

[1180] Step 4:

[1181] The device sends the recognized emotion data to the server at regular intervals. The input is the emotional state label obtained in step 3. As an output, the emotion data is sent to the server. This involves transferring the data to the server using a communication protocol.

[1182] Step 5:

[1183] The server stores emotion data and other video and audio data received from the device. The input is the data sent from the device. The output is the received data stored in a database. Specifically, the server stores the data using a database system (e.g., MySQL).

[1184] Step 6:

[1185] The server analyzes the stored data and generates feedback using a generation AI. The inputs are the video, audio, and emotional data stored in the database. The generation AI evaluates the emotional state, work efficiency, and safety based on this data, and generates specific feedback. The generated feedback is obtained as the output.

[1186] Step 7:

[1187] The server notifies the generated feedback to the workers and managers on-site. The input is the feedback obtained in step 6. As an output, a notification is sent to the workers' terminals and digital signage. Specifically, the server sends a notification message via the network, conveying the feedback to the workers and managers in real time.

[1188] Through these steps, the system grasps the worker's emotional state in real time and provides specific feedback that contributes to improving work efficiency and safety.

[1189] 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.

[1190] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1191] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1192] 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.

[1193] FIG. 9 is a diagram illustrating 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 actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect 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.

[1194] 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.

[1195] 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).

[1196] 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 indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, 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 indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1197] 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."

[1198] 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.

[1199] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1200] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1201] 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.

[1202] 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.

[1203] 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.

[1204] The hardware resource for executing a specific process can be any of the following processors: An example of a processor 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. Another example of a processor is 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.

[1205] The hardware resource that executes the specific processing 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 processing may be a single processor.

[1206] 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.

[1207] 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.

[1208] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1209] 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.

[1210] The following is further disclosed regarding the above embodiment.

[1211] (Claim 1)

[1212] means for capturing and transmitting video and audio data of the conference from the terminal;

[1213] a means for storing the received data on the server;

[1214] A means for analyzing the stored data and generating feedback using generative AI;

[1215] means for transmitting the generated feedback to the terminal;

[1216] A system including:

[1217] (Claim 2)

[1218] 2. The system according to claim 1, wherein the server evaluates the frequency of speech and question-and-answer patterns of each participant when analyzing the conference data.

[1219] (Claim 3)

[1220] 2. The system according to claim 1, wherein the terminal captures the conference data in real time and transmits the data to the server at regular intervals.

[1221] "Example 1"

[1222] (Claim 1)

[1223] means for capturing and transmitting video and audio data of the conference from the terminal;

[1224] a means for storing the received data on the server;

[1225] A means for analyzing the stored data with a generative AI model and generating feedback;

[1226] means for transmitting the generated feedback to the terminal;

[1227] A system including:

[1228] (Claim 2)

[1229] 2. The system according to claim 1, wherein the server analyzes the conference data, evaluates the frequency of speech of each participant and patterns of questions and answers, and generates feedback based on the evaluation.

[1230] (Claim 3)

[1231] 2. The system according to claim 1, wherein the terminal captures the conference data in real time and transmits the data to the server at regular intervals.

[1232] "Application Example 1"

[1233] (Claim 1)

[1234] means for capturing and transmitting video and audio data of the conference from the terminal;

[1235] a means for storing the received data on the server;

[1236] A means for analyzing the stored data and generating feedback using generative AI;

[1237] A means of providing immediate feedback to the facilitator during or after the meeting;

[1238] A means to support the efficiency of meetings and work instructions within the factory,

[1239] means for transmitting the generated feedback to the terminal;

[1240] A system including:

[1241] (Claim 2)

[1242] 2. The system according to claim 1, wherein the server analyzes the meeting data to evaluate each participant's speech frequency and question-and-answer patterns, thereby supporting the improvement of communication efficiency within the factory.

[1243] (Claim 3)

[1244] 2. The system according to claim 1, wherein the terminal captures the conference data in real time and transmits the data to the server at regular intervals.

[1245] "Example 2: Combining Emotion Engines"

[1246] (Claim 1)

[1247] means for capturing and transmitting video and audio data of the conference from the terminal;

[1248] a means for analyzing the data captured by the emotion engine in real time and recognizing the user's emotions;

[1249] a means for storing the received data on the server;

[1250] A means for analyzing the stored data using a generative AI model and an emotion engine to generate feedback;

[1251] means for transmitting the generated feedback to the terminal;

[1252] A system including:

[1253] (Claim 2)

[1254] 2. The system according to claim 1, wherein the server evaluates the emotional state, speech frequency, and question and answer patterns of each participant when analyzing the conference data.

[1255] (Claim 3)

[1256] 2. The system according to claim 1, wherein the terminal captures the conference data in real time and transmits the analysis results to the server at regular intervals.

[1257] "Application example 2 when combining emotion engines"

[1258] (Claim 1)

[1259] means for capturing and transmitting video and audio data from the terminal;

[1260] a means for storing the received data on the server;

[1261] A means for analyzing the stored data and generating feedback using generative AI;

[1262] means for transmitting the generated feedback to the terminal;

[1263] An emotion engine that recognizes the emotions of workers based on analyzed data,

[1264] A means for generating feedback regarding work efficiency and safety based on the recognized emotion data;

[1265] A means of communicating the generated feedback to field workers and management;

[1266] A system including:

[1267] (Claim 2)

[1268] 2. The system according to claim 1, which uses an emotion engine to recognize the emotional state of workers in real time from their facial expressions and tone of voice.

[1269] (Claim 3)

[1270] 2. The system according to claim 1, wherein the terminal captures video data in real time and transmits the data to the server at regular intervals. [Explanation of symbols]

[1271] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for capturing and transmitting video and audio data of the conference from the terminal; a means for storing the received data on the server; A means for analyzing the stored data and generating feedback using generative AI; means for transmitting the generated feedback to the terminal; A system including:

2. 2. The system according to claim 1, wherein the server evaluates the frequency of speech and question-and-answer patterns of each participant when analyzing the conference data.

3. 2. The system according to claim 1, wherein the terminal captures the conference data in real time and transmits the data to the server at regular intervals.

Images