System

Abstract

A system is provided.SOLUTION: A system comprising: means for presetting a purpose, a precondition, a rule, and an additional condition of a conference; means for performing AI recognition in real time and converting utterances of participants into text; means for analyzing the utterances converted into text by a generation-related AI model and generating appropriate feedback and additional questions; means for transmitting the generated feedback and questions to terminals of the participants; and means for recording utterance contents and feedback of the generation-related speech during the conference.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] In traditional meetings, facilitators are required to take the time and effort to conduct meetings in a neutral and fair manner, but efficient conduct is difficult. Furthermore, comments and discussions during meetings are often unclear, leading to disagreements between participants. Furthermore, meeting records and post-meeting reviews are often insufficient, making it difficult to use the information in the next meeting. There is a need for a system that can solve these issues and ensure efficient and fair meeting conduct. [Means for solving the problem]

[0005] The present invention solves the above problems by providing a system that includes a means for setting the purpose, prerequisites, rules, and additional conditions of a meeting in advance, a means for performing real-time speech recognition and converting participants' comments into text, a means for analyzing the converted text using a generative AI model and generating appropriate feedback and follow-up questions, a means for transmitting the generated feedback and questions to participants' devices, and a means for recording the comments made during the meeting and the generative AI feedback. Furthermore, by providing a means for later reviewing the recorded meeting content and a means for providing participants with speech recognition results not only in text but also in audio, it is possible to ensure efficient and fair meeting progress and comprehensive recording.

[0006] The "purpose of the meeting" refers to the goal or theme that the meeting is trying to achieve.

[0007] "Preconditions" refer to conditions and background information that are set in advance for holding a conference.

[0008] "Rules" refer to the rules and guidelines set to ensure that meetings proceed smoothly and efficiently.

[0009] "Additional conditions" refer to supplementary conditions or restrictions that are required in addition to the main conditions.

[0010] "Speech recognition" refers to the technology of analyzing speech and converting it into text.

[0011] "Converting to text" refers to expressing speech input as text information.

[0012] A "generative AI model" refers to an artificial intelligence model that makes predictions and generates data based on input data.

[0013] "Feedback" refers to the answers and advice that a generative AI model provides in response to input information.

[0014] "Follow-up questions" refer to further questions provided by the generative AI model to deepen statements or discussions.

[0015] "Participant's terminal" refers to a device or equipment used by a participant in a conference.

[0016] "Recording" refers to saving what is said in a meeting and the feedback from generative AI.

[0017] "Reviewing later" refers to checking and reflecting on the recorded content after the meeting has ended.

[0018] "Providing audio" refers to playing textual information as audio. [Brief explanation of the drawings]

[0019] [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

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] The present invention relates to a meeting progress system using a generative AI model to improve the efficiency and fairness of meetings. This system includes a means for setting the purpose, prerequisites, rules, and conditions of a meeting in advance, a means for real-time speech recognition and conversion of comments into text, a means for analyzing the content of comments using a generative AI model and generating feedback and follow-up questions, a means for sending the generated information to the participants' devices, a means for recording comments and feedback during the meeting, and a means for later reviewing these records.

[0041] System configuration

[0042] The server is responsible for the main processing and plays a central role in the progress of the conference. The server houses the speech recognition engine, generative AI model, and database. On the other hand, the terminals are devices used by participants to communicate with the server. Users join the conference and operate their terminals to exchange data with the server.

[0043] Explanation of program processing

[0044] 1. Set up a meeting:

[0045] The user (organizer) inputs the purpose, prerequisites, rules, and additional conditions of the meeting through the interface and sends them to the server, which stores this information in a database and uses it to progress the meeting.

[0046] 2. Start the meeting:

[0047] When a conference starts, the server sends a notification to the participants' devices to announce the start of the conference. The devices activate their microphones and collect audio data in real time. This audio data is then sent to the server.

[0048] 3. Speech Recognition and Text Transcription:

[0049] The server runs the received voice data through a speech recognition engine and converts what is being said into text, which is then input into a generative AI model for analysis.

[0050] 4. Generate feedback and questions:

[0051] The generative AI model analyzes the textual utterances and generates appropriate feedback and follow-up questions based on the meeting's objectives and rules. The generated feedback and questions are then sent to the device.

[0052] 5. Provision of Information:

[0053] The terminal provides the user with feedback and questions received from the server via voice or text, providing guidance for the progress of the meeting.

[0054] 6. Records of meetings:

[0055] All statements made during the meeting, as well as any feedback or questions generated, are recorded by the server, and these recordings are stored for later review and analysis.

[0056] Specific examples

[0057] 1. Pre-settings:

[0058] The user enters the purpose of the meeting, such as "Check the progress of project X and discuss countermeasures for delays," into the interface and sends it to the server, which then stores this information in a database.

[0059] 2. Meeting begins:

[0060] At the designated start time, the server sends a notification to each participant's device to announce the start of the conference. The device starts collecting voice data and sends it to the server.

[0061] 3. Speech, transcription and feedback:

[0062] User A says, "Currently, the project is one week behind schedule." The device sends this speech to the server, which converts it into text using a speech recognition engine. The generative AI model analyzes the text and generates feedback such as, "What is causing the delay? Are there any specific obstacles?" The device then relays this feedback to User A via voice.

[0063] 4. New statements and responses:

[0064] User B responds, "The main cause is a lack of resources." The device sends this speech to the server, which converts it into text and analyzes it using a generative AI model. The device generates a question, "Do we need more resources, or can we address this in other ways?" and relays this to User B.

[0065] This not only helps organize what is being said and keeps the meeting running smoothly, but also allows for accurate review later.

[0066] The processing flow will be explained below.

[0067] Step 1:

[0068] The user (organizer) inputs the purpose, prerequisites, rules, and additional conditions of the meeting into the interface and sends them to the server, which stores this information in a database.

[0069] Step 2:

[0070] The server sends a notification to each participant at the start time of the conference, announcing the start of the conference. The terminal receives the notification and prepares to collect voice data.

[0071] Step 3:

[0072] When the conference starts, the device activates the microphone and collects participants' speech as audio data, which is then sent to the server in real time.

[0073] Step 4:

[0074] The server converts the received voice data into text data using a speech recognition engine, which is then input into a generative AI model.

[0075] Step 5:

[0076] The generative AI model analyzes text data and generates appropriate feedback and follow-up questions based on the meeting's objectives and rules.

[0077] Step 6:

[0078] The generated feedback and questions are sent from the server to the device, which then provides the received feedback and questions to the user in voice or text format.

[0079] Step 7:

[0080] The user makes further statements and answers based on the feedback and questions from the generative AI model, and the device again transmits these new statements as voice data to the server.

[0081] Step 8:

[0082] The server then converts the newly received voice data into text using a speech recognition engine and analyzes it using a generative AI model. This process is repeated throughout the conference.

[0083] Step 9:

[0084] All statements made during the meeting, as well as feedback and questions from the generative AI model, are recorded by the server, and the recordings are time-stamped, allowing the order and time of statements to be tracked.

[0085] Step 10:

[0086] After the meeting, the server organizes all recorded data and automatically generates meeting minutes, which are then stored for user access.

[0087] Step 11:

[0088] Users can check the minutes of the meeting and make corrections or additional comments as necessary, which can be useful in preparing for the next meeting.

[0089] Step 12:

[0090] For the next meeting, the server can refer to past records and help set new topics and goals for discussion.

[0091] Example 1

[0092] 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."

[0093] Conventional conference systems are inefficient in sharing information and advancing discussions among participants, and have limitations in recording what is being said and providing feedback. Furthermore, real-time speech recognition, transcription of speech, and subsequent generation of feedback and questions are all performed manually, which can easily disrupt the flow of the meeting. This creates problems that reduce the efficiency and fairness of meetings.

[0094] 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.

[0095] In this invention, the server includes means for setting the purpose, prerequisites, rules, and additional conditions of the meeting in advance, means for performing real-time speech recognition and converting participants' comments into text, means for analyzing the textual comments with a generative AI model and generating appropriate feedback and follow-up questions, means for transmitting the generated feedback and questions to the participants' terminals, means for recording the comments made during the meeting and the feedback from the generative AI, means for sending a notification to the participants' terminals at the start of the meeting and starting to collect voice data, means for transmitting the voice data to the server in streaming format, means for inputting prompt sentences into the generative AI model, and means for displaying the comments, generated feedback, and questions on a screen or by voice, thereby enabling real-time feedback provision and efficient meeting progress.

[0096] "Means for setting the purpose, prerequisites, rules, and additional conditions of a meeting in advance" refers to an interface and software for inputting information and rules necessary for the progress of a meeting in advance and storing them in a database.

[0097] "Means for real-time speech recognition and conversion of participants' speech into text" refers to a speech recognition engine and related technology for instantly converting participants' speech into text during a meeting.

[0098] "Means of analyzing textual comments using a generative AI model to generate appropriate feedback and follow-up questions" refers to software that analyzes textual comments using an AI model that uses natural language processing technology, and automatically generates feedback and questions based on the purpose and rules of the meeting.

[0099] "Means for transmitting generated feedback and questions to participant devices" refers to the communications means and protocols for transmitting feedback and questions generated by the AI ​​model to participant devices.

[0100] "Means for recording statements made during meetings and feedback from the generative AI" refers to a system configuration for storing all statements made during meetings and feedback provided by the generative AI in a database.

[0101] "Means for sending a notification to the participant's device at the start of the meeting and starting the collection of audio data" refers to software and hardware for sending a notification to the participant's device at the start of the meeting, activating the microphone, and starting the collection of audio data.

[0102] "Means for transmitting audio data to a server in streaming format" refers to data communications technologies and protocols for transmitting collected audio data to a server in real time.

[0103] "Means for inputting prompts into a generative AI model" refers to interfaces and software tools for inputting text data and instructions for analysis into a generative AI model.

[0104] "Means for displaying or providing audio of statements, generated feedback, and questions" refers to the interface and speech synthesis engine for providing visual or audio notification of generated feedback and questions to the participant's device.

[0105] This invention relates to a conference progress system that uses a generative AI model to improve the efficiency and fairness of conferences. This system is mainly composed of a server, terminals, and users. The details are explained below.

[0106] System configuration

[0107] The server is responsible for the main processing and plays a central role in the progress of the conference. The server houses the speech recognition engine, generative AI model, and database. The terminals are devices used by participants to communicate with the server. Users join the conference and operate their terminals to exchange data with the server.

[0108] Meeting Setup

[0109] First, the user (organizer) inputs the purpose, prerequisites, rules, and additional conditions of the meeting through the interface and sends them to the server. The server stores this information in a database and uses it to guide the progress of the meeting. For example, the purpose might be to "check the progress of Project X and discuss countermeasures for delays," and rules might be set such as "each comment has a time limit of three minutes."

[0110] Starting a meeting

[0111] At the designated start time, the server sends a notification to each participant's device to announce the start of the conference. The device activates its microphone and collects audio data in real time. The collected audio data is then sent to the server in streaming format.

[0112] Speech recognition and text conversion

[0113] The server runs the received voice data through a speech recognition engine (e.g., Google® Cloud Speech-to-Text) to convert what is being said into text. This text data is then input into a generative AI model for analysis. The speech recognition engine provides highly accurate speech recognition in real time, instantly converting what is being said into text.

[0114] Generate feedback and questions

[0115] A generative AI model (e.g., OpenAI® GPT-4®) analyzes the textual utterances and generates appropriate feedback and follow-up questions based on the meeting's objectives and rules. The generated feedback and questions are sent to the device. For example, feedback such as "What is causing the delay? Are there any specific obstacles?" may be generated.

[0116] Providing information

[0117] The terminal provides the user with feedback and questions received from the server via voice or text, giving the user guidance on how to proceed with the meeting. Information can be provided either as text displayed on the terminal screen or as voice using a speech synthesis engine.

[0118] Meeting Records

[0119] All statements made during the meeting, as well as any feedback or questions generated, are recorded by the server. These records are stored for later review and analysis. If the user wishes to review the recording after the meeting, the server provides a detailed recording.

[0120] Examples of prompt statements

[0121] Below are some examples of prompts to input to the generative AI model.

[0122] Purpose of the meeting: Check the progress of Project X and discuss measures to deal with delays

[0123] Statement: The project is currently one week behind schedule.

[0124] Questions and feedback: What is causing the delay? Are there any particular obstacles?

[0125] This keeps meetings running smoothly and provides necessary feedback and questions in real time, allowing meeting participants to respond quickly and efficiently.

[0126] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0127] Step 1: Set up a meeting

[0128] The user inputs the purpose of the meeting, prerequisites, rules, and additional conditions through the interface and sends them to the server. The input data includes the purpose of the meeting (e.g., "Check the progress of Project X and discuss countermeasures for delays") and meeting rules (e.g., "Each comment has a time limit of three minutes"). The server receives this information and stores it in a database. Based on this, the data required for subsequent processing is constructed.

[0129] Step 2: Start the meeting

[0130] At the specified start time, the server sends a notification to each participant's device to announce the start of the conference. The input includes the conference setting information and start time. The output is a notification that the conference has started sent to each device. When the device receives the notification, it activates its microphone and begins collecting audio data in real time. This audio data is sent to the server in streaming format.

[0131] Step 3: Speech recognition and text conversion

[0132] The server runs the received voice data through a speech recognition engine (e.g., Google Cloud Speech-to-Text) and converts what is being said into text. The input includes the collected voice data. The output is the converted text data. Specifically, the server processes the voice data in real time and generates highly accurate text data.

[0133] Step 4: Generate feedback and questions

[0134] The server inputs the converted text data into a generative AI model (e.g., OpenAI GPT-4) to generate appropriate feedback and follow-up questions based on the meeting's purpose and rules. The input includes the textual utterances and meeting setting information. The output is generated feedback and questions. The generative AI model analyzes the utterances and generates appropriate utterances. For example, feedback such as "What is causing the delay? Are there any specific obstacles?" is generated.

[0135] Step 5: Provide information

[0136] The server sends the generated feedback and questions to each device. The input includes the generated feedback and questions. The output is provided as a display or voice message on each participant's device. The device displays the received information as text on the screen or uses a speech synthesis engine to convey it to the user audibly. For example, feedback in response to user A's statement is played audibly.

[0137] Step 6: Record the meeting

[0138] The server records all statements made during the meeting, as well as any feedback or questions generated. The input includes statements, feedback, and questions generated during the meeting. The output is stored in a database, which provides the data for users to review after the meeting.

[0139] Examples of prompt statements

[0140] Below is an example of a prompt sentence to be input to the generative AI model in step 4.

[0141] Purpose of the meeting: Check the progress of Project X and discuss measures to deal with delays

[0142] Statement: The project is currently one week behind schedule.

[0143] Questions and feedback: What is causing the delay? Are there any particular obstacles?

[0144] This allows the meeting to proceed more effectively and efficiently.

[0145] (Application example 1)

[0146] 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."

[0147] Improving the efficiency and fairness of meetings and troubleshooting in factories is an important issue. In particular, there is a need for a system that can analyze information in real time and provide prompt and appropriate feedback. Implementing such a system would facilitate smooth communication within the factory, leading to improved productivity and faster problem resolution. However, such systems are currently not fully implemented, which often leads to inefficient meetings and delays in problem resolution in factory operations.

[0148] 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.

[0149] In this invention, the server includes: means for setting the purpose, prerequisites, rules, and additional conditions of the meeting in advance; means for performing real-time speech recognition and converting participants' comments into text; means for analyzing the converted text using a generative AI model and generating appropriate feedback and follow-up questions; means for transmitting the generated feedback and questions to the participants' terminals; means for recording the content of comments made during the meeting and the generative AI feedback; means for supporting factory meetings and troubleshooting meetings in real time; and means for providing industrial speech recognition results and generated feedback to participants using smart glasses or a voice interface. This enables improved efficiency and fairness in factory meetings and troubleshooting.

[0150] A "meeting objective" is a specific goal or objective that a particular meeting aims to achieve.

[0151] "Preconditions" are the basic conditions or situations that must be established first in order for a meeting to proceed.

[0152] "Rules" are instructions and guidelines that participants must follow to ensure the meeting runs smoothly.

[0153] "Conditions" means any additional conditions or restrictions associated with a conference.

[0154] "Speech recognition" is a technology that analyzes voice data collected using a microphone and converts it into text information.

[0155] "Means for converting speech to text" refers to a method or device for converting speech from participants into text in real time using speech recognition.

[0156] A "generative AI model" is an artificial intelligence model that is trained to analyze input data and perform specific tasks automatically.

[0157] "Feedback" refers to responses or additional information provided by a generative AI model based on the results of its analysis.

[0158] A "terminal" is a device used by a participant to exchange data with the server.

[0159] "Means of recording" refers to methods or devices for saving what is said during a meeting and feedback from generative AI.

[0160] A "factory meeting" is a discussion or meeting with a specific purpose that takes place on the production floor or within a factory.

[0161] A "troubleshooting meeting" is a meeting held to resolve problems that arise in a system or process.

[0162] "Smart glasses" are glasses-type information and communication devices that provide visual information.

[0163] A "voice interface" is a technology or device that allows a user to communicate with a system through speech.

[0164] This invention is a system for supporting meetings and troubleshooting meetings in factories, and aims to improve the efficiency and fairness of meetings. A specific method for realizing this system will be described below.

[0165] The server is responsible for the main processing and plays a central role in the progress of the conference. This server houses the speech recognition engine, generative AI model, and database. Meanwhile, the terminals are devices used by participants to communicate with the server. Terminals include smart glasses and voice interfaces.

[0166] First, the user (organizer) inputs the purpose, prerequisites, rules, and additional conditions of the meeting through the interface and sends them to the server. The server stores this information in a database and uses it to progress the meeting.

[0167] When a meeting starts, the server sends a notification to the participants' devices to announce the start of the meeting. The devices turn on their microphones and collect audio data in real time. This audio data is sent to the server. The server then runs the received audio data through a speech recognition engine and converts what is being said into text. The SpeechRecognition library is used for speech recognition, and Google's speech recognition API is used to convert what is being said into text.

[0168] The textual comments are input into a generative AI model for analysis. The generative AI model uses Hugging Face's Transformers (pipeline functions) to generate appropriate feedback and follow-up questions based on the meeting's objectives and rules. The generated feedback and questions are sent to the device, which then provides them to the user via the smart glasses' display or voice interface. This allows the user to obtain guidance on how the meeting should proceed.

[0169] All statements made during the meeting, as well as any feedback or questions generated, are recorded by the server, and these recordings are stored for later review and analysis.

[0170] As a concrete example, consider a meeting to discuss the cause of a line stoppage and measures to prevent recurrence. The organizer sets the purpose of the meeting as "to investigate the cause of the line stoppage and consider measures to prevent recurrence." At the start of the meeting, User A says, "The line suddenly stopped. The cause is currently unknown." This speech is sent to the server via smart glasses and converted into text. The generative AI model analyzes this text and generates feedback such as "What is the cause?" and provides it to User A. This series of steps allows the meeting to proceed smoothly and enables efficient problem solving.

[0171] An example of a prompt sentence for the statement "The line has stopped suddenly. The cause is currently unknown." would be:

[0172] "What is the cause?"

[0173] This system contributes to improving the efficiency and fairness of meetings and troubleshooting within the factory.

[0174] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0175] Step 1:

[0176] The server receives information about the purpose, prerequisites, rules, and additional conditions of the meeting entered by the user (organizer) through the interface and stores it in a database. The entered data is the detailed information necessary for the progress of the meeting, and this will be the basis for the smooth running of the meeting in later steps.

[0177] Step 2:

[0178] When a conference starts, the server sends a notification to the participants' devices to announce the start of the conference. When the device receives the notification, it activates the microphone and starts collecting audio data. The collected audio data becomes the material for analysis in later processes.

[0179] Step 3:

[0180] The device sends the collected voice data to the server. The server passes the received voice data to a voice recognition engine in real time and converts what is being said into text. The process of converting this voice data into text data uses the SpeechRecognition library and Google's voice recognition API. The input is voice data and the output is text data.

[0181] Step 4:

[0182] The server inputs the textualized utterances into a generative AI model for analysis. The generative AI model uses Hugging Face's Transformers (pipeline function). This analysis generates appropriate feedback and follow-up questions based on the utterance content. Here, the input is text data, and the output is text data of feedback or questions.

[0183] Step 5:

[0184] The generated feedback and questions are sent from the server to the device. The device then provides the feedback and questions to the user in the form of voice or text. For example, it displays the feedback and questions as text on the smart glasses display or reads them out loud using a voice interface. The input is the text data of the feedback and questions, and the output is a notification to the user.

[0185] Step 6:

[0186] The server records all statements made during the meeting, as well as any feedback or questions generated, which are then stored in a database for later review and analysis. The input is the text data of statements made during the meeting, as well as any feedback or questions, and the output is the recorded data.

[0187] Step 7:

[0188] After the meeting is over, the server provides a function for later review of the recorded meeting contents. The user (host) can view this recording to confirm and analyze the contents of the meeting. The input is the recorded data stored in the database, and the output is data in a format that can be viewed by the user.

[0189] 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.

[0190] This invention improves the efficiency and fairness of meetings by combining an emotion engine with a meeting progress system using a generative AI model, and further recognizes the emotions of meeting participants and provides appropriate feedback. This system includes means for setting the purpose, prerequisites, rules, and conditions of the meeting in advance, means for performing real-time speech recognition and converting comments into text, means for analyzing the content of comments and the emotion recognition results using a generative AI model and generating feedback and follow-up questions, means for sending the generated information to the participants' devices, means for recording the content of comments made during the meeting and the results of the generative AI and emotion engine, and means for reviewing them.

[0191] System configuration

[0192] The server is responsible for the main processing and serves as the center of the conference. The server houses a speech recognition engine, generative AI model, emotion engine, and database. The terminals are devices used by participants to communicate with the server. Users join the conference and exchange data with the server through their terminals.

[0193] Explanation of program processing

[0194] 1. Set up a meeting:

[0195] The user (organizer) inputs the purpose, prerequisites, rules, and additional conditions of the meeting through the interface and sends them to the server, which stores this information in a database and uses it to progress the meeting.

[0196] 2. Start the meeting:

[0197] When the conference starts, the server sends a notification to the participants' terminals to announce the start of the conference. The terminals receive the notification and prepare to collect voice data.

[0198] 3. Speech Recognition and Text Transcription:

[0199] When the conference starts, the device activates the microphone and collects participants' speech as voice data. The server converts the received voice data into text data using a voice recognition engine.

[0200] 4. Emotion recognition:

[0201] The collected voice data is converted into text and simultaneously analyzed by an emotion engine to recognize the participants' emotional state. The emotion recognition results are then input into a generative AI model.

[0202] 5. Generate feedback and questions:

[0203] The generative AI model analyzes the text data and emotion recognition results, and generates appropriate feedback and follow-up questions based on the purpose and rules of the meeting. The generated feedback and questions are sent from the server to the device and provided to the user in voice or text format.

[0204] 6. Provision of Information:

[0205] The device provides the user with feedback, questions, and emotion recognition results received from the server, allowing the user to understand the guidelines for the progress of the meeting and the emotional situation.

[0206] 7. Records of meetings:

[0207] All statements made during the meeting, the feedback generated, questions asked, and emotion recognition results are recorded by the server, and the recordings are time-stamped to track the order and duration of statements.

[0208] 8. Reviews and Feedback:

[0209] After the meeting, the server organizes all recorded data and automatically generates meeting minutes, which include emotion recognition results and are saved for user access. Feedback based on the emotion recognition results is also provided, and an overall evaluation of the meeting and areas for improvement are identified.

[0210] Specific examples

[0211] 1. Pre-settings:

[0212] The user enters the purpose of the meeting, such as "Check the progress of project X and discuss countermeasures for delays," into the interface and sends it to the server, which then stores this information in a database.

[0213] 2. Meeting begins:

[0214] The server sends a notification to each participant at the start time to announce the start of the conference, and the device activates the microphone and prepares to collect audio.

[0215] 3. Speech, transcription and feedback:

[0216] User A says, "The project is currently one week behind schedule." The device sends this speech to the server, which converts it into text using a speech recognition engine and recognizes the emotion using an emotion engine. The generative AI model analyzes the speech and generates feedback such as, "What is causing the delay? Are there any specific obstacles?" The device then provides this feedback to User A. At the same time, the emotion engine detects the tension and provides additional feedback such as, "Let's calmly analyze the situation."

[0217] The system helps meetings run smoothly and produce rational outcomes by organizing what is being said and providing feedback that takes into account emotional states.

[0218] The processing flow will be explained below.

[0219] Step 1:

[0220] The user (organizer) inputs the purpose, prerequisites, rules, and additional conditions of the meeting into the interface and sends them to the server, which stores this information in a database.

[0221] Step 2:

[0222] The server sends a notification to each participant at the start time of the conference, announcing the start of the conference. The terminal receives the notification and prepares to collect voice data.

[0223] Step 3:

[0224] When the conference starts, the device activates the microphone and collects participants' speech as audio data, which is then sent to the server in real time.

[0225] Step 4:

[0226] The server converts the received voice data into text data using a speech recognition engine, which is then input into a generative AI model.

[0227] Step 5:

[0228] The collected voice data is converted into text and simultaneously analyzed by an emotion engine to recognize the participants' emotional state. The emotion recognition results are then input into a generative AI model.

[0229] Step 6:

[0230] The generative AI model analyzes text data and emotion recognition results to generate appropriate feedback and follow-up questions based on the meeting's objectives and rules.

[0231] Step 7:

[0232] The generated feedback and questions are sent from the server to the device, which then provides the received feedback and questions to the user in voice or text format.

[0233] Step 8:

[0234] The user makes further statements and answers based on the feedback and questions from the generative AI model, and the device again transmits these new statements as voice data to the server.

[0235] Step 9:

[0236] The server then converts the newly received voice data into text using the speech recognition engine and analyzes it using the generative AI model. At the same time, the emotion engine generates new emotion recognition results. This process is repeated throughout the conference.

[0237] Step 10:

[0238] During the meeting, all statements, generated feedback, questions, and emotional states recognized by the emotion engine are recorded by the server, and the recordings are time-stamped, allowing for tracking of the order and time of statements.

[0239] Step 11:

[0240] After the meeting, the server organizes all recorded data and automatically generates meeting minutes, which are stored for user access. Feedback based on emotion recognition results is also provided, and an overall evaluation of the meeting and suggestions for improvement are identified.

[0241] Specific examples

[0242] 1. Pre-settings:

[0243] The user enters the purpose of the meeting, such as "Check the progress of project X and discuss countermeasures for delays," into the interface and sends it to the server, which then stores this information in a database.

[0244] 2. Meeting begins:

[0245] The server sends a notification to each participant at the start time to announce the start of the conference, and the device activates the microphone and prepares to collect audio.

[0246] 3. Speech and text conversion, emotion recognition, and feedback:

[0247] User A says, "The project is currently one week behind schedule." The device sends this speech to the server, which converts it into text using a speech recognition engine and recognizes the emotion using an emotion engine. The generative AI model analyzes it and generates feedback such as, "What is causing the delay? Are there any specific obstacles?" At the same time, the emotion engine detects the tension and generates additional feedback such as, "Let's calmly analyze the situation," which the device provides to User A.

[0248] The system helps meetings run smoothly and produce rational outcomes by organizing what is being said and providing feedback that takes into account emotional states.

[0249] Example 2

[0250] 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."

[0251] Conventional meeting systems rarely provide appropriate feedback on the progress of meetings or participants' comments, hindering effective discussion and decision-making. Furthermore, feedback that does not reflect participants' emotional states can lead to inefficient meetings and unfair treatment of some participants. Furthermore, the post-meeting review process is cumbersome, and organizing and evaluating records takes time.

[0252] 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.

[0253] In this invention, the server includes: means for setting the purpose, prerequisites, rules, and additional conditions of the meeting in advance; means for recognizing speech in real time and converting participants' comments into text; means for recognizing the emotional state of the participants from the text comments using emotion analysis means; means for analyzing the text comments and the emotion recognition results using a generative artificial intelligence model to generate appropriate feedback and follow-up questions; means for transmitting the generated feedback and questions to the participants' communication devices; and means for recording the content of comments made during the meeting and the feedback and emotion recognition results of the generative artificial intelligence model. This makes the meeting more efficient, and fair and effective communication is achieved by providing feedback that takes into account the emotional state of each participant. It also facilitates review after the meeting, allowing for quick minutes creation and review of the meeting.

[0254] "Means for setting the purpose, prerequisites, rules, and additional conditions of a meeting in advance" refers to a function that allows you to input and save the purpose, rules, etc. of a meeting in advance in order to determine the progress of the meeting and the direction of the discussion, and to ensure that the meeting is run based on specific conditions and rules.

[0255] "Means for recognizing speech in real time and converting participants' comments into text" refers to a function that analyzes speech made by participants during a meeting in real time and instantly converts the speech into text using speech recognition technology.

[0256] "Means for recognizing the emotional state of participants from textualized statements using emotion analysis means" is a function for analyzing and confirming the emotional state of speakers using emotion analysis technology based on text data generated by voice recognition.

[0257] "Means for analyzing textual statements and emotion recognition results using a generative artificial intelligence model, and generating appropriate feedback and follow-up questions" refers to a function that analyzes text data and emotion recognition results using a generative artificial intelligence model (e.g., a language model), and automatically generates highly relevant feedback and questions based on the analysis results.

[0258] "Means for sending generated feedback and questions to participants' communication devices" refers to a function that sends feedback and questions generated by the generative artificial intelligence model to the communication devices used by participants (e.g., smartphones or personal computers).

[0259] "Means for recording statements made during a meeting, feedback from a generative AI model, and emotion recognition results" refers to a function that records all statements made during a meeting, generated feedback and questions, and emotion recognition results with timestamps, and saves them for later access.

[0260] This invention combines a generative AI model-based conference proceeding system with an emotion analysis engine to improve the efficiency and fairness of conferences, and also recognizes the emotions of conference participants and provides appropriate feedback. The system includes the following main hardware and software components:

[0261] Hardware and software used

[0262] 1. Server

[0263] The server is responsible for the main processing and serves as the center of the conference. This server houses a speech recognition engine, a generative AI model, an emotion analysis engine, and a database. The speech recognition engine uses the Google Cloud Speech-to-Text API, and the emotion analysis engine uses the Microsoft® Azure® Emotion API.

[0264] 2. Terminal

[0265] The terminal is a device used by participants to communicate with the server. Terminals can be smartphones, tablets, PCs, etc. Terminals collect voice data, receive feedback, and display it.

[0266] 3. Users

[0267] Users participate in the conference and exchange data with the server through their devices, as well as set up the conference and check feedback.

[0268] Specific processing of the system

[0269] The operation of the system proceeds as follows.

[0270] 1. Set up a meeting:

[0271] The user (organizer) inputs the purpose of the meeting ("Check the progress of Project X"), prerequisites, rules ("Keep comments brief"), and additional conditions ("Use diagrams and tables as needed") through the interface. Once input is complete, the settings are sent to the server. The server stores the received settings in a database and uses them to progress the meeting.

[0272] 2. Start the meeting:

[0273] When the meeting start time arrives, the server sends a push notification to each participant's device. The notification contains a message informing them that the meeting is about to begin. The device receives this notification and prepares to turn on its microphone and speaker.

[0274] 3. Speech Recognition and Text Transcription:

[0275] The user's speech is collected as voice data through the device's microphone. For example, if the user says, "Project X is progressing smoothly," the voice data is sent to the server in real time. The server then converts the received voice data into text data using the Google Cloud Speech-to-Text API.

[0276] 4. Emotion recognition:

[0277] The server uses an emotion analysis engine to analyze the voice data and the user's emotions. For example, if the user's speech is analyzed to indicate "anxiety," this result is recorded along with the text data. The emotion recognition results are provided to a generative AI model, forming the basis for future feedback generation.

[0278] 5. Generate feedback and questions:

[0279] The generative AI model analyzes the text data stored on the server and the emotion recognition results. For example, if a user says, "Project X is behind schedule," the model generates feedback such as, "What is the cause of the delay?" or "Let's think of specific countermeasures." The generated feedback and questions are sent from the server to the device and provided to the participants.

[0280] 6. Provision of Information:

[0281] The device then provides the received feedback, questions, and emotion recognition results to the user. For example, feedback such as "Analyze the situation calmly" is displayed to the user as voice or text. This allows the user to understand the progress of the meeting and the emotional situation.

[0282] 7. Records of meetings:

[0283] The server records all statements made during the meeting, along with any feedback generated, questions asked, and emotion recognition results, with timestamps, allowing for tracking of the order and duration of statements. This data is stored in a database for later review.

[0284] 8. Reviews and Feedback:

[0285] After the meeting, the server organizes all recorded data and automatically generates meeting minutes, which include the content of comments, emotion recognition results, and feedback. Users can access the minutes and review the entire meeting. Based on the emotion recognition results, the server also provides suggestions for improvements and guidelines for future meetings.

[0286] Examples of prompt statements

[0287] Please report on the progress of the project.

[0288] Please enter the purpose of the meeting.

[0289] "Convert what is being said into text and analyze the emotional state."

[0290] "Generate appropriate feedback and questions based on your analysis."

[0291] This system is expected to help meetings be run efficiently and fairly, and to lead to more constructive discussions by providing feedback that reflects the emotional state of participants.

[0292] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0293] Step 1:

[0294] Meeting Setup

[0295] The user (organizer) enters the purpose of the meeting, "Check the progress of Project X," the prerequisites, the rule, "Keep comments brief," and the additional condition, "Use diagrams and tables as necessary," into the interface. Once the input is complete, the user clicks the "Set" button to send the settings to the server. The server stores the received settings data in a database and makes them available for use in the progress of the meeting. As a specific example, the contents stored in the database include the "start date and time," "list of participants," and "meeting agenda."

[0296] Step 2:

[0297] Starting a meeting

[0298] When the meeting starts, the server sends a push notification to the participants' devices. The notification includes the message "The meeting has started. Please prepare to speak." This is transmitted to the device as input, and the device prepares the microphone and speaker, making it ready to collect audio data.

[0299] Step 3:

[0300] Speech recognition and text conversion

[0301] The meeting officially begins, and a user speaks. The device's microphone collects audio data, such as "Project X is progressing well," and sends it to the server. The server converts the received audio data into text data using the Google Cloud Speech-to-Text API. In this case, the input is audio data, and the output is text data: "Project X is progressing well."

[0302] Step 4:

[0303] emotion recognition

[0304] The server inputs the text data along with the voice data into an emotion analysis engine (such as Microsoft Azure's Emotion API) to recognize the emotional state. For example, if the statement "Project X is progressing smoothly" is analyzed as indicating "joy," the emotion recognition engine will return the result "joy." The input is text data and voice data, and the output is the emotion recognition result of "joy."

[0305] Step 5:

[0306] Generate feedback and questions

[0307] The server uses a generative artificial intelligence model (e.g., OpenAI's GPT-3 (registered trademark)) to analyze text data and emotion recognition results. For example, if someone says, "Project X is behind schedule," the model generates a question such as, "What is the cause of the delay?" or feedback such as, "Let's think of specific countermeasures." The input is the text data and emotion recognition results, and the output is the generated feedback or question.

[0308] Step 6:

[0309] Providing information

[0310] The generated feedback and questions are sent from the server to the device. The device receives them and displays them to the user as voice or text. For example, the feedback "Let's calmly analyze the situation" is provided to the user. The input is the generated feedback and questions, and the output is a notification to the user as voice or text.

[0311] Step 7:

[0312] Meeting Records

[0313] The server records all statements made during the meeting, generated feedback, questions, and emotion recognition results with timestamps. This allows the order and time of statements to be tracked. The recorded data is saved in a database and can be referenced later. The input is all data from the meeting, and the output is the recorded data with timestamps.

[0314] Step 8:

[0315] Reviews and Feedback

[0316] After the meeting, the server organizes all recorded data and creates automatically generated minutes. These minutes include the content of the remarks, emotion recognition results, and feedback. Users can access these minutes and review the entire meeting. In addition, the emotion recognition results provide improvements and guidelines for future meetings. The input is the recorded data, and the output is the automatically generated minutes and feedback.

[0317] (Application example 2)

[0318] 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."

[0319] Traditional security meetings and briefings have had issues with the content of each person's comments being subjective, and limited feedback tailored to the speaker's emotions and the progress of the meeting. Furthermore, meeting recordings are insufficient, making subsequent review and analysis difficult. These limitations compromise the efficiency and fairness of security meetings and put important information at risk of being overlooked.

[0320] The specific processing by the specific 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 setting the purpose, prerequisites, rules, and additional conditions of a meeting or briefing in advance; means for performing real-time speech recognition and converting participants' or staff's comments into text; means for analyzing the converted text using a generative AI model and generating appropriate feedback and follow-up questions; means for transmitting the generated feedback and questions to the participants' devices; means for analyzing collected voice data using an emotion engine and recognizing emotional states; means for the generative AI model to generate feedback and questions based on the emotion recognition results; and means for recording the content of comments made during the meeting and the generative AI feedback. This allows for objective analysis of participants' comments during the security meeting and provides feedback that takes their emotional states into account. Furthermore, detailed records of the meeting content and automatically generated minutes enable comprehensive reviews, allowing for efficient understanding and improvement of the security situation.

[0321] "Methods for setting the purpose, prerequisites, rules, and additional conditions of a meeting or briefing in advance" refers to a method by which participants share the information and rules necessary for the progress of a meeting or briefing and decide on them in advance to support smooth progress.

[0322] "Means for real-time speech recognition and conversion of participants' or representatives' speech into text" refers to technology that recognizes words spoken during a meeting in real time and converts them into digital text.

[0323] "Means for analyzing textual statements using a generative AI model and generating appropriate feedback and follow-up questions" refers to a system that uses a generative artificial intelligence model to analyze text data and automatically generate feedback and questions.

[0324] The "means for transmitting the generated feedback and questions to the participant's terminal" is a method for transmitting automatically generated feedback and questions to the device used by the participant.

[0325] "Means for analyzing collected voice data using an emotion engine and recognizing emotional states" refers to equipment that uses voice data collected by sensors or other devices to analyze and sense the speaker's emotions using an emotion analysis engine.

[0326] "Means for a generative AI model to generate feedback and questions based on emotion recognition results" refers to a system that uses emotion recognition results obtained from an emotion analysis engine to generate appropriate feedback and questions using a generative AI model.

[0327] "Means for recording statements made during meetings and feedback from generative AI" refers to technology that saves statements made during meetings and feedback output by generative AI models so that they can be reviewed later.

[0328] "Means for later reviewing recorded meeting content and automatically generating minutes that include emotion recognition results" refers to a system that automatically creates and enables review of meeting minutes based on the content recorded during the meeting and the results of emotion analysis.

[0329] The "means for providing participants with speech recognition results and emotion recognition results not only in text but also in audio" is a technology for conveying speech recognition and emotion recognition results to participants not only in text format but also as audio.

[0330] This invention provides a system for improving the efficiency and fairness of security conferences and briefings. The system includes a server, a terminal (e.g., smart glasses), and a user called a security officer. Specific embodiments for implementing this invention will be described below.

[0331] System Configuration

[0332] The server is the main processing center and contains the following modules:

[0333] Speech recognition engine (e.g. Google Cloud Speech-to-Text API)

[0334] Generative AI models (e.g., OpenAI GPT-4)

[0335] Emotion engine (e.g. Amazon Lex or Affectiva SDK)

[0336] Database (e.g. Amazon RDS)

[0337] Terminals are devices used by security personnel and include smart glasses (e.g., Google Glass (registered trademark), Vuzix Blade).

[0338] Data processing flow

[0339] 1. Setting up meetings and briefings

[0340] The user (the organizer among the security personnel) inputs the purpose, prerequisites, rules, and additional conditions of the meeting through the interface of the smart glasses and sends them to the server, which stores this information in a database and uses it to guide the progress of the meeting.

[0341] 2. Real-time speech recognition and emotion analysis

[0342] When a meeting or briefing begins, the device activates its microphone and collects participants' speech as voice data. The server converts the received voice data into text data using a voice recognition engine, and simultaneously analyzes the participants' emotional states using an emotion engine.

[0343] 3. Generate feedback and questions

[0344] The textual comments and emotion recognition results are analyzed using a generative AI model to generate appropriate feedback and follow-up questions as the meeting progresses. The generated feedback and questions are sent from the server to the device and provided to the user in voice or text format.

[0345] 4. Recording and reviewing during the meeting

[0346] All statements made during the meeting and feedback output by the generative AI model are recorded, including emotion recognition results, with a timestamp. After the meeting ends, the server organizes this data and automatically generates minutes. The minutes, which also include emotion recognition results, are used for review and to identify areas for improvement.

[0347] Examples of concrete examples and prompts

[0348] For example, if a security officer says "There were no abnormalities at the site today" during a security meeting, this statement is converted into text by a speech recognition engine, and the emotion engine recognizes "sense of security." The generative AI model analyzes this information and generates feedback such as "What part of the site is the situation? Please tell us the details." This feedback is displayed on the officer's smart glasses.

[0349] Example prompt sentence:

[0350] Input: "Nothing unusual at the site today."

[0351] Prompt: Use this statement to generate questions that ask for more information.

[0352] Example: "What part of the site is the situation? Please tell me the details."

[0353] This allows for objective analysis of participants' comments during security meetings and provides feedback that takes into account their emotional state. It also enables comprehensive reviews, allowing for efficient understanding and improvement of the security situation.

[0354] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0355] Step 1:

[0356] The user inputs the purpose, prerequisites, rules, and additional conditions of the meeting or briefing through the terminal interface and sends them to the server. The server stores this information in a database. The input is the setting information from the user, and the output is saved in the database. In this step, the information necessary to proceed with the meeting is prepared in advance.

[0357] Step 2:

[0358] At the start of a meeting or briefing, the server sends a start notification to the device. The device receives the notification and activates the microphone to prepare to collect audio data. The input is the notification from the server, and the output is the activation of the microphone. In this step, the start of the meeting is notified to the entire system, and audio recording is prepared.

[0359] Step 3:

[0360] The device sends the voice data collected during the meeting to the server. The server inputs the received voice data into a voice recognition engine and converts it into text data. The input is voice data and the output is text data. In this step, the participants' remarks are converted into text.

[0361] Step 4:

[0362] The server inputs the textual utterances into the emotion engine and analyzes the emotional state. The input is text data, and the output is emotion recognition results. In this step, the speaker's emotional state is understood.

[0363] Step 5:

[0364] The server inputs text data and emotion recognition results into the generative AI model to generate appropriate feedback and follow-up questions. The input is text data and emotion recognition results, and the output is feedback and questions. In this step, the generative AI model automatically generates responses that are appropriate for the progress of the meeting.

[0365] Step 6:

[0366] The server sends the generated feedback and questions to the terminal and provides them to the user. The terminal displays the feedback and questions as voice or text. The input is the feedback and questions, and the output is what is presented to the user. In this step, the user receives the feedback and questions in real time.

[0367] Step 7:

[0368] The server records all statements made during the meeting, the generated feedback, and the emotion recognition results. The input is the statements, feedback, and emotion recognition results, and the output is the recorded data. In this step, all meeting data is saved with a timestamp.

[0369] Step 8:

[0370] After the meeting, the server automatically generates minutes based on the recorded data and creates a report that includes the emotion recognition results. The input is the recorded data, and the output is the minutes and report. In this step, the meeting is automatically summarized, making it easier to review later.

[0371] 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.

[0372] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0373] 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.

[0374] [Second embodiment]

[0375] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0376] 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.

[0377] 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).

[0378] 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.

[0379] 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.

[0380] 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).

[0381] 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.

[0382] 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.

[0383] 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.

[0384] 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.

[0385] 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.

[0386] 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."

[0387] The present invention relates to a meeting progress system using a generative AI model to improve the efficiency and fairness of meetings. This system includes a means for setting the purpose, prerequisites, rules, and conditions of a meeting in advance, a means for real-time speech recognition and conversion of comments into text, a means for analyzing the content of comments using a generative AI model and generating feedback and follow-up questions, a means for sending the generated information to the participants' devices, a means for recording comments and feedback during the meeting, and a means for later reviewing these records.

[0388] System configuration

[0389] The server is responsible for the main processing and plays a central role in the progress of the conference. The server houses the speech recognition engine, generative AI model, and database. On the other hand, the terminals are devices used by participants to communicate with the server. Users join the conference and operate their terminals to exchange data with the server.

[0390] Explanation of program processing

[0391] 1. Set up a meeting:

[0392] The user (organizer) inputs the purpose, prerequisites, rules, and additional conditions of the meeting through the interface and sends them to the server, which stores this information in a database and uses it to progress the meeting.

[0393] 2. Start the meeting:

[0394] When a conference starts, the server sends a notification to the participants' devices to announce the start of the conference. The devices activate their microphones and collect audio data in real time. This audio data is then sent to the server.

[0395] 3. Speech Recognition and Text Transcription:

[0396] The server runs the received voice data through a speech recognition engine and converts what is being said into text, which is then input into a generative AI model for analysis.

[0397] 4. Generate feedback and questions:

[0398] The generative AI model analyzes the textual utterances and generates appropriate feedback and follow-up questions based on the meeting's objectives and rules. The generated feedback and questions are then sent to the device.

[0399] 5. Provision of Information:

[0400] The terminal provides the user with feedback and questions received from the server via voice or text, providing guidance for the progress of the meeting.

[0401] 6. Records of meetings:

[0402] All statements made during the meeting, as well as any feedback or questions generated, are recorded by the server, and these recordings are stored for later review and analysis.

[0403] Specific examples

[0404] 1. Pre-settings:

[0405] The user enters the purpose of the meeting, such as "Check the progress of project X and discuss countermeasures for delays," into the interface and sends it to the server, which then stores this information in a database.

[0406] 2. Meeting begins:

[0407] At the designated start time, the server sends a notification to each participant's device to announce the start of the conference. The device starts collecting voice data and sends it to the server.

[0408] 3. Speech, transcription and feedback:

[0409] User A says, "Currently, the project is one week behind schedule." The device sends this speech to the server, which converts it into text using a speech recognition engine. The generative AI model analyzes the text and generates feedback such as, "What is causing the delay? Are there any specific obstacles?" The device then relays this feedback to User A via voice.

[0410] 4. New statements and responses:

[0411] User B responds, "The main cause is a lack of resources." The device sends this speech to the server, which converts it into text and analyzes it using a generative AI model. The device generates a question, "Do we need more resources, or can we address this in other ways?" and relays this to User B.

[0412] This not only helps organize what is being said and keeps the meeting running smoothly, but also allows for accurate review later.

[0413] The processing flow will be explained below.

[0414] Step 1:

[0415] The user (organizer) inputs the purpose, prerequisites, rules, and additional conditions of the meeting into the interface and sends them to the server, which stores this information in a database.

[0416] Step 2:

[0417] The server sends a notification to each participant at the start time of the conference, announcing the start of the conference. The terminal receives the notification and prepares to collect voice data.

[0418] Step 3:

[0419] When the conference starts, the device activates the microphone and collects participants' speech as audio data, which is then sent to the server in real time.

[0420] Step 4:

[0421] The server converts the received voice data into text data using a speech recognition engine, which is then input into a generative AI model.

[0422] Step 5:

[0423] The generative AI model analyzes text data and generates appropriate feedback and follow-up questions based on the meeting's objectives and rules.

[0424] Step 6:

[0425] The generated feedback and questions are sent from the server to the device, which then provides the received feedback and questions to the user in voice or text format.

[0426] Step 7:

[0427] The user makes further statements and answers based on the feedback and questions from the generative AI model, and the device again transmits these new statements as voice data to the server.

[0428] Step 8:

[0429] The server then converts the newly received voice data into text using a speech recognition engine and analyzes it using a generative AI model. This process is repeated throughout the conference.

[0430] Step 9:

[0431] All statements made during the meeting, as well as feedback and questions from the generative AI model, are recorded by the server, and the recordings are time-stamped, allowing the order and time of statements to be tracked.

[0432] Step 10:

[0433] After the meeting, the server organizes all recorded data and automatically generates meeting minutes, which are then stored for user access.

[0434] Step 11:

[0435] Users can check the minutes of the meeting and make corrections or additional comments as necessary, which can be useful in preparing for the next meeting.

[0436] Step 12:

[0437] For the next meeting, the server can refer to past records and help set new topics and goals for discussion.

[0438] Example 1

[0439] 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."

[0440] Conventional conference systems are inefficient in sharing information and advancing discussions among participants, and have limitations in recording what is being said and providing feedback. Furthermore, real-time speech recognition, transcription of speech, and subsequent generation of feedback and questions are all performed manually, which can easily disrupt the flow of the meeting. This creates problems that reduce the efficiency and fairness of meetings.

[0441] 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.

[0442] In this invention, the server includes means for setting the purpose, prerequisites, rules, and additional conditions of the meeting in advance, means for performing real-time speech recognition and converting participants' comments into text, means for analyzing the textual comments with a generative AI model and generating appropriate feedback and follow-up questions, means for transmitting the generated feedback and questions to the participants' terminals, means for recording the comments made during the meeting and the feedback from the generative AI, means for sending a notification to the participants' terminals at the start of the meeting and starting to collect voice data, means for transmitting the voice data to the server in streaming format, means for inputting prompt sentences into the generative AI model, and means for displaying the comments, generated feedback, and questions on a screen or by voice, thereby enabling real-time feedback provision and efficient meeting progress.

[0443] "Means for setting the purpose, prerequisites, rules, and additional conditions of a meeting in advance" refers to an interface and software for inputting information and rules necessary for the progress of a meeting in advance and storing them in a database.

[0444] "Means for real-time speech recognition and conversion of participants' speech into text" refers to a speech recognition engine and related technology for instantly converting participants' speech into text during a meeting.

[0445] "Means of analyzing textual comments using a generative AI model to generate appropriate feedback and follow-up questions" refers to software that analyzes textual comments using an AI model that uses natural language processing technology, and automatically generates feedback and questions based on the purpose and rules of the meeting.

[0446] "Means for transmitting generated feedback and questions to participant devices" refers to the communications means and protocols for transmitting feedback and questions generated by the AI ​​model to participant devices.

[0447] "Means for recording statements made during meetings and feedback from the generative AI" refers to a system configuration for storing all statements made during meetings and feedback provided by the generative AI in a database.

[0448] "Means for sending a notification to the participant's device at the start of the meeting and starting the collection of audio data" refers to software and hardware for sending a notification to the participant's device at the start of the meeting, activating the microphone, and starting the collection of audio data.

[0449] "Means for transmitting audio data to a server in streaming format" refers to data communications technologies and protocols for transmitting collected audio data to a server in real time.

[0450] "Means for inputting prompts into a generative AI model" refers to interfaces and software tools for inputting text data and instructions for analysis into a generative AI model.

[0451] "Means for displaying or providing audio of statements, generated feedback, and questions" refers to the interface and speech synthesis engine for providing visual or audio notification of generated feedback and questions to the participant's device.

[0452] This invention relates to a conference progress system that uses a generative AI model to improve the efficiency and fairness of conferences. This system is mainly composed of a server, terminals, and users. The details are explained below.

[0453] System configuration

[0454] The server is responsible for the main processing and plays a central role in the progress of the conference. The server houses the speech recognition engine, generative AI model, and database. The terminals are devices used by participants to communicate with the server. Users join the conference and operate their terminals to exchange data with the server.

[0455] Meeting Setup

[0456] First, the user (organizer) inputs the purpose, prerequisites, rules, and additional conditions of the meeting through the interface and sends them to the server. The server stores this information in a database and uses it to guide the progress of the meeting. For example, the purpose might be to "check the progress of Project X and discuss countermeasures for delays," and rules might be set such as "each comment has a time limit of three minutes."

[0457] Starting a meeting

[0458] At the designated start time, the server sends a notification to each participant's device to announce the start of the conference. The device activates its microphone and collects audio data in real time. The collected audio data is then sent to the server in streaming format.

[0459] Speech recognition and text conversion

[0460] The server runs the received voice data through a speech recognition engine (e.g., Google Cloud Speech-to-Text) to convert what is being said into text. This text data is then input into a generative AI model for analysis. The speech recognition engine provides highly accurate speech recognition in real time, instantly converting what is being said into text.

[0461] Generate feedback and questions

[0462] A generative AI model (e.g., OpenAI GPT-4) analyzes the textual utterances and generates appropriate feedback and follow-up questions based on the meeting's objectives and rules. The generated feedback and questions are sent to the device. For example, feedback such as "What is causing the delay? Are there any specific obstacles?" is generated.

[0463] Providing information

[0464] The terminal provides the user with feedback and questions received from the server via voice or text, giving the user guidance on how to proceed with the meeting. Information can be provided either as text displayed on the terminal screen or as voice using a speech synthesis engine.

[0465] Meeting Records

[0466] All statements made during the meeting, as well as any feedback or questions generated, are recorded by the server. These records are stored for later review and analysis. If the user wishes to review the recording after the meeting, the server provides a detailed recording.

[0467] Examples of prompt statements

[0468] Below are some examples of prompts to input to the generative AI model.

[0469] Purpose of the meeting: Check the progress of Project X and discuss measures to deal with delays

[0470] Statement: The project is currently one week behind schedule.

[0471] Questions and feedback: What is causing the delay? Are there any particular obstacles?

[0472] This keeps meetings running smoothly and provides necessary feedback and questions in real time, allowing meeting participants to respond quickly and efficiently.

[0473] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0474] Step 1: Set up a meeting

[0475] The user inputs the purpose of the meeting, prerequisites, rules, and additional conditions through the interface and sends them to the server. The input data includes the purpose of the meeting (e.g., "Check the progress of Project X and discuss countermeasures for delays") and meeting rules (e.g., "Each comment has a time limit of three minutes"). The server receives this information and stores it in a database. Based on this, the data required for subsequent processing is constructed.

[0476] Step 2: Start the meeting

[0477] At the specified start time, the server sends a notification to each participant's device to announce the start of the conference. The input includes the conference setting information and start time. The output is a notification that the conference has started sent to each device. When the device receives the notification, it activates its microphone and begins collecting audio data in real time. This audio data is sent to the server in streaming format.

[0478] Step 3: Speech recognition and text conversion

[0479] The server runs the received voice data through a speech recognition engine (e.g., Google Cloud Speech-to-Text) and converts what is being said into text. The input includes the collected voice data. The output is the converted text data. Specifically, the server processes the voice data in real time and generates highly accurate text data.

[0480] Step 4: Generate feedback and questions

[0481] The server inputs the converted text data into a generative AI model (e.g., OpenAI GPT-4) to generate appropriate feedback and follow-up questions based on the meeting's purpose and rules. The input includes the textual utterances and meeting setting information. The output is generated feedback and questions. The generative AI model analyzes the utterances and generates appropriate utterances. For example, feedback such as "What is causing the delay? Are there any specific obstacles?" is generated.

[0482] Step 5: Provide information

[0483] The server sends the generated feedback and questions to each device. The input includes the generated feedback and questions. The output is provided as a display or voice message on each participant's device. The device displays the received information as text on the screen or uses a speech synthesis engine to convey it to the user audibly. For example, feedback in response to user A's statement is played audibly.

[0484] Step 6: Record the meeting

[0485] The server records all statements made during the meeting, as well as any feedback or questions generated. The input includes statements, feedback, and questions generated during the meeting. The output is stored in a database, which provides the data for users to review after the meeting.

[0486] Examples of prompt statements

[0487] Below is an example of a prompt sentence to be input to the generative AI model in step 4.

[0488] Purpose of the meeting: Check the progress of Project X and discuss measures to deal with delays

[0489] Statement: The project is currently one week behind schedule.

[0490] Questions and feedback: What is causing the delay? Are there any particular obstacles?

[0491] This allows the meeting to proceed more effectively and efficiently.

[0492] (Application example 1)

[0493] 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."

[0494] Improving the efficiency and fairness of meetings and troubleshooting in factories is an important issue. In particular, there is a need for a system that can analyze information in real time and provide prompt and appropriate feedback. Implementing such a system would facilitate smooth communication within the factory, leading to improved productivity and faster problem resolution. However, such systems are currently not fully implemented, which often leads to inefficient meetings and delays in problem resolution in factory operations.

[0495] 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.

[0496] In this invention, the server includes: means for setting the purpose, prerequisites, rules, and additional conditions of the meeting in advance; means for performing real-time speech recognition and converting participants' comments into text; means for analyzing the converted text using a generative AI model and generating appropriate feedback and follow-up questions; means for transmitting the generated feedback and questions to the participants' terminals; means for recording the content of comments made during the meeting and the generative AI feedback; means for supporting factory meetings and troubleshooting meetings in real time; and means for providing industrial speech recognition results and generated feedback to participants using smart glasses or a voice interface. This enables improved efficiency and fairness in factory meetings and troubleshooting.

[0497] A "meeting objective" is a specific goal or objective that a particular meeting aims to achieve.

[0498] "Preconditions" are the basic conditions or situations that must be established first in order for a meeting to proceed.

[0499] "Rules" are instructions and guidelines that participants must follow to ensure the meeting runs smoothly.

[0500] "Conditions" means any additional conditions or restrictions associated with a conference.

[0501] "Speech recognition" is a technology that analyzes voice data collected using a microphone and converts it into text information.

[0502] "Means for converting speech to text" refers to a method or device for converting speech from participants into text in real time using speech recognition.

[0503] A "generative AI model" is an artificial intelligence model that is trained to analyze input data and perform specific tasks automatically.

[0504] "Feedback" refers to responses or additional information provided by a generative AI model based on the results of its analysis.

[0505] A "terminal" is a device used by a participant to exchange data with the server.

[0506] "Means of recording" refers to methods or devices for saving what is said during a meeting and feedback from generative AI.

[0507] A "factory meeting" is a discussion or meeting with a specific purpose that takes place on the production floor or within a factory.

[0508] A "troubleshooting meeting" is a meeting held to resolve problems that arise in a system or process.

[0509] "Smart glasses" are glasses-type information and communication devices that provide visual information.

[0510] A "voice interface" is a technology or device that allows a user to communicate with a system through speech.

[0511] This invention is a system for supporting meetings and troubleshooting meetings in factories, and aims to improve the efficiency and fairness of meetings. A specific method for realizing this system will be described below.

[0512] The server is responsible for the main processing and plays a central role in the progress of the conference. This server houses the speech recognition engine, generative AI model, and database. Meanwhile, the terminals are devices used by participants to communicate with the server. Terminals include smart glasses and voice interfaces.

[0513] First, the user (organizer) inputs the purpose, prerequisites, rules, and additional conditions of the meeting through the interface and sends them to the server. The server stores this information in a database and uses it to progress the meeting.

[0514] When a meeting starts, the server sends a notification to the participants' devices to announce the start of the meeting. The devices turn on their microphones and collect audio data in real time. This audio data is sent to the server. The server then runs the received audio data through a speech recognition engine and converts what is being said into text. The SpeechRecognition library is used for speech recognition, and Google's speech recognition API is used to convert what is being said into text.

[0515] The textual comments are input into a generative AI model for analysis. The generative AI model uses Hugging Face's Transformers (pipeline functions) to generate appropriate feedback and follow-up questions based on the meeting's objectives and rules. The generated feedback and questions are sent to the device, which then provides them to the user via the smart glasses' display or voice interface. This allows the user to obtain guidance on how the meeting should proceed.

[0516] All statements made during the meeting, as well as any feedback or questions generated, are recorded by the server, and these recordings are stored for later review and analysis.

[0517] As a concrete example, consider a meeting to discuss the cause of a line stoppage and measures to prevent recurrence. The organizer sets the purpose of the meeting as "to investigate the cause of the line stoppage and consider measures to prevent recurrence." At the start of the meeting, User A says, "The line suddenly stopped. The cause is currently unknown." This speech is sent to the server via smart glasses and converted into text. The generative AI model analyzes this text and generates feedback such as "What is the cause?" and provides it to User A. This series of steps allows the meeting to proceed smoothly and enables efficient problem solving.

[0518] An example of a prompt sentence for the statement "The line has stopped suddenly. The cause is currently unknown." would be:

[0519] "What is the cause?"

[0520] This system contributes to improving the efficiency and fairness of meetings and troubleshooting within the factory.

[0521] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0522] Step 1:

[0523] The server receives information about the purpose, prerequisites, rules, and additional conditions of the meeting entered by the user (organizer) through the interface and stores it in a database. The entered data is the detailed information necessary for the progress of the meeting, and this will be the basis for the smooth running of the meeting in later steps.

[0524] Step 2:

[0525] When a conference starts, the server sends a notification to the participants' devices to announce the start of the conference. When the device receives the notification, it activates the microphone and starts collecting audio data. The collected audio data becomes the material for analysis in later processes.

[0526] Step 3:

[0527] The device sends the collected voice data to the server. The server passes the received voice data to a voice recognition engine in real time and converts what is being said into text. The process of converting this voice data into text data uses the SpeechRecognition library and Google's voice recognition API. The input is voice data and the output is text data.

[0528] Step 4:

[0529] The server inputs the textualized utterances into a generative AI model for analysis. The generative AI model uses Hugging Face's Transformers (pipeline function). This analysis generates appropriate feedback and follow-up questions based on the utterance content. Here, the input is text data, and the output is text data of feedback or questions.

[0530] Step 5:

[0531] The generated feedback and questions are sent from the server to the device. The device then provides the feedback and questions to the user in the form of voice or text. For example, it displays the feedback and questions as text on the smart glasses display or reads them out loud using a voice interface. The input is the text data of the feedback and questions, and the output is a notification to the user.

[0532] Step 6:

[0533] The server records all statements made during the meeting, as well as any feedback or questions generated, which are then stored in a database for later review and analysis. The input is the text data of statements made during the meeting, as well as any feedback or questions, and the output is the recorded data.

[0534] Step 7:

[0535] After the meeting is over, the server provides a function for later review of the recorded meeting contents. The user (host) can view this recording to confirm and analyze the contents of the meeting. The input is the recorded data stored in the database, and the output is data in a format that can be viewed by the user.

[0536] 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.

[0537] This invention improves the efficiency and fairness of meetings by combining an emotion engine with a meeting progress system using a generative AI model, and further recognizes the emotions of meeting participants and provides appropriate feedback. This system includes means for setting the purpose, prerequisites, rules, and conditions of the meeting in advance, means for performing real-time speech recognition and converting comments into text, means for analyzing the content of comments and the emotion recognition results using a generative AI model and generating feedback and follow-up questions, means for sending the generated information to the participants' devices, means for recording the content of comments made during the meeting and the results of the generative AI and emotion engine, and means for reviewing them.

[0538] System configuration

[0539] The server is responsible for the main processing and serves as the center of the conference. The server houses a speech recognition engine, generative AI model, emotion engine, and database. The terminals are devices used by participants to communicate with the server. Users join the conference and exchange data with the server through their terminals.

[0540] Explanation of program processing

[0541] 1. Set up a meeting:

[0542] The user (organizer) inputs the purpose, prerequisites, rules, and additional conditions of the meeting through the interface and sends them to the server, which stores this information in a database and uses it to progress the meeting.

[0543] 2. Start the meeting:

[0544] When the conference starts, the server sends a notification to the participants' terminals to announce the start of the conference. The terminals receive the notification and prepare to collect voice data.

[0545] 3. Speech Recognition and Text Transcription:

[0546] When the conference starts, the device activates the microphone and collects participants' speech as voice data. The server converts the received voice data into text data using a voice recognition engine.

[0547] 4. Emotion recognition:

[0548] The collected voice data is converted into text and simultaneously analyzed by an emotion engine to recognize the participants' emotional state. The emotion recognition results are then input into a generative AI model.

[0549] 5. Generate feedback and questions:

[0550] The generative AI model analyzes the text data and emotion recognition results, and generates appropriate feedback and follow-up questions based on the purpose and rules of the meeting. The generated feedback and questions are sent from the server to the device and provided to the user in voice or text format.

[0551] 6. Provision of Information:

[0552] The device provides the user with feedback, questions, and emotion recognition results received from the server, allowing the user to understand the guidelines for the progress of the meeting and the emotional situation.

[0553] 7. Records of meetings:

[0554] All statements made during the meeting, the feedback generated, questions asked, and emotion recognition results are recorded by the server, and the recordings are time-stamped to track the order and duration of statements.

[0555] 8. Reviews and Feedback:

[0556] After the meeting, the server organizes all recorded data and automatically generates meeting minutes, which include emotion recognition results and are saved for user access. Feedback based on the emotion recognition results is also provided, and an overall evaluation of the meeting and areas for improvement are identified.

[0557] Specific examples

[0558] 1. Pre-settings:

[0559] The user enters the purpose of the meeting, such as "Check the progress of project X and discuss countermeasures for delays," into the interface and sends it to the server, which then stores this information in a database.

[0560] 2. Meeting begins:

[0561] The server sends a notification to each participant at the start time to announce the start of the conference, and the device activates the microphone and prepares to collect audio.

[0562] 3. Speech, transcription and feedback:

[0563] User A says, "The project is currently one week behind schedule." The device sends this speech to the server, which converts it into text using a speech recognition engine and recognizes the emotion using an emotion engine. The generative AI model analyzes the speech and generates feedback such as, "What is causing the delay? Are there any specific obstacles?" The device then provides this feedback to User A. At the same time, the emotion engine detects the tension and provides additional feedback such as, "Let's calmly analyze the situation."

[0564] The system helps meetings run smoothly and produce rational outcomes by organizing what is being said and providing feedback that takes into account emotional states.

[0565] The processing flow will be explained below.

[0566] Step 1:

[0567] The user (organizer) inputs the purpose, prerequisites, rules, and additional conditions of the meeting into the interface and sends them to the server, which stores this information in a database.

[0568] Step 2:

[0569] The server sends a notification to each participant at the start time of the conference, announcing the start of the conference. The terminal receives the notification and prepares to collect voice data.

[0570] Step 3:

[0571] When the conference starts, the device activates the microphone and collects participants' speech as audio data, which is then sent to the server in real time.

[0572] Step 4:

[0573] The server converts the received voice data into text data using a speech recognition engine, which is then input into a generative AI model.

[0574] Step 5:

[0575] The collected voice data is converted into text and simultaneously analyzed by an emotion engine to recognize the participants' emotional state. The emotion recognition results are then input into a generative AI model.

[0576] Step 6:

[0577] The generative AI model analyzes text data and emotion recognition results to generate appropriate feedback and follow-up questions based on the meeting's objectives and rules.

[0578] Step 7:

[0579] The generated feedback and questions are sent from the server to the device, which then provides the received feedback and questions to the user in voice or text format.

[0580] Step 8:

[0581] The user makes further statements and answers based on the feedback and questions from the generative AI model, and the device again transmits these new statements as voice data to the server.

[0582] Step 9:

[0583] The server then converts the newly received voice data into text using the speech recognition engine and analyzes it using the generative AI model. At the same time, the emotion engine generates new emotion recognition results. This process is repeated throughout the conference.

[0584] Step 10:

[0585] During the meeting, all statements, generated feedback, questions, and emotional states recognized by the emotion engine are recorded by the server, and the recordings are time-stamped, allowing for tracking of the order and time of statements.

[0586] Step 11:

[0587] After the meeting, the server organizes all recorded data and automatically generates meeting minutes, which are stored for user access. Feedback based on emotion recognition results is also provided, and an overall evaluation of the meeting and suggestions for improvement are identified.

[0588] Specific examples

[0589] 1. Pre-settings:

[0590] The user enters the purpose of the meeting, such as "Check the progress of project X and discuss countermeasures for delays," into the interface and sends it to the server, which then stores this information in a database.

[0591] 2. Meeting begins:

[0592] The server sends a notification to each participant at the start time to announce the start of the conference, and the device activates the microphone and prepares to collect audio.

[0593] 3. Speech and text conversion, emotion recognition, and feedback:

[0594] User A says, "The project is currently one week behind schedule." The device sends this speech to the server, which converts it into text using a speech recognition engine and recognizes the emotion using an emotion engine. The generative AI model analyzes it and generates feedback such as, "What is causing the delay? Are there any specific obstacles?" At the same time, the emotion engine detects the tension and generates additional feedback such as, "Let's calmly analyze the situation," which the device provides to User A.

[0595] The system helps meetings run smoothly and produce rational outcomes by organizing what is being said and providing feedback that takes into account emotional states.

[0596] Example 2

[0597] 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."

[0598] Conventional meeting systems rarely provide appropriate feedback on the progress of meetings or participants' comments, hindering effective discussion and decision-making. Furthermore, feedback that does not reflect participants' emotional states can lead to inefficient meetings and unfair treatment of some participants. Furthermore, the post-meeting review process is cumbersome, and organizing and evaluating records takes time.

[0599] 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.

[0600] In this invention, the server includes: means for setting the purpose, prerequisites, rules, and additional conditions of the meeting in advance; means for recognizing speech in real time and converting participants' comments into text; means for recognizing the emotional state of the participants from the text comments using emotion analysis means; means for analyzing the text comments and the emotion recognition results using a generative artificial intelligence model to generate appropriate feedback and follow-up questions; means for transmitting the generated feedback and questions to the participants' communication devices; and means for recording the content of comments made during the meeting and the feedback and emotion recognition results of the generative artificial intelligence model. This makes the meeting more efficient, and fair and effective communication is achieved by providing feedback that takes into account the emotional state of each participant. It also facilitates review after the meeting, allowing for quick minutes creation and review of the meeting.

[0601] "Means for setting the purpose, prerequisites, rules, and additional conditions of a meeting in advance" refers to a function that allows you to input and save the purpose, rules, etc. of a meeting in advance in order to determine the progress of the meeting and the direction of the discussion, and to ensure that the meeting is run based on specific conditions and rules.

[0602] "Means for recognizing speech in real time and converting participants' comments into text" refers to a function that analyzes speech made by participants during a meeting in real time and instantly converts the speech into text using speech recognition technology.

[0603] "Means for recognizing the emotional state of participants from textualized statements using emotion analysis means" is a function for analyzing and confirming the emotional state of speakers using emotion analysis technology based on text data generated by voice recognition.

[0604] "Means for analyzing textual statements and emotion recognition results using a generative artificial intelligence model, and generating appropriate feedback and follow-up questions" refers to a function that analyzes text data and emotion recognition results using a generative artificial intelligence model (e.g., a language model), and automatically generates highly relevant feedback and questions based on the analysis results.

[0605] "Means for sending generated feedback and questions to participants' communication devices" refers to a function that sends feedback and questions generated by the generative artificial intelligence model to the communication devices used by participants (e.g., smartphones or personal computers).

[0606] "Means for recording statements made during a meeting, feedback from a generative AI model, and emotion recognition results" refers to a function that records all statements made during a meeting, generated feedback and questions, and emotion recognition results with timestamps, and saves them for later access.

[0607] This invention combines a generative AI model-based conference proceeding system with an emotion analysis engine to improve the efficiency and fairness of conferences, and also recognizes the emotions of conference participants and provides appropriate feedback. The system includes the following main hardware and software components:

[0608] Hardware and software used

[0609] 1. Server

[0610] The server is responsible for the main processing and serves as the center of the conference. This server houses a speech recognition engine, generative AI model, emotion analysis engine, and database. The speech recognition engine uses the Google Cloud Speech-to-Text API, and the emotion analysis engine uses the Microsoft Azure Emotion API.

[0611] 2. Terminal

[0612] The terminal is a device used by participants to communicate with the server. Terminals can be smartphones, tablets, PCs, etc. Terminals collect voice data, receive feedback, and display it.

[0613] 3. Users

[0614] Users participate in the conference and exchange data with the server through their devices, as well as set up the conference and check feedback.

[0615] Specific processing of the system

[0616] The operation of the system proceeds as follows.

[0617] 1. Set up a meeting:

[0618] The user (organizer) inputs the purpose of the meeting ("Check the progress of Project X"), prerequisites, rules ("Keep comments brief"), and additional conditions ("Use diagrams and tables as needed") through the interface. Once input is complete, the settings are sent to the server. The server stores the received settings in a database and uses them to progress the meeting.

[0619] 2. Start the meeting:

[0620] When the meeting start time arrives, the server sends a push notification to each participant's device. The notification contains a message informing them that the meeting is about to begin. The device receives this notification and prepares to turn on its microphone and speaker.

[0621] 3. Speech Recognition and Text Transcription:

[0622] The user's speech is collected as voice data through the device's microphone. For example, if the user says, "Project X is progressing smoothly," the voice data is sent to the server in real time. The server then converts the received voice data into text data using the Google Cloud Speech-to-Text API.

[0623] 4. Emotion recognition:

[0624] The server uses an emotion analysis engine to analyze the voice data and the user's emotions. For example, if the user's speech is analyzed to indicate "anxiety," this result is recorded along with the text data. The emotion recognition results are provided to a generative AI model, forming the basis for future feedback generation.

[0625] 5. Generate feedback and questions:

[0626] The generative AI model analyzes the text data stored on the server and the emotion recognition results. For example, if a user says, "Project X is behind schedule," the model generates feedback such as, "What is the cause of the delay?" or "Let's think of specific countermeasures." The generated feedback and questions are sent from the server to the device and provided to the participants.

[0627] 6. Provision of Information:

[0628] The device then provides the received feedback, questions, and emotion recognition results to the user. For example, feedback such as "Analyze the situation calmly" is displayed to the user as voice or text. This allows the user to understand the progress of the meeting and the emotional situation.

[0629] 7. Records of meetings:

[0630] The server records all statements made during the meeting, along with any feedback generated, questions asked, and emotion recognition results, with timestamps, allowing for tracking of the order and duration of statements. This data is stored in a database for later review.

[0631] 8. Reviews and Feedback:

[0632] After the meeting, the server organizes all recorded data and automatically generates meeting minutes, which include the content of comments, emotion recognition results, and feedback. Users can access the minutes and review the entire meeting. Based on the emotion recognition results, the server also provides suggestions for improvements and guidelines for future meetings.

[0633] Examples of prompt statements

[0634] Please report on the progress of the project.

[0635] Please enter the purpose of the meeting.

[0636] "Convert what is being said into text and analyze the emotional state."

[0637] "Generate appropriate feedback and questions based on your analysis."

[0638] This system is expected to help meetings be run efficiently and fairly, and to lead to more constructive discussions by providing feedback that reflects the emotional state of participants.

[0639] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0640] Step 1:

[0641] Meeting Setup

[0642] The user (organizer) enters the purpose of the meeting, "Check the progress of Project X," the prerequisites, the rule, "Keep comments brief," and the additional condition, "Use diagrams and tables as necessary," into the interface. Once the input is complete, the user clicks the "Set" button to send the settings to the server. The server stores the received settings data in a database and makes them available for use in the progress of the meeting. As a specific example, the contents stored in the database include the "start date and time," "list of participants," and "meeting agenda."

[0643] Step 2:

[0644] Starting a meeting

[0645] When the meeting starts, the server sends a push notification to the participants' devices. The notification includes the message "The meeting has started. Please prepare to speak." This is transmitted to the device as input, and the device prepares the microphone and speaker, making it ready to collect audio data.

[0646] Step 3:

[0647] Speech recognition and text conversion

[0648] The meeting officially begins, and a user speaks. The device's microphone collects audio data, such as "Project X is progressing well," and sends it to the server. The server converts the received audio data into text data using the Google Cloud Speech-to-Text API. In this case, the input is audio data, and the output is text data: "Project X is progressing well."

[0649] Step 4:

[0650] emotion recognition

[0651] The server inputs the text data along with the voice data into an emotion analysis engine (such as Microsoft Azure's Emotion API) to recognize the emotional state. For example, if the statement "Project X is progressing smoothly" is analyzed as indicating "joy," the emotion recognition engine will return the result "joy." The input is text data and voice data, and the output is the emotion recognition result of "joy."

[0652] Step 5:

[0653] Generate feedback and questions

[0654] The server uses a generative artificial intelligence model (e.g., OpenAI's GPT-3) to analyze text data and emotion recognition results. For example, if someone says, "Project X is behind schedule," the model generates a question such as, "What is the cause of the delay?" or feedback such as, "Let's think of specific countermeasures." The input is the text data and emotion recognition results, and the output is the generated feedback or question.

[0655] Step 6:

[0656] Providing information

[0657] The generated feedback and questions are sent from the server to the device. The device receives them and displays them to the user as voice or text. For example, the feedback "Let's calmly analyze the situation" is provided to the user. The input is the generated feedback and questions, and the output is a notification to the user as voice or text.

[0658] Step 7:

[0659] Meeting Records

[0660] The server records all statements made during the meeting, generated feedback, questions, and emotion recognition results with timestamps. This allows the order and time of statements to be tracked. The recorded data is saved in a database and can be referenced later. The input is all data from the meeting, and the output is the recorded data with timestamps.

[0661] Step 8:

[0662] Reviews and Feedback

[0663] After the meeting, the server organizes all recorded data and creates automatically generated minutes. These minutes include the content of the remarks, emotion recognition results, and feedback. Users can access these minutes and review the entire meeting. In addition, the emotion recognition results provide improvements and guidelines for future meetings. The input is the recorded data, and the output is the automatically generated minutes and feedback.

[0664] (Application example 2)

[0665] 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."

[0666] Traditional security meetings and briefings have had issues with the content of each person's comments being subjective, and limited feedback tailored to the speaker's emotions and the progress of the meeting. Furthermore, meeting recordings are insufficient, making subsequent review and analysis difficult. These limitations compromise the efficiency and fairness of security meetings and put important information at risk of being overlooked.

[0667] The specific processing by the specific 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 setting the purpose, prerequisites, rules, and additional conditions of a meeting or briefing in advance; means for performing real-time speech recognition and converting participants' or staff's comments into text; means for analyzing the converted text using a generative AI model and generating appropriate feedback and follow-up questions; means for transmitting the generated feedback and questions to the participants' devices; means for analyzing collected voice data using an emotion engine and recognizing emotional states; means for the generative AI model to generate feedback and questions based on the emotion recognition results; and means for recording the content of comments made during the meeting and the generative AI feedback. This allows for objective analysis of participants' comments during the security meeting and provides feedback that takes their emotional states into account. Furthermore, detailed records of the meeting content and automatically generated minutes enable comprehensive reviews, allowing for efficient understanding and improvement of the security situation.

[0668] "Methods for setting the purpose, prerequisites, rules, and additional conditions of a meeting or briefing in advance" refers to a method by which participants share the information and rules necessary for the progress of a meeting or briefing and decide on them in advance to support smooth progress.

[0669] "Means for real-time speech recognition and conversion of participants' or representatives' speech into text" refers to technology that recognizes words spoken during a meeting in real time and converts them into digital text.

[0670] "Means for analyzing textual statements using a generative AI model and generating appropriate feedback and follow-up questions" refers to a system that uses a generative artificial intelligence model to analyze text data and automatically generate feedback and questions.

[0671] The "means for transmitting the generated feedback and questions to the participant's terminal" is a method for transmitting automatically generated feedback and questions to the device used by the participant.

[0672] "Means for analyzing collected voice data using an emotion engine and recognizing emotional states" refers to equipment that uses voice data collected by sensors or other devices to analyze and sense the speaker's emotions using an emotion analysis engine.

[0673] "Means for a generative AI model to generate feedback and questions based on emotion recognition results" refers to a system that uses emotion recognition results obtained from an emotion analysis engine to generate appropriate feedback and questions using a generative AI model.

[0674] "Means for recording statements made during meetings and feedback from generative AI" refers to technology that saves statements made during meetings and feedback output by generative AI models so that they can be reviewed later.

[0675] "Means for later reviewing recorded meeting content and automatically generating minutes that include emotion recognition results" refers to a system that automatically creates and enables review of meeting minutes based on the content recorded during the meeting and the results of emotion analysis.

[0676] The "means for providing participants with speech recognition results and emotion recognition results not only in text but also in audio" is a technology for conveying speech recognition and emotion recognition results to participants not only in text format but also as audio.

[0677] This invention provides a system for improving the efficiency and fairness of security conferences and briefings. The system includes a server, a terminal (e.g., smart glasses), and a user called a security officer. Specific embodiments for implementing this invention will be described below.

[0678] System Configuration

[0679] The server is the main processing center and contains the following modules:

[0680] Speech recognition engine (e.g. Google Cloud Speech-to-Text API)

[0681] Generative AI models (e.g., OpenAI GPT-4)

[0682] Emotion engine (e.g. Amazon Lex or Affectiva SDK)

[0683] Database (e.g. Amazon RDS)

[0684] Terminals are devices used by security personnel and include smart glasses (e.g., Google Glass, Vuzix Blade).

[0685] Data processing flow

[0686] 1. Setting up meetings and briefings

[0687] The user (the organizer among the security personnel) inputs the purpose, prerequisites, rules, and additional conditions of the meeting through the interface of the smart glasses and sends them to the server, which stores this information in a database and uses it to guide the progress of the meeting.

[0688] 2. Real-time speech recognition and emotion analysis

[0689] When a meeting or briefing begins, the device activates its microphone and collects participants' speech as voice data. The server converts the received voice data into text data using a voice recognition engine, and simultaneously analyzes the participants' emotional states using an emotion engine.

[0690] 3. Generate feedback and questions

[0691] The textual comments and emotion recognition results are analyzed using a generative AI model to generate appropriate feedback and follow-up questions as the meeting progresses. The generated feedback and questions are sent from the server to the device and provided to the user in voice or text format.

[0692] 4. Recording and reviewing during the meeting

[0693] All statements made during the meeting and feedback output by the generative AI model are recorded, including emotion recognition results, with a timestamp. After the meeting ends, the server organizes this data and automatically generates minutes. The minutes, which also include emotion recognition results, are used for review and to identify areas for improvement.

[0694] Examples of concrete examples and prompts

[0695] For example, if a security officer says "There were no abnormalities at the site today" during a security meeting, this statement is converted into text by a speech recognition engine, and the emotion engine recognizes "sense of security." The generative AI model analyzes this information and generates feedback such as "What part of the site is the situation? Please tell us the details." This feedback is displayed on the officer's smart glasses.

[0696] Example prompt sentence:

[0697] Input: "Nothing unusual at the site today."

[0698] Prompt: Use this statement to generate questions that ask for more information.

[0699] Example: "What part of the site is the situation? Please tell me the details."

[0700] This allows for objective analysis of participants' comments during security meetings and provides feedback that takes into account their emotional state. It also enables comprehensive reviews, allowing for efficient understanding and improvement of the security situation.

[0701] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0702] Step 1:

[0703] The user inputs the purpose, prerequisites, rules, and additional conditions of the meeting or briefing through the terminal interface and sends them to the server. The server stores this information in a database. The input is the setting information from the user, and the output is saved in the database. In this step, the information necessary to proceed with the meeting is prepared in advance.

[0704] Step 2:

[0705] At the start of a meeting or briefing, the server sends a start notification to the device. The device receives the notification and activates the microphone to prepare to collect audio data. The input is the notification from the server, and the output is the activation of the microphone. In this step, the start of the meeting is notified to the entire system, and audio recording is prepared.

[0706] Step 3:

[0707] The device sends the voice data collected during the meeting to the server. The server inputs the received voice data into a voice recognition engine and converts it into text data. The input is voice data and the output is text data. In this step, the participants' remarks are converted into text.

[0708] Step 4:

[0709] The server inputs the textual utterances into the emotion engine and analyzes the emotional state. The input is text data, and the output is emotion recognition results. In this step, the speaker's emotional state is understood.

[0710] Step 5:

[0711] The server inputs text data and emotion recognition results into the generative AI model to generate appropriate feedback and follow-up questions. The input is text data and emotion recognition results, and the output is feedback and questions. In this step, the generative AI model automatically generates responses that are appropriate for the progress of the meeting.

[0712] Step 6:

[0713] The server sends the generated feedback and questions to the terminal and provides them to the user. The terminal displays the feedback and questions as voice or text. The input is the feedback and questions, and the output is what is presented to the user. In this step, the user receives the feedback and questions in real time.

[0714] Step 7:

[0715] The server records all statements made during the meeting, the generated feedback, and the emotion recognition results. The input is the statements, feedback, and emotion recognition results, and the output is the recorded data. In this step, all meeting data is saved with a timestamp.

[0716] Step 8:

[0717] After the meeting, the server automatically generates minutes based on the recorded data and creates a report that includes the emotion recognition results. The input is the recorded data, and the output is the minutes and report. In this step, the meeting is automatically summarized, making it easier to review later.

[0718] 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.

[0719] 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.

[0720] 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.

[0721] [Third embodiment]

[0722] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0723] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0724] 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).

[0725] 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.

[0726] 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.

[0727] 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).

[0728] 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. 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.

[0729] 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.

[0730] 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.

[0731] 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.

[0732] 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.

[0733] 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."

[0734] The present invention relates to a meeting progress system using a generative AI model to improve the efficiency and fairness of meetings. This system includes a means for setting the purpose, prerequisites, rules, and conditions of a meeting in advance, a means for real-time speech recognition and conversion of comments into text, a means for analyzing the content of comments using a generative AI model and generating feedback and follow-up questions, a means for sending the generated information to the participants' devices, a means for recording comments and feedback during the meeting, and a means for later reviewing these records.

[0735] System configuration

[0736] The server is responsible for the main processing and plays a central role in the progress of the conference. The server houses the speech recognition engine, generative AI model, and database. On the other hand, the terminals are devices used by participants to communicate with the server. Users join the conference and operate their terminals to exchange data with the server.

[0737] Explanation of program processing

[0738] 1. Set up a meeting:

[0739] The user (organizer) inputs the purpose, prerequisites, rules, and additional conditions of the meeting through the interface and sends them to the server, which stores this information in a database and uses it to progress the meeting.

[0740] 2. Start the meeting:

[0741] When a conference starts, the server sends a notification to the participants' devices to announce the start of the conference. The devices activate their microphones and collect audio data in real time. This audio data is then sent to the server.

[0742] 3. Speech Recognition and Text Transcription:

[0743] The server runs the received voice data through a speech recognition engine and converts what is being said into text, which is then input into a generative AI model for analysis.

[0744] 4. Generate feedback and questions:

[0745] The generative AI model analyzes the textual utterances and generates appropriate feedback and follow-up questions based on the meeting's objectives and rules. The generated feedback and questions are then sent to the device.

[0746] 5. Provision of Information:

[0747] The terminal provides the user with feedback and questions received from the server via voice or text, providing guidance for the progress of the meeting.

[0748] 6. Records of meetings:

[0749] All statements made during the meeting, as well as any feedback or questions generated, are recorded by the server, and these recordings are stored for later review and analysis.

[0750] Specific examples

[0751] 1. Pre-settings:

[0752] The user enters the purpose of the meeting, such as "Check the progress of project X and discuss countermeasures for delays," into the interface and sends it to the server, which then stores this information in a database.

[0753] 2. Meeting begins:

[0754] At the designated start time, the server sends a notification to each participant's device to announce the start of the conference. The device starts collecting voice data and sends it to the server.

[0755] 3. Speech, transcription and feedback:

[0756] User A says, "Currently, the project is one week behind schedule." The device sends this speech to the server, which converts it into text using a speech recognition engine. The generative AI model analyzes the text and generates feedback such as, "What is causing the delay? Are there any specific obstacles?" The device then relays this feedback to User A via voice.

[0757] 4. New statements and responses:

[0758] User B responds, "The main cause is a lack of resources." The device sends this speech to the server, which converts it into text and analyzes it using a generative AI model. The device generates a question, "Do we need more resources, or can we address this in other ways?" and relays this to User B.

[0759] This not only helps organize what is being said and keeps the meeting running smoothly, but also allows for accurate review later.

[0760] The processing flow will be explained below.

[0761] Step 1:

[0762] The user (organizer) inputs the purpose, prerequisites, rules, and additional conditions of the meeting into the interface and sends them to the server, which stores this information in a database.

[0763] Step 2:

[0764] The server sends a notification to each participant at the start time of the conference, announcing the start of the conference. The terminal receives the notification and prepares to collect voice data.

[0765] Step 3:

[0766] When the conference starts, the device activates the microphone and collects participants' speech as audio data, which is then sent to the server in real time.

[0767] Step 4:

[0768] The server converts the received voice data into text data using a speech recognition engine, which is then input into a generative AI model.

[0769] Step 5:

[0770] The generative AI model analyzes text data and generates appropriate feedback and follow-up questions based on the meeting's objectives and rules.

[0771] Step 6:

[0772] The generated feedback and questions are sent from the server to the device, which then provides the received feedback and questions to the user in voice or text format.

[0773] Step 7:

[0774] The user makes further statements and answers based on the feedback and questions from the generative AI model, and the device again transmits these new statements as voice data to the server.

[0775] Step 8:

[0776] The server then converts the newly received voice data into text using a speech recognition engine and analyzes it using a generative AI model. This process is repeated throughout the conference.

[0777] Step 9:

[0778] All statements made during the meeting, as well as feedback and questions from the generative AI model, are recorded by the server, and the recordings are time-stamped, allowing the order and time of statements to be tracked.

[0779] Step 10:

[0780] After the meeting, the server organizes all recorded data and automatically generates meeting minutes, which are then stored for user access.

[0781] Step 11:

[0782] Users can check the minutes of the meeting and make corrections or additional comments as necessary, which can be useful in preparing for the next meeting.

[0783] Step 12:

[0784] For the next meeting, the server can refer to past records and help set new topics and goals for discussion.

[0785] Example 1

[0786] 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."

[0787] Conventional conference systems are inefficient in sharing information and advancing discussions among participants, and have limitations in recording what is being said and providing feedback. Furthermore, real-time speech recognition, transcription of speech, and subsequent generation of feedback and questions are all performed manually, which can easily disrupt the flow of the meeting. This creates problems that reduce the efficiency and fairness of meetings.

[0788] 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.

[0789] In this invention, the server includes means for setting the purpose, prerequisites, rules, and additional conditions of the meeting in advance, means for performing real-time speech recognition and converting participants' comments into text, means for analyzing the textual comments with a generative AI model and generating appropriate feedback and follow-up questions, means for transmitting the generated feedback and questions to the participants' terminals, means for recording the comments made during the meeting and the feedback from the generative AI, means for sending a notification to the participants' terminals at the start of the meeting and starting to collect voice data, means for transmitting the voice data to the server in streaming format, means for inputting prompt sentences into the generative AI model, and means for displaying the comments, generated feedback, and questions on a screen or by voice, thereby enabling real-time feedback provision and efficient meeting progress.

[0790] "Means for setting the purpose, prerequisites, rules, and additional conditions of a meeting in advance" refers to an interface and software for inputting information and rules necessary for the progress of a meeting in advance and storing them in a database.

[0791] "Means for real-time speech recognition and conversion of participants' speech into text" refers to a speech recognition engine and related technology for instantly converting participants' speech into text during a meeting.

[0792] "Means of analyzing textual comments using a generative AI model to generate appropriate feedback and follow-up questions" refers to software that analyzes textual comments using an AI model that uses natural language processing technology, and automatically generates feedback and questions based on the purpose and rules of the meeting.

[0793] "Means for transmitting generated feedback and questions to participant devices" refers to the communications means and protocols for transmitting feedback and questions generated by the AI ​​model to participant devices.

[0794] "Means for recording statements made during meetings and feedback from the generative AI" refers to a system configuration for storing all statements made during meetings and feedback provided by the generative AI in a database.

[0795] "Means for sending a notification to the participant's device at the start of the meeting and starting the collection of audio data" refers to software and hardware for sending a notification to the participant's device at the start of the meeting, activating the microphone, and starting the collection of audio data.

[0796] "Means for transmitting audio data to a server in streaming format" refers to data communications technologies and protocols for transmitting collected audio data to a server in real time.

[0797] "Means for inputting prompts into a generative AI model" refers to interfaces and software tools for inputting text data and instructions for analysis into a generative AI model.

[0798] "Means for displaying or providing audio of statements, generated feedback, and questions" refers to the interface and speech synthesis engine for providing visual or audio notification of generated feedback and questions to the participant's device.

[0799] This invention relates to a conference progress system that uses a generative AI model to improve the efficiency and fairness of conferences. This system is mainly composed of a server, terminals, and users. The details are explained below.

[0800] System configuration

[0801] The server is responsible for the main processing and plays a central role in the progress of the conference. The server houses the speech recognition engine, generative AI model, and database. The terminals are devices used by participants to communicate with the server. Users join the conference and operate their terminals to exchange data with the server.

[0802] Meeting Setup

[0803] First, the user (organizer) inputs the purpose, prerequisites, rules, and additional conditions of the meeting through the interface and sends them to the server. The server stores this information in a database and uses it to guide the progress of the meeting. For example, the purpose might be to "check the progress of Project X and discuss countermeasures for delays," and rules might be set such as "each comment has a time limit of three minutes."

[0804] Starting a meeting

[0805] At the designated start time, the server sends a notification to each participant's device to announce the start of the conference. The device activates its microphone and collects audio data in real time. The collected audio data is then sent to the server in streaming format.

[0806] Speech recognition and text conversion

[0807] The server runs the received voice data through a speech recognition engine (e.g., Google Cloud Speech-to-Text) to convert what is being said into text. This text data is then input into a generative AI model for analysis. The speech recognition engine provides highly accurate speech recognition in real time, instantly converting what is being said into text.

[0808] Generate feedback and questions

[0809] A generative AI model (e.g., OpenAI GPT-4) analyzes the textual utterances and generates appropriate feedback and follow-up questions based on the meeting's objectives and rules. The generated feedback and questions are sent to the device. For example, feedback such as "What is causing the delay? Are there any specific obstacles?" is generated.

[0810] Providing information

[0811] The terminal provides the user with feedback and questions received from the server via voice or text, giving the user guidance on how to proceed with the meeting. Information can be provided either as text displayed on the terminal screen or as voice using a speech synthesis engine.

[0812] Meeting Records

[0813] All statements made during the meeting, as well as any feedback or questions generated, are recorded by the server. These records are stored for later review and analysis. If the user wishes to review the recording after the meeting, the server provides a detailed recording.

[0814] Examples of prompt statements

[0815] Below are some examples of prompts to input to the generative AI model.

[0816] Purpose of the meeting: Check the progress of Project X and discuss measures to deal with delays

[0817] Statement: The project is currently one week behind schedule.

[0818] Questions and feedback: What is causing the delay? Are there any particular obstacles?

[0819] This keeps meetings running smoothly and provides necessary feedback and questions in real time, allowing meeting participants to respond quickly and efficiently.

[0820] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0821] Step 1: Set up a meeting

[0822] The user inputs the purpose of the meeting, prerequisites, rules, and additional conditions through the interface and sends them to the server. The input data includes the purpose of the meeting (e.g., "Check the progress of Project X and discuss countermeasures for delays") and meeting rules (e.g., "Each comment has a time limit of three minutes"). The server receives this information and stores it in a database. Based on this, the data required for subsequent processing is constructed.

[0823] Step 2: Start the meeting

[0824] At the specified start time, the server sends a notification to each participant's device to announce the start of the conference. The input includes the conference setting information and start time. The output is a notification that the conference has started sent to each device. When the device receives the notification, it activates its microphone and begins collecting audio data in real time. This audio data is sent to the server in streaming format.

[0825] Step 3: Speech recognition and text conversion

[0826] The server runs the received voice data through a speech recognition engine (e.g., Google Cloud Speech-to-Text) and converts what is being said into text. The input includes the collected voice data. The output is the converted text data. Specifically, the server processes the voice data in real time and generates highly accurate text data.

[0827] Step 4: Generate feedback and questions

[0828] The server inputs the converted text data into a generative AI model (e.g., OpenAI GPT-4) to generate appropriate feedback and follow-up questions based on the meeting's purpose and rules. The input includes the textual utterances and meeting setting information. The output is generated feedback and questions. The generative AI model analyzes the utterances and generates appropriate utterances. For example, feedback such as "What is causing the delay? Are there any specific obstacles?" is generated.

[0829] Step 5: Provide information

[0830] The server sends the generated feedback and questions to each device. The input includes the generated feedback and questions. The output is provided as a display or voice message on each participant's device. The device displays the received information as text on the screen or uses a speech synthesis engine to convey it to the user audibly. For example, feedback in response to user A's statement is played audibly.

[0831] Step 6: Record the meeting

[0832] The server records all statements made during the meeting, as well as any feedback or questions generated. The input includes statements, feedback, and questions generated during the meeting. The output is stored in a database, which provides the data for users to review after the meeting.

[0833] Examples of prompt statements

[0834] Below is an example of a prompt sentence to be input to the generative AI model in step 4.

[0835] Purpose of the meeting: Check the progress of Project X and discuss measures to deal with delays

[0836] Statement: The project is currently one week behind schedule.

[0837] Questions and feedback: What is causing the delay? Are there any particular obstacles?

[0838] This allows the meeting to proceed more effectively and efficiently.

[0839] (Application example 1)

[0840] 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."

[0841] Improving the efficiency and fairness of meetings and troubleshooting in factories is an important issue. In particular, there is a need for a system that can analyze information in real time and provide prompt and appropriate feedback. Implementing such a system would facilitate smooth communication within the factory, leading to improved productivity and faster problem resolution. However, such systems are currently not fully implemented, which often leads to inefficient meetings and delays in problem resolution in factory operations.

[0842] 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.

[0843] In this invention, the server includes: means for setting the purpose, prerequisites, rules, and additional conditions of the meeting in advance; means for performing real-time speech recognition and converting participants' comments into text; means for analyzing the converted text using a generative AI model and generating appropriate feedback and follow-up questions; means for transmitting the generated feedback and questions to the participants' terminals; means for recording the content of comments made during the meeting and the generative AI feedback; means for supporting factory meetings and troubleshooting meetings in real time; and means for providing industrial speech recognition results and generated feedback to participants using smart glasses or a voice interface. This enables improved efficiency and fairness in factory meetings and troubleshooting.

[0844] A "meeting objective" is a specific goal or objective that a particular meeting aims to achieve.

[0845] "Preconditions" are the basic conditions or situations that must be established first in order for a meeting to proceed.

[0846] "Rules" are instructions and guidelines that participants must follow to ensure the meeting runs smoothly.

[0847] "Conditions" means any additional conditions or restrictions associated with a conference.

[0848] "Speech recognition" is a technology that analyzes voice data collected using a microphone and converts it into text information.

[0849] "Means for converting speech to text" refers to a method or device for converting speech from participants into text in real time using speech recognition.

[0850] A "generative AI model" is an artificial intelligence model that is trained to analyze input data and perform specific tasks automatically.

[0851] "Feedback" refers to responses or additional information provided by a generative AI model based on the results of its analysis.

[0852] A "terminal" is a device used by a participant to exchange data with the server.

[0853] "Means of recording" refers to methods or devices for saving what is said during a meeting and feedback from generative AI.

[0854] A "factory meeting" is a discussion or meeting with a specific purpose that takes place on the production floor or within a factory.

[0855] A "troubleshooting meeting" is a meeting held to resolve problems that arise in a system or process.

[0856] "Smart glasses" are glasses-type information and communication devices that provide visual information.

[0857] A "voice interface" is a technology or device that allows a user to communicate with a system through speech.

[0858] This invention is a system for supporting meetings and troubleshooting meetings in factories, and aims to improve the efficiency and fairness of meetings. A specific method for realizing this system will be described below.

[0859] The server is responsible for the main processing and plays a central role in the progress of the conference. This server houses the speech recognition engine, generative AI model, and database. Meanwhile, the terminals are devices used by participants to communicate with the server. Terminals include smart glasses and voice interfaces.

[0860] First, the user (organizer) inputs the purpose, prerequisites, rules, and additional conditions of the meeting through the interface and sends them to the server. The server stores this information in a database and uses it to progress the meeting.

[0861] When a meeting starts, the server sends a notification to the participants' devices to announce the start of the meeting. The devices turn on their microphones and collect audio data in real time. This audio data is sent to the server. The server then runs the received audio data through a speech recognition engine and converts what is being said into text. The SpeechRecognition library is used for speech recognition, and Google's speech recognition API is used to convert what is being said into text.

[0862] The textual comments are input into a generative AI model for analysis. The generative AI model uses Hugging Face's Transformers (pipeline functions) to generate appropriate feedback and follow-up questions based on the meeting's objectives and rules. The generated feedback and questions are sent to the device, which then provides them to the user via the smart glasses' display or voice interface. This allows the user to obtain guidance on how the meeting should proceed.

[0863] All statements made during the meeting, as well as any feedback or questions generated, are recorded by the server, and these recordings are stored for later review and analysis.

[0864] As a concrete example, consider a meeting to discuss the cause of a line stoppage and measures to prevent recurrence. The organizer sets the purpose of the meeting as "to investigate the cause of the line stoppage and consider measures to prevent recurrence." At the start of the meeting, User A says, "The line suddenly stopped. The cause is currently unknown." This speech is sent to the server via smart glasses and converted into text. The generative AI model analyzes this text and generates feedback such as "What is the cause?" and provides it to User A. This series of steps allows the meeting to proceed smoothly and enables efficient problem solving.

[0865] An example of a prompt sentence for the statement "The line has stopped suddenly. The cause is currently unknown." would be:

[0866] "What is the cause?"

[0867] This system contributes to improving the efficiency and fairness of meetings and troubleshooting within the factory.

[0868] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0869] Step 1:

[0870] The server receives information about the purpose, prerequisites, rules, and additional conditions of the meeting entered by the user (organizer) through the interface and stores it in a database. The entered data is the detailed information necessary for the progress of the meeting, and this will be the basis for the smooth running of the meeting in later steps.

[0871] Step 2:

[0872] When a conference starts, the server sends a notification to the participants' devices to announce the start of the conference. When the device receives the notification, it activates the microphone and starts collecting audio data. The collected audio data becomes the material for analysis in later processes.

[0873] Step 3:

[0874] The device sends the collected voice data to the server. The server passes the received voice data to a voice recognition engine in real time and converts what is being said into text. The process of converting this voice data into text data uses the SpeechRecognition library and Google's voice recognition API. The input is voice data and the output is text data.

[0875] Step 4:

[0876] The server inputs the textualized utterances into a generative AI model for analysis. The generative AI model uses Hugging Face's Transformers (pipeline function). This analysis generates appropriate feedback and follow-up questions based on the utterance content. Here, the input is text data, and the output is text data of feedback or questions.

[0877] Step 5:

[0878] The generated feedback and questions are sent from the server to the device. The device then provides the feedback and questions to the user in the form of voice or text. For example, it displays the feedback and questions as text on the smart glasses display or reads them out loud using a voice interface. The input is the text data of the feedback and questions, and the output is a notification to the user.

[0879] Step 6:

[0880] The server records all statements made during the meeting, as well as any feedback or questions generated, which are then stored in a database for later review and analysis. The input is the text data of statements made during the meeting, as well as any feedback or questions, and the output is the recorded data.

[0881] Step 7:

[0882] After the meeting is over, the server provides a function for later review of the recorded meeting contents. The user (host) can view this recording to confirm and analyze the contents of the meeting. The input is the recorded data stored in the database, and the output is data in a format that can be viewed by the user.

[0883] 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.

[0884] This invention improves the efficiency and fairness of meetings by combining an emotion engine with a meeting progress system using a generative AI model, and further recognizes the emotions of meeting participants and provides appropriate feedback. This system includes means for setting the purpose, prerequisites, rules, and conditions of the meeting in advance, means for performing real-time speech recognition and converting comments into text, means for analyzing the content of comments and the emotion recognition results using a generative AI model and generating feedback and follow-up questions, means for sending the generated information to the participants' devices, means for recording the content of comments made during the meeting and the results of the generative AI and emotion engine, and means for reviewing them.

[0885] System configuration

[0886] The server is responsible for the main processing and serves as the center of the conference. The server houses a speech recognition engine, generative AI model, emotion engine, and database. The terminals are devices used by participants to communicate with the server. Users join the conference and exchange data with the server through their terminals.

[0887] Explanation of program processing

[0888] 1. Set up a meeting:

[0889] The user (organizer) inputs the purpose, prerequisites, rules, and additional conditions of the meeting through the interface and sends them to the server, which stores this information in a database and uses it to progress the meeting.

[0890] 2. Start the meeting:

[0891] When the conference starts, the server sends a notification to the participants' terminals to announce the start of the conference. The terminals receive the notification and prepare to collect voice data.

[0892] 3. Speech Recognition and Text Transcription:

[0893] When the conference starts, the device activates the microphone and collects participants' speech as voice data. The server converts the received voice data into text data using a voice recognition engine.

[0894] 4. Emotion recognition:

[0895] The collected voice data is converted into text and simultaneously analyzed by an emotion engine to recognize the participants' emotional state. The emotion recognition results are then input into a generative AI model.

[0896] 5. Generate feedback and questions:

[0897] The generative AI model analyzes the text data and emotion recognition results, and generates appropriate feedback and follow-up questions based on the purpose and rules of the meeting. The generated feedback and questions are sent from the server to the device and provided to the user in voice or text format.

[0898] 6. Provision of Information:

[0899] The device provides the user with feedback, questions, and emotion recognition results received from the server, allowing the user to understand the guidelines for the progress of the meeting and the emotional situation.

[0900] 7. Records of meetings:

[0901] All statements made during the meeting, the feedback generated, questions asked, and emotion recognition results are recorded by the server, and the recordings are time-stamped to track the order and duration of statements.

[0902] 8. Reviews and Feedback:

[0903] After the meeting, the server organizes all recorded data and automatically generates meeting minutes, which include emotion recognition results and are saved for user access. Feedback based on the emotion recognition results is also provided, and an overall evaluation of the meeting and areas for improvement are identified.

[0904] Specific examples

[0905] 1. Pre-settings:

[0906] The user enters the purpose of the meeting, such as "Check the progress of project X and discuss countermeasures for delays," into the interface and sends it to the server, which then stores this information in a database.

[0907] 2. Meeting begins:

[0908] The server sends a notification to each participant at the start time to announce the start of the conference, and the device activates the microphone and prepares to collect audio.

[0909] 3. Speech, transcription and feedback:

[0910] User A says, "The project is currently one week behind schedule." The device sends this speech to the server, which converts it into text using a speech recognition engine and recognizes the emotion using an emotion engine. The generative AI model analyzes the speech and generates feedback such as, "What is causing the delay? Are there any specific obstacles?" The device then provides this feedback to User A. At the same time, the emotion engine detects the tension and provides additional feedback such as, "Let's calmly analyze the situation."

[0911] The system helps meetings run smoothly and produce rational outcomes by organizing what is being said and providing feedback that takes into account emotional states.

[0912] The processing flow will be explained below.

[0913] Step 1:

[0914] The user (organizer) inputs the purpose, prerequisites, rules, and additional conditions of the meeting into the interface and sends them to the server, which stores this information in a database.

[0915] Step 2:

[0916] The server sends a notification to each participant at the start time of the conference, announcing the start of the conference. The terminal receives the notification and prepares to collect voice data.

[0917] Step 3:

[0918] When the conference starts, the device activates the microphone and collects participants' speech as audio data, which is then sent to the server in real time.

[0919] Step 4:

[0920] The server converts the received voice data into text data using a speech recognition engine, which is then input into a generative AI model.

[0921] Step 5:

[0922] The collected voice data is converted into text and simultaneously analyzed by an emotion engine to recognize the participants' emotional state. The emotion recognition results are then input into a generative AI model.

[0923] Step 6:

[0924] The generative AI model analyzes text data and emotion recognition results to generate appropriate feedback and follow-up questions based on the meeting's objectives and rules.

[0925] Step 7:

[0926] The generated feedback and questions are sent from the server to the device, which then provides the received feedback and questions to the user in voice or text format.

[0927] Step 8:

[0928] The user makes further statements and answers based on the feedback and questions from the generative AI model, and the device again transmits these new statements as voice data to the server.

[0929] Step 9:

[0930] The server then converts the newly received voice data into text using the speech recognition engine and analyzes it using the generative AI model. At the same time, the emotion engine generates new emotion recognition results. This process is repeated throughout the conference.

[0931] Step 10:

[0932] During the meeting, all statements, generated feedback, questions, and emotional states recognized by the emotion engine are recorded by the server, and the recordings are time-stamped, allowing for tracking of the order and time of statements.

[0933] Step 11:

[0934] After the meeting, the server organizes all recorded data and automatically generates meeting minutes, which are stored for user access. Feedback based on emotion recognition results is also provided, and an overall evaluation of the meeting and suggestions for improvement are identified.

[0935] Specific examples

[0936] 1. Pre-settings:

[0937] The user enters the purpose of the meeting, such as "Check the progress of project X and discuss countermeasures for delays," into the interface and sends it to the server, which then stores this information in a database.

[0938] 2. Meeting begins:

[0939] The server sends a notification to each participant at the start time to announce the start of the conference, and the device activates the microphone and prepares to collect audio.

[0940] 3. Speech and text conversion, emotion recognition, and feedback:

[0941] User A says, "The project is currently one week behind schedule." The device sends this speech to the server, which converts it into text using a speech recognition engine and recognizes the emotion using an emotion engine. The generative AI model analyzes it and generates feedback such as, "What is causing the delay? Are there any specific obstacles?" At the same time, the emotion engine detects the tension and generates additional feedback such as, "Let's calmly analyze the situation," which the device provides to User A.

[0942] The system helps meetings run smoothly and produce rational outcomes by organizing what is being said and providing feedback that takes into account emotional states.

[0943] Example 2

[0944] 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."

[0945] Conventional meeting systems rarely provide appropriate feedback on the progress of meetings or participants' comments, hindering effective discussion and decision-making. Furthermore, feedback that does not reflect participants' emotional states can lead to inefficient meetings and unfair treatment of some participants. Furthermore, the post-meeting review process is cumbersome, and organizing and evaluating records takes time.

[0946] 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.

[0947] In this invention, the server includes: means for setting the purpose, prerequisites, rules, and additional conditions of the meeting in advance; means for recognizing speech in real time and converting participants' comments into text; means for recognizing the emotional state of the participants from the text comments using emotion analysis means; means for analyzing the text comments and the emotion recognition results using a generative artificial intelligence model to generate appropriate feedback and follow-up questions; means for transmitting the generated feedback and questions to the participants' communication devices; and means for recording the content of comments made during the meeting and the feedback and emotion recognition results of the generative artificial intelligence model. This makes the meeting more efficient, and fair and effective communication is achieved by providing feedback that takes into account the emotional state of each participant. It also facilitates review after the meeting, allowing for quick minutes creation and review of the meeting.

[0948] "Means for setting the purpose, prerequisites, rules, and additional conditions of a meeting in advance" refers to a function that allows you to input and save the purpose, rules, etc. of a meeting in advance in order to determine the progress of the meeting and the direction of the discussion, and to ensure that the meeting is run based on specific conditions and rules.

[0949] "Means for recognizing speech in real time and converting participants' comments into text" refers to a function that analyzes speech made by participants during a meeting in real time and instantly converts the speech into text using speech recognition technology.

[0950] "Means for recognizing the emotional state of participants from textualized statements using emotion analysis means" is a function for analyzing and confirming the emotional state of speakers using emotion analysis technology based on text data generated by voice recognition.

[0951] "Means for analyzing textual statements and emotion recognition results using a generative artificial intelligence model, and generating appropriate feedback and follow-up questions" refers to a function that analyzes text data and emotion recognition results using a generative artificial intelligence model (e.g., a language model), and automatically generates highly relevant feedback and questions based on the analysis results.

[0952] "Means for sending generated feedback and questions to participants' communication devices" refers to a function that sends feedback and questions generated by the generative artificial intelligence model to the communication devices used by participants (e.g., smartphones or personal computers).

[0953] "Means for recording statements made during a meeting, feedback from a generative AI model, and emotion recognition results" refers to a function that records all statements made during a meeting, generated feedback and questions, and emotion recognition results with timestamps, and saves them for later access.

[0954] This invention combines a generative AI model-based conference proceeding system with an emotion analysis engine to improve the efficiency and fairness of conferences, and also recognizes the emotions of conference participants and provides appropriate feedback. The system includes the following main hardware and software components:

[0955] Hardware and software used

[0956] 1. Server

[0957] The server is responsible for the main processing and serves as the center of the conference. This server houses a speech recognition engine, generative AI model, emotion analysis engine, and database. The speech recognition engine uses the Google Cloud Speech-to-Text API, and the emotion analysis engine uses the Microsoft Azure Emotion API.

[0958] 2. Terminal

[0959] The terminal is a device used by participants to communicate with the server. Terminals can be smartphones, tablets, PCs, etc. Terminals collect voice data, receive feedback, and display it.

[0960] 3. Users

[0961] Users participate in the conference and exchange data with the server through their devices, as well as set up the conference and check feedback.

[0962] Specific processing of the system

[0963] The operation of the system proceeds as follows.

[0964] 1. Set up a meeting:

[0965] The user (organizer) inputs the purpose of the meeting ("Check the progress of Project X"), prerequisites, rules ("Keep comments brief"), and additional conditions ("Use diagrams and tables as needed") through the interface. Once input is complete, the settings are sent to the server. The server stores the received settings in a database and uses them to progress the meeting.

[0966] 2. Start the meeting:

[0967] When the meeting start time arrives, the server sends a push notification to each participant's device. The notification contains a message informing them that the meeting is about to begin. The device receives this notification and prepares to turn on its microphone and speaker.

[0968] 3. Speech Recognition and Text Transcription:

[0969] The user's speech is collected as voice data through the device's microphone. For example, if the user says, "Project X is progressing smoothly," the voice data is sent to the server in real time. The server then converts the received voice data into text data using the Google Cloud Speech-to-Text API.

[0970] 4. Emotion recognition:

[0971] The server uses an emotion analysis engine to analyze the voice data and the user's emotions. For example, if the user's speech is analyzed to indicate "anxiety," this result is recorded along with the text data. The emotion recognition results are provided to a generative AI model, forming the basis for future feedback generation.

[0972] 5. Generate feedback and questions:

[0973] The generative AI model analyzes the text data stored on the server and the emotion recognition results. For example, if a user says, "Project X is behind schedule," the model generates feedback such as, "What is the cause of the delay?" or "Let's think of specific countermeasures." The generated feedback and questions are sent from the server to the device and provided to the participants.

[0974] 6. Provision of Information:

[0975] The device then provides the received feedback, questions, and emotion recognition results to the user. For example, feedback such as "Analyze the situation calmly" is displayed to the user as voice or text. This allows the user to understand the progress of the meeting and the emotional situation.

[0976] 7. Records of meetings:

[0977] The server records all statements made during the meeting, along with any feedback generated, questions asked, and emotion recognition results, with timestamps, allowing for tracking of the order and duration of statements. This data is stored in a database for later review.

[0978] 8. Reviews and Feedback:

[0979] After the meeting, the server organizes all recorded data and automatically generates meeting minutes, which include the content of comments, emotion recognition results, and feedback. Users can access the minutes and review the entire meeting. Based on the emotion recognition results, the server also provides suggestions for improvements and guidelines for future meetings.

[0980] Examples of prompt statements

[0981] Please report on the progress of the project.

[0982] Please enter the purpose of the meeting.

[0983] "Convert what is being said into text and analyze the emotional state."

[0984] "Generate appropriate feedback and questions based on your analysis."

[0985] This system is expected to help meetings be run efficiently and fairly, and to lead to more constructive discussions by providing feedback that reflects the emotional state of participants.

[0986] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0987] Step 1:

[0988] Meeting Setup

[0989] The user (organizer) enters the purpose of the meeting, "Check the progress of Project X," the prerequisites, the rule, "Keep comments brief," and the additional condition, "Use diagrams and tables as necessary," into the interface. Once the input is complete, the user clicks the "Set" button to send the settings to the server. The server stores the received settings data in a database and makes them available for use in the progress of the meeting. As a specific example, the contents stored in the database include the "start date and time," "list of participants," and "meeting agenda."

[0990] Step 2:

[0991] Starting a meeting

[0992] When the meeting starts, the server sends a push notification to the participants' devices. The notification includes the message "The meeting has started. Please prepare to speak." This is transmitted to the device as input, and the device prepares the microphone and speaker, making it ready to collect audio data.

[0993] Step 3:

[0994] Speech recognition and text conversion

[0995] The meeting officially begins, and a user speaks. The device's microphone collects audio data, such as "Project X is progressing well," and sends it to the server. The server converts the received audio data into text data using the Google Cloud Speech-to-Text API. In this case, the input is audio data, and the output is text data: "Project X is progressing well."

[0996] Step 4:

[0997] emotion recognition

[0998] The server inputs the text data along with the voice data into an emotion analysis engine (such as Microsoft Azure's Emotion API) to recognize the emotional state. For example, if the statement "Project X is progressing smoothly" is analyzed as indicating "joy," the emotion recognition engine will return the result "joy." The input is text data and voice data, and the output is the emotion recognition result of "joy."

[0999] Step 5:

[1000] Generate feedback and questions

[1001] The server uses a generative artificial intelligence model (e.g., OpenAI's GPT-3) to analyze text data and emotion recognition results. For example, if someone says, "Project X is behind schedule," the model generates a question such as, "What is the cause of the delay?" or feedback such as, "Let's think of specific countermeasures." The input is the text data and emotion recognition results, and the output is the generated feedback or question.

[1002] Step 6:

[1003] Providing information

[1004] The generated feedback and questions are sent from the server to the device. The device receives them and displays them to the user as voice or text. For example, the feedback "Let's calmly analyze the situation" is provided to the user. The input is the generated feedback and questions, and the output is a notification to the user as voice or text.

[1005] Step 7:

[1006] Meeting Records

[1007] The server records all statements made during the meeting, generated feedback, questions, and emotion recognition results with timestamps. This allows the order and time of statements to be tracked. The recorded data is saved in a database and can be referenced later. The input is all data from the meeting, and the output is the recorded data with timestamps.

[1008] Step 8:

[1009] Reviews and Feedback

[1010] After the meeting, the server organizes all recorded data and creates automatically generated minutes. These minutes include the content of the remarks, emotion recognition results, and feedback. Users can access these minutes and review the entire meeting. In addition, the emotion recognition results provide improvements and guidelines for future meetings. The input is the recorded data, and the output is the automatically generated minutes and feedback.

[1011] (Application example 2)

[1012] 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."

[1013] Traditional security meetings and briefings have had issues with the content of each person's comments being subjective, and limited feedback tailored to the speaker's emotions and the progress of the meeting. Furthermore, meeting recordings are insufficient, making subsequent review and analysis difficult. These limitations compromise the efficiency and fairness of security meetings and put important information at risk of being overlooked.

[1014] The specific processing by the specific 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 setting the purpose, prerequisites, rules, and additional conditions of a meeting or briefing in advance; means for performing real-time speech recognition and converting participants' or staff's comments into text; means for analyzing the converted text using a generative AI model and generating appropriate feedback and follow-up questions; means for transmitting the generated feedback and questions to the participants' devices; means for analyzing collected voice data using an emotion engine and recognizing emotional states; means for the generative AI model to generate feedback and questions based on the emotion recognition results; and means for recording the content of comments made during the meeting and the generative AI feedback. This allows for objective analysis of participants' comments during the security meeting and provides feedback that takes their emotional states into account. Furthermore, detailed records of the meeting content and automatically generated minutes enable comprehensive reviews, allowing for efficient understanding and improvement of the security situation.

[1015] "Methods for setting the purpose, prerequisites, rules, and additional conditions of a meeting or briefing in advance" refers to a method by which participants share the information and rules necessary for the progress of a meeting or briefing and decide on them in advance to support smooth progress.

[1016] "Means for real-time speech recognition and conversion of participants' or representatives' speech into text" refers to technology that recognizes words spoken during a meeting in real time and converts them into digital text.

[1017] "Means for analyzing textual statements using a generative AI model and generating appropriate feedback and follow-up questions" refers to a system that uses a generative artificial intelligence model to analyze text data and automatically generate feedback and questions.

[1018] The "means for transmitting the generated feedback and questions to the participant's terminal" is a method for transmitting automatically generated feedback and questions to the device used by the participant.

[1019] "Means for analyzing collected voice data using an emotion engine and recognizing emotional states" refers to equipment that uses voice data collected by sensors or other devices to analyze and sense the speaker's emotions using an emotion analysis engine.

[1020] "Means for a generative AI model to generate feedback and questions based on emotion recognition results" refers to a system that uses emotion recognition results obtained from an emotion analysis engine to generate appropriate feedback and questions using a generative AI model.

[1021] "Means for recording statements made during meetings and feedback from generative AI" refers to technology that saves statements made during meetings and feedback output by generative AI models so that they can be reviewed later.

[1022] "Means for later reviewing recorded meeting content and automatically generating minutes that include emotion recognition results" refers to a system that automatically creates and enables review of meeting minutes based on the content recorded during the meeting and the results of emotion analysis.

[1023] The "means for providing participants with speech recognition results and emotion recognition results not only in text but also in audio" is a technology for conveying speech recognition and emotion recognition results to participants not only in text format but also as audio.

[1024] This invention provides a system for improving the efficiency and fairness of security conferences and briefings. The system includes a server, a terminal (e.g., smart glasses), and a user called a security officer. Specific embodiments for implementing this invention will be described below.

[1025] System Configuration

[1026] The server is the main processing center and contains the following modules:

[1027] Speech recognition engine (e.g. Google Cloud Speech-to-Text API)

[1028] Generative AI models (e.g., OpenAI GPT-4)

[1029] Emotion engine (e.g. Amazon Lex or Affectiva SDK)

[1030] Database (e.g. Amazon RDS)

[1031] Terminals are devices used by security personnel and include smart glasses (e.g., Google Glass, Vuzix Blade).

[1032] Data processing flow

[1033] 1. Setting up meetings and briefings

[1034] The user (the organizer among the security personnel) inputs the purpose, prerequisites, rules, and additional conditions of the meeting through the interface of the smart glasses and sends them to the server, which stores this information in a database and uses it to guide the progress of the meeting.

[1035] 2. Real-time speech recognition and emotion analysis

[1036] When a meeting or briefing begins, the device activates its microphone and collects participants' speech as voice data. The server converts the received voice data into text data using a voice recognition engine, and simultaneously analyzes the participants' emotional states using an emotion engine.

[1037] 3. Generate feedback and questions

[1038] The textual comments and emotion recognition results are analyzed using a generative AI model to generate appropriate feedback and follow-up questions as the meeting progresses. The generated feedback and questions are sent from the server to the device and provided to the user in voice or text format.

[1039] 4. Recording and reviewing during the meeting

[1040] All statements made during the meeting and feedback output by the generative AI model are recorded, including emotion recognition results, with a timestamp. After the meeting ends, the server organizes this data and automatically generates minutes. The minutes, which also include emotion recognition results, are used for review and to identify areas for improvement.

[1041] Examples of concrete examples and prompts

[1042] For example, if a security officer says "There were no abnormalities at the site today" during a security meeting, this statement is converted into text by a speech recognition engine, and the emotion engine recognizes "sense of security." The generative AI model analyzes this information and generates feedback such as "What part of the site is the situation? Please tell us the details." This feedback is displayed on the officer's smart glasses.

[1043] Example prompt sentence:

[1044] Input: "Nothing unusual at the site today."

[1045] Prompt: Use this statement to generate questions that ask for more information.

[1046] Example: "What part of the site is the situation? Please tell me the details."

[1047] This allows for objective analysis of participants' comments during security meetings and provides feedback that takes into account their emotional state. It also enables comprehensive reviews, allowing for efficient understanding and improvement of the security situation.

[1048] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1049] Step 1:

[1050] The user inputs the purpose, prerequisites, rules, and additional conditions of the meeting or briefing through the terminal interface and sends them to the server. The server stores this information in a database. The input is the setting information from the user, and the output is saved in the database. In this step, the information necessary to proceed with the meeting is prepared in advance.

[1051] Step 2:

[1052] At the start of a meeting or briefing, the server sends a start notification to the device. The device receives the notification and activates the microphone to prepare to collect audio data. The input is the notification from the server, and the output is the activation of the microphone. In this step, the start of the meeting is notified to the entire system, and audio recording is prepared.

[1053] Step 3:

[1054] The device sends the voice data collected during the meeting to the server. The server inputs the received voice data into a voice recognition engine and converts it into text data. The input is voice data and the output is text data. In this step, the participants' remarks are converted into text.

[1055] Step 4:

[1056] The server inputs the textual utterances into the emotion engine and analyzes the emotional state. The input is text data, and the output is emotion recognition results. In this step, the speaker's emotional state is understood.

[1057] Step 5:

[1058] The server inputs text data and emotion recognition results into the generative AI model to generate appropriate feedback and follow-up questions. The input is text data and emotion recognition results, and the output is feedback and questions. In this step, the generative AI model automatically generates responses that are appropriate for the progress of the meeting.

[1059] Step 6:

[1060] The server sends the generated feedback and questions to the terminal and provides them to the user. The terminal displays the feedback and questions as voice or text. The input is the feedback and questions, and the output is what is presented to the user. In this step, the user receives the feedback and questions in real time.

[1061] Step 7:

[1062] The server records all statements made during the meeting, the generated feedback, and the emotion recognition results. The input is the statements, feedback, and emotion recognition results, and the output is the recorded data. In this step, all meeting data is saved with a timestamp.

[1063] Step 8:

[1064] After the meeting, the server automatically generates minutes based on the recorded data and creates a report that includes the emotion recognition results. The input is the recorded data, and the output is the minutes and report. In this step, the meeting is automatically summarized, making it easier to review later.

[1065] 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.

[1066] 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.

[1067] 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.

[1068] [Fourth embodiment]

[1069] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1070] 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.

[1071] 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).

[1072] 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.

[1073] 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.

[1074] 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).

[1075] 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. 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.

[1076] 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.

[1077] 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.

[1078] 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.

[1079] 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.

[1080] 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.

[1081] 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."

[1082] The present invention relates to a meeting progress system using a generative AI model to improve the efficiency and fairness of meetings. This system includes a means for setting the purpose, prerequisites, rules, and conditions of a meeting in advance, a means for real-time speech recognition and conversion of comments into text, a means for analyzing the content of comments using a generative AI model and generating feedback and follow-up questions, a means for sending the generated information to the participants' devices, a means for recording comments and feedback during the meeting, and a means for later reviewing these records.

[1083] System configuration

[1084] The server is responsible for the main processing and plays a central role in the progress of the conference. The server houses the speech recognition engine, generative AI model, and database. On the other hand, the terminals are devices used by participants to communicate with the server. Users join the conference and operate their terminals to exchange data with the server.

[1085] Explanation of program processing

[1086] 1. Set up a meeting:

[1087] The user (organizer) inputs the purpose, prerequisites, rules, and additional conditions of the meeting through the interface and sends them to the server, which stores this information in a database and uses it to progress the meeting.

[1088] 2. Start the meeting:

[1089] When a conference starts, the server sends a notification to the participants' devices to announce the start of the conference. The devices activate their microphones and collect audio data in real time. This audio data is then sent to the server.

[1090] 3. Speech Recognition and Text Transcription:

[1091] The server runs the received voice data through a speech recognition engine and converts what is being said into text, which is then input into a generative AI model for analysis.

[1092] 4. Generate feedback and questions:

[1093] The generative AI model analyzes the textual utterances and generates appropriate feedback and follow-up questions based on the meeting's objectives and rules. The generated feedback and questions are then sent to the device.

[1094] 5. Provision of Information:

[1095] The terminal provides the user with feedback and questions received from the server via voice or text, providing guidance for the progress of the meeting.

[1096] 6. Records of meetings:

[1097] All statements made during the meeting, as well as any feedback or questions generated, are recorded by the server, and these recordings are stored for later review and analysis.

[1098] Specific examples

[1099] 1. Pre-settings:

[1100] The user enters the purpose of the meeting, such as "Check the progress of project X and discuss countermeasures for delays," into the interface and sends it to the server, which then stores this information in a database.

[1101] 2. Meeting begins:

[1102] At the designated start time, the server sends a notification to each participant's device to announce the start of the conference. The device starts collecting voice data and sends it to the server.

[1103] 3. Speech, transcription and feedback:

[1104] User A says, "Currently, the project is one week behind schedule." The device sends this speech to the server, which converts it into text using a speech recognition engine. The generative AI model analyzes the text and generates feedback such as, "What is causing the delay? Are there any specific obstacles?" The device then relays this feedback to User A via voice.

[1105] 4. New statements and responses:

[1106] User B responds, "The main cause is a lack of resources." The device sends this speech to the server, which converts it into text and analyzes it using a generative AI model. The device generates a question, "Do we need more resources, or can we address this in other ways?" and relays this to User B.

[1107] This not only helps organize what is being said and keeps the meeting running smoothly, but also allows for accurate review later.

[1108] The processing flow will be explained below.

[1109] Step 1:

[1110] The user (organizer) inputs the purpose, prerequisites, rules, and additional conditions of the meeting into the interface and sends them to the server, which stores this information in a database.

[1111] Step 2:

[1112] The server sends a notification to each participant at the start time of the conference, announcing the start of the conference. The terminal receives the notification and prepares to collect voice data.

[1113] Step 3:

[1114] When the conference starts, the device activates the microphone and collects participants' speech as audio data, which is then sent to the server in real time.

[1115] Step 4:

[1116] The server converts the received voice data into text data using a speech recognition engine, which is then input into a generative AI model.

[1117] Step 5:

[1118] The generative AI model analyzes text data and generates appropriate feedback and follow-up questions based on the meeting's objectives and rules.

[1119] Step 6:

[1120] The generated feedback and questions are sent from the server to the device, which then provides the received feedback and questions to the user in voice or text format.

[1121] Step 7:

[1122] The user makes further statements and answers based on the feedback and questions from the generative AI model, and the device again transmits these new statements as voice data to the server.

[1123] Step 8:

[1124] The server then converts the newly received voice data into text using a speech recognition engine and analyzes it using a generative AI model. This process is repeated throughout the conference.

[1125] Step 9:

[1126] All statements made during the meeting, as well as feedback and questions from the generative AI model, are recorded by the server, and the recordings are time-stamped, allowing the order and time of statements to be tracked.

[1127] Step 10:

[1128] After the meeting, the server organizes all recorded data and automatically generates meeting minutes, which are then stored for user access.

[1129] Step 11:

[1130] Users can check the minutes of the meeting and make corrections or additional comments as necessary, which can be useful in preparing for the next meeting.

[1131] Step 12:

[1132] For the next meeting, the server can refer to past records and help set new topics and goals for discussion.

[1133] Example 1

[1134] 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."

[1135] Conventional conference systems are inefficient in sharing information and advancing discussions among participants, and have limitations in recording what is being said and providing feedback. Furthermore, real-time speech recognition, transcription of speech, and subsequent generation of feedback and questions are all performed manually, which can easily disrupt the flow of the meeting. This creates problems that reduce the efficiency and fairness of meetings.

[1136] 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.

[1137] In this invention, the server includes means for setting the purpose, prerequisites, rules, and additional conditions of the meeting in advance, means for performing real-time speech recognition and converting participants' comments into text, means for analyzing the textual comments with a generative AI model and generating appropriate feedback and follow-up questions, means for transmitting the generated feedback and questions to the participants' terminals, means for recording the comments made during the meeting and the feedback from the generative AI, means for sending a notification to the participants' terminals at the start of the meeting and starting to collect voice data, means for transmitting the voice data to the server in streaming format, means for inputting prompt sentences into the generative AI model, and means for displaying the comments, generated feedback, and questions on a screen or by voice, thereby enabling real-time feedback provision and efficient meeting progress.

[1138] "Means for setting the purpose, prerequisites, rules, and additional conditions of a meeting in advance" refers to an interface and software for inputting information and rules necessary for the progress of a meeting in advance and storing them in a database.

[1139] "Means for real-time speech recognition and conversion of participants' speech into text" refers to a speech recognition engine and related technology for instantly converting participants' speech into text during a meeting.

[1140] "Means of analyzing textual comments using a generative AI model to generate appropriate feedback and follow-up questions" refers to software that analyzes textual comments using an AI model that uses natural language processing technology, and automatically generates feedback and questions based on the purpose and rules of the meeting.

[1141] "Means for transmitting generated feedback and questions to participant devices" refers to the communications means and protocols for transmitting feedback and questions generated by the AI ​​model to participant devices.

[1142] "Means for recording statements made during meetings and feedback from the generative AI" refers to a system configuration for storing all statements made during meetings and feedback provided by the generative AI in a database.

[1143] "Means for sending a notification to the participant's device at the start of the meeting and starting the collection of audio data" refers to software and hardware for sending a notification to the participant's device at the start of the meeting, activating the microphone, and starting the collection of audio data.

[1144] "Means for transmitting audio data to a server in streaming format" refers to data communications technologies and protocols for transmitting collected audio data to a server in real time.

[1145] "Means for inputting prompts into a generative AI model" refers to interfaces and software tools for inputting text data and instructions for analysis into a generative AI model.

[1146] "Means for displaying or providing audio of statements, generated feedback, and questions" refers to the interface and speech synthesis engine for providing visual or audio notification of generated feedback and questions to the participant's device.

[1147] This invention relates to a conference progress system that uses a generative AI model to improve the efficiency and fairness of conferences. This system is mainly composed of a server, terminals, and users. The details are explained below.

[1148] System configuration

[1149] The server is responsible for the main processing and plays a central role in the progress of the conference. The server houses the speech recognition engine, generative AI model, and database. The terminals are devices used by participants to communicate with the server. Users join the conference and operate their terminals to exchange data with the server.

[1150] Meeting Setup

[1151] First, the user (organizer) inputs the purpose, prerequisites, rules, and additional conditions of the meeting through the interface and sends them to the server. The server stores this information in a database and uses it to guide the progress of the meeting. For example, the purpose might be to "check the progress of Project X and discuss countermeasures for delays," and rules might be set such as "each comment has a time limit of three minutes."

[1152] Starting a meeting

[1153] At the designated start time, the server sends a notification to each participant's device to announce the start of the conference. The device activates its microphone and collects audio data in real time. The collected audio data is then sent to the server in streaming format.

[1154] Speech recognition and text conversion

[1155] The server runs the received voice data through a speech recognition engine (e.g., Google Cloud Speech-to-Text) to convert what is being said into text. This text data is then input into a generative AI model for analysis. The speech recognition engine provides highly accurate speech recognition in real time, instantly converting what is being said into text.

[1156] Generate feedback and questions

[1157] A generative AI model (e.g., OpenAI GPT-4) analyzes the textual utterances and generates appropriate feedback and follow-up questions based on the meeting's objectives and rules. The generated feedback and questions are sent to the device. For example, feedback such as "What is causing the delay? Are there any specific obstacles?" is generated.

[1158] Providing information

[1159] The terminal provides the user with feedback and questions received from the server via voice or text, giving the user guidance on how to proceed with the meeting. Information can be provided either as text displayed on the terminal screen or as voice using a speech synthesis engine.

[1160] Meeting Records

[1161] All statements made during the meeting, as well as any feedback or questions generated, are recorded by the server. These records are stored for later review and analysis. If the user wishes to review the recording after the meeting, the server provides a detailed recording.

[1162] Examples of prompt statements

[1163] Below are some examples of prompts to input to the generative AI model.

[1164] Purpose of the meeting: Check the progress of Project X and discuss measures to deal with delays

[1165] Statement: The project is currently one week behind schedule.

[1166] Questions and feedback: What is causing the delay? Are there any particular obstacles?

[1167] This keeps meetings running smoothly and provides necessary feedback and questions in real time, allowing meeting participants to respond quickly and efficiently.

[1168] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1169] Step 1: Set up a meeting

[1170] The user inputs the purpose of the meeting, prerequisites, rules, and additional conditions through the interface and sends them to the server. The input data includes the purpose of the meeting (e.g., "Check the progress of Project X and discuss countermeasures for delays") and meeting rules (e.g., "Each comment has a time limit of three minutes"). The server receives this information and stores it in a database. Based on this, the data required for subsequent processing is constructed.

[1171] Step 2: Start the meeting

[1172] At the specified start time, the server sends a notification to each participant's device to announce the start of the conference. The input includes the conference setting information and start time. The output is a notification that the conference has started sent to each device. When the device receives the notification, it activates its microphone and begins collecting audio data in real time. This audio data is sent to the server in streaming format.

[1173] Step 3: Speech recognition and text conversion

[1174] The server runs the received voice data through a speech recognition engine (e.g., Google Cloud Speech-to-Text) and converts what is being said into text. The input includes the collected voice data. The output is the converted text data. Specifically, the server processes the voice data in real time and generates highly accurate text data.

[1175] Step 4: Generate feedback and questions

[1176] The server inputs the converted text data into a generative AI model (e.g., OpenAI GPT-4) to generate appropriate feedback and follow-up questions based on the meeting's purpose and rules. The input includes the textual utterances and meeting setting information. The output is generated feedback and questions. The generative AI model analyzes the utterances and generates appropriate utterances. For example, feedback such as "What is causing the delay? Are there any specific obstacles?" is generated.

[1177] Step 5: Provide information

[1178] The server sends the generated feedback and questions to each device. The input includes the generated feedback and questions. The output is provided as a display or voice message on each participant's device. The device displays the received information as text on the screen or uses a speech synthesis engine to convey it to the user audibly. For example, feedback in response to user A's statement is played audibly.

[1179] Step 6: Record the meeting

[1180] The server records all statements made during the meeting, as well as any feedback or questions generated. The input includes statements, feedback, and questions generated during the meeting. The output is stored in a database, which provides the data for users to review after the meeting.

[1181] Examples of prompt statements

[1182] Below is an example of a prompt sentence to be input to the generative AI model in step 4.

[1183] Purpose of the meeting: Check the progress of Project X and discuss measures to deal with delays

[1184] Statement: The project is currently one week behind schedule.

[1185] Questions and feedback: What is causing the delay? Are there any particular obstacles?

[1186] This allows the meeting to proceed more effectively and efficiently.

[1187] (Application example 1)

[1188] 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."

[1189] Improving the efficiency and fairness of meetings and troubleshooting in factories is an important issue. In particular, there is a need for a system that can analyze information in real time and provide prompt and appropriate feedback. Implementing such a system would facilitate smooth communication within the factory, leading to improved productivity and faster problem resolution. However, such systems are currently not fully implemented, which often leads to inefficient meetings and delays in problem resolution in factory operations.

[1190] 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.

[1191] In this invention, the server includes: means for setting the purpose, prerequisites, rules, and additional conditions of the meeting in advance; means for performing real-time speech recognition and converting participants' comments into text; means for analyzing the converted text using a generative AI model and generating appropriate feedback and follow-up questions; means for transmitting the generated feedback and questions to the participants' terminals; means for recording the content of comments made during the meeting and the generative AI feedback; means for supporting factory meetings and troubleshooting meetings in real time; and means for providing industrial speech recognition results and generated feedback to participants using smart glasses or a voice interface. This enables improved efficiency and fairness in factory meetings and troubleshooting.

[1192] A "meeting objective" is a specific goal or objective that a particular meeting aims to achieve.

[1193] "Preconditions" are the basic conditions or situations that must be established first in order for a meeting to proceed.

[1194] "Rules" are instructions and guidelines that participants must follow to ensure the meeting runs smoothly.

[1195] "Conditions" means any additional conditions or restrictions associated with a conference.

[1196] "Speech recognition" is a technology that analyzes voice data collected using a microphone and converts it into text information.

[1197] "Means for converting speech to text" refers to a method or device for converting speech from participants into text in real time using speech recognition.

[1198] A "generative AI model" is an artificial intelligence model that is trained to analyze input data and perform specific tasks automatically.

[1199] "Feedback" refers to responses or additional information provided by a generative AI model based on the results of its analysis.

[1200] A "terminal" is a device used by a participant to exchange data with the server.

[1201] "Means of recording" refers to methods or devices for saving what is said during a meeting and feedback from generative AI.

[1202] A "factory meeting" is a discussion or meeting with a specific purpose that takes place on the production floor or within a factory.

[1203] A "troubleshooting meeting" is a meeting held to resolve problems that arise in a system or process.

[1204] "Smart glasses" are glasses-type information and communication devices that provide visual information.

[1205] A "voice interface" is a technology or device that allows a user to communicate with a system through speech.

[1206] This invention is a system for supporting meetings and troubleshooting meetings in factories, and aims to improve the efficiency and fairness of meetings. A specific method for realizing this system will be described below.

[1207] The server is responsible for the main processing and plays a central role in the progress of the conference. This server houses the speech recognition engine, generative AI model, and database. Meanwhile, the terminals are devices used by participants to communicate with the server. Terminals include smart glasses and voice interfaces.

[1208] First, the user (organizer) inputs the purpose, prerequisites, rules, and additional conditions of the meeting through the interface and sends them to the server. The server stores this information in a database and uses it to progress the meeting.

[1209] When a meeting starts, the server sends a notification to the participants' devices to announce the start of the meeting. The devices turn on their microphones and collect audio data in real time. This audio data is sent to the server. The server then runs the received audio data through a speech recognition engine and converts what is being said into text. The SpeechRecognition library is used for speech recognition, and Google's speech recognition API is used to convert what is being said into text.

[1210] The textual comments are input into a generative AI model for analysis. The generative AI model uses Hugging Face's Transformers (pipeline functions) to generate appropriate feedback and follow-up questions based on the meeting's objectives and rules. The generated feedback and questions are sent to the device, which then provides them to the user via the smart glasses' display or voice interface. This allows the user to obtain guidance on how the meeting should proceed.

[1211] All statements made during the meeting, as well as any feedback or questions generated, are recorded by the server, and these recordings are stored for later review and analysis.

[1212] As a concrete example, consider a meeting to discuss the cause of a line stoppage and measures to prevent recurrence. The organizer sets the purpose of the meeting as "to investigate the cause of the line stoppage and consider measures to prevent recurrence." At the start of the meeting, User A says, "The line suddenly stopped. The cause is currently unknown." This speech is sent to the server via smart glasses and converted into text. The generative AI model analyzes this text and generates feedback such as "What is the cause?" and provides it to User A. This series of steps allows the meeting to proceed smoothly and enables efficient problem solving.

[1213] An example of a prompt sentence for the statement "The line has stopped suddenly. The cause is currently unknown." would be:

[1214] "What is the cause?"

[1215] This system contributes to improving the efficiency and fairness of meetings and troubleshooting within the factory.

[1216] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1217] Step 1:

[1218] The server receives information about the purpose, prerequisites, rules, and additional conditions of the meeting entered by the user (organizer) through the interface and stores it in a database. The entered data is the detailed information necessary for the progress of the meeting, and this will be the basis for the smooth running of the meeting in later steps.

[1219] Step 2:

[1220] When a conference starts, the server sends a notification to the participants' devices to announce the start of the conference. When the device receives the notification, it activates the microphone and starts collecting audio data. The collected audio data becomes the material for analysis in later processes.

[1221] Step 3:

[1222] The device sends the collected voice data to the server. The server passes the received voice data to a voice recognition engine in real time and converts what is being said into text. The process of converting this voice data into text data uses the SpeechRecognition library and Google's voice recognition API. The input is voice data and the output is text data.

[1223] Step 4:

[1224] The server inputs the textualized utterances into a generative AI model for analysis. The generative AI model uses Hugging Face's Transformers (pipeline function). This analysis generates appropriate feedback and follow-up questions based on the utterance content. Here, the input is text data, and the output is text data of feedback or questions.

[1225] Step 5:

[1226] The generated feedback and questions are sent from the server to the device. The device then provides the feedback and questions to the user in the form of voice or text. For example, it displays the feedback and questions as text on the smart glasses display or reads them out loud using a voice interface. The input is the text data of the feedback and questions, and the output is a notification to the user.

[1227] Step 6:

[1228] The server records all statements made during the meeting, as well as any feedback or questions generated, which are then stored in a database for later review and analysis. The input is the text data of statements made during the meeting, as well as any feedback or questions, and the output is the recorded data.

[1229] Step 7:

[1230] After the meeting is over, the server provides a function for later review of the recorded meeting contents. The user (host) can view this recording to confirm and analyze the contents of the meeting. The input is the recorded data stored in the database, and the output is data in a format that can be viewed by the user.

[1231] 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.

[1232] This invention improves the efficiency and fairness of meetings by combining an emotion engine with a meeting progress system using a generative AI model, and further recognizes the emotions of meeting participants and provides appropriate feedback. This system includes means for setting the purpose, prerequisites, rules, and conditions of the meeting in advance, means for performing real-time speech recognition and converting comments into text, means for analyzing the content of comments and the emotion recognition results using a generative AI model and generating feedback and follow-up questions, means for sending the generated information to the participants' devices, means for recording the content of comments made during the meeting and the results of the generative AI and emotion engine, and means for reviewing them.

[1233] System configuration

[1234] The server is responsible for the main processing and serves as the center of the conference. The server houses a speech recognition engine, generative AI model, emotion engine, and database. The terminals are devices used by participants to communicate with the server. Users join the conference and exchange data with the server through their terminals.

[1235] Explanation of program processing

[1236] 1. Set up a meeting:

[1237] The user (organizer) inputs the purpose, prerequisites, rules, and additional conditions of the meeting through the interface and sends them to the server, which stores this information in a database and uses it to progress the meeting.

[1238] 2. Start the meeting:

[1239] When the conference starts, the server sends a notification to the participants' terminals to announce the start of the conference. The terminals receive the notification and prepare to collect voice data.

[1240] 3. Speech Recognition and Text Transcription:

[1241] When the conference starts, the device activates the microphone and collects participants' speech as voice data. The server converts the received voice data into text data using a voice recognition engine.

[1242] 4. Emotion recognition:

[1243] The collected voice data is converted into text and simultaneously analyzed by an emotion engine to recognize the participants' emotional state. The emotion recognition results are then input into a generative AI model.

[1244] 5. Generate feedback and questions:

[1245] The generative AI model analyzes the text data and emotion recognition results, and generates appropriate feedback and follow-up questions based on the purpose and rules of the meeting. The generated feedback and questions are sent from the server to the device and provided to the user in voice or text format.

[1246] 6. Provision of Information:

[1247] The device provides the user with feedback, questions, and emotion recognition results received from the server, allowing the user to understand the guidelines for the progress of the meeting and the emotional situation.

[1248] 7. Records of meetings:

[1249] All statements made during the meeting, the feedback generated, questions asked, and emotion recognition results are recorded by the server, and the recordings are time-stamped to track the order and duration of statements.

[1250] 8. Reviews and Feedback:

[1251] After the meeting, the server organizes all recorded data and automatically generates meeting minutes, which include emotion recognition results and are saved for user access. Feedback based on the emotion recognition results is also provided, and an overall evaluation of the meeting and areas for improvement are identified.

[1252] Specific examples

[1253] 1. Pre-settings:

[1254] The user enters the purpose of the meeting, such as "Check the progress of project X and discuss countermeasures for delays," into the interface and sends it to the server, which then stores this information in a database.

[1255] 2. Meeting begins:

[1256] The server sends a notification to each participant at the start time to announce the start of the conference, and the device activates the microphone and prepares to collect audio.

[1257] 3. Speech, transcription and feedback:

[1258] User A says, "The project is currently one week behind schedule." The device sends this speech to the server, which converts it into text using a speech recognition engine and recognizes the emotion using an emotion engine. The generative AI model analyzes the speech and generates feedback such as, "What is causing the delay? Are there any specific obstacles?" The device then provides this feedback to User A. At the same time, the emotion engine detects the tension and provides additional feedback such as, "Let's calmly analyze the situation."

[1259] The system helps meetings run smoothly and produce rational outcomes by organizing what is being said and providing feedback that takes into account emotional states.

[1260] The processing flow will be explained below.

[1261] Step 1:

[1262] The user (organizer) inputs the purpose, prerequisites, rules, and additional conditions of the meeting into the interface and sends them to the server, which stores this information in a database.

[1263] Step 2:

[1264] The server sends a notification to each participant at the start time of the conference, announcing the start of the conference. The terminal receives the notification and prepares to collect voice data.

[1265] Step 3:

[1266] When the conference starts, the device activates the microphone and collects participants' speech as audio data, which is then sent to the server in real time.

[1267] Step 4:

[1268] The server converts the received voice data into text data using a speech recognition engine, which is then input into a generative AI model.

[1269] Step 5:

[1270] The collected voice data is converted into text and simultaneously analyzed by an emotion engine to recognize the participants' emotional state. The emotion recognition results are then input into a generative AI model.

[1271] Step 6:

[1272] The generative AI model analyzes text data and emotion recognition results to generate appropriate feedback and follow-up questions based on the meeting's objectives and rules.

[1273] Step 7:

[1274] The generated feedback and questions are sent from the server to the device, which then provides the received feedback and questions to the user in voice or text format.

[1275] Step 8:

[1276] The user makes further statements and answers based on the feedback and questions from the generative AI model, and the device again transmits these new statements as voice data to the server.

[1277] Step 9:

[1278] The server then converts the newly received voice data into text using the speech recognition engine and analyzes it using the generative AI model. At the same time, the emotion engine generates new emotion recognition results. This process is repeated throughout the conference.

[1279] Step 10:

[1280] During the meeting, all statements, generated feedback, questions, and emotional states recognized by the emotion engine are recorded by the server, and the recordings are time-stamped, allowing for tracking of the order and time of statements.

[1281] Step 11:

[1282] After the meeting, the server organizes all recorded data and automatically generates meeting minutes, which are stored for user access. Feedback based on emotion recognition results is also provided, and an overall evaluation of the meeting and suggestions for improvement are identified.

[1283] Specific examples

[1284] 1. Pre-settings:

[1285] The user enters the purpose of the meeting, such as "Check the progress of project X and discuss countermeasures for delays," into the interface and sends it to the server, which then stores this information in a database.

[1286] 2. Meeting begins:

[1287] The server sends a notification to each participant at the start time to announce the start of the conference, and the device activates the microphone and prepares to collect audio.

[1288] 3. Speech and text conversion, emotion recognition, and feedback:

[1289] User A says, "The project is currently one week behind schedule." The device sends this speech to the server, which converts it into text using a speech recognition engine and recognizes the emotion using an emotion engine. The generative AI model analyzes it and generates feedback such as, "What is causing the delay? Are there any specific obstacles?" At the same time, the emotion engine detects the tension and generates additional feedback such as, "Let's calmly analyze the situation," which the device provides to User A.

[1290] The system helps meetings run smoothly and produce rational outcomes by organizing what is being said and providing feedback that takes into account emotional states.

[1291] Example 2

[1292] 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."

[1293] Conventional meeting systems rarely provide appropriate feedback on the progress of meetings or participants' comments, hindering effective discussion and decision-making. Furthermore, feedback that does not reflect participants' emotional states can lead to inefficient meetings and unfair treatment of some participants. Furthermore, the post-meeting review process is cumbersome, and organizing and evaluating records takes time.

[1294] 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.

[1295] In this invention, the server includes: means for setting the purpose, prerequisites, rules, and additional conditions of the meeting in advance; means for recognizing speech in real time and converting participants' comments into text; means for recognizing the emotional state of the participants from the text comments using emotion analysis means; means for analyzing the text comments and the emotion recognition results using a generative artificial intelligence model to generate appropriate feedback and follow-up questions; means for transmitting the generated feedback and questions to the participants' communication devices; and means for recording the content of comments made during the meeting and the feedback and emotion recognition results of the generative artificial intelligence model. This makes the meeting more efficient, and fair and effective communication is achieved by providing feedback that takes into account the emotional state of each participant. It also facilitates review after the meeting, allowing for quick minutes creation and review of the meeting.

[1296] "Means for setting the purpose, prerequisites, rules, and additional conditions of a meeting in advance" refers to a function that allows you to input and save the purpose, rules, etc. of a meeting in advance in order to determine the progress of the meeting and the direction of the discussion, and to ensure that the meeting is run based on specific conditions and rules.

[1297] "Means for recognizing speech in real time and converting participants' comments into text" refers to a function that analyzes speech made by participants during a meeting in real time and instantly converts the speech into text using speech recognition technology.

[1298] "Means for recognizing the emotional state of participants from textualized statements using emotion analysis means" is a function for analyzing and confirming the emotional state of speakers using emotion analysis technology based on text data generated by voice recognition.

[1299] "Means for analyzing textual statements and emotion recognition results using a generative artificial intelligence model, and generating appropriate feedback and follow-up questions" refers to a function that analyzes text data and emotion recognition results using a generative artificial intelligence model (e.g., a language model), and automatically generates highly relevant feedback and questions based on the analysis results.

[1300] "Means for sending generated feedback and questions to participants' communication devices" refers to a function that sends feedback and questions generated by the generative artificial intelligence model to the communication devices used by participants (e.g., smartphones or personal computers).

[1301] "Means for recording statements made during a meeting, feedback from a generative AI model, and emotion recognition results" refers to a function that records all statements made during a meeting, generated feedback and questions, and emotion recognition results with timestamps, and saves them for later access.

[1302] This invention combines a generative AI model-based conference proceeding system with an emotion analysis engine to improve the efficiency and fairness of conferences, and also recognizes the emotions of conference participants and provides appropriate feedback. The system includes the following main hardware and software components:

[1303] Hardware and software used

[1304] 1. Server

[1305] The server is responsible for the main processing and serves as the center of the conference. This server houses a speech recognition engine, generative AI model, emotion analysis engine, and database. The speech recognition engine uses the Google Cloud Speech-to-Text API, and the emotion analysis engine uses the Microsoft Azure Emotion API.

[1306] 2. Terminal

[1307] The terminal is a device used by participants to communicate with the server. Terminals can be smartphones, tablets, PCs, etc. Terminals collect voice data, receive feedback, and display it.

[1308] 3. Users

[1309] Users participate in the conference and exchange data with the server through their devices, as well as set up the conference and check feedback.

[1310] Specific processing of the system

[1311] The operation of the system proceeds as follows.

[1312] 1. Set up a meeting:

[1313] The user (organizer) inputs the purpose of the meeting ("Check the progress of Project X"), prerequisites, rules ("Keep comments brief"), and additional conditions ("Use diagrams and tables as needed") through the interface. Once input is complete, the settings are sent to the server. The server stores the received settings in a database and uses them to progress the meeting.

[1314] 2. Start the meeting:

[1315] When the meeting start time arrives, the server sends a push notification to each participant's device. The notification contains a message informing them that the meeting is about to begin. The device receives this notification and prepares to turn on its microphone and speaker.

[1316] 3. Speech Recognition and Text Transcription:

[1317] The user's speech is collected as voice data through the device's microphone. For example, if the user says, "Project X is progressing smoothly," the voice data is sent to the server in real time. The server then converts the received voice data into text data using the Google Cloud Speech-to-Text API.

[1318] 4. Emotion recognition:

[1319] The server uses an emotion analysis engine to analyze the voice data and the user's emotions. For example, if the user's speech is analyzed to indicate "anxiety," this result is recorded along with the text data. The emotion recognition results are provided to a generative AI model, forming the basis for future feedback generation.

[1320] 5. Generate feedback and questions:

[1321] The generative AI model analyzes the text data stored on the server and the emotion recognition results. For example, if a user says, "Project X is behind schedule," the model generates feedback such as, "What is the cause of the delay?" or "Let's think of specific countermeasures." The generated feedback and questions are sent from the server to the device and provided to the participants.

[1322] 6. Provision of Information:

[1323] The device then provides the received feedback, questions, and emotion recognition results to the user. For example, feedback such as "Analyze the situation calmly" is displayed to the user as voice or text. This allows the user to understand the progress of the meeting and the emotional situation.

[1324] 7. Records of meetings:

[1325] The server records all statements made during the meeting, along with any feedback generated, questions asked, and emotion recognition results, with timestamps, allowing for tracking of the order and duration of statements. This data is stored in a database for later review.

[1326] 8. Reviews and Feedback:

[1327] After the meeting, the server organizes all recorded data and automatically generates meeting minutes, which include the content of comments, emotion recognition results, and feedback. Users can access the minutes and review the entire meeting. Based on the emotion recognition results, the server also provides suggestions for improvements and guidelines for future meetings.

[1328] Examples of prompt statements

[1329] Please report on the progress of the project.

[1330] Please enter the purpose of the meeting.

[1331] "Convert what is being said into text and analyze the emotional state."

[1332] "Generate appropriate feedback and questions based on your analysis."

[1333] This system is expected to help meetings be run efficiently and fairly, and to lead to more constructive discussions by providing feedback that reflects the emotional state of participants.

[1334] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1335] Step 1:

[1336] Meeting Setup

[1337] The user (organizer) enters the purpose of the meeting, "Check the progress of Project X," the prerequisites, the rule, "Keep comments brief," and the additional condition, "Use diagrams and tables as necessary," into the interface. Once the input is complete, the user clicks the "Set" button to send the settings to the server. The server stores the received settings data in a database and makes them available for use in the progress of the meeting. As a specific example, the contents stored in the database include the "start date and time," "list of participants," and "meeting agenda."

[1338] Step 2:

[1339] Starting a meeting

[1340] When the meeting starts, the server sends a push notification to the participants' devices. The notification includes the message "The meeting has started. Please prepare to speak." This is transmitted to the device as input, and the device prepares the microphone and speaker, making it ready to collect audio data.

[1341] Step 3:

[1342] Speech recognition and text conversion

[1343] The meeting officially begins, and a user speaks. The device's microphone collects audio data, such as "Project X is progressing well," and sends it to the server. The server converts the received audio data into text data using the Google Cloud Speech-to-Text API. In this case, the input is audio data, and the output is text data: "Project X is progressing well."

[1344] Step 4:

[1345] emotion recognition

[1346] The server inputs the text data along with the voice data into an emotion analysis engine (such as Microsoft Azure's Emotion API) to recognize the emotional state. For example, if the statement "Project X is progressing smoothly" is analyzed as indicating "joy," the emotion recognition engine will return the result "joy." The input is text data and voice data, and the output is the emotion recognition result of "joy."

[1347] Step 5:

[1348] Generate feedback and questions

[1349] The server uses a generative artificial intelligence model (e.g., OpenAI's GPT-3) to analyze text data and emotion recognition results. For example, if someone says, "Project X is behind schedule," the model generates a question such as, "What is the cause of the delay?" or feedback such as, "Let's think of specific countermeasures." The input is the text data and emotion recognition results, and the output is the generated feedback or question.

[1350] Step 6:

[1351] Providing information

[1352] The generated feedback and questions are sent from the server to the device. The device receives them and displays them to the user as voice or text. For example, the feedback "Let's calmly analyze the situation" is provided to the user. The input is the generated feedback and questions, and the output is a notification to the user as voice or text.

[1353] Step 7:

[1354] Meeting Records

[1355] The server records all statements made during the meeting, generated feedback, questions, and emotion recognition results with timestamps. This allows the order and time of statements to be tracked. The recorded data is saved in a database and can be referenced later. The input is all data from the meeting, and the output is the recorded data with timestamps.

[1356] Step 8:

[1357] Reviews and Feedback

[1358] After the meeting, the server organizes all recorded data and creates automatically generated minutes. These minutes include the content of the remarks, emotion recognition results, and feedback. Users can access these minutes and review the entire meeting. In addition, the emotion recognition results provide improvements and guidelines for future meetings. The input is the recorded data, and the output is the automatically generated minutes and feedback.

[1359] (Application example 2)

[1360] 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."

[1361] Traditional security meetings and briefings have had issues with the content of each person's comments being subjective, and limited feedback tailored to the speaker's emotions and the progress of the meeting. Furthermore, meeting recordings are insufficient, making subsequent review and analysis difficult. These limitations compromise the efficiency and fairness of security meetings and put important information at risk of being overlooked.

[1362] The specific processing by the specific 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 setting the purpose, prerequisites, rules, and additional conditions of a meeting or briefing in advance; means for performing real-time speech recognition and converting participants' or staff's comments into text; means for analyzing the converted text using a generative AI model and generating appropriate feedback and follow-up questions; means for transmitting the generated feedback and questions to the participants' devices; means for analyzing collected voice data using an emotion engine and recognizing emotional states; means for the generative AI model to generate feedback and questions based on the emotion recognition results; and means for recording the content of comments made during the meeting and the generative AI feedback. This allows for objective analysis of participants' comments during the security meeting and provides feedback that takes their emotional states into account. Furthermore, detailed records of the meeting content and automatically generated minutes enable comprehensive reviews, allowing for efficient understanding and improvement of the security situation.

[1363] "Methods for setting the purpose, prerequisites, rules, and additional conditions of a meeting or briefing in advance" refers to a method by which participants share the information and rules necessary for the progress of a meeting or briefing and decide on them in advance to support smooth progress.

[1364] "Means for real-time speech recognition and conversion of participants' or representatives' speech into text" refers to technology that recognizes words spoken during a meeting in real time and converts them into digital text.

[1365] "Means for analyzing textual statements using a generative AI model and generating appropriate feedback and follow-up questions" refers to a system that uses a generative artificial intelligence model to analyze text data and automatically generate feedback and questions.

[1366] The "means for transmitting the generated feedback and questions to the participant's terminal" is a method for transmitting automatically generated feedback and questions to the device used by the participant.

[1367] "Means for analyzing collected voice data using an emotion engine and recognizing emotional states" refers to equipment that uses voice data collected by sensors or other devices to analyze and sense the speaker's emotions using an emotion analysis engine.

[1368] "Means for a generative AI model to generate feedback and questions based on emotion recognition results" refers to a system that uses emotion recognition results obtained from an emotion analysis engine to generate appropriate feedback and questions using a generative AI model.

[1369] "Means for recording statements made during meetings and feedback from generative AI" refers to technology that saves statements made during meetings and feedback output by generative AI models so that they can be reviewed later.

[1370] "Means for later reviewing recorded meeting content and automatically generating minutes that include emotion recognition results" refers to a system that automatically creates and enables review of meeting minutes based on the content recorded during the meeting and the results of emotion analysis.

[1371] The "means for providing participants with speech recognition results and emotion recognition results not only in text but also in audio" is a technology for conveying speech recognition and emotion recognition results to participants not only in text format but also as audio.

[1372] This invention provides a system for improving the efficiency and fairness of security conferences and briefings. The system includes a server, a terminal (e.g., smart glasses), and a user called a security officer. Specific embodiments for implementing this invention will be described below.

[1373] System Configuration

[1374] The server is the main processing center and contains the following modules:

[1375] Speech recognition engine (e.g. Google Cloud Speech-to-Text API)

[1376] Generative AI models (e.g., OpenAI GPT-4)

[1377] Emotion engine (e.g. Amazon Lex or Affectiva SDK)

[1378] Database (e.g. Amazon RDS)

[1379] Terminals are devices used by security personnel and include smart glasses (e.g., Google Glass, Vuzix Blade).

[1380] Data processing flow

[1381] 1. Setting up meetings and briefings

[1382] The user (the organizer among the security personnel) inputs the purpose, prerequisites, rules, and additional conditions of the meeting through the interface of the smart glasses and sends them to the server, which stores this information in a database and uses it to guide the progress of the meeting.

[1383] 2. Real-time speech recognition and emotion analysis

[1384] When a meeting or briefing begins, the device activates its microphone and collects participants' speech as voice data. The server converts the received voice data into text data using a voice recognition engine, and simultaneously analyzes the participants' emotional states using an emotion engine.

[1385] 3. Generate feedback and questions

[1386] The textual comments and emotion recognition results are analyzed using a generative AI model to generate appropriate feedback and follow-up questions as the meeting progresses. The generated feedback and questions are sent from the server to the device and provided to the user in voice or text format.

[1387] 4. Recording and reviewing during the meeting

[1388] All statements made during the meeting and feedback output by the generative AI model are recorded, including emotion recognition results, with a timestamp. After the meeting ends, the server organizes this data and automatically generates minutes. The minutes, which also include emotion recognition results, are used for review and to identify areas for improvement.

[1389] Examples of concrete examples and prompts

[1390] For example, if a security officer says "There were no abnormalities at the site today" during a security meeting, this statement is converted into text by a speech recognition engine, and the emotion engine recognizes "sense of security." The generative AI model analyzes this information and generates feedback such as "What part of the site is the situation? Please tell us the details." This feedback is displayed on the officer's smart glasses.

[1391] Example prompt sentence:

[1392] Input: "Nothing unusual at the site today."

[1393] Prompt: Use this statement to generate questions that ask for more information.

[1394] Example: "What part of the site is the situation? Please tell me the details."

[1395] This allows for objective analysis of participants' comments during security meetings and provides feedback that takes into account their emotional state. It also enables comprehensive reviews, allowing for efficient understanding and improvement of the security situation.

[1396] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1397] Step 1:

[1398] The user inputs the purpose, prerequisites, rules, and additional conditions of the meeting or briefing through the terminal interface and sends them to the server. The server stores this information in a database. The input is the setting information from the user, and the output is saved in the database. In this step, the information necessary to proceed with the meeting is prepared in advance.

[1399] Step 2:

[1400] At the start of a meeting or briefing, the server sends a start notification to the device. The device receives the notification and activates the microphone to prepare to collect audio data. The input is the notification from the server, and the output is the activation of the microphone. In this step, the start of the meeting is notified to the entire system, and audio recording is prepared.

[1401] Step 3:

[1402] The device sends the voice data collected during the meeting to the server. The server inputs the received voice data into a voice recognition engine and converts it into text data. The input is voice data and the output is text data. In this step, the participants' remarks are converted into text.

[1403] Step 4:

[1404] The server inputs the textual utterances into the emotion engine and analyzes the emotional state. The input is text data, and the output is emotion recognition results. In this step, the speaker's emotional state is understood.

[1405] Step 5:

[1406] The server inputs text data and emotion recognition results into the generative AI model to generate appropriate feedback and follow-up questions. The input is text data and emotion recognition results, and the output is feedback and questions. In this step, the generative AI model automatically generates responses that are appropriate for the progress of the meeting.

[1407] Step 6:

[1408] The server sends the generated feedback and questions to the terminal and provides them to the user. The terminal displays the feedback and questions as voice or text. The input is the feedback and questions, and the output is what is presented to the user. In this step, the user receives the feedback and questions in real time.

[1409] Step 7:

[1410] The server records all statements made during the meeting, the generated feedback, and the emotion recognition results. The input is the statements, feedback, and emotion recognition results, and the output is the recorded data. In this step, all meeting data is saved with a timestamp.

[1411] Step 8:

[1412] After the meeting, the server automatically generates minutes based on the recorded data and creates a report that includes the emotion recognition results. The input is the recorded data, and the output is the minutes and report. In this step, the meeting is automatically summarized, making it easier to review later.

[1413] 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.

[1414] 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.

[1415] 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.

[1416] 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.

[1417] 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.

[1418] 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.

[1419] 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).

[1420] 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.

[1421] 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."

[1422] 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.

[1423] 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).

[1424] 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.

[1425] 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.

[1426] 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.

[1427] 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.

[1428] 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.

[1429] 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.

[1430] 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.

[1431] 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.

[1432] 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.

[1433] 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.

[1434] The following is further disclosed regarding the above embodiment.

[1435] (Claim 1)

[1436] A means to set the purpose, prerequisites, rules, and conditions of the meeting in advance;

[1437] A means of real-time speech recognition and conversion of participants' speech into text;

[1438] A means to analyze the textual statements using a generative AI model and generate appropriate feedback and follow-up questions,

[1439] a means for transmitting the generated feedback and questions to the participant's device;

[1440] A means of recording what is said during the meeting and the feedback from the generative AI,

[1441] A system including:

[1442] (Claim 2)

[1443] 10. The system of claim 1, further comprising means for later reviewing the recorded meeting content.

[1444] (Claim 3)

[1445] 10. The system of claim 1, further comprising means for providing speech recognition results to the participant in audio as well as text.

[1446] "Example 1"

[1447] (Claim 1)

[1448] A means to set the purpose, prerequisites, rules, and conditions of the meeting in advance;

[1449] A means of real-time speech recognition and conversion of participants' speech into text;

[1450] A means to analyze the textual statements using a generative AI model and generate appropriate feedback and follow-up questions,

[1451] a means for transmitting the generated feedback and questions to the participant's device;

[1452] A means of recording what is said during the meeting and the feedback from the generative AI,

[1453] A means for sending a notification to the participant's device at the start of the meeting to start collecting voice data;

[1454] means for transmitting audio data to a server in streaming format;

[1455] A means for inputting prompts into the generative AI model;

[1456] A means to display or provide audio of what is being said, any feedback generated, or any questions;

[1457] A system including:

[1458] (Claim 2)

[1459] 10. The system of claim 1, further comprising means for later reviewing the recorded meeting content.

[1460] (Claim 3)

[1461] 10. The system of claim 1, further comprising means for providing speech recognition results to the participant in audio as well as text.

[1462] "Application Example 1"

[1463] (Claim 1)

[1464] A means to set the purpose, prerequisites, rules, and conditions of the meeting in advance;

[1465] A means of real-time speech recognition and conversion of participants' speech into text;

[1466] A means to analyze the textual statements using a generative AI model and generate appropriate feedback and follow-up questions,

[1467] a means for transmitting the generated feedback and questions to the participant's device;

[1468] A means of recording what is said during the meeting and the feedback from the generative AI,

[1469] A means to support real-time factory meetings and troubleshooting sessions;

[1470] A means for providing industrial speech recognition results and generated feedback to participants using smart glasses or a voice interface;

[1471] A system including:

[1472] (Claim 2)

[1473] 10. The system of claim 1, further comprising means for later reviewing the recorded meeting content.

[1474] (Claim 3)

[1475] 10. The system of claim 1, further comprising means for providing speech recognition results to the participant in audio as well as text.

[1476] "Example 2: Combining Emotion Engines"

[1477] (Claim 1)

[1478] A means to set the purpose, prerequisites, rules, and conditions of the meeting in advance;

[1479] A means of real-time speech recognition and conversion of participants' speech into text;

[1480] A means for recognizing the emotional state of participants by analyzing the textual statements;

[1481] A means for analyzing the textual utterances and emotion recognition results using a generative AI model to generate appropriate feedback and follow-up questions;

[1482] a means for transmitting the generated feedback and questions to the participant's communication device;

[1483] A means for recording the content of statements made during the meeting, feedback from the generative AI model, and emotion recognition results;

[1484] A system including:

[1485] (Claim 2)

[1486] 10. The system of claim 1, further comprising means for later reviewing the recorded meeting content.

[1487] (Claim 3)

[1488] 10. The system of claim 1, further comprising means for providing speech recognition results to the participant in audio as well as text.

[1489] "Application example 2 when combining emotion engines"

[1490] (Claim 1)

[1491] A means to set the purpose, prerequisites, rules, and conditions of meetings and briefings in advance;

[1492] A means of real-time speech recognition and conversion of participant or representative speech into text;

[1493] A means to analyze the textual statements using a generative AI model and generate appropriate feedback and follow-up questions,

[1494] a means for transmitting the generated feedback and questions to the participant's device;

[1495] A means for analyzing the collected voice data with an emotion engine and recognizing the emotional state;

[1496] A means for the generative AI model to generate feedback and questions based on emotion recognition results, and

[1497] A means of recording what is said during the meeting and the feedback from the generative AI,

[1498] A system including:

[1499] (Claim 2)

[1500] 10. The system of claim 1, further comprising means for later reviewing the recorded meeting content and automatically generating minutes that also include emotion recognition results.

[1501] (Claim 3)

[1502] 10. The system of claim 1, further comprising means for providing speech recognition results and emotion recognition results to the participant in audio as well as text. [Explanation of symbols]

[1503] 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. A means to set the purpose, prerequisites, rules, and conditions of the meeting in advance; A means of real-time speech recognition and conversion of participants' speech into text; A means to analyze the textual statements using a generative AI model and generate appropriate feedback and follow-up questions, a means for transmitting the generated feedback and questions to the participant's device; A means of recording what is said during the meeting and the feedback from the generative AI, A system including:

2. 10. The system of claim 1, further comprising means for later reviewing the recorded meeting content.

3. The system of claim 1 further comprising means for providing speech recognition results to the participant in audio as well as text.

Images