system

Abstract

We provide the system. [Solution] Means of obtaining meeting schedules, A means of generating agenda items by analyzing past meeting records, A method for analyzing statements made during a meeting and extracting important keywords, A means of presenting relevant data based on the extracted information, A system that includes means for generating summaries and action items after a meeting.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] The facilitation of meetings plays an important role in many operations, but it takes a considerable amount of time and effort to prepare for, conduct, and follow up on them. In particular, when there are a large number of participants and a vast amount of related information, it is difficult to efficiently operate a meeting. Also, decision - making based on objective information not influenced by subjective opinions is required. In such a situation, there is a need to provide technical means to smooth the operation of meetings and reduce the burden on participants.

Means for Solving the Problems

[0005] This invention is a system for efficiently conducting meetings, and includes means for obtaining meeting schedules, means for analyzing past meeting records to generate agenda drafts, means for analyzing statements made during meetings and extracting important keywords, means for presenting relevant data based on the extracted information, and means for generating summaries and action items after meetings. This automates the entire process from meeting preparation to post-meeting follow-up, and supports decision-making based on objective data that is not influenced by subjectivity. Furthermore, by including functions for setting meeting objectives and optimizing the agenda based on them, and functions for sending deadline-based reminders to those responsible for action items, it enables more organized and effective meeting management.

[0006] "Method for obtaining meeting schedules" refers to a function that automatically retrieves information about the date and expected participants of a specific meeting from the calendar data of a company or organization.

[0007] "A method for generating agenda proposals by analyzing past meeting records" refers to an algorithm that analyzes saved meeting history data and automatically suggests agenda items and topics suitable for the next meeting.

[0008] "Methods for analyzing speech during meetings and extracting important keywords" refers to technologies that process real-time audio or text data from meetings to identify noteworthy words, phrases, and topics within the conversation.

[0009] "Means of presenting relevant data based on extracted information" refers to a system that automatically searches for additional data and materials related to keywords and topics collected during the meeting and provides them to participants.

[0010] "Methods for generating summaries and action items after a meeting" refers to a function that automatically organizes the content of a meeting, lists key conclusions and future actions, and ensures that participants have a clear understanding of the next steps. [Brief explanation of the drawing]

[0011] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] An example of an embodiment of the system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0013] First, the terms used in the following description will be explained.

[0014] In the following embodiments, a labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0015] In the following embodiments, a labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, a labeled storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0017] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0018] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] As shown in Figure 1, the 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.

[0022] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0023] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0024] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0025] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0026] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0029] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0030] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0031] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0032] This invention is a system for efficiently conducting and managing corporate meetings, and the software program for implementing this system runs on a server and terminals.

[0033] The server first extracts meeting schedules from the company's internal scheduling system and collects participant information. This prepares the server to provide relevant information to stakeholders before the meeting begins. Next, it analyzes records of similar past meetings and uses that data to generate potential topics for discussion in the new meeting.

[0034] Once preparations are complete, the user (the meeting organizer) reviews the draft agenda generated by the server and makes any necessary revisions or additions. As a result, an optimized agenda is established, and specific goals for the meeting are set.

[0035] During the meeting, the terminal uses speech recognition technology to convert participants' speech into text in real time and sends that data to the server. Based on this information, the server extracts important keywords and immediately analyzes and provides relevant industry data and past case studies. This enables meeting participants to make more informed decisions.

[0036] After the meeting ends, the server organizes the collected data and generates a summary of the content and a list of action items. This information is distributed to relevant parties via terminals, and those responsible for each action item receive a time-limited reminder. For example, in a project progress meeting, specific actions such as reviewing sales targets for the next quarter and risk mitigation measures are listed, enabling efficient follow-up.

[0037] This system automates and streamlines the entire process, from meeting preparation to post-meeting follow-up, supporting meeting management based on objective data.

[0038] The following describes the processing flow.

[0039] Step 1:

[0040] The server retrieves meeting schedules from the company's scheduling management system and collects participant lists. It also extracts relevant past meeting data from the database.

[0041] Step 2:

[0042] The server analyzes past meeting data to extract topics and issues that should be discussed in the next meeting, and generates a draft agenda. This forms the basis for proposing it to the user.

[0043] Step 3:

[0044] Users review the proposed agenda, adjust the meeting objectives and specific agenda as needed, and provide feedback to the server. The server then incorporates this information to finalize the agenda.

[0045] Step 4:

[0046] The terminal converts the audio from the meeting into text data in real time and sends it to the server. This process allows for the recording of what is said during the meeting.

[0047] Step 5:

[0048] The server analyzes the received text data and extracts key keywords. Furthermore, it searches for relevant external data and industry case studies and presents them to the participants.

[0049] Step 6:

[0050] After the meeting ends, the server generates a summary and action items based on the data collected during the meeting. This helps organize the meeting's results and clarify the next steps.

[0051] Step 7:

[0052] The device distributes the generated summary and action items to the assigned person. It also sends time-limited reminders for the action items to prompt the person to complete the task.

[0053] (Example 1)

[0054] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0055] In today's business environment, meetings are crucial for important decisions, yet they are often inefficient and unproductive. This is due to insufficient preparation, poor information management during meetings, and delayed follow-up. As a result, valuable participant time is wasted, and the quality of decision-making suffers. Therefore, it is essential to streamline the meeting preparation, execution, and follow-up processes throughout the entire system, supporting participants in making meaningful contributions.

[0056] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0057] In this invention, the server includes means for extracting scheduled information, means for analyzing past information to generate agenda candidates, and means for converting audio information into text in real time. This streamlines the process from meeting preparation to progress and follow-up, enabling participants to make more informed decisions more quickly.

[0058] "Methods for extracting schedule information" refers to a function that retrieves meeting and related event schedule information from a company's internal data management system and processes it to make the necessary schedule data available within the system.

[0059] "Methods for generating agenda candidates by analyzing past information" refers to a function that analyzes records and data from similar meetings held in the past to suggest topics and themes that should be discussed at the next meeting.

[0060] "A means of converting audio information to text in real time" refers to a function that instantly converts participants' speech during a meeting into text information using speech recognition technology, and makes that text information available for use within the system.

[0061] "Methods for extracting important elements from transcribed information" refers to a function that automatically identifies important keywords and phrases from the transcribed audio content of a meeting's decision-making and discussions, and separates them as necessary information.

[0062] "Means of presenting relevant information based on extracted key elements" refers to a function that quickly references relevant management information, case studies, and historical data based on extracted keywords and phrases, and presents necessary materials and data to meeting participants.

[0063] "A means of generating summaries and work items after a meeting" refers to a function that summarizes the content discussed in a meeting, compiles it into a concrete list of future action plans and tasks to be addressed, and provides it to meeting participants and relevant departments.

[0064] "Setting meeting objectives and optimizing the plan based on them" refers to a function that involves establishing specific goals to achieve the meeting's objectives and refining the agenda and meeting proceedings in line with those goals.

[0065] "A means of sending time-sensitive notifications to those responsible for work items" refers to a function that designates a person responsible for each work item decided at a meeting and notifies the designated person of important reminders such as submission deadlines.

[0066] To implement this invention, a system is required in which a server and terminals play crucial roles. The server first extracts meeting schedule information from a schedule management system. This is done using the Google® Calendar API and the Microsoft® Graph API. The server then analyzes a database of past meeting records and extracts important information using natural language processing techniques. This automatically generates potential agenda items for the next meeting. For this analysis, a machine learning model using, for example, Tensorflow® is implemented.

[0067] The user, acting as the meeting organizer, reviews the server-generated agenda draft on a dedicated management screen and makes modifications or additions as needed. This management screen is provided as a web application and built using React or Angular. Through this screen, users can optimize the agenda draft and plan the meeting according to its objectives.

[0068] During the meeting, the terminal uses speech recognition technology to transcribe participants' speech in real time. This process utilizes Google Speech-to-Text and Amazon Transcribe. The terminal sends the obtained text data to a server, which extracts keywords and immediately analyzes and presents relevant information. This enables meeting participants to make quick decisions.

[0069] After the meeting ends, the server organizes all transcripts, including data obtained through speech recognition, and uses natural language generation technology to generate a meeting summary and action items. This information is distributed to users via communication tools such as Microsoft Teams® and Slack. Furthermore, integration with to-do list apps sends reminder notifications for tasks to those responsible.

[0070] As a concrete example, in a project progress meeting, specific action items such as reviewing sales targets and risk mitigation measures for the next quarter are listed. This allows meeting participants to clearly understand what needs to be done next and to quickly take necessary follow-up actions.

[0071] Generative AI models use prompt statements like the following:

[0072] "Please extract key topics from past meeting records to generate discussion points for the next meeting."

[0073] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0074] Step 1:

[0075] The server connects to the company's scheduling management system via API to extract meeting schedules and participant information. The input is raw schedule data retrieved from the scheduling management system, which is then formatted and stored in the required format. The output is provided as a dataset containing meeting dates, times, locations, and participant lists. Specifically, it sends API requests, parses the responses, and stores them in the database.

[0076] Step 2:

[0077] The server retrieves past meeting records from the database and analyzes them. The input is past meeting records, and important themes and topics are extracted using natural language processing techniques. Text mining is performed as data processing, and potential agenda items for the next meeting are generated as output. Specifically, a machine learning model is used to extract frequently occurring keywords from past statements and meeting minutes.

[0078] Step 3:

[0079] The user, the meeting organizer, reviews the draft agenda generated through the server's management screen and makes revisions as needed. The input is the draft agenda provided by the server. The output is saved as the revised, final draft agenda. Specifically, the user edits the draft agenda through a web browser interface and sends it to the server.

[0080] Step 4:

[0081] During the meeting, the terminal uses a microphone to capture participants' voices and converts them to text in real time using speech recognition software. The input is the voice data of the participants during the meeting. As data processing, the voice is converted to text, and the text data is sent to the server as output. Specifically, the speech recognition API is used to transcribe the speech, and the results are relayed to the server.

[0082] Step 5:

[0083] The server analyzes the received text data, extracts keywords, and presents relevant information. The input is text data sent from a terminal. Data processing involves text analysis, and the output generates information useful to meeting participants. Specifically, it uses a search algorithm to query internal and external databases and provides relevant information immediately.

[0084] Step 6:

[0085] After the meeting ends, the server organizes all the collected data and generates a summary and action items. The input is all the text data collected during the meeting. As a data calculation, it categorizes and summarizes the information, and as output, it generates a summary report and an action list. Specifically, it uses a natural language generation tool to summarize the key points of the meeting and list the next steps.

[0086] Step 7:

[0087] The server distributes the generated summary and action items to users via communication tools and sets reminders for responsible parties. The input is the generated summary and action list. The output is a notification message containing that information. Specifically, it uses an API to send information via Slack or email systems and adds items to to-do lists with deadlines.

[0088] (Application Example 1)

[0089] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0090] Logistics meetings require efficient agenda setting using historical data and rapid information sharing during meetings. However, current systems make these processes manual and time-consuming, making efficient management difficult. In particular, the lack of automated generation of improvement suggestions based on historical logistics delay data hinders rapid decision-making.

[0091] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0092] In this invention, the server includes means for acquiring meeting plans, means for analyzing past meeting data to generate agenda proposals, and means for analyzing statements made during meetings and extracting important keywords. This streamlines meetings in logistics operations, enables the automatic generation of improvement proposals based on past data, and allows for the rapid provision of information.

[0093] "Meeting plan" refers to the details set out in advance for holding a meeting, including the date, time, location, purpose, and participant list.

[0094] "Past meeting data" refers to records of agenda items, participants' comments, and decisions made in meetings held to date.

[0095] A "proposal for agenda items" is a list of topics or themes to be discussed at a meeting, generated based on past data and current needs.

[0096] "Key terms" are keywords or phrases mentioned during a meeting that are deemed to have an impact on achieving the meeting's objectives or influencing decisions made.

[0097] "Related information based on extracted information" refers to additional data and examples provided by the server after analyzing the terms discussed during the meeting.

[0098] "Action items" are a list of specific tasks and actions that have been clarified as a result of the meeting and that should be carried out.

[0099] A "generative AI model" is a program that uses artificial intelligence technology to perform data analysis and text generation, automatically generating new ideas and proposals.

[0100] "Logistics operations" refer to the entire operation within the supply chain, including processes such as the transportation, storage, inventory management, and delivery of goods.

[0101] To implement this invention, the following system is required. First, the server retrieves the meeting plan and analyzes past meeting data. This includes extracting meeting details from the company's scheduling management system and reading relevant records from the database. A database such as MongoDB is used to manage and retrieve the necessary information.

[0102] Next, a generative AI model is used to generate agenda proposals based on historical data and current business needs. The generative AI model utilizes natural language processing technologies such as GPT-3 (registered trademark) to generate optimized agendas for new meetings. During the meeting, the terminal uses the Google Cloud Speech-to-Text API to convert speech to text and sends this data to the server in real time. The server analyzes this text information using natural language processing technologies such as BERT to extract important keywords.

[0103] Based on the extracted information, the server immediately presents relevant information, including data from external sources and past case studies. After the meeting, the server organizes the collected data and generates action items. These action items are then used as specific work tasks, and assigned personnel are notified as reminders to complete them within a specified timeframe.

[0104] As a concrete example, in a meeting system for logistics operations, an AI model is used to generate improvement suggestions based on past delivery delay data. During the meeting, a speech recognition system transcribes speech in real time, and a server quickly analyzes the data and provides the results to the meeting participants. This process begins when a prompt message is entered stating, "Generate a draft agenda for a new logistics meeting based on recent logistics meetings. Pay particular attention to topics related to delivery efficiency."

[0105] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0106] Step 1:

[0107] The server retrieves meeting plans from the company's scheduling management system. This input data includes the date, time, location, and participant list of the meeting. Based on this information, the server stores a detailed summary of the meeting in its database.

[0108] Step 2:

[0109] The server retrieves past meeting data from MongoDB and generates agenda proposals. This data includes agenda items, participants, and discussion content from past meetings. The server uses a generative AI model (GPT-3) to analyze this data and generate optimized agenda proposals. The output is a list of agenda items to be discussed at the next meeting.

[0110] Step 3:

[0111] The user starts a meeting using their device and records audio data in real time. The device uses the Google Cloud Speech-to-Text API to convert the audio data into text data. The input is the audio data from the meeting, and the output is the transcribed speech.

[0112] Step 4:

[0113] The server receives text data sent from the terminal and performs natural language processing using Google BERT. It extracts important words and phrases in real time and instantly searches the database for information related to those words. The output is either a link to the relevant data or a summary.

[0114] Step 5:

[0115] After the meeting ends, the server analyzes the collected text data and generates action items based on key points and decisions. The output data consists of specific tasks and a list of responsible parties. This allows for the development of a plan for the next steps.

[0116] Step 6:

[0117] The server notifies the user of the action list and sends reminders to each person in charge to complete the action items within the set deadline. The input is a list of action items, and the output is delivered to each person in charge in the form of a notification.

[0118] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0119] This invention is a system for efficiently conducting meetings and optimizing meeting management by taking participants' emotions into consideration. This system is operated by multiple components, including a server, terminals, and an emotion engine.

[0120] The server first retrieves meeting schedules from the company's scheduling management system and collects relevant participant lists. This process prepares the necessary meeting information. Next, the server analyzes past meeting records, automatically extracts topics and issues to be discussed in the new meeting, and provides the user with a draft agenda. Based on the draft agenda suggested by the server, the user sets the meeting objectives and agenda and provides feedback to the server.

[0121] During the meeting, the device uses speech recognition and an emotion engine to analyze participants' statements in real time. The emotion engine detects the participants' emotional state (e.g., positive, negative, neutral) from the tone and content of their statements. This data is sent to a server and used as a reference when adjusting the meeting's progress.

[0122] Based on the analyzed sentiment data, the server presents relevant industry data and past case studies. It also provides necessary data and suggestions in response to comments made during the meeting, helping participants to gain a more balanced perspective.

[0123] After the meeting concludes, the server summarizes the information gathered during the meeting and generates key conclusions and action items. This information is sent to stakeholders via their terminals. Each person responsible for an action item receives a time-limited reminder from the server, allowing them to clearly see the next steps.

[0124] As a concrete example, in a project progress meeting, the emotion engine detects when participants have concerns about a particular agenda item and, based on this, suggests providing additional information or re-evaluating the agenda item. As a result, the efficiency of the meeting and participant satisfaction improve.

[0125] The following describes the processing flow.

[0126] Step 1:

[0127] The server retrieves meeting schedule information from the company's scheduling management system and creates a participant list. It also extracts past meeting data from the database and prepares necessary reference materials for the next meeting.

[0128] Step 2:

[0129] The server analyzes past meeting data, automatically extracts new topics and issues to consider, and generates a draft agenda. This draft agenda is provided to the user, who reviews it and sets the meeting goals and agenda.

[0130] Step 3:

[0131] Based on the proposed agenda provided by the server, users adjust the meeting objectives and provide feedback to the server with the final agenda. The server records this information and updates the meeting plan.

[0132] Step 4:

[0133] During the meeting, the terminal uses speech recognition technology to transcribe spoken content into text in real time and send it to the server. Simultaneously, an emotion engine operates to analyze emotions from the tone and keywords of the speech.

[0134] Step 5:

[0135] The server extracts key keywords based on analyzed sentiment and text data, and searches for relevant industry data and case studies. This information is immediately provided to participants, improving the quality of the meeting.

[0136] Step 6:

[0137] The emotion engine monitors the emotional state of participants, and if negative emotions are detected, the server generates suggestions for how to proceed with the meeting. For example, a short break or a reassessment of the agenda might be considered.

[0138] Step 7:

[0139] After the meeting ends, the server automatically generates a meeting summary and action items based on the collected data. This organizes key conclusions and next steps, which are then distributed to relevant parties via their devices.

[0140] Step 8:

[0141] The device notifies the responsible party of action items and sends reminders with deadlines to facilitate execution. This ensures that meeting results are followed up on.

[0142] (Example 2)

[0143] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0144] Meetings involve handling a large amount of information, requiring efficient agenda setting and the rapid provision of relevant data while considering participants' emotions and opinions. However, traditional methods struggle to optimize meetings while taking emotional states into account, and post-meeting information organization and clarification of the next steps in activities require considerable time and effort.

[0145] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0146] In this invention, the server includes means for acquiring meeting schedules, means for analyzing past meeting records to generate agenda items, means for transcribing speech during meetings into text using speech recognition technology and detecting participants' emotional states using sentiment analysis technology, means for providing relevant data based on the detected emotional states, and means for summarizing data collected after the meeting and generating conclusions and next action items. This enables efficient meeting progress, visualization of information, and rapid information organization and action plan formulation after the meeting.

[0147] "Means of retrieving meeting schedules" refers to a function that integrates with an internal or external scheduling management system to retrieve information about the date, time, location, and participants of a specific meeting.

[0148] "A means of generating agenda proposals by analyzing past meeting records" refers to a function that retrieves records of past meetings from a database, analyzes them, extracts themes and issues that should be discussed at the next meeting, and proposes them.

[0149] "A method for transcribing speech during a meeting into text using speech recognition technology and detecting participants' emotional states using sentiment analysis technology" refers to a technology that converts participants' speech into text information during a meeting, and further analyzes the content and tone of their speech to understand their emotions.

[0150] "Means for providing relevant data based on detected emotional states" refers to a function that provides appropriate information and suggestions in real time, based on the analysis results of participants' emotional states.

[0151] "A means of summarizing data collected after a meeting and generating conclusions and next action items" refers to a function that organizes the statements and decisions made during the meeting, summarizes the key points, and constructs future steps and responsibilities.

[0152] This invention is a system aimed at efficient meeting management and optimal use of information. The system integrates a server, terminals, and sentiment analysis modules to support the entire process of a meeting.

[0153] The server first integrates with the company's scheduling software to retrieve meeting schedules. Specifically, the server accesses the database from the scheduling management system via an API to retrieve the meeting date, time, location, and participant list. Next, it uses a generative AI model with natural language processing technology to analyze past meeting records. This model extracts important topics from past meeting data and presents the user with proposed agenda items.

[0154] During the meeting, the terminal uses speech recognition software to transcribe speech in real time. This process utilizes existing speech recognition APIs to convert audio data into text data. Furthermore, the terminal uses sentiment analysis technology to determine the emotional state (positive, negative, neutral) of participants based on the content and tone of their speech. This data is sent to the server to facilitate the meeting while considering the nuances of speech.

[0155] Based on the sentiment analysis results, the server presents relevant industry information and past success stories. This information allows participants to engage in discussions from multiple perspectives. After the meeting, the server summarizes all meeting data, generates conclusions and next action steps, and distributes them to participants via their terminals. This step helps ensure that necessary preparations for the next meeting proceed smoothly.

[0156] As a concrete example, during a project progress meeting, the device sends a prompt message to the AI ​​model saying, "Please analyze the emotional state of the participants in real time and suggest ways to optimize the direction of the meeting." Based on this prompt, the generated suggestions are appropriate to the meeting's topic, ultimately promoting more efficient discussion.

[0157] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0158] Step 1:

[0159] The server integrates with the company's scheduling software, retrieving meeting schedules and participant lists via API. It uses data from the scheduling management system as input and outputs meeting dates, times, locations, and participant information. Specifically, it filters the necessary fields from the database and saves them as structured data.

[0160] Step 2:

[0161] The server analyzes past meeting records using natural language processing technology and generates agenda items using a generative AI model. The input is past meeting data, the model analyzes the frequency and importance of topics, and the output is a list of agenda items to be discussed at the next meeting. Specifically, the process involves preprocessing the text data and then having the model extract and prioritize keywords.

[0162] Step 3:

[0163] The terminal acquires audio data from a meeting via speech recognition software and transcribes it into text in real time. The input is the audio of the meeting participants' speeches, and the output is a transcript of the speeches in text format. Specifically, it analyzes the audio data stream, performs accurate text conversion, and immediately sends the result to the server.

[0164] Step 4:

[0165] The terminal analyzes the transcribed speech content using sentiment analysis technology to detect the emotional state of the participants. It uses text data sent from the terminal as input, and the output is an emotional state label (e.g., positive, negative, neutral). Specifically, it quantifies emotions through tone analysis and keyword analysis, and sends the results to the server.

[0166] Step 5:

[0167] Based on the analysis results, the server uses a generating AI model to search for relevant industry data and past case studies, and provides them to participants. Inputs are the sentiment analysis results and real-time comments. The output generates reference data and suggestions. Specifically, it creates database queries based on sentiment data, extracts relevant information, and presents it.

[0168] Step 6:

[0169] After the meeting, the server summarizes all the collected data and generates conclusions and action items. The input is the data accumulated during the meeting, and the output is a summary and action plan. Specifically, it extracts and compiles key information and sends it to the user's terminal as feedback.

[0170] (Application Example 2)

[0171] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0172] In today's surveillance and security industry, real-time decision-making and countermeasures are required, but traditional methods have difficulty grasping emotional states, sometimes resulting in inappropriate responses. Therefore, there is a need for a system that can detect emotions more quickly and accurately, and provide information and propose countermeasures based on that detection.

[0173] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0174] In this invention, the server includes means for acquiring meeting schedules, means for analyzing past conversation records to generate agenda items, and means for analyzing acoustic data of conversations to determine emotional states in real time. This enables immediate information provision and countermeasures to be proposed in response to changes in emotions.

[0175] "Method for obtaining meeting schedules" refers to a function that automatically collects pre-set meeting schedule information from business management systems or calendar applications.

[0176] "A means of generating agenda proposals by analyzing past meeting records" refers to a function that analyzes the record data of past meetings and extracts and presents topics and issues that should be addressed in the next meeting.

[0177] "A means of analyzing conversational audio data to determine emotional states in real time" refers to a function that has an algorithm that analyzes participants' voice information in real time and judges their emotions from their tone and content.

[0178] "Means of presenting relevant information based on the determined emotional state" refers to a function that provides information to suggest past cases and immediate countermeasures in response to the results obtained from emotion analysis.

[0179] "A means of generating summaries and action items after a meeting" refers to a function that efficiently summarizes the content discussed during a meeting and extracts and presents action plans that need to be implemented.

[0180] The system for realizing this invention includes a server, a mobile terminal, a voice analysis engine, an emotion determination engine, and a database management system.

[0181] The server first retrieves meeting schedules from the business management system or calendar application. Based on this information, it analyzes past meeting record data, generates a new agenda, and notifies mobile devices. A speech analysis engine (such as Google Speech-to-Text API) transcribes the conversation into text in real time, and this text is passed to an emotion detection engine (such as Amazon Comprehend) to determine the emotional state of the participants during the meeting.

[0182] The device sends the determined emotion information to the server. Based on this information, the server provides the user with information including relevant case data and immediate countermeasures. For example, if tension is increasing regarding a particular issue, past data is used to suggest directions for discussion that can help alleviate tension.

[0183] Furthermore, at the end of the meeting, the server compiles a summary of the statements and sentiment analysis results, extracts action items, and presents them to the user. Reminders can be sent for these action items with a set deadline.

[0184] As a concrete example, in the security response for a large-scale event, if on-site staff use smartphones for voice input and analysis detects potential anxiety among participants, the server will suggest appropriate relocation to maintain a stable situation. As a result, the event is expected to proceed smoothly.

[0185] An example of a prompt is as follows: "In crowd management at a large-scale event, we used speech recognition and sentiment analysis to detect tension and anxiety. Please refer to past data and advise on appropriate crowd control measures and ways to prevent disruption."

[0186] In this way, it becomes possible to provide real-time support for appropriate decision-making.

[0187] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0188] Step 1:

[0189] The server retrieves meeting schedule information as input from the business management system or calendar application. This makes basic data about the next meeting available. This information is registered in the database and used in subsequent processing.

[0190] Step 2:

[0191] The server extracts past meeting records from a database and analyzes them as input. Using natural language processing technology, it automatically extracts keywords and topics that should be included in the agenda and outputs them to the user as a draft agenda. In this process, important topics are identified, and the user proceeds with meeting preparations based on this information.

[0192] Step 3:

[0193] The device receives audio data collected during the meeting as input and converts the speech to text using a speech recognition API (e.g., Google Speech-to-Text). This text data is sent in real time to an emotion determination engine (e.g., Amazon Comprehend) which analyzes and outputs the emotional state from the utterances. The analysis results are used to understand the emotional background of the speaker.

[0194] Step 4:

[0195] The server takes the sentiment analysis results received from the terminal as input, compares them with relevant information in the database, and generates appropriate information and examples based on the determined sentiment as output. This information helps users make appropriate decisions during meetings. At the same time, it supports the smooth progress of meetings by presenting relevant materials and suggestions.

[0196] Step 5:

[0197] After the meeting ends, the server integrates the meeting's content and sentiment data as input to generate a summary and action items. These results are then sent to the user as output. This process identifies key discussion points and actions to be taken during the meeting, providing detailed information to support the execution of the next steps.

[0198] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0199] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0200] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0201] [Second Embodiment]

[0202] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0203] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0204] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0205] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0206] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0207] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0208] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0209] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0210] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0211] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0212] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0213] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0214] This invention is a system for efficiently conducting and managing corporate meetings, and the software program for implementing this system runs on a server and terminals.

[0215] The server first extracts meeting schedules from the company's internal scheduling system and collects participant information. This prepares the server to provide relevant information to stakeholders before the meeting begins. Next, it analyzes records of similar past meetings and uses that data to generate potential topics for discussion in the new meeting.

[0216] Once preparations are complete, the user (the meeting organizer) reviews the draft agenda generated by the server and makes any necessary revisions or additions. As a result, an optimized agenda is established, and specific goals for the meeting are set.

[0217] During the meeting, the terminal uses speech recognition technology to convert participants' speech into text in real time and sends that data to the server. Based on this information, the server extracts important keywords and immediately analyzes and provides relevant industry data and past case studies. This enables meeting participants to make more informed decisions.

[0218] After the meeting ends, the server organizes the collected data and generates a summary of the content and a list of action items. This information is distributed to relevant parties via terminals, and those responsible for each action item receive a time-limited reminder. For example, in a project progress meeting, specific actions such as reviewing sales targets for the next quarter and risk mitigation measures are listed, enabling efficient follow-up.

[0219] This system automates and streamlines the entire process, from meeting preparation to post-meeting follow-up, supporting meeting management based on objective data.

[0220] The following describes the processing flow.

[0221] Step 1:

[0222] The server retrieves meeting schedules from the company's scheduling management system and collects participant lists. It also extracts relevant past meeting data from the database.

[0223] Step 2:

[0224] The server analyzes past meeting data to extract topics and issues that should be discussed in the next meeting, and generates a draft agenda. This forms the basis for proposing it to the user.

[0225] Step 3:

[0226] Users review the proposed agenda, adjust the meeting objectives and specific agenda as needed, and provide feedback to the server. The server then incorporates this information to finalize the agenda.

[0227] Step 4:

[0228] The terminal converts the audio from the meeting into text data in real time and sends it to the server. This process allows for the recording of what is said during the meeting.

[0229] Step 5:

[0230] The server analyzes the received text data and extracts key keywords. Furthermore, it searches for relevant external data and industry case studies and presents them to the participants.

[0231] Step 6:

[0232] After the meeting ends, the server generates a summary and action items based on the data collected during the meeting. This helps organize the meeting's results and clarify the next steps.

[0233] Step 7:

[0234] The device distributes the generated summary and action items to the assigned person. It also sends time-limited reminders for the action items to prompt the person to complete the task.

[0235] (Example 1)

[0236] Next, we will describe Example 1. 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."

[0237] In today's business environment, meetings are crucial for important decisions, yet they are often inefficient and unproductive. This is due to insufficient preparation, poor information management during meetings, and delayed follow-up. As a result, valuable participant time is wasted, and the quality of decision-making suffers. Therefore, it is essential to streamline the meeting preparation, execution, and follow-up processes throughout the entire system, supporting participants in making meaningful contributions.

[0238] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0239] In this invention, the server includes means for extracting scheduled information, means for analyzing past information to generate agenda candidates, and means for converting audio information into text in real time. This streamlines the process from meeting preparation to progress and follow-up, enabling participants to make more informed decisions more quickly.

[0240] "Methods for extracting schedule information" refers to a function that retrieves meeting and related event schedule information from a company's internal data management system and processes it to make the necessary schedule data available within the system.

[0241] "Methods for generating agenda candidates by analyzing past information" refers to a function that analyzes records and data from similar meetings held in the past to suggest topics and themes that should be discussed at the next meeting.

[0242] "A means of converting audio information to text in real time" refers to a function that instantly converts participants' speech during a meeting into text information using speech recognition technology, and makes that text information available for use within the system.

[0243] "Methods for extracting important elements from transcribed information" refers to a function that automatically identifies important keywords and phrases from the transcribed audio content of a meeting's decision-making and discussions, and separates them as necessary information.

[0244] "Means of presenting relevant information based on extracted key elements" refers to a function that quickly references relevant management information, case studies, and historical data based on extracted keywords and phrases, and presents necessary materials and data to meeting participants.

[0245] "A means of generating summaries and work items after a meeting" refers to a function that summarizes the content discussed in a meeting, compiles it into a concrete list of future action plans and tasks to be addressed, and provides it to meeting participants and relevant departments.

[0246] "Setting meeting objectives and optimizing the plan based on them" refers to a function that involves establishing specific goals to achieve the meeting's objectives and refining the agenda and meeting proceedings in line with those goals.

[0247] "A means of sending time-sensitive notifications to those responsible for work items" refers to a function that designates a person responsible for each work item decided at a meeting and notifies the designated person of important reminders such as submission deadlines.

[0248] To implement this invention, a system is required in which a server and terminals play crucial roles. The server first extracts meeting schedule information from a schedule management system, using the Google Calendar API or Microsoft Graph API. The server then analyzes a database of past meeting records and extracts important information using natural language processing techniques. This allows for the automatic generation of potential agenda items for the next meeting. For this analysis, a machine learning model using TensorFlow, for example, could be implemented.

[0249] The user, acting as the meeting organizer, reviews the server-generated agenda draft on a dedicated management screen and makes modifications or additions as needed. This management screen is provided as a web application and built using React or Angular. Through this screen, users can optimize the agenda draft and plan the meeting according to its objectives.

[0250] During the meeting, the terminal uses speech recognition technology to transcribe participants' speech in real time. This process utilizes Google Speech-to-Text and Amazon Transcribe. The terminal sends the obtained text data to a server, which extracts keywords and immediately analyzes and presents relevant information. This enables meeting participants to make quick decisions.

[0251] After the meeting ends, the server organizes all transcripts, including data obtained through speech recognition, and uses natural language generation technology to generate a meeting summary and action items. This information is then distributed to users via communication tools such as Microsoft Teams and Slack. Furthermore, integration with to-do list apps sends reminder notifications for tasks to those responsible.

[0252] As a concrete example, in a project progress meeting, specific action items such as reviewing sales targets and risk mitigation measures for the next quarter are listed. This allows meeting participants to clearly understand what needs to be done next and to quickly take necessary follow-up actions.

[0253] Generative AI models use prompt statements like the following:

[0254] "Please extract key topics from past meeting records to generate discussion points for the next meeting."

[0255] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0256] Step 1:

[0257] The server connects to the company's scheduling management system via API to extract meeting schedules and participant information. The input is raw schedule data retrieved from the scheduling management system, which is then formatted and stored in the required format. The output is provided as a dataset containing meeting dates, times, locations, and participant lists. Specifically, it sends API requests, parses the responses, and stores them in the database.

[0258] Step 2:

[0259] The server retrieves past meeting records from the database and analyzes them. The input is past meeting records, and important themes and topics are extracted using natural language processing techniques. Text mining is performed as data processing, and potential agenda items for the next meeting are generated as output. Specifically, a machine learning model is used to extract frequently occurring keywords from past statements and meeting minutes.

[0260] Step 3:

[0261] The user, the meeting organizer, reviews the draft agenda generated through the server's management screen and makes revisions as needed. The input is the draft agenda provided by the server. The output is saved as the revised, final draft agenda. Specifically, the user edits the draft agenda through a web browser interface and sends it to the server.

[0262] Step 4:

[0263] During the meeting, the terminal uses a microphone to capture participants' voices and converts them to text in real time using speech recognition software. The input is the voice data of the participants during the meeting. As data processing, the voice is converted to text, and the text data is sent to the server as output. Specifically, the speech recognition API is used to transcribe the speech, and the results are relayed to the server.

[0264] Step 5:

[0265] The server analyzes the received text data, extracts keywords, and presents relevant information. The input is text data sent from a terminal. Data processing involves text analysis, and the output generates information useful to meeting participants. Specifically, it uses a search algorithm to query internal and external databases and provides relevant information immediately.

[0266] Step 6:

[0267] After the meeting ends, the server organizes all the collected data and generates a summary and action items. The input is all the text data collected during the meeting. As a data calculation, it categorizes and summarizes the information, and as output, it generates a summary report and an action list. Specifically, it uses a natural language generation tool to summarize the key points of the meeting and list the next steps.

[0268] Step 7:

[0269] The server distributes the generated summary and action items to users via communication tools and sets reminders for responsible parties. The input is the generated summary and action list. The output is a notification message containing that information. Specifically, it uses an API to send information via Slack or email systems and adds items to to-do lists with deadlines.

[0270] (Application Example 1)

[0271] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0272] Logistics meetings require efficient agenda setting using historical data and rapid information sharing during meetings. However, current systems make these processes manual and time-consuming, making efficient management difficult. In particular, the lack of automated generation of improvement suggestions based on historical logistics delay data hinders rapid decision-making.

[0273] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0274] In this invention, the server includes means for acquiring meeting plans, means for analyzing past meeting data to generate agenda proposals, and means for analyzing statements made during meetings and extracting important keywords. This streamlines meetings in logistics operations, enables the automatic generation of improvement proposals based on past data, and allows for the rapid provision of information.

[0275] "Meeting plan" refers to the details set out in advance for holding a meeting, including the date, time, location, purpose, and participant list.

[0276] "Past meeting data" refers to records of agenda items, participants' comments, and decisions made in meetings held to date.

[0277] A "proposal for agenda items" is a list of topics or themes to be discussed at a meeting, generated based on past data and current needs.

[0278] "Key terms" are keywords or phrases mentioned during a meeting that are deemed to have an impact on achieving the meeting's objectives or influencing decisions made.

[0279] "Related information based on extracted information" refers to additional data and examples provided by the server after analyzing the terms discussed during the meeting.

[0280] An "action item" is a list of specific tasks or actions that have been clearly identified as a result of a meeting and need to be specifically executed.

[0281] A "generative AI model" is a program that uses artificial intelligence technology to perform data analysis and text generation, and automatically creates new ideas and proposals.

[0282] "Logistics operations" refer to the overall operations in the supply chain, including processes such as transportation, storage, inventory management, and distribution of goods.

[0283] To implement this invention, the following system is required. First, the server acquires the meeting plan and analyzes past meeting data. This includes extracting the details of the meeting from the company's scheduling management system and loading relevant records from the database. A database such as MongoDB is used to manage and acquire the necessary information.

[0284] Next, a generative AI model is utilized to generate topic proposals based on past data and current business needs. Natural language processing technologies such as GPT-3 are used in the generative AI model to generate optimized topics for a new meeting. During the meeting, the terminal uses the Google Cloud Speech-to-Text API to convert speech into text and transmits this data to the server in real time. The server analyzes this text information using natural language processing technologies such as BERT and extracts important phrases.

[0285] Based on the extracted information, the server immediately presents relevant related information. This includes data obtained from external information sources and past cases, etc. After the meeting ends, the server organizes the collected data and generates action items. These action items are notified to the responsible person as reminders to be implemented within the specified period as specific business tasks.

[0286] As a specific example, in a conference system for logistics operations, improvement proposals are made using an AI model generated based on past delivery delay data. During the conference, a speech recognition system converts the speech into text in real time, and the server quickly analyzes it and provides the results to the conference participants. This process is initiated by inputting a prompt sentence such as "Based on recent logistics conferences, please generate a proposal for the topic of a new logistics conference. Please pay particular attention to topics related to improving delivery efficiency."

[0287] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0288] Step 1:

[0289] The server obtains the conference plan from the company's schedule management system. This input data includes the conference date, location, and participant list. Based on this information, the server saves a detailed overview of the conference in the database.

[0290] Step 2:

[0291] The server retrieves past conference data from MongoDB and generates topic proposals. This data includes the topics, participants, and speech content of past conferences. The server uses a generative AI model (GPT-3) to analyze this data and generate optimized topic proposals. The output is a list of topics to be considered at the next conference.

[0292] Step 3:

[0293] The user starts the conference using a terminal and records the audio data in real time. The terminal uses the Google Cloud Speech-to-Text API to convert the audio data into text data. The input is the audio data during the conference, and the output is the texturized speech content.

[0294] Step 4:

[0295] The server receives text data sent from the terminal and performs natural language processing using Google BERT. It extracts important words and phrases in real time and instantly searches the database for information related to those words. The output is either a link to the relevant data or a summary.

[0296] Step 5:

[0297] After the meeting ends, the server analyzes the collected text data and generates action items based on key points and decisions. The output data consists of specific tasks and a list of responsible parties. This allows for the development of a plan for the next steps.

[0298] Step 6:

[0299] The server notifies the user of the action list and sends reminders to each person in charge to complete the action items within the set deadline. The input is a list of action items, and the output is delivered to each person in charge in the form of a notification.

[0300] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0301] This invention is a system for efficiently conducting meetings and optimizing meeting management by taking participants' emotions into consideration. This system is operated by multiple components, including a server, terminals, and an emotion engine.

[0302] The server first retrieves meeting schedules from the company's scheduling management system and collects relevant participant lists. This process prepares the necessary meeting information. Next, the server analyzes past meeting records, automatically extracts topics and issues to be discussed in the new meeting, and provides the user with a draft agenda. Based on the draft agenda suggested by the server, the user sets the meeting objectives and agenda and provides feedback to the server.

[0303] During the meeting, the terminal analyzes the participants' speeches in real time using speech recognition and an emotion engine. The emotion engine detects the participants' emotional states (e.g., positive, negative, neutral) from the tone and content of the speeches. This data is sent to the server and used as a reference when adjusting the progress of the meeting.

[0304] Based on the analyzed emotion data, the server presents relevant industry data and past cases. Also, necessary data and proposals are provided according to the speeches during the meeting to assist the participants in obtaining more balanced opinions.

[0305] After the meeting, the server summarizes the content collected during the meeting and generates the main conclusions and action items. This information is sent to the relevant parties through the terminal. Each person in charge of an action item can receive a reminder with a deadline from the server and clearly confirm the next steps.

[0306] As a specific example, in a project progress meeting, the emotion engine detects that the participants have concerns about a specific issue, and based on this, additional information provision and re-evaluation of the issue are proposed. As a result, the efficiency of the meeting and the satisfaction of the participants are improved.

[0307] The following describes the processing flow.

[0308] Step 1:

[0309] The server obtains the meeting schedule information from the company's schedule management system and creates a participant list. Also, it extracts past meeting data from the database and prepares reference materials required for the next meeting.

[0310] Step 2:

[0311] The server analyzes past meeting data, automatically extracts new topics and issues to consider, and generates a draft agenda. This draft agenda is provided to the user, who reviews it and sets the meeting goals and agenda.

[0312] Step 3:

[0313] Based on the proposed agenda provided by the server, users adjust the meeting objectives and provide feedback to the server with the final agenda. The server records this information and updates the meeting plan.

[0314] Step 4:

[0315] During the meeting, the terminal uses speech recognition technology to transcribe spoken content into text in real time and send it to the server. Simultaneously, an emotion engine operates to analyze emotions from the tone and keywords of the speech.

[0316] Step 5:

[0317] The server extracts key keywords based on analyzed sentiment and text data, and searches for relevant industry data and case studies. This information is immediately provided to participants, improving the quality of the meeting.

[0318] Step 6:

[0319] The emotion engine monitors the emotional state of participants, and if negative emotions are detected, the server generates suggestions for how to proceed with the meeting. For example, a short break or a reassessment of the agenda might be considered.

[0320] Step 7:

[0321] After the meeting ends, the server automatically generates a meeting summary and action items based on the collected data. This organizes key conclusions and next steps, which are then distributed to relevant parties via their devices.

[0322] Step 8:

[0323] The device notifies the responsible party of action items and sends reminders with deadlines to facilitate execution. This ensures that meeting results are followed up on.

[0324] (Example 2)

[0325] Next, we will describe Example 2. 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".

[0326] Meetings involve handling a large amount of information, requiring efficient agenda setting and the rapid provision of relevant data while considering participants' emotions and opinions. However, traditional methods struggle to optimize meetings while taking emotional states into account, and post-meeting information organization and clarification of the next steps in activities require considerable time and effort.

[0327] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0328] In this invention, the server includes means for acquiring meeting schedules, means for analyzing past meeting records to generate agenda items, means for transcribing speech during meetings into text using speech recognition technology and detecting participants' emotional states using sentiment analysis technology, means for providing relevant data based on the detected emotional states, and means for summarizing data collected after the meeting and generating conclusions and next action items. This enables efficient meeting progress, visualization of information, and rapid information organization and action plan formulation after the meeting.

[0329] "Means of retrieving meeting schedules" refers to a function that integrates with an internal or external scheduling management system to retrieve information about the date, time, location, and participants of a specific meeting.

[0330] "A means of generating agenda proposals by analyzing past meeting records" refers to a function that retrieves records of past meetings from a database, analyzes them, extracts themes and issues that should be discussed at the next meeting, and proposes them.

[0331] "A method for transcribing speech during a meeting into text using speech recognition technology and detecting participants' emotional states using sentiment analysis technology" refers to a technology that converts participants' speech into text information during a meeting, and further analyzes the content and tone of their speech to understand their emotions.

[0332] "Means for providing relevant data based on detected emotional states" refers to a function that provides appropriate information and suggestions in real time, based on the analysis results of participants' emotional states.

[0333] "A means of summarizing data collected after a meeting and generating conclusions and next action items" refers to a function that organizes the statements and decisions made during the meeting, summarizes the key points, and constructs future steps and responsibilities.

[0334] This invention is a system aimed at efficient meeting management and optimal use of information. The system integrates a server, terminals, and sentiment analysis modules to support the entire process of a meeting.

[0335] The server first integrates with the company's scheduling software to retrieve meeting schedules. Specifically, the server accesses the database from the scheduling management system via an API to retrieve the meeting date, time, location, and participant list. Next, it uses a generative AI model with natural language processing technology to analyze past meeting records. This model extracts important topics from past meeting data and presents the user with proposed agenda items.

[0336] During the meeting, the terminal uses speech recognition software to transcribe speech in real time. This process utilizes existing speech recognition APIs to convert audio data into text data. Furthermore, the terminal uses sentiment analysis technology to determine the emotional state (positive, negative, neutral) of participants based on the content and tone of their speech. This data is sent to the server to facilitate the meeting while considering the nuances of speech.

[0337] Based on the sentiment analysis results, the server presents relevant industry information and past success stories. This information allows participants to engage in discussions from multiple perspectives. After the meeting, the server summarizes all meeting data, generates conclusions and next action steps, and distributes them to participants via their terminals. This step helps ensure that necessary preparations for the next meeting proceed smoothly.

[0338] As a concrete example, during a project progress meeting, the device sends a prompt message to the AI ​​model saying, "Please analyze the emotional state of the participants in real time and suggest ways to optimize the direction of the meeting." Based on this prompt, the generated suggestions are appropriate to the meeting's topic, ultimately promoting more efficient discussion.

[0339] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0340] Step 1:

[0341] The server integrates with the company's scheduling software, retrieving meeting schedules and participant lists via API. It uses data from the scheduling management system as input and outputs meeting dates, times, locations, and participant information. Specifically, it filters the necessary fields from the database and saves them as structured data.

[0342] Step 2:

[0343] The server analyzes past meeting records using natural language processing technology and generates agenda items using a generative AI model. The input is past meeting data, the model analyzes the frequency and importance of topics, and the output is a list of agenda items to be discussed at the next meeting. Specifically, the process involves preprocessing the text data and then having the model extract and prioritize keywords.

[0344] Step 3:

[0345] The terminal acquires audio data from a meeting via speech recognition software and transcribes it into text in real time. The input is the audio of the meeting participants' speeches, and the output is a transcript of the speeches in text format. Specifically, it analyzes the audio data stream, performs accurate text conversion, and immediately sends the result to the server.

[0346] Step 4:

[0347] The terminal analyzes the transcribed speech content using sentiment analysis technology to detect the emotional state of the participants. It uses text data sent from the terminal as input, and the output is an emotional state label (e.g., positive, negative, neutral). Specifically, it quantifies emotions through tone analysis and keyword analysis, and sends the results to the server.

[0348] Step 5:

[0349] Based on the analysis results, the server uses a generating AI model to search for relevant industry data and past case studies, and provides them to participants. Inputs are the sentiment analysis results and real-time comments. The output generates reference data and suggestions. Specifically, it creates database queries based on sentiment data, extracts relevant information, and presents it.

[0350] Step 6:

[0351] After the meeting, the server summarizes all the collected data and generates conclusions and action items. The input is the data accumulated during the meeting, and the output is a summary and action plan. Specifically, it extracts and compiles key information and sends it to the user's terminal as feedback.

[0352] (Application Example 2)

[0353] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0354] In today's surveillance and security industry, real-time decision-making and countermeasures are required, but traditional methods have difficulty grasping emotional states, sometimes resulting in inappropriate responses. Therefore, there is a need for a system that can detect emotions more quickly and accurately, and provide information and propose countermeasures based on that detection.

[0355] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0356] In this invention, the server includes means for acquiring meeting schedules, means for analyzing past conversation records to generate agenda items, and means for analyzing acoustic data of conversations to determine emotional states in real time. This enables immediate information provision and countermeasures to be proposed in response to changes in emotions.

[0357] "Method for obtaining meeting schedules" refers to a function that automatically collects pre-set meeting schedule information from business management systems or calendar applications.

[0358] "A means of generating agenda proposals by analyzing past meeting records" refers to a function that analyzes the record data of past meetings and extracts and presents topics and issues that should be addressed in the next meeting.

[0359] "A means of analyzing conversational audio data to determine emotional states in real time" refers to a function that has an algorithm that analyzes participants' voice information in real time and judges their emotions from their tone and content.

[0360] "Means of presenting relevant information based on the determined emotional state" refers to a function that provides information to suggest past cases and immediate countermeasures in response to the results obtained from emotion analysis.

[0361] "A means of generating summaries and action items after a meeting" refers to a function that efficiently summarizes the content discussed during a meeting and extracts and presents action plans that need to be implemented.

[0362] The system for realizing this invention includes a server, a mobile terminal, a voice analysis engine, an emotion determination engine, and a database management system.

[0363] The server first retrieves meeting schedules from the business management system or calendar application. Based on this information, it analyzes past meeting record data, generates a new agenda, and notifies mobile devices. A speech analysis engine (such as Google Speech-to-Text API) transcribes the conversation into text in real time, and this text is passed to an emotion detection engine (such as Amazon Comprehend) to determine the emotional state of the participants during the meeting.

[0364] The device sends the determined emotion information to the server. Based on this information, the server provides the user with information including relevant case data and immediate countermeasures. For example, if tension is increasing regarding a particular issue, past data is used to suggest directions for discussion that can help alleviate tension.

[0365] Furthermore, at the end of the meeting, the server compiles a summary of the statements and sentiment analysis results, extracts action items, and presents them to the user. Reminders can be sent for these action items with a set deadline.

[0366] As a concrete example, in the security response for a large-scale event, if on-site staff use smartphones for voice input and analysis detects potential anxiety among participants, the server will suggest appropriate relocation to maintain a stable situation. As a result, the event is expected to proceed smoothly.

[0367] An example of a prompt is as follows: "In crowd management at a large-scale event, we used speech recognition and sentiment analysis to detect tension and anxiety. Please refer to past data and advise on appropriate crowd control measures and ways to prevent disruption."

[0368] In this way, it becomes possible to provide real-time support for appropriate decision-making.

[0369] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0370] Step 1:

[0371] The server retrieves meeting schedule information as input from the business management system or calendar application. This makes basic data about the next meeting available. This information is registered in the database and used in subsequent processing.

[0372] Step 2:

[0373] The server extracts past meeting records from a database and analyzes them as input. Using natural language processing technology, it automatically extracts keywords and topics that should be included in the agenda and outputs them to the user as a draft agenda. In this process, important topics are identified, and the user proceeds with meeting preparations based on this information.

[0374] Step 3:

[0375] The device receives audio data collected during the meeting as input and converts the speech to text using a speech recognition API (e.g., Google Speech-to-Text). This text data is sent in real time to an emotion determination engine (e.g., Amazon Comprehend) which analyzes and outputs the emotional state from the utterances. The analysis results are used to understand the emotional background of the speaker.

[0376] Step 4:

[0377] The server takes the sentiment analysis results received from the terminal as input, compares them with relevant information in the database, and generates appropriate information and examples based on the determined sentiment as output. This information helps users make appropriate decisions during meetings. At the same time, it supports the smooth progress of meetings by presenting relevant materials and suggestions.

[0378] Step 5:

[0379] After the meeting ends, the server integrates the meeting's content and sentiment data as input to generate a summary and action items. These results are then sent to the user as output. This process identifies key discussion points and actions to be taken during the meeting, providing detailed information to support the execution of the next steps.

[0380] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0381] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0382] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0383] [Third Embodiment]

[0384] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0385] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0386] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0387] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0388] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0389] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0390] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0391] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0392] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0393] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0394] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0395] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0396] This invention is a system for efficiently conducting and managing corporate meetings, and the software program for implementing this system runs on a server and terminals.

[0397] The server first extracts meeting schedules from the company's internal scheduling system and collects participant information. This prepares the server to provide relevant information to stakeholders before the meeting begins. Next, it analyzes records of similar past meetings and uses that data to generate potential topics for discussion in the new meeting.

[0398] Once preparations are complete, the user (the meeting organizer) reviews the draft agenda generated by the server and makes any necessary revisions or additions. As a result, an optimized agenda is established, and specific goals for the meeting are set.

[0399] During the meeting, the terminal uses speech recognition technology to convert participants' speech into text in real time and sends that data to the server. Based on this information, the server extracts important keywords and immediately analyzes and provides relevant industry data and past case studies. This enables meeting participants to make more informed decisions.

[0400] After the meeting ends, the server organizes the collected data and generates a summary of the content and a list of action items. This information is distributed to relevant parties via terminals, and those responsible for each action item receive a time-limited reminder. For example, in a project progress meeting, specific actions such as reviewing sales targets for the next quarter and risk mitigation measures are listed, enabling efficient follow-up.

[0401] This system automates and streamlines the entire process, from meeting preparation to post-meeting follow-up, supporting meeting management based on objective data.

[0402] The following describes the processing flow.

[0403] Step 1:

[0404] The server retrieves meeting schedules from the company's scheduling management system and collects participant lists. It also extracts relevant past meeting data from the database.

[0405] Step 2:

[0406] The server analyzes past meeting data to extract topics and issues that should be discussed in the next meeting, and generates a draft agenda. This forms the basis for proposing it to the user.

[0407] Step 3:

[0408] Users review the proposed agenda, adjust the meeting objectives and specific agenda as needed, and provide feedback to the server. The server then incorporates this information to finalize the agenda.

[0409] Step 4:

[0410] The terminal converts the audio from the meeting into text data in real time and sends it to the server. This process allows for the recording of what is said during the meeting.

[0411] Step 5:

[0412] The server analyzes the received text data and extracts key keywords. Furthermore, it searches for relevant external data and industry case studies and presents them to the participants.

[0413] Step 6:

[0414] After the meeting ends, the server generates a summary and action items based on the data collected during the meeting. This helps organize the meeting's results and clarify the next steps.

[0415] Step 7:

[0416] The device distributes the generated summary and action items to the assigned person. It also sends time-limited reminders for the action items to prompt the person to complete the task.

[0417] (Example 1)

[0418] Next, we will describe Example 1. 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."

[0419] In today's business environment, meetings are crucial for important decisions, yet they are often inefficient and unproductive. This is due to insufficient preparation, poor information management during meetings, and delayed follow-up. As a result, valuable participant time is wasted, and the quality of decision-making suffers. Therefore, it is essential to streamline the meeting preparation, execution, and follow-up processes throughout the entire system, supporting participants in making meaningful contributions.

[0420] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0421] In this invention, the server includes means for extracting scheduled information, means for analyzing past information to generate agenda candidates, and means for converting audio information into text in real time. This streamlines the process from meeting preparation to progress and follow-up, enabling participants to make more informed decisions more quickly.

[0422] "Methods for extracting schedule information" refers to a function that retrieves meeting and related event schedule information from a company's internal data management system and processes it to make the necessary schedule data available within the system.

[0423] "Methods for generating agenda candidates by analyzing past information" refers to a function that analyzes records and data from similar meetings held in the past to suggest topics and themes that should be discussed at the next meeting.

[0424] "A means of converting audio information to text in real time" refers to a function that instantly converts participants' speech during a meeting into text information using speech recognition technology, and makes that text information available for use within the system.

[0425] "Methods for extracting important elements from transcribed information" refers to a function that automatically identifies important keywords and phrases from the transcribed audio content of a meeting's decision-making and discussions, and separates them as necessary information.

[0426] "Means of presenting relevant information based on extracted key elements" refers to a function that quickly references relevant management information, case studies, and historical data based on extracted keywords and phrases, and presents necessary materials and data to meeting participants.

[0427] "A means of generating summaries and work items after a meeting" refers to a function that summarizes the content discussed in a meeting, compiles it into a concrete list of future action plans and tasks to be addressed, and provides it to meeting participants and relevant departments.

[0428] "Setting meeting objectives and optimizing the plan based on them" refers to a function that involves establishing specific goals to achieve the meeting's objectives and refining the agenda and meeting proceedings in line with those goals.

[0429] "A means of sending time-sensitive notifications to those responsible for work items" refers to a function that designates a person responsible for each work item decided at a meeting and notifies the designated person of important reminders such as submission deadlines.

[0430] To implement this invention, a system is required in which a server and terminals play crucial roles. The server first extracts meeting schedule information from a schedule management system, using the Google Calendar API or Microsoft Graph API. The server then analyzes a database of past meeting records and extracts important information using natural language processing techniques. This allows for the automatic generation of potential agenda items for the next meeting. For this analysis, a machine learning model using TensorFlow, for example, could be implemented.

[0431] The user, acting as the meeting organizer, reviews the server-generated agenda draft on a dedicated management screen and makes modifications or additions as needed. This management screen is provided as a web application and built using React or Angular. Through this screen, users can optimize the agenda draft and plan the meeting according to its objectives.

[0432] During the meeting, the terminal uses speech recognition technology to transcribe participants' speech in real time. This process utilizes Google Speech-to-Text and Amazon Transcribe. The terminal sends the obtained text data to a server, which extracts keywords and immediately analyzes and presents relevant information. This enables meeting participants to make quick decisions.

[0433] After the meeting ends, the server organizes all transcripts, including data obtained through speech recognition, and uses natural language generation technology to generate a meeting summary and action items. This information is then distributed to users via communication tools such as Microsoft Teams and Slack. Furthermore, integration with to-do list apps sends reminder notifications for tasks to those responsible.

[0434] As a concrete example, in a project progress meeting, specific action items such as reviewing sales targets and risk mitigation measures for the next quarter are listed. This allows meeting participants to clearly understand what needs to be done next and to quickly take necessary follow-up actions.

[0435] Generative AI models use prompt statements like the following:

[0436] "Please extract key topics from past meeting records to generate discussion points for the next meeting."

[0437] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0438] Step 1:

[0439] The server connects to the company's scheduling management system via API to extract meeting schedules and participant information. The input is raw schedule data retrieved from the scheduling management system, which is then formatted and stored in the required format. The output is provided as a dataset containing meeting dates, times, locations, and participant lists. Specifically, it sends API requests, parses the responses, and stores them in the database.

[0440] Step 2:

[0441] The server retrieves past meeting records from the database and analyzes them. The input is past meeting records, and important themes and topics are extracted using natural language processing techniques. Text mining is performed as data processing, and potential agenda items for the next meeting are generated as output. Specifically, a machine learning model is used to extract frequently occurring keywords from past statements and meeting minutes.

[0442] Step 3:

[0443] The user, the meeting organizer, reviews the draft agenda generated through the server's management screen and makes revisions as needed. The input is the draft agenda provided by the server. The output is saved as the revised, final draft agenda. Specifically, the user edits the draft agenda through a web browser interface and sends it to the server.

[0444] Step 4:

[0445] During the meeting, the terminal uses a microphone to capture participants' voices and converts them to text in real time using speech recognition software. The input is the voice data of the participants during the meeting. As data processing, the voice is converted to text, and the text data is sent to the server as output. Specifically, the speech recognition API is used to transcribe the speech, and the results are relayed to the server.

[0446] Step 5:

[0447] The server analyzes the received text data, extracts keywords, and presents relevant information. The input is text data sent from a terminal. Data processing involves text analysis, and the output generates information useful to meeting participants. Specifically, it uses a search algorithm to query internal and external databases and provides relevant information immediately.

[0448] Step 6:

[0449] After the meeting ends, the server organizes all the collected data and generates a summary and action items. The input is all the text data collected during the meeting. As a data calculation, it categorizes and summarizes the information, and as output, it generates a summary report and an action list. Specifically, it uses a natural language generation tool to summarize the key points of the meeting and list the next steps.

[0450] Step 7:

[0451] The server distributes the generated summary and action items to users via communication tools and sets reminders for responsible parties. The input is the generated summary and action list. The output is a notification message containing that information. Specifically, it uses an API to send information via Slack or email systems and adds items to to-do lists with deadlines.

[0452] (Application Example 1)

[0453] Next, we will explain Application Example 1. In the following explanation, 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."

[0454] Logistics meetings require efficient agenda setting using historical data and rapid information sharing during meetings. However, current systems make these processes manual and time-consuming, making efficient management difficult. In particular, the lack of automated generation of improvement suggestions based on historical logistics delay data hinders rapid decision-making.

[0455] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0456] In this invention, the server includes means for acquiring meeting plans, means for analyzing past meeting data to generate agenda proposals, and means for analyzing statements made during meetings and extracting important keywords. This streamlines meetings in logistics operations, enables the automatic generation of improvement proposals based on past data, and allows for the rapid provision of information.

[0457] "Meeting plan" refers to the details set out in advance for holding a meeting, including the date, time, location, purpose, and participant list.

[0458] "Past meeting data" refers to records of agenda items, participants' comments, and decisions made in meetings held to date.

[0459] A "proposal for agenda items" is a list of topics or themes to be discussed at a meeting, generated based on past data and current needs.

[0460] "Key terms" are keywords or phrases mentioned during a meeting that are deemed to have an impact on achieving the meeting's objectives or influencing decisions made.

[0461] "Related information based on extracted information" refers to additional data and examples provided by the server after analyzing the terms discussed during the meeting.

[0462] "Action items" are a list of specific tasks and actions that have been clarified as a result of the meeting and that should be carried out.

[0463] A "generative AI model" is a program that uses artificial intelligence technology to perform data analysis and text generation, automatically generating new ideas and proposals.

[0464] "Logistics operations" refer to the entire operation within the supply chain, including processes such as the transportation, storage, inventory management, and delivery of goods.

[0465] To implement this invention, the following system is required. First, the server retrieves the meeting plan and analyzes past meeting data. This includes extracting meeting details from the company's scheduling management system and reading relevant records from the database. A database such as MongoDB is used to manage and retrieve the necessary information.

[0466] Next, a generative AI model is used to generate agenda proposals based on historical data and current business needs. The generative AI model employs natural language processing techniques such as GPT-3 to generate optimized agendas for new meetings. During the meeting, the terminal uses the Google Cloud Speech-to-Text API to convert speech to text and sends this data to the server in real time. The server analyzes this text information using natural language processing techniques such as BERT to extract important keywords.

[0467] Based on the extracted information, the server immediately presents relevant information, including data from external sources and past case studies. After the meeting, the server organizes the collected data and generates action items. These action items are then used as specific work tasks, and assigned personnel are notified as reminders to complete them within a specified timeframe.

[0468] As a concrete example, in a meeting system for logistics operations, an AI model is used to generate improvement suggestions based on past delivery delay data. During the meeting, a speech recognition system transcribes speech in real time, and a server quickly analyzes the data and provides the results to the meeting participants. This process begins when a prompt message is entered stating, "Generate a draft agenda for a new logistics meeting based on recent logistics meetings. Pay particular attention to topics related to delivery efficiency."

[0469] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0470] Step 1:

[0471] The server retrieves meeting plans from the company's scheduling management system. This input data includes the date, time, location, and participant list of the meeting. Based on this information, the server stores a detailed summary of the meeting in its database.

[0472] Step 2:

[0473] The server retrieves past meeting data from MongoDB and generates agenda proposals. This data includes agenda items, participants, and discussion content from past meetings. The server uses a generative AI model (GPT-3) to analyze this data and generate optimized agenda proposals. The output is a list of agenda items to be discussed at the next meeting.

[0474] Step 3:

[0475] The user starts a meeting using their device and records audio data in real time. The device uses the Google Cloud Speech-to-Text API to convert the audio data into text data. The input is the audio data from the meeting, and the output is the transcribed speech.

[0476] Step 4:

[0477] The server receives text data sent from the terminal and performs natural language processing using Google BERT. It extracts important words and phrases in real time and instantly searches the database for information related to those words. The output is either a link to the relevant data or a summary.

[0478] Step 5:

[0479] After the meeting ends, the server analyzes the collected text data and generates action items based on key points and decisions. The output data consists of specific tasks and a list of responsible parties. This allows for the development of a plan for the next steps.

[0480] Step 6:

[0481] The server notifies the user of the action list and sends reminders to each person in charge to complete the action items within the set deadline. The input is a list of action items, and the output is delivered to each person in charge in the form of a notification.

[0482] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0483] This invention is a system for efficiently conducting meetings and optimizing meeting management by taking participants' emotions into consideration. This system is operated by multiple components, including a server, terminals, and an emotion engine.

[0484] The server first retrieves meeting schedules from the company's scheduling management system and collects relevant participant lists. This process prepares the necessary meeting information. Next, the server analyzes past meeting records, automatically extracts topics and issues to be discussed in the new meeting, and provides the user with a draft agenda. Based on the draft agenda suggested by the server, the user sets the meeting objectives and agenda and provides feedback to the server.

[0485] During the meeting, the device uses speech recognition and an emotion engine to analyze participants' statements in real time. The emotion engine detects the participants' emotional state (e.g., positive, negative, neutral) from the tone and content of their statements. This data is sent to a server and used as a reference when adjusting the meeting's progress.

[0486] Based on the analyzed sentiment data, the server presents relevant industry data and past case studies. It also provides necessary data and suggestions in response to comments made during the meeting, helping participants to gain a more balanced perspective.

[0487] After the meeting concludes, the server summarizes the information gathered during the meeting and generates key conclusions and action items. This information is sent to stakeholders via their terminals. Each person responsible for an action item receives a time-limited reminder from the server, allowing them to clearly see the next steps.

[0488] As a concrete example, in a project progress meeting, the emotion engine detects when participants have concerns about a particular agenda item and, based on this, suggests providing additional information or re-evaluating the agenda item. As a result, the efficiency of the meeting and participant satisfaction improve.

[0489] The following describes the processing flow.

[0490] Step 1:

[0491] The server retrieves meeting schedule information from the company's scheduling management system and creates a participant list. It also extracts past meeting data from the database and prepares necessary reference materials for the next meeting.

[0492] Step 2:

[0493] The server analyzes past meeting data, automatically extracts new topics and issues to consider, and generates a draft agenda. This draft agenda is provided to the user, who reviews it and sets the meeting goals and agenda.

[0494] Step 3:

[0495] Based on the proposed agenda provided by the server, users adjust the meeting objectives and provide feedback to the server with the final agenda. The server records this information and updates the meeting plan.

[0496] Step 4:

[0497] During the meeting, the terminal uses speech recognition technology to transcribe spoken content into text in real time and send it to the server. Simultaneously, an emotion engine operates to analyze emotions from the tone and keywords of the speech.

[0498] Step 5:

[0499] The server extracts key keywords based on analyzed sentiment and text data, and searches for relevant industry data and case studies. This information is immediately provided to participants, improving the quality of the meeting.

[0500] Step 6:

[0501] The emotion engine monitors the emotional state of participants, and if negative emotions are detected, the server generates suggestions for how to proceed with the meeting. For example, a short break or a reassessment of the agenda might be considered.

[0502] Step 7:

[0503] After the meeting ends, the server automatically generates a meeting summary and action items based on the collected data. This organizes key conclusions and next steps, which are then distributed to relevant parties via their devices.

[0504] Step 8:

[0505] The device notifies the responsible party of action items and sends reminders with deadlines to facilitate execution. This ensures that meeting results are followed up on.

[0506] (Example 2)

[0507] Next, we will describe Example 2. 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."

[0508] Meetings involve handling a large amount of information, requiring efficient agenda setting and the rapid provision of relevant data while considering participants' emotions and opinions. However, traditional methods struggle to optimize meetings while taking emotional states into account, and post-meeting information organization and clarification of the next steps in activities require considerable time and effort.

[0509] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0510] In this invention, the server includes means for acquiring meeting schedules, means for analyzing past meeting records to generate agenda items, means for transcribing speech during meetings into text using speech recognition technology and detecting participants' emotional states using sentiment analysis technology, means for providing relevant data based on the detected emotional states, and means for summarizing data collected after the meeting and generating conclusions and next action items. This enables efficient meeting progress, visualization of information, and rapid information organization and action plan formulation after the meeting.

[0511] "Means of retrieving meeting schedules" refers to a function that integrates with an internal or external scheduling management system to retrieve information about the date, time, location, and participants of a specific meeting.

[0512] "A means of generating agenda proposals by analyzing past meeting records" refers to a function that retrieves records of past meetings from a database, analyzes them, extracts themes and issues that should be discussed at the next meeting, and proposes them.

[0513] "A method for transcribing speech during a meeting into text using speech recognition technology and detecting participants' emotional states using sentiment analysis technology" refers to a technology that converts participants' speech into text information during a meeting, and further analyzes the content and tone of their speech to understand their emotions.

[0514] "Means for providing relevant data based on detected emotional states" refers to a function that provides appropriate information and suggestions in real time, based on the analysis results of participants' emotional states.

[0515] "A means of summarizing data collected after a meeting and generating conclusions and next action items" refers to a function that organizes the statements and decisions made during the meeting, summarizes the key points, and constructs future steps and responsibilities.

[0516] This invention is a system aimed at efficient meeting management and optimal use of information. The system integrates a server, terminals, and sentiment analysis modules to support the entire process of a meeting.

[0517] The server first integrates with the company's scheduling software to retrieve meeting schedules. Specifically, the server accesses the database from the scheduling management system via an API to retrieve the meeting date, time, location, and participant list. Next, it uses a generative AI model with natural language processing technology to analyze past meeting records. This model extracts important topics from past meeting data and presents the user with proposed agenda items.

[0518] During the meeting, the terminal uses speech recognition software to transcribe speech in real time. This process utilizes existing speech recognition APIs to convert audio data into text data. Furthermore, the terminal uses sentiment analysis technology to determine the emotional state (positive, negative, neutral) of participants based on the content and tone of their speech. This data is sent to the server to facilitate the meeting while considering the nuances of speech.

[0519] Based on the sentiment analysis results, the server presents relevant industry information and past success stories. This information allows participants to engage in discussions from multiple perspectives. After the meeting, the server summarizes all meeting data, generates conclusions and next action steps, and distributes them to participants via their terminals. This step helps ensure that necessary preparations for the next meeting proceed smoothly.

[0520] As a concrete example, during a project progress meeting, the device sends a prompt message to the AI ​​model saying, "Please analyze the emotional state of the participants in real time and suggest ways to optimize the direction of the meeting." Based on this prompt, the generated suggestions are appropriate to the meeting's topic, ultimately promoting more efficient discussion.

[0521] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0522] Step 1:

[0523] The server integrates with the company's scheduling software, retrieving meeting schedules and participant lists via API. It uses data from the scheduling management system as input and outputs meeting dates, times, locations, and participant information. Specifically, it filters the necessary fields from the database and saves them as structured data.

[0524] Step 2:

[0525] The server analyzes past meeting records using natural language processing technology and generates agenda items using a generative AI model. The input is past meeting data, the model analyzes the frequency and importance of topics, and the output is a list of agenda items to be discussed at the next meeting. Specifically, the process involves preprocessing the text data and then having the model extract and prioritize keywords.

[0526] Step 3:

[0527] The terminal acquires audio data from a meeting via speech recognition software and transcribes it into text in real time. The input is the audio of the meeting participants' speeches, and the output is a transcript of the speeches in text format. Specifically, it analyzes the audio data stream, performs accurate text conversion, and immediately sends the result to the server.

[0528] Step 4:

[0529] The terminal analyzes the transcribed speech content using sentiment analysis technology to detect the emotional state of the participants. It uses text data sent from the terminal as input, and the output is an emotional state label (e.g., positive, negative, neutral). Specifically, it quantifies emotions through tone analysis and keyword analysis, and sends the results to the server.

[0530] Step 5:

[0531] Based on the analysis results, the server uses a generating AI model to search for relevant industry data and past case studies, and provides them to participants. Inputs are the sentiment analysis results and real-time comments. The output generates reference data and suggestions. Specifically, it creates database queries based on sentiment data, extracts relevant information, and presents it.

[0532] Step 6:

[0533] After the meeting, the server summarizes all the collected data and generates conclusions and action items. The input is the data accumulated during the meeting, and the output is a summary and action plan. Specifically, it extracts and compiles key information and sends it to the user's terminal as feedback.

[0534] (Application Example 2)

[0535] Next, we will explain application example 2. In the following explanation, 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."

[0536] In today's surveillance and security industry, real-time decision-making and countermeasures are required, but traditional methods have difficulty grasping emotional states, sometimes resulting in inappropriate responses. Therefore, there is a need for a system that can detect emotions more quickly and accurately, and provide information and propose countermeasures based on that detection.

[0537] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0538] In this invention, the server includes means for acquiring meeting schedules, means for analyzing past conversation records to generate agenda items, and means for analyzing acoustic data of conversations to determine emotional states in real time. This enables immediate information provision and countermeasures to be proposed in response to changes in emotions.

[0539] "Method for obtaining meeting schedules" refers to a function that automatically collects pre-set meeting schedule information from business management systems or calendar applications.

[0540] "A means of generating agenda proposals by analyzing past meeting records" refers to a function that analyzes the record data of past meetings and extracts and presents topics and issues that should be addressed in the next meeting.

[0541] "A means of analyzing conversational audio data to determine emotional states in real time" refers to a function that has an algorithm that analyzes participants' voice information in real time and judges their emotions from their tone and content.

[0542] "Means of presenting relevant information based on the determined emotional state" refers to a function that provides information to suggest past cases and immediate countermeasures in response to the results obtained from emotion analysis.

[0543] "A means of generating summaries and action items after a meeting" refers to a function that efficiently summarizes the content discussed during a meeting and extracts and presents action plans that need to be implemented.

[0544] The system for realizing this invention includes a server, a mobile terminal, a voice analysis engine, an emotion determination engine, and a database management system.

[0545] The server first retrieves meeting schedules from the business management system or calendar application. Based on this information, it analyzes past meeting record data, generates a new agenda, and notifies mobile devices. A speech analysis engine (such as Google Speech-to-Text API) transcribes the conversation into text in real time, and this text is passed to an emotion detection engine (such as Amazon Comprehend) to determine the emotional state of the participants during the meeting.

[0546] The device sends the determined emotion information to the server. Based on this information, the server provides the user with information including relevant case data and immediate countermeasures. For example, if tension is increasing regarding a particular issue, past data is used to suggest directions for discussion that can help alleviate tension.

[0547] Furthermore, at the end of the meeting, the server compiles a summary of the statements and sentiment analysis results, extracts action items, and presents them to the user. Reminders can be sent for these action items with a set deadline.

[0548] As a concrete example, in the security response for a large-scale event, if on-site staff use smartphones for voice input and analysis detects potential anxiety among participants, the server will suggest appropriate relocation to maintain a stable situation. As a result, the event is expected to proceed smoothly.

[0549] An example of a prompt is as follows: "In crowd management at a large-scale event, we used speech recognition and sentiment analysis to detect tension and anxiety. Please refer to past data and advise on appropriate crowd control measures and ways to prevent disruption."

[0550] In this way, it becomes possible to provide real-time support for appropriate decision-making.

[0551] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0552] Step 1:

[0553] The server retrieves meeting schedule information as input from the business management system or calendar application. This makes basic data about the next meeting available. This information is registered in the database and used in subsequent processing.

[0554] Step 2:

[0555] The server extracts past meeting records from a database and analyzes them as input. Using natural language processing technology, it automatically extracts keywords and topics that should be included in the agenda and outputs them to the user as a draft agenda. In this process, important topics are identified, and the user proceeds with meeting preparations based on this information.

[0556] Step 3:

[0557] The device receives audio data collected during the meeting as input and converts the speech to text using a speech recognition API (e.g., Google Speech-to-Text). This text data is sent in real time to an emotion determination engine (e.g., Amazon Comprehend) which analyzes and outputs the emotional state from the utterances. The analysis results are used to understand the emotional background of the speaker.

[0558] Step 4:

[0559] The server takes the sentiment analysis results received from the terminal as input, compares them with relevant information in the database, and generates appropriate information and examples based on the determined sentiment as output. This information helps users make appropriate decisions during meetings. At the same time, it supports the smooth progress of meetings by presenting relevant materials and suggestions.

[0560] Step 5:

[0561] After the meeting ends, the server integrates the meeting's content and sentiment data as input to generate a summary and action items. These results are then sent to the user as output. This process identifies key discussion points and actions to be taken during the meeting, providing detailed information to support the execution of the next steps.

[0562] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0563] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0564] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0565] [Fourth Embodiment]

[0566] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0567] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0568] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0569] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0570] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0571] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0572] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0573] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0574] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0575] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0576] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0577] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0578] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0579] This invention is a system for efficiently conducting and managing corporate meetings, and the software program for implementing this system runs on a server and terminals.

[0580] The server first extracts meeting schedules from the company's internal scheduling system and collects participant information. This prepares the server to provide relevant information to stakeholders before the meeting begins. Next, it analyzes records of similar past meetings and uses that data to generate potential topics for discussion in the new meeting.

[0581] Once preparations are complete, the user (the meeting organizer) reviews the draft agenda generated by the server and makes any necessary revisions or additions. As a result, an optimized agenda is established, and specific goals for the meeting are set.

[0582] During the meeting, the terminal uses speech recognition technology to convert participants' speech into text in real time and sends that data to the server. Based on this information, the server extracts important keywords and immediately analyzes and provides relevant industry data and past case studies. This enables meeting participants to make more informed decisions.

[0583] After the meeting ends, the server organizes the collected data and generates a summary of the content and a list of action items. This information is distributed to relevant parties via terminals, and those responsible for each action item receive a time-limited reminder. For example, in a project progress meeting, specific actions such as reviewing sales targets for the next quarter and risk mitigation measures are listed, enabling efficient follow-up.

[0584] This system automates and streamlines the entire process, from meeting preparation to post-meeting follow-up, supporting meeting management based on objective data.

[0585] The following describes the processing flow.

[0586] Step 1:

[0587] The server retrieves meeting schedules from the company's scheduling management system and collects participant lists. It also extracts relevant past meeting data from the database.

[0588] Step 2:

[0589] The server analyzes past meeting data to extract topics and issues that should be discussed in the next meeting, and generates a draft agenda. This forms the basis for proposing it to the user.

[0590] Step 3:

[0591] Users review the proposed agenda, adjust the meeting objectives and specific agenda as needed, and provide feedback to the server. The server then incorporates this information to finalize the agenda.

[0592] Step 4:

[0593] The terminal converts the audio from the meeting into text data in real time and sends it to the server. This process allows for the recording of what is said during the meeting.

[0594] Step 5:

[0595] The server analyzes the received text data and extracts key keywords. Furthermore, it searches for relevant external data and industry case studies and presents them to the participants.

[0596] Step 6:

[0597] After the meeting ends, the server generates a summary and action items based on the data collected during the meeting. This helps organize the meeting's results and clarify the next steps.

[0598] Step 7:

[0599] The device distributes the generated summary and action items to the assigned person. It also sends time-limited reminders for the action items to prompt the person to complete the task.

[0600] (Example 1)

[0601] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0602] In today's business environment, meetings are crucial for important decisions, yet they are often inefficient and unproductive. This is due to insufficient preparation, poor information management during meetings, and delayed follow-up. As a result, valuable participant time is wasted, and the quality of decision-making suffers. Therefore, it is essential to streamline the meeting preparation, execution, and follow-up processes throughout the entire system, supporting participants in making meaningful contributions.

[0603] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0604] In this invention, the server includes means for extracting scheduled information, means for analyzing past information to generate agenda candidates, and means for converting audio information into text in real time. This streamlines the process from meeting preparation to progress and follow-up, enabling participants to make more informed decisions more quickly.

[0605] "Methods for extracting schedule information" refers to a function that retrieves meeting and related event schedule information from a company's internal data management system and processes it to make the necessary schedule data available within the system.

[0606] "Methods for generating agenda candidates by analyzing past information" refers to a function that analyzes records and data from similar meetings held in the past to suggest topics and themes that should be discussed at the next meeting.

[0607] "A means of converting audio information to text in real time" refers to a function that instantly converts participants' speech during a meeting into text information using speech recognition technology, and makes that text information available for use within the system.

[0608] "Methods for extracting important elements from transcribed information" refers to a function that automatically identifies important keywords and phrases from the transcribed audio content of a meeting's decision-making and discussions, and separates them as necessary information.

[0609] "Means of presenting relevant information based on extracted key elements" refers to a function that quickly references relevant management information, case studies, and historical data based on extracted keywords and phrases, and presents necessary materials and data to meeting participants.

[0610] "A means of generating summaries and work items after a meeting" refers to a function that summarizes the content discussed in a meeting, compiles it into a concrete list of future action plans and tasks to be addressed, and provides it to meeting participants and relevant departments.

[0611] "Setting meeting objectives and optimizing the plan based on them" refers to a function that involves establishing specific goals to achieve the meeting's objectives and refining the agenda and meeting proceedings in line with those goals.

[0612] "A means of sending time-sensitive notifications to those responsible for work items" refers to a function that designates a person responsible for each work item decided at a meeting and notifies the designated person of important reminders such as submission deadlines.

[0613] To implement this invention, a system is required in which a server and terminals play crucial roles. The server first extracts meeting schedule information from a schedule management system, using the Google Calendar API or Microsoft Graph API. The server then analyzes a database of past meeting records and extracts important information using natural language processing techniques. This allows for the automatic generation of potential agenda items for the next meeting. For this analysis, a machine learning model using TensorFlow, for example, could be implemented.

[0614] The user, acting as the meeting organizer, reviews the server-generated agenda draft on a dedicated management screen and makes modifications or additions as needed. This management screen is provided as a web application and built using React or Angular. Through this screen, users can optimize the agenda draft and plan the meeting according to its objectives.

[0615] During the meeting, the terminal uses speech recognition technology to transcribe participants' speech in real time. This process utilizes Google Speech-to-Text and Amazon Transcribe. The terminal sends the obtained text data to a server, which extracts keywords and immediately analyzes and presents relevant information. This enables meeting participants to make quick decisions.

[0616] After the meeting ends, the server organizes all transcripts, including data obtained through speech recognition, and uses natural language generation technology to generate a meeting summary and action items. This information is then distributed to users via communication tools such as Microsoft Teams and Slack. Furthermore, integration with to-do list apps sends reminder notifications for tasks to those responsible.

[0617] As a concrete example, in a project progress meeting, specific action items such as reviewing sales targets and risk mitigation measures for the next quarter are listed. This allows meeting participants to clearly understand what needs to be done next and to quickly take necessary follow-up actions.

[0618] Generative AI models use prompt statements like the following:

[0619] "Please extract key topics from past meeting records to generate discussion points for the next meeting."

[0620] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0621] Step 1:

[0622] The server connects to the company's scheduling management system via API to extract meeting schedules and participant information. The input is raw schedule data retrieved from the scheduling management system, which is then formatted and stored in the required format. The output is provided as a dataset containing meeting dates, times, locations, and participant lists. Specifically, it sends API requests, parses the responses, and stores them in the database.

[0623] Step 2:

[0624] The server retrieves past meeting records from the database and analyzes them. The input is past meeting records, and important themes and topics are extracted using natural language processing techniques. Text mining is performed as data processing, and potential agenda items for the next meeting are generated as output. Specifically, a machine learning model is used to extract frequently occurring keywords from past statements and meeting minutes.

[0625] Step 3:

[0626] The user, the meeting organizer, reviews the draft agenda generated through the server's management screen and makes revisions as needed. The input is the draft agenda provided by the server. The output is saved as the revised, final draft agenda. Specifically, the user edits the draft agenda through a web browser interface and sends it to the server.

[0627] Step 4:

[0628] During the meeting, the terminal uses a microphone to capture participants' voices and converts them to text in real time using speech recognition software. The input is the voice data of the participants during the meeting. As data processing, the voice is converted to text, and the text data is sent to the server as output. Specifically, the speech recognition API is used to transcribe the speech, and the results are relayed to the server.

[0629] Step 5:

[0630] The server analyzes the received text data, extracts keywords, and presents relevant information. The input is text data sent from a terminal. Data processing involves text analysis, and the output generates information useful to meeting participants. Specifically, it uses a search algorithm to query internal and external databases and provides relevant information immediately.

[0631] Step 6:

[0632] After the meeting ends, the server organizes all the collected data and generates a summary and action items. The input is all the text data collected during the meeting. As a data calculation, it categorizes and summarizes the information, and as output, it generates a summary report and an action list. Specifically, it uses a natural language generation tool to summarize the key points of the meeting and list the next steps.

[0633] Step 7:

[0634] The server distributes the generated summary and action items to users via communication tools and sets reminders for responsible parties. The input is the generated summary and action list. The output is a notification message containing that information. Specifically, it uses an API to send information via Slack or email systems and adds items to to-do lists with deadlines.

[0635] (Application Example 1)

[0636] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0637] Logistics meetings require efficient agenda setting using historical data and rapid information sharing during meetings. However, current systems make these processes manual and time-consuming, making efficient management difficult. In particular, the lack of automated generation of improvement suggestions based on historical logistics delay data hinders rapid decision-making.

[0638] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0639] In this invention, the server includes means for acquiring meeting plans, means for analyzing past meeting data to generate agenda proposals, and means for analyzing statements made during meetings and extracting important keywords. This streamlines meetings in logistics operations, enables the automatic generation of improvement proposals based on past data, and allows for the rapid provision of information.

[0640] "Meeting plan" refers to the details set out in advance for holding a meeting, including the date, time, location, purpose, and participant list.

[0641] "Past meeting data" refers to records of agenda items, participants' comments, and decisions made in meetings held to date.

[0642] A "proposal for agenda items" is a list of topics or themes to be discussed at a meeting, generated based on past data and current needs.

[0643] "Key terms" are keywords or phrases mentioned during a meeting that are deemed to have an impact on achieving the meeting's objectives or influencing decisions made.

[0644] "Related information based on extracted information" refers to additional data and examples provided by the server after analyzing the terms discussed during the meeting.

[0645] "Action items" are a list of specific tasks and actions that have been clarified as a result of the meeting and that should be carried out.

[0646] A "generative AI model" is a program that uses artificial intelligence technology to perform data analysis and text generation, automatically generating new ideas and proposals.

[0647] "Logistics operations" refer to the entire operation within the supply chain, including processes such as the transportation, storage, inventory management, and delivery of goods.

[0648] To implement this invention, the following system is required. First, the server retrieves the meeting plan and analyzes past meeting data. This includes extracting meeting details from the company's scheduling management system and reading relevant records from the database. A database such as MongoDB is used to manage and retrieve the necessary information.

[0649] Next, a generative AI model is used to generate agenda proposals based on historical data and current business needs. The generative AI model employs natural language processing techniques such as GPT-3 to generate optimized agendas for new meetings. During the meeting, the terminal uses the Google Cloud Speech-to-Text API to convert speech to text and sends this data to the server in real time. The server analyzes this text information using natural language processing techniques such as BERT to extract important keywords.

[0650] Based on the extracted information, the server immediately presents relevant information, including data from external sources and past case studies. After the meeting, the server organizes the collected data and generates action items. These action items are then used as specific work tasks, and assigned personnel are notified as reminders to complete them within a specified timeframe.

[0651] As a concrete example, in a meeting system for logistics operations, an AI model is used to generate improvement suggestions based on past delivery delay data. During the meeting, a speech recognition system transcribes speech in real time, and a server quickly analyzes the data and provides the results to the meeting participants. This process begins when a prompt message is entered stating, "Generate a draft agenda for a new logistics meeting based on recent logistics meetings. Pay particular attention to topics related to delivery efficiency."

[0652] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0653] Step 1:

[0654] The server retrieves meeting plans from the company's scheduling management system. This input data includes the date, time, location, and participant list of the meeting. Based on this information, the server stores a detailed summary of the meeting in its database.

[0655] Step 2:

[0656] The server retrieves past meeting data from MongoDB and generates agenda proposals. This data includes agenda items, participants, and discussion content from past meetings. The server uses a generative AI model (GPT-3) to analyze this data and generate optimized agenda proposals. The output is a list of agenda items to be discussed at the next meeting.

[0657] Step 3:

[0658] The user starts a meeting using their device and records audio data in real time. The device uses the Google Cloud Speech-to-Text API to convert the audio data into text data. The input is the audio data from the meeting, and the output is the transcribed speech.

[0659] Step 4:

[0660] The server receives text data sent from the terminal and performs natural language processing using Google BERT. It extracts important words and phrases in real time and instantly searches the database for information related to those words. The output is either a link to the relevant data or a summary.

[0661] Step 5:

[0662] After the meeting ends, the server analyzes the collected text data and generates action items based on key points and decisions. The output data consists of specific tasks and a list of responsible parties. This allows for the development of a plan for the next steps.

[0663] Step 6:

[0664] The server notifies the user of the action list and sends reminders to each person in charge to complete the action items within the set deadline. The input is a list of action items, and the output is delivered to each person in charge in the form of a notification.

[0665] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0666] This invention is a system for efficiently conducting meetings and optimizing meeting management by taking participants' emotions into consideration. This system is operated by multiple components, including a server, terminals, and an emotion engine.

[0667] The server first retrieves meeting schedules from the company's scheduling management system and collects relevant participant lists. This process prepares the necessary meeting information. Next, the server analyzes past meeting records, automatically extracts topics and issues to be discussed in the new meeting, and provides the user with a draft agenda. Based on the draft agenda suggested by the server, the user sets the meeting objectives and agenda and provides feedback to the server.

[0668] During the meeting, the device uses speech recognition and an emotion engine to analyze participants' statements in real time. The emotion engine detects the participants' emotional state (e.g., positive, negative, neutral) from the tone and content of their statements. This data is sent to a server and used as a reference when adjusting the meeting's progress.

[0669] Based on the analyzed sentiment data, the server presents relevant industry data and past case studies. It also provides necessary data and suggestions in response to comments made during the meeting, helping participants to gain a more balanced perspective.

[0670] After the meeting concludes, the server summarizes the information gathered during the meeting and generates key conclusions and action items. This information is sent to stakeholders via their terminals. Each person responsible for an action item receives a time-limited reminder from the server, allowing them to clearly see the next steps.

[0671] As a concrete example, in a project progress meeting, the emotion engine detects when participants have concerns about a particular agenda item and, based on this, suggests providing additional information or re-evaluating the agenda item. As a result, the efficiency of the meeting and participant satisfaction improve.

[0672] The following describes the processing flow.

[0673] Step 1:

[0674] The server retrieves meeting schedule information from the company's scheduling management system and creates a participant list. It also extracts past meeting data from the database and prepares necessary reference materials for the next meeting.

[0675] Step 2:

[0676] The server analyzes past meeting data, automatically extracts new topics and issues to consider, and generates a draft agenda. This draft agenda is provided to the user, who reviews it and sets the meeting goals and agenda.

[0677] Step 3:

[0678] Based on the proposed agenda provided by the server, users adjust the meeting objectives and provide feedback to the server with the final agenda. The server records this information and updates the meeting plan.

[0679] Step 4:

[0680] During the meeting, the terminal uses speech recognition technology to transcribe spoken content into text in real time and send it to the server. Simultaneously, an emotion engine operates to analyze emotions from the tone and keywords of the speech.

[0681] Step 5:

[0682] The server extracts key keywords based on analyzed sentiment and text data, and searches for relevant industry data and case studies. This information is immediately provided to participants, improving the quality of the meeting.

[0683] Step 6:

[0684] The emotion engine monitors the emotional state of participants, and if negative emotions are detected, the server generates suggestions for how to proceed with the meeting. For example, a short break or a reassessment of the agenda might be considered.

[0685] Step 7:

[0686] After the meeting ends, the server automatically generates a meeting summary and action items based on the collected data. This organizes key conclusions and next steps, which are then distributed to relevant parties via their devices.

[0687] Step 8:

[0688] The device notifies the responsible party of action items and sends reminders with deadlines to facilitate execution. This ensures that meeting results are followed up on.

[0689] (Example 2)

[0690] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0691] Meetings involve handling a large amount of information, requiring efficient agenda setting and the rapid provision of relevant data while considering participants' emotions and opinions. However, traditional methods struggle to optimize meetings while taking emotional states into account, and post-meeting information organization and clarification of the next steps in activities require considerable time and effort.

[0692] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0693] In this invention, the server includes means for acquiring meeting schedules, means for analyzing past meeting records to generate agenda items, means for transcribing speech during meetings into text using speech recognition technology and detecting participants' emotional states using sentiment analysis technology, means for providing relevant data based on the detected emotional states, and means for summarizing data collected after the meeting and generating conclusions and next action items. This enables efficient meeting progress, visualization of information, and rapid information organization and action plan formulation after the meeting.

[0694] "Means of retrieving meeting schedules" refers to a function that integrates with an internal or external scheduling management system to retrieve information about the date, time, location, and participants of a specific meeting.

[0695] "A means of generating agenda proposals by analyzing past meeting records" refers to a function that retrieves records of past meetings from a database, analyzes them, extracts themes and issues that should be discussed at the next meeting, and proposes them.

[0696] "A method for transcribing speech during a meeting into text using speech recognition technology and detecting participants' emotional states using sentiment analysis technology" refers to a technology that converts participants' speech into text information during a meeting, and further analyzes the content and tone of their speech to understand their emotions.

[0697] "Means for providing relevant data based on detected emotional states" refers to a function that provides appropriate information and suggestions in real time, based on the analysis results of participants' emotional states.

[0698] "A means of summarizing data collected after a meeting and generating conclusions and next action items" refers to a function that organizes the statements and decisions made during the meeting, summarizes the key points, and constructs future steps and responsibilities.

[0699] This invention is a system aimed at efficient meeting management and optimal use of information. The system integrates a server, terminals, and sentiment analysis modules to support the entire process of a meeting.

[0700] The server first integrates with the company's scheduling software to retrieve meeting schedules. Specifically, the server accesses the database from the scheduling management system via an API to retrieve the meeting date, time, location, and participant list. Next, it uses a generative AI model with natural language processing technology to analyze past meeting records. This model extracts important topics from past meeting data and presents the user with proposed agenda items.

[0701] During the meeting, the terminal uses speech recognition software to transcribe speech in real time. This process utilizes existing speech recognition APIs to convert audio data into text data. Furthermore, the terminal uses sentiment analysis technology to determine the emotional state (positive, negative, neutral) of participants based on the content and tone of their speech. This data is sent to the server to facilitate the meeting while considering the nuances of speech.

[0702] Based on the sentiment analysis results, the server presents relevant industry information and past success stories. This information allows participants to engage in discussions from multiple perspectives. After the meeting, the server summarizes all meeting data, generates conclusions and next action steps, and distributes them to participants via their terminals. This step helps ensure that necessary preparations for the next meeting proceed smoothly.

[0703] As a concrete example, during a project progress meeting, the device sends a prompt message to the AI ​​model saying, "Please analyze the emotional state of the participants in real time and suggest ways to optimize the direction of the meeting." Based on this prompt, the generated suggestions are appropriate to the meeting's topic, ultimately promoting more efficient discussion.

[0704] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0705] Step 1:

[0706] The server integrates with the company's scheduling software, retrieving meeting schedules and participant lists via API. It uses data from the scheduling management system as input and outputs meeting dates, times, locations, and participant information. Specifically, it filters the necessary fields from the database and saves them as structured data.

[0707] Step 2:

[0708] The server analyzes past meeting records using natural language processing technology and generates agenda items using a generative AI model. The input is past meeting data, the model analyzes the frequency and importance of topics, and the output is a list of agenda items to be discussed at the next meeting. Specifically, the process involves preprocessing the text data and then having the model extract and prioritize keywords.

[0709] Step 3:

[0710] The terminal acquires audio data from a meeting via speech recognition software and transcribes it into text in real time. The input is the audio of the meeting participants' speeches, and the output is a transcript of the speeches in text format. Specifically, it analyzes the audio data stream, performs accurate text conversion, and immediately sends the result to the server.

[0711] Step 4:

[0712] The terminal analyzes the transcribed speech content using sentiment analysis technology to detect the emotional state of the participants. It uses text data sent from the terminal as input, and the output is an emotional state label (e.g., positive, negative, neutral). Specifically, it quantifies emotions through tone analysis and keyword analysis, and sends the results to the server.

[0713] Step 5:

[0714] Based on the analysis results, the server uses a generating AI model to search for relevant industry data and past case studies, and provides them to participants. Inputs are the sentiment analysis results and real-time comments. The output generates reference data and suggestions. Specifically, it creates database queries based on sentiment data, extracts relevant information, and presents it.

[0715] Step 6:

[0716] After the meeting, the server summarizes all the collected data and generates conclusions and action items. The input is the data accumulated during the meeting, and the output is a summary and action plan. Specifically, it extracts and compiles key information and sends it to the user's terminal as feedback.

[0717] (Application Example 2)

[0718] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0719] In today's surveillance and security industry, real-time decision-making and countermeasures are required, but traditional methods have difficulty grasping emotional states, sometimes resulting in inappropriate responses. Therefore, there is a need for a system that can detect emotions more quickly and accurately, and provide information and propose countermeasures based on that detection.

[0720] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0721] In this invention, the server includes means for acquiring meeting schedules, means for analyzing past conversation records to generate agenda items, and means for analyzing acoustic data of conversations to determine emotional states in real time. This enables immediate information provision and countermeasures to be proposed in response to changes in emotions.

[0722] "Method for obtaining meeting schedules" refers to a function that automatically collects pre-set meeting schedule information from business management systems or calendar applications.

[0723] "A means of generating agenda proposals by analyzing past meeting records" refers to a function that analyzes the record data of past meetings and extracts and presents topics and issues that should be addressed in the next meeting.

[0724] "A means of analyzing conversational audio data to determine emotional states in real time" refers to a function that has an algorithm that analyzes participants' voice information in real time and judges their emotions from their tone and content.

[0725] "Means of presenting relevant information based on the determined emotional state" refers to a function that provides information to suggest past cases and immediate countermeasures in response to the results obtained from emotion analysis.

[0726] "A means of generating summaries and action items after a meeting" refers to a function that efficiently summarizes the content discussed during a meeting and extracts and presents action plans that need to be implemented.

[0727] The system for realizing this invention includes a server, a mobile terminal, a voice analysis engine, an emotion determination engine, and a database management system.

[0728] The server first retrieves meeting schedules from the business management system or calendar application. Based on this information, it analyzes past meeting record data, generates a new agenda, and notifies mobile devices. A speech analysis engine (such as Google Speech-to-Text API) transcribes the conversation into text in real time, and this text is passed to an emotion detection engine (such as Amazon Comprehend) to determine the emotional state of the participants during the meeting.

[0729] The device sends the determined emotion information to the server. Based on this information, the server provides the user with information including relevant case data and immediate countermeasures. For example, if tension is increasing regarding a particular issue, past data is used to suggest directions for discussion that can help alleviate tension.

[0730] Furthermore, at the end of the meeting, the server compiles a summary of the statements and sentiment analysis results, extracts action items, and presents them to the user. Reminders can be sent for these action items with a set deadline.

[0731] As a concrete example, in the security response for a large-scale event, if on-site staff use smartphones for voice input and analysis detects potential anxiety among participants, the server will suggest appropriate relocation to maintain a stable situation. As a result, the event is expected to proceed smoothly.

[0732] An example of a prompt is as follows: "In crowd management at a large-scale event, we used speech recognition and sentiment analysis to detect tension and anxiety. Please refer to past data and advise on appropriate crowd control measures and ways to prevent disruption."

[0733] In this way, it becomes possible to provide real-time support for appropriate decision-making.

[0734] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0735] Step 1:

[0736] The server retrieves meeting schedule information as input from the business management system or calendar application. This makes basic data about the next meeting available. This information is registered in the database and used in subsequent processing.

[0737] Step 2:

[0738] The server extracts past meeting records from a database and analyzes them as input. Using natural language processing technology, it automatically extracts keywords and topics that should be included in the agenda and outputs them to the user as a draft agenda. In this process, important topics are identified, and the user proceeds with meeting preparations based on this information.

[0739] Step 3:

[0740] The device receives audio data collected during the meeting as input and converts the speech to text using a speech recognition API (e.g., Google Speech-to-Text). This text data is sent in real time to an emotion determination engine (e.g., Amazon Comprehend) which analyzes and outputs the emotional state from the utterances. The analysis results are used to understand the emotional background of the speaker.

[0741] Step 4:

[0742] The server takes the sentiment analysis results received from the terminal as input, compares them with relevant information in the database, and generates appropriate information and examples based on the determined sentiment as output. This information helps users make appropriate decisions during meetings. At the same time, it supports the smooth progress of meetings by presenting relevant materials and suggestions.

[0743] Step 5:

[0744] After the meeting ends, the server integrates the meeting's content and sentiment data as input to generate a summary and action items. These results are then sent to the user as output. This process identifies key discussion points and actions to be taken during the meeting, providing detailed information to support the execution of the next steps.

[0745] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0746] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0747] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0748] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0749] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0750] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0751] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0752] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0753] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0754] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0755] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0756] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0757] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0758] 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.

[0759] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0760] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0761] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0762] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0763] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0764] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0765] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0766] The following is further disclosed regarding the embodiments described above.

[0767] (Claim 1)

[0768] Means of obtaining meeting schedules,

[0769] A means of generating agenda items by analyzing past meeting records,

[0770] A method for analyzing statements made during a meeting and extracting important keywords,

[0771] A means of presenting relevant data based on the extracted information,

[0772] A system that includes means for generating summaries and action items after a meeting.

[0773] (Claim 2)

[0774] The system according to claim 1, comprising means for setting the objectives of a meeting and optimizing the agenda based thereon.

[0775] (Claim 3)

[0776] The system according to claim 1, comprising means for sending a time-limited implementation reminder to the person in charge of an action item.

[0777] "Example 1"

[0778] (Claim 1)

[0779] A means of extracting schedule information,

[0780] A means of generating agenda items by analyzing past information,

[0781] A means of converting audio information to text in real time,

[0782] A means of extracting important elements from textual information,

[0783] A means of presenting relevant information based on the extracted key elements,

[0784] A system that includes a means for generating summaries and work items after a meeting.

[0785] (Claim 2)

[0786] The system according to claim 1, comprising means for setting meeting objectives and optimizing the plan based thereon.

[0787] (Claim 3)

[0788] The system according to claim 1, comprising means for sending a time-limited notification to the person responsible for a work item.

[0789] "Application Example 1"

[0790] (Claim 1)

[0791] Means of obtaining the meeting plan,

[0792] A method for generating agenda proposals by analyzing past meeting data,

[0793] A method for analyzing statements made during a meeting and extracting important words and phrases,

[0794] A means of presenting relevant information based on the extracted information,

[0795] A means of generating summaries and action items after a meeting,

[0796] A means of presenting results using a generative AI model that processes information based on a planned agenda,

[0797] To improve the efficiency of meetings in logistics operations, a method is needed to analyze past delay data and create improvement plans.

[0798] A system that includes this.

[0799] (Claim 2)

[0800] The system according to claim 1, comprising means for creating an optimized plan based on the purpose of a meeting using a generative AI model.

[0801] (Claim 3)

[0802] The system according to claim 1, comprising means for sending a notice of implementation with a limited period to the person responsible for the action item.

[0803] "Example 2 of combining an emotion engine"

[0804] (Claim 1)

[0805] Means of obtaining meeting schedules,

[0806] A means of generating agenda items by analyzing past meeting records,

[0807] A method for transcribing speech during a meeting into text using speech recognition technology and detecting the emotional state of participants using sentiment analysis technology,

[0808] A means of providing relevant data based on the detected emotional state,

[0809] A system that includes means for summarizing data collected after a meeting and generating conclusions and subsequent action items.

[0810] (Claim 2)

[0811] The system according to claim 1, comprising means for setting the objectives of a meeting and optimizing the agenda based thereon.

[0812] (Claim 3)

[0813] The system according to claim 1, comprising means for sending a time-limited reminder to the person who will carry out the action item.

[0814] "Application example 2 when combining with an emotional engine"

[0815] (Claim 1)

[0816] Means of obtaining meeting schedules,

[0817] A means of generating agenda items by analyzing past meeting records,

[0818] A method for analyzing conversational audio data to determine emotional states in real time,

[0819] A means of presenting relevant information based on the determined emotional state,

[0820] A system that includes means for generating summaries and action items after a meeting.

[0821] (Claim 2)

[0822] The system according to claim 1, comprising means for setting the objectives of a meeting and optimizing the schedule based thereon.

[0823] (Claim 3)

[0824] The system according to claim 1, further comprising means for sending a time-limited implementation notice to the person in charge of an action item. [Explanation of Symbols]

[0825] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of obtaining meeting schedules, A means of generating agenda items by analyzing past meeting records, A method for analyzing statements made during a meeting and extracting important keywords, A means of presenting relevant data based on the extracted information, A system that includes means for generating summaries and action items after a meeting.

2. The system according to claim 1, comprising means for setting the objectives of a meeting and optimizing the agenda based thereon.

3. The system according to claim 1, further comprising means for sending a time-limited implementation reminder to the person in charge of an action item.

Images