system

Abstract

The system according to this embodiment aims to detect casual conversation and deviations from the agenda during meetings, thereby promoting efficient meeting progress. [Solution] The system according to the embodiment comprises a casual conversation detection unit, a display unit, a progress monitoring unit, a real-time monitoring unit, and a progress support unit. The casual conversation detection unit analyzes audio data during the meeting in real time and detects casual conversation. The display unit displays a summary of the meeting minutes based on the casual conversation detected by the casual conversation detection unit. The progress monitoring unit constantly monitors the meeting time, agenda, and meeting goals, and prompts progress with audio and text when there is a stagnation. The real-time monitoring unit analyzes audio data during the meeting and detects deviations from the agenda. The progress support unit prompts the progress of the meeting based on the deviations from the agenda detected by the real-time monitoring unit.

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, which is performed by at least one processor and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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] In the prior art, there is a problem that the productivity decreases due to small talk during a meeting or deviation from the topic, and it is difficult to conduct an efficient meeting.

[0005] The system according to the embodiment aims to detect small talk during a meeting or deviation from the topic and promote an efficient meeting progress.

Means for Solving the Problems

[0006] The system according to this embodiment includes a casual conversation detection unit, a display unit, a progress monitoring unit, a real-time monitoring unit, and a progress support unit. The casual conversation detection unit analyzes audio data during the meeting in real time and detects casual conversation. The display unit displays a summary of the meeting minutes based on the casual conversation detected by the casual conversation detection unit. The progress monitoring unit constantly monitors the meeting time, agenda, and meeting goals, and prompts progress with audio and text when the meeting stalls. The real-time monitoring unit analyzes audio data during the meeting and detects deviations from the agenda. The progress support unit prompts the progress of the meeting based on the deviations from the agenda detected by the real-time monitoring unit. [Effects of the Invention]

[0007] The system according to this embodiment can detect casual conversation and deviations from the agenda during a meeting, thereby promoting efficient meeting progress. [Brief explanation of the drawing]

[0008] [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. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the signed communication I / F (Interface) is an interface including a communication processor, an antenna, etc. The communication I / F manages communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] 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 only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 comprises a computer 36, a receiving 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 receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice 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 unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (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.

[0022] 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.

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

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

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

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

[0028] (Example of form 1) The AI ​​agent system for facilitating meetings according to an embodiment of the present invention is a system for solving meeting-related challenges faced by companies and organizations. This system creates an environment in which both in-person and online participants can efficiently participate in meetings. The AI ​​agent system for facilitating meetings is equipped with a casual conversation detection function, and if casual conversation escalates during a meeting, it automatically displays a summary of the minutes on a whiteboard or online meeting tool and navigates the meeting towards its goal. For example, if the topic deviates during a meeting, the AI ​​agent detects this and displays a summary of the minutes to encourage the meeting to proceed. Next, it is equipped with a progress monitoring function, constantly keeping track of meeting time, agenda, and meeting goals, and prompting progress with voice and text when the meeting stalls. For example, if the meeting is running behind schedule, the AI ​​agent prompts progress with voice alerts and text messages to improve meeting efficiency. Furthermore, it is equipped with a real-time monitoring function, detecting casual conversation and deviations from the agenda through audio analysis during the meeting. For example, if the topic deviates during a meeting, the AI ​​agent detects this in real time and takes appropriate action. Furthermore, it features a meeting summary display function, showing meeting minutes and progress on a whiteboard or online tool. For example, displaying the meeting progress in real time makes it easier for all participants to understand the current status. Finally, it has a progress support function, prompting progress with audio alerts and text messages when the meeting progress stalls, leading to a more productive meeting. For example, if the meeting is stalled, the AI ​​agent prompts progress with audio alerts and text messages to improve meeting efficiency. In this way, the AI ​​agent system that facilitates meetings can improve meeting efficiency and productivity, creating an environment where each employee can generate creative ideas. This will further promote work style reform and aim to achieve employee satisfaction, happiness, and corporate growth simultaneously. Thus, the AI ​​agent system that facilitates meetings can improve meeting efficiency and productivity.

[0029] The AI ​​agent system for facilitating a meeting according to this embodiment comprises a casual conversation detection unit, a display unit, a progress monitoring unit, a real-time monitoring unit, and a progress support unit. The casual conversation detection unit analyzes audio data during the meeting in real time and detects casual conversation. The casual conversation detection unit analyzes audio data during the meeting using, for example, speech recognition technology to distinguish between casual conversation and statements related to the agenda. The casual conversation detection unit can also detect casual conversation using keyword matching or contextual analysis. Furthermore, the casual conversation detection unit can learn the speaking patterns of meeting participants to improve the accuracy of casual conversation detection. For example, the casual conversation detection unit learns past meeting data to more accurately distinguish between casual conversation and statements related to the agenda. The display unit displays a meeting summary based on the casual conversation detected by the casual conversation detection unit. The display unit displays the meeting summary on, for example, a whiteboard or an online meeting tool. The display unit can also display the progress of the meeting in real time. Furthermore, the display unit can estimate the emotions of meeting participants and adjust the display method of the meeting summary based on the estimated emotions. For example, the display unit shows a detailed meeting summary when meeting participants are relaxed, and a concise summary when they are tense. The progress monitoring unit constantly monitors the meeting time, agenda, and goals, and prompts progress with voice and text when stalls occur. The progress monitoring unit can, for example, pre-set the meeting agenda and goals and monitor the progress in real time. It can also estimate the emotions of meeting participants and adjust the monitoring method based on the estimated emotions. For example, it can monitor the progress more loosely when meeting participants are relaxed and more strictly when they are tense. The real-time monitoring unit analyzes audio data during the meeting to detect deviations from the agenda. For example, it can use speech recognition technology to analyze audio data during the meeting and detect statements unrelated to the agenda. It can also learn the speech patterns of meeting participants to more accurately detect deviations from the agenda. Furthermore, the real-time monitoring unit can estimate the emotions of meeting participants and adjust the accuracy of agenda deviation detection based on the estimated emotions.For example, the real-time monitoring unit sets a lower accuracy for detecting deviations from the agenda when meeting participants are relaxed, and a higher accuracy when they are tense. The progress support unit guides the meeting based on the deviations from the agenda detected by the real-time monitoring unit. The progress support unit guides the meeting using, for example, voice alerts or text messages. The progress support unit can also estimate the emotions of meeting participants and adjust its progress support methods based on the estimated emotions. For example, the progress support unit provides gentle progress support when meeting participants are relaxed, and provides quick and clear progress support when they are tense. As a result, the AI ​​agent system facilitating meetings according to this embodiment can achieve increased meeting efficiency and productivity.

[0030] The casual conversation detection unit analyzes audio data during meetings in real time to detect casual conversation. For example, it uses speech recognition technology to analyze the audio data during meetings and distinguish between casual conversation and statements related to the agenda. Specifically, speech recognition technology converts the audio data into text, and then analyzes that text using natural language processing technology. The casual conversation detection unit can also detect casual conversation using keyword matching and contextual analysis. For example, if a particular keyword or phrase appears frequently, it is determined that it is likely to be casual conversation. Furthermore, by using contextual analysis, it is possible to understand the context and flow of the topic, and distinguish between casual conversation and statements related to the agenda more accurately. In addition, the casual conversation detection unit can learn the speaking patterns of meeting participants to improve the accuracy of casual conversation detection. For example, by learning past meeting data and understanding the tendency of certain participants to make certain statements, the accuracy of casual conversation detection can be improved. As a result, the casual conversation detection unit can quickly and accurately detect casual conversation during meetings, contributing to the efficiency of meetings.

[0031] The display unit shows a meeting summary based on the casual conversation detected by the casual conversation detection unit. The display unit displays the meeting summary on a whiteboard or online meeting tool, for example. Specifically, it excludes casual conversation detected by the casual conversation detection unit and extracts only statements related to the agenda to create a summary. The display unit can also display the progress of the meeting in real time. For example, it can display the current agenda, progress, and remaining time to make it easier for participants to understand the progress of the meeting. In addition, the display unit can estimate the emotions of meeting participants and adjust how the meeting summary is displayed based on the estimated emotions. For example, if meeting participants are relaxed, the display unit will display a detailed meeting summary, and if they are tense, it will display a concise meeting summary. In this way, the display unit can support the progress of the meeting and enable participants to efficiently grasp information. Furthermore, the display unit can dynamically update the displayed content according to the progress of the meeting, always providing the latest information. In this way, the display unit can contribute to the efficiency and productivity of meetings.

[0032] The progress monitoring unit constantly keeps track of meeting time, agenda, and goals, and prompts progress via voice and text when stalls occur. For example, the progress monitoring unit pre-sets the meeting agenda and goals and monitors the progress in real time. Specifically, it inputs the agenda and goals into the system before the meeting starts and tracks the progress in real time. The progress monitoring unit analyzes the statements and actions of meeting participants and prompts progress via voice and text if progress stalls. The progress monitoring unit can also estimate the emotions of meeting participants and adjust the monitoring method based on the estimated emotions. For example, if meeting participants are relaxed, the monitoring will be less strict, and if they are tense, it will be more strict. In this way, the progress monitoring unit can ensure smooth meeting progress and support efficient meeting management. Furthermore, the progress monitoring unit can record the progress of the meeting and provide data for later analysis. In this way, the progress monitoring unit can contribute to increased meeting efficiency and productivity.

[0033] The real-time monitoring unit analyzes audio data during meetings to detect deviations from the agenda. For example, it uses speech recognition technology to analyze audio data during meetings and detect statements unrelated to the agenda. Specifically, it uses speech recognition technology to convert audio data into text, and then analyzes that text using natural language processing technology. The real-time monitoring unit can also learn the speaking patterns of meeting participants to more accurately detect deviations from the agenda. For example, by learning past meeting data and understanding the tendency of certain participants to speak, it can more accurately detect deviations from the agenda. Furthermore, the real-time monitoring unit can estimate the emotions of meeting participants and adjust the accuracy of agenda deviation detection based on the estimated emotions. For example, if meeting participants are relaxed, the accuracy of agenda deviation detection is set low, and if they are tense, it is set high. In this way, the real-time monitoring unit can quickly and accurately detect deviations from the agenda during meetings, contributing to the efficiency of meetings.

[0034] The meeting support unit facilitates the meeting based on deviations from the agenda detected by the real-time monitoring unit. The support unit uses methods such as audio alerts and text messages to guide the meeting. Specifically, if the real-time monitoring unit detects a deviation from the agenda, the support unit issues an audio alert to prompt participants to return to the topic. It can also provide specific instructions and advice via text messages. The support unit can also estimate the emotions of meeting participants and adjust its support methods based on these estimations. For example, if participants are relaxed, it provides gentle support; if they are tense, it provides quick and clear support. This allows the support unit to ensure a smooth meeting and support efficient meeting management. Furthermore, the support unit can record the meeting's progress and provide data for later analysis. This allows the support unit to contribute to increased meeting efficiency and productivity.

[0035] The casual conversation detection unit can analyze audio data during a meeting in real time and distinguish between casual conversation and statements related to the agenda. For example, the casual conversation detection unit can analyze the audio data during the meeting using speech recognition technology to distinguish between casual conversation and statements related to the agenda. The casual conversation detection unit can also detect casual conversation using keyword matching and contextual analysis. Furthermore, the casual conversation detection unit can learn the speaking patterns of meeting participants to improve the accuracy of casual conversation detection. For example, the casual conversation detection unit can learn from past meeting data to more accurately distinguish between casual conversation and statements related to the agenda. This makes it possible to make the meeting proceed more smoothly by distinguishing between casual conversation and statements related to the agenda. Some or all of the above processing in the casual conversation detection unit may be performed using AI, for example, or without AI. For example, the casual conversation detection unit can input the audio data during the meeting into a generating AI and have the generating AI perform the distinction between casual conversation and statements related to the agenda.

[0036] The progress monitoring unit can pre-set the meeting agenda and goals and monitor the progress in real time. For example, the progress monitoring unit can pre-set the meeting agenda and goals and monitor the progress in real time. The progress monitoring unit can also estimate the emotions of meeting participants and adjust the monitoring method based on the estimated emotions. For example, if meeting participants are relaxed, the progress monitoring unit will monitor the progress loosely, and if they are tense, it will monitor strictly. Furthermore, the progress monitoring unit can dynamically change the priority of the agenda and goals according to the progress of the meeting. For example, if the progress monitoring unit is behind schedule, it will prioritize important agendas and goals, and if it is on track, it will proceed with detailed agendas and goals. This allows for efficient management of the meeting by pre-setting the agenda and goals and monitoring the progress in real time. Some or all of the above processes in the progress monitoring unit may be performed using AI, for example, or not. For example, the progress monitoring unit can input the meeting agenda and goals into a generation AI and have the generation AI monitor the progress.

[0037] The real-time monitoring unit can analyze audio data to detect deviations from the agenda. For example, the real-time monitoring unit can use speech recognition technology to analyze audio data during a meeting and detect statements unrelated to the agenda. The real-time monitoring unit can also learn the speaking patterns of meeting participants to more accurately detect deviations from the agenda. Furthermore, the real-time monitoring unit can estimate the emotions of meeting participants and adjust the accuracy of agenda deviation detection based on the estimated emotions. For example, the real-time monitoring unit can set the accuracy of agenda deviation detection lower when meeting participants are relaxed and higher when they are tense. This allows for appropriate support of the meeting's progress by analyzing audio data and detecting deviations from the agenda. Some or all of the above processing in the real-time monitoring unit may be performed using AI, for example, or without AI. For example, the real-time monitoring unit can input audio data from the meeting into a generating AI and have the generating AI perform the detection of deviations from the agenda.

[0038] The display unit can display meeting minutes and meeting progress on a whiteboard or online tool. For example, it can display a meeting summary on a whiteboard or online meeting tool. The display unit can also display the meeting progress in real time. Furthermore, the display unit can estimate the emotions of meeting participants and adjust how the meeting summary is displayed based on the estimated emotions. For example, if meeting participants are relaxed, the display unit will display a detailed meeting summary, and if they are tense, it will display a concise summary. This makes it easier for all participants to understand the current progress by displaying the meeting minutes and meeting progress. Some or all of the above processing in the display unit may be performed using AI, for example, or not using AI. For example, the display unit can input the meeting progress into a generating AI and have the generating AI perform the display of the meeting summary.

[0039] The meeting support unit can prompt progress with audio alerts and text messages when the meeting is stalled. For example, the meeting support unit can use audio alerts and text messages to encourage the meeting to continue. The meeting support unit can also estimate the emotions of meeting participants and adjust its support methods based on those estimates. For example, if participants are relaxed, the support unit will provide gentle support; if they are tense, it will provide quick and clear support. Furthermore, the meeting support unit can dynamically change the content of audio alerts and text messages according to the progress of the meeting. For example, if the meeting is behind schedule, the support unit will send urgent audio alerts and text messages; if it is progressing smoothly, it will send gentle audio alerts and text messages. This allows for more productive meetings by prompting progress when the meeting stalls. Some or all of the above processes in the meeting support unit may be performed using AI, for example, or not. For example, the meeting support unit can input the progress of the meeting into a generating AI and have the generating AI execute the methods of support.

[0040] The casual conversation detection unit, upon detecting casual conversation, can evaluate its importance according to the progress of the meeting and issue a warning as necessary. For example, if the meeting is progressing smoothly, the casual conversation detection unit may evaluate the importance of the casual conversation low and not issue a warning. Conversely, if the meeting is behind schedule, the casual conversation detection unit may evaluate the importance of the casual conversation high and issue a warning. Furthermore, if the meeting is stalled, the casual conversation detection unit may evaluate the importance of the casual conversation to a moderate level and issue an appropriate warning. In this way, by evaluating the importance of casual conversation according to the progress of the meeting and issuing warnings as necessary, the progress of the meeting can be appropriately managed. Some or all of the above processing in the casual conversation detection unit may be performed using AI, for example, or not using AI. For example, the casual conversation detection unit can input meeting progress data into a generating AI and have the generating AI perform the evaluation of the importance of casual conversation and issue warnings.

[0041] The casual conversation detection unit learns the speaking patterns of meeting participants when it detects casual conversation, enabling it to more accurately distinguish between casual conversation and statements related to the agenda. For example, the casual conversation detection unit learns the past speaking patterns of meeting participants to distinguish between casual conversation and statements related to the agenda. It can also analyze the frequency and content of meeting participants' statements to distinguish between casual conversation and statements related to the agenda. Furthermore, the casual conversation detection unit can analyze the tone and emotion of meeting participants' statements to distinguish between casual conversation and statements related to the agenda. In this way, by learning the speaking patterns of meeting participants, it can more accurately distinguish between casual conversation and statements related to the agenda. Some or all of the above processing in the casual conversation detection unit may be performed using AI, for example, or without AI. For example, the casual conversation detection unit can input meeting participants' speaking data into a generating AI and have the generating AI perform the distinction between casual conversation and statements related to the agenda.

[0042] The casual conversation detection unit can evaluate the impact of casual conversation based on the meeting participants' positions and areas of expertise when it detects it. For example, if a meeting participant has a high position, the casual conversation detection unit may evaluate the impact of casual conversation as low and allow it. The casual conversation detection unit may also evaluate the impact of casual conversation as low and allow it if the meeting participant's area of ​​expertise is related to the meeting agenda. Furthermore, if a meeting participant has a low position, the casual conversation detection unit may evaluate the impact of casual conversation as high and detect it early. This allows for appropriate management of the meeting's progress by evaluating the impact of casual conversation based on the meeting participants' positions and areas of expertise. Some or all of the above processing in the casual conversation detection unit may be performed using AI, for example, or without AI. For example, the casual conversation detection unit can input meeting participants' position and area of ​​expertise data into a generating AI and have the generating AI perform the evaluation of the impact of casual conversation.

[0043] The casual conversation detection unit can dynamically set the acceptable range of casual conversation according to the meeting's theme and purpose when it detects casual conversation. For example, if the meeting's theme is important, the casual conversation detection unit can set a narrower acceptable range of casual conversation to detect it early. Conversely, if the meeting's theme is light, the casual conversation detection unit can set a wider acceptable range of casual conversation to allow it. Furthermore, if the meeting's purpose is clear, the casual conversation detection unit can set a moderate acceptable range of casual conversation to allow a reasonable amount of casual conversation. In this way, by dynamically setting the acceptable range of casual conversation according to the meeting's theme and purpose, the progress of the meeting can be appropriately managed. Some or all of the above processing in the casual conversation detection unit may be performed using AI, for example, or without AI. For example, the casual conversation detection unit can input meeting theme and purpose data into a generating AI and have the generating AI set the acceptable range of casual conversation.

[0044] The display unit can dynamically update its content according to the progress of the meeting. For example, the display unit can update the meeting minutes summary in real time according to the progress of the meeting. The display unit can also highlight important meeting minutes summaries if the meeting is behind schedule. Furthermore, if the meeting is progressing smoothly, the display unit can display a detailed meeting minutes summary. This allows all participants to stay informed of the latest information by dynamically updating the display content according to the progress of the meeting. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input meeting progress data into a generating AI and have the generating AI perform the dynamic updating of the display content.

[0045] The display unit can customize the displayed content according to the position and area of ​​expertise of the meeting participants. For example, if a meeting participant holds a high position, the display unit will highlight and display important minutes summaries. The display unit can also display detailed minutes summaries if the meeting participant's area of ​​expertise is related to the meeting agenda. Furthermore, if a meeting participant holds a low position, the display unit can display a concise minutes summary. In this way, more appropriate information is provided by customizing the displayed content according to the position and area of ​​expertise of the meeting participants. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input meeting participant position and area of ​​expertise data into a generating AI and have the generating AI perform the customization of the displayed content.

[0046] The display unit can select the optimal display method based on the device information of the meeting participants when displaying information. For example, if a meeting participant is using a smartphone, the display unit can provide a display method that matches the screen size. Furthermore, if a meeting participant is using a tablet, the display unit can provide a display method optimized for a larger screen. In addition, if a meeting participant is using a smartwatch, the display unit can provide a concise and highly visible display method. This ensures that more relevant information is provided by selecting the optimal display method based on the device information of the meeting participants. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input the device information of the meeting participants into a generating AI and have the generating AI select the optimal display method.

[0047] The display unit can dynamically change its display content according to the meeting's theme and purpose. For example, if the meeting's theme is important, the display unit will highlight important information. If the meeting's theme is less important, the display unit can also display detailed information. Furthermore, if the meeting's purpose is clear, the display unit can display information tailored to that purpose. This dynamic change in display content according to the meeting's theme and purpose provides more appropriate information. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input meeting theme and purpose data into a generating AI, and have the generating AI dynamically change the display content.

[0048] The progress monitoring unit can dynamically change the priority of agendas and goals according to the progress of the meeting during progress monitoring. For example, if the meeting is behind schedule, the progress monitoring unit will prioritize important agendas and goals. If the meeting is progressing smoothly, the progress monitoring unit can also proceed with detailed agendas and goals. Furthermore, if the meeting is stalled, the progress monitoring unit can re-evaluate important agendas and goals and proceed accordingly. This allows for efficient management of the meeting by dynamically changing the priority of agendas and goals according to the progress of the meeting. Some or all of the above processing in the progress monitoring unit may be performed using AI, for example, or without AI. For example, the progress monitoring unit can input meeting progress data into a generating AI and have the generating AI execute dynamic changes to the priority of agendas and goals.

[0049] The progress monitoring unit can learn the speaking patterns of meeting participants during progress monitoring to improve the accuracy of monitoring the progress. For example, the progress monitoring unit can learn the past speaking patterns of meeting participants to improve the accuracy of monitoring the progress. The progress monitoring unit can also analyze the frequency and content of meeting participants' statements to improve the accuracy of monitoring the progress. Furthermore, the progress monitoring unit can analyze the tone and emotion of meeting participants' statements to improve the accuracy of monitoring the progress. In this way, by learning the speaking patterns of meeting participants, the accuracy of monitoring the progress can be improved. Some or all of the above processing in the progress monitoring unit may be performed using AI, for example, or without using AI. For example, the progress monitoring unit can input meeting participants' speaking data into a generating AI and have the generating AI perform the improvement of the accuracy of monitoring the progress.

[0050] The progress monitoring unit can set evaluation criteria for the progress of a meeting based on the roles and areas of expertise of the meeting participants during progress monitoring. For example, if a meeting participant holds a high-ranking position, the progress monitoring unit can set the evaluation criteria for the progress more leniently. It can also set the evaluation criteria for the progress more leniently if the meeting participant's area of ​​expertise is related to the meeting agenda. Furthermore, if a meeting participant holds a low-ranking position, the progress monitoring unit can set the evaluation criteria for the progress more strictly. This allows for more appropriate progress management by setting evaluation criteria based on the roles and areas of expertise of the meeting participants. Some or all of the above processing in the progress monitoring unit may be performed using AI, for example, or not using AI. For example, the progress monitoring unit can input meeting participant role and area of ​​expertise data into a generating AI and have the generating AI set the evaluation criteria for the progress.

[0051] The progress monitoring unit can dynamically change its monitoring method according to the meeting's theme and objectives during progress monitoring. For example, if the meeting's theme is important, the progress monitoring unit will strictly monitor the progress. Conversely, if the meeting's theme is less important, the progress monitoring unit can also monitor the progress more loosely. Furthermore, if the meeting's objective is clear, the progress monitoring unit can monitor the progress in a way that aligns with that objective. This allows for more appropriate progress management by dynamically changing the monitoring method according to the meeting's theme and objectives. Some or all of the above processing in the progress monitoring unit may be performed using AI, for example, or without AI. For example, the progress monitoring unit can input meeting theme and objective data into a generating AI and have the generating AI dynamically change the monitoring method.

[0052] The real-time monitoring unit can evaluate the importance of deviations from the agenda according to the progress of the meeting during real-time monitoring. For example, if the meeting is progressing smoothly, the real-time monitoring unit may evaluate the importance of deviations from the agenda at a low level and tolerate them. Conversely, if the meeting is behind schedule, the real-time monitoring unit may evaluate the importance of deviations from the agenda at a high level and detect them early. Furthermore, if the meeting is stalled, the real-time monitoring unit may evaluate the importance of deviations from the agenda at a moderate level and tolerate a moderate degree of deviation. This enables more appropriate management of deviations from the agenda by evaluating the importance of deviations from the agenda according to the progress of the meeting. Some or all of the above processing in the real-time monitoring unit may be performed using AI, for example, or without AI. For example, the real-time monitoring unit can input meeting progress data into a generating AI and have the generating AI perform the evaluation of the importance of deviations from the agenda.

[0053] The real-time monitoring unit can learn the speaking patterns of meeting participants during real-time monitoring, enabling more accurate detection of deviations from the agenda. For example, the real-time monitoring unit can learn the past speaking patterns of meeting participants to accurately detect deviations from the agenda. Furthermore, the real-time monitoring unit can analyze the frequency and content of participants' statements to accurately detect deviations from the agenda. In addition, the real-time monitoring unit can analyze the tone and emotion of participants' statements to accurately detect deviations from the agenda. This allows for more accurate detection of deviations from the agenda by learning the speaking patterns of meeting participants. Some or all of the above processing in the real-time monitoring unit may be performed using AI, for example, or without AI. For example, the real-time monitoring unit can input meeting participant speech data into a generating AI and have the generating AI perform the detection of deviations from the agenda.

[0054] The real-time monitoring unit can evaluate the impact of agenda deviations based on the positions and areas of expertise of meeting participants during real-time monitoring. For example, if a meeting participant holds a high position, the real-time monitoring unit may evaluate the impact of agenda deviations as low and tolerate the deviation. Furthermore, if a meeting participant's area of ​​expertise is related to the meeting agenda, the real-time monitoring unit may also evaluate the impact of agenda deviations as low and tolerate the deviation. Additionally, if a meeting participant holds a low position, the real-time monitoring unit may evaluate the impact of agenda deviations as high and detect the deviation early. This enables more appropriate agenda deviation management by evaluating the impact of agenda deviations based on the positions and areas of expertise of meeting participants. Some or all of the above processing in the real-time monitoring unit may be performed using AI, or not. For example, the real-time monitoring unit can input meeting participant position and area of ​​expertise data into a generating AI and have the generating AI perform the evaluation of the impact of agenda deviations.

[0055] The real-time monitoring unit can dynamically set the acceptable range of deviation from the agenda according to the meeting's theme and objectives during real-time monitoring. For example, if the meeting's theme is important, the real-time monitoring unit can set a narrower acceptable range of deviation to detect deviations early. Conversely, if the meeting's theme is less important, the real-time monitoring unit can set a wider acceptable range of deviation to allow deviations. Furthermore, if the meeting's objective is clear, the real-time monitoring unit can set a moderate acceptable range of deviation to allow a moderate amount of deviation. This allows for more appropriate management of agenda deviations by dynamically setting the acceptable range of deviation according to the meeting's theme and objectives. Some or all of the above processing in the real-time monitoring unit may be performed using AI, for example, or without AI. For example, the real-time monitoring unit can input meeting theme and objective data into a generating AI and have the generating AI set the acceptable range of deviation from the agenda.

[0056] The progress support unit can dynamically change the content of audio alerts and text messages according to the progress of the meeting during progress support. For example, if the meeting is behind schedule, the progress support unit can send urgent audio alerts and text messages. It can also send calm audio alerts and text messages if the meeting is progressing smoothly. Furthermore, if the meeting is stalled, the progress support unit can send audio alerts and text messages to encourage progress. By dynamically changing the content of audio alerts and text messages according to the progress of the meeting, more appropriate progress support becomes possible. Some or all of the above processing in the progress support unit may be performed using AI, for example, or not using AI. For example, the progress support unit can input meeting progress data into a generating AI and have the generating AI dynamically change the content of audio alerts and text messages.

[0057] The progress support unit can improve the accuracy of its progress support by learning the speaking patterns of meeting participants during progress support. For example, the progress support unit can improve the accuracy of its progress support by learning the past speaking patterns of meeting participants. It can also improve the accuracy of its progress support by analyzing the frequency and content of meeting participants' statements. Furthermore, it can improve the accuracy of its progress support by analyzing the tone and emotion of meeting participants' statements. In this way, the accuracy of progress support can be improved by learning the speaking patterns of meeting participants. Some or all of the above processing in the progress support unit may be performed using AI, for example, or without AI. For example, the progress support unit can input meeting participant statement data into a generating AI and have the generating AI perform the improvement of progress support accuracy.

[0058] The progress support unit can customize the content of its progress support based on the roles and areas of expertise of the meeting participants. For example, if a meeting participant holds a high-ranking position, the progress support unit can provide important progress support. Furthermore, if a meeting participant's area of ​​expertise is relevant to the meeting agenda, the progress support unit can provide detailed progress support. Additionally, if a meeting participant holds a low-ranking position, the progress support unit can provide concise progress support. This allows for more appropriate progress support by customizing the content based on the roles and areas of expertise of the meeting participants. Some or all of the above processing in the progress support unit may be performed using AI, or not. For example, the progress support unit can input meeting participant role and area of ​​expertise data into a generating AI and have the generating AI customize the content of the progress support.

[0059] The progress support unit can dynamically change its method of progress support depending on the theme and purpose of the meeting. For example, if the meeting theme is important, the progress support unit can provide strict progress support. If the meeting theme is light, the progress support unit can also provide relaxed progress support. Furthermore, if the purpose of the meeting is clear, the progress support unit can provide progress support tailored to that purpose. By dynamically changing the method of progress support according to the theme and purpose of the meeting, more appropriate progress support becomes possible. Some or all of the above processing in the progress support unit may be performed using AI, for example, or not using AI. For example, the progress support unit can input meeting theme and purpose data into a generating AI and have the generating AI execute the dynamic change in the method of progress support.

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

[0061] An AI agent system for facilitating meetings can also be equipped with the ability to analyze the content of participants' remarks and evaluate the importance of those remarks. For example, if a remark is directly related to the meeting's goals, it will be highly rated and reflected in the meeting minutes. Conversely, if a remark does not contribute to the progress of the meeting, it will be lowly rated and not reflected in the minutes. Furthermore, if a remark hinders the progress of the meeting, it can be displayed as a warning to encourage the meeting to proceed smoothly. In this way, by evaluating the content of participants' remarks, the progress of the meeting can be managed more efficiently.

[0062] AI agent systems for facilitating meetings can also include features to monitor the frequency of participation and ensure equal opportunities for speaking. For example, if a particular participant speaks too much, the system can prompt that participant to reduce their participation. It can also display messages encouraging participants who speak less to speak up. Furthermore, to ensure equal opportunities for speaking, the system can display the number of times each participant has spoken in real time, allowing all participants to understand the speaking situation. This equalization of speaking opportunities can lead to smoother meeting progress.

[0063] AI agent systems for facilitating meetings can also have the ability to summarize participants' statements and extract key points. For example, they can analyze statements in real time and extract important keywords and phrases. They can also automatically generate meeting minutes summaries based on the extracted keywords and phrases. Furthermore, they can highlight important points to make them easy for all participants to understand. This allows for more efficient management of meeting progress by summarizing statements and extracting key points.

[0064] AI agent systems for facilitating meetings can also be equipped with the ability to analyze the content of participants' statements and evaluate the reliability of those statements. For example, if a statement is based on a highly reliable source, it will be highly rated and reflected in the meeting minutes. Conversely, if a statement is based on a less reliable source, it will be lowly rated and not reflected in the meeting minutes. Furthermore, if a statement is based on a moderately reliable source, it can be moderately rated and reflected in the meeting minutes. This allows for more efficient management of meeting progress by evaluating the reliability of statements.

[0065] An AI agent system for facilitating meetings can also be equipped with the ability to analyze the content of participants' remarks and evaluate their relevance. For example, if a remark is directly related to the meeting agenda, it will be highly rated and reflected in the meeting minutes. Conversely, if a remark is not related to the agenda, it will be lowly rated and not reflected in the minutes. Furthermore, if a remark is partially related to the agenda, it can be moderately rated and reflected in the minutes. This allows for more efficient management of the meeting's progress by evaluating the relevance of remarks.

[0066] AI agent systems for facilitating meetings can also be equipped with the ability to analyze the content of participants' statements and evaluate the reliability of those statements. For example, if a statement is based on a highly reliable source, it will be highly rated and reflected in the meeting minutes. Conversely, if a statement is based on a less reliable source, it will be lowly rated and not reflected in the meeting minutes. Furthermore, if a statement is based on a moderately reliable source, it can be moderately rated and reflected in the meeting minutes. This allows for more efficient management of meeting progress by evaluating the reliability of statements.

[0067] An AI agent system for facilitating meetings can also be equipped with the ability to analyze the content of participants' remarks and evaluate their relevance. For example, if a remark is directly related to the meeting agenda, it will be highly rated and reflected in the meeting minutes. Conversely, if a remark is not related to the agenda, it will be lowly rated and not reflected in the minutes. Furthermore, if a remark is partially related to the agenda, it can be moderately rated and reflected in the minutes. This allows for more efficient management of the meeting's progress by evaluating the relevance of remarks.

[0068] The following briefly describes the processing flow for example form 1.

[0069] Step 1: The chat detection unit analyzes the audio data during the meeting in real time to detect chatter. The chat detection unit uses speech recognition technology to analyze the audio data during the meeting and distinguishes between chatter and statements related to the agenda. It can also detect chatter using keyword matching and contextual analysis. Furthermore, the chat detection unit can learn the speaking patterns of meeting participants to improve the accuracy of chatter detection. Step 2: The display unit displays a meeting summary based on the casual conversation detected by the casual conversation detection unit. The display unit displays the meeting summary on a whiteboard or online meeting tool. It can also display the progress of the meeting in real time. Furthermore, it can estimate the emotions of meeting participants and adjust the way the meeting summary is displayed based on the estimated emotions. Step 3: The progress monitoring unit keeps track of meeting time, agenda, and goals, and prompts progress via voice and text when stalls occur. The progress monitoring unit pre-sets the meeting agenda and goals and monitors progress in real time. It can also estimate the emotions of meeting participants and adjust the progress monitoring method based on the estimated emotions. Step 4: The real-time monitoring unit analyzes the audio data during the meeting to detect deviations from the agenda. The real-time monitoring unit uses speech recognition technology to analyze the audio data during the meeting and detect statements unrelated to the agenda. It can also learn the speaking patterns of meeting participants to more accurately detect deviations from the agenda. Furthermore, it can estimate the emotions of meeting participants and adjust the accuracy of agenda deviation detection based on the estimated emotions. Step 5: The meeting support unit prompts the meeting to proceed based on deviations from the agenda detected by the real-time monitoring unit. The meeting support unit prompts the meeting to proceed using voice alerts and text messages. It can also estimate the emotions of meeting participants and adjust the method of meeting support based on the estimated emotions.

[0070] (Example of form 2) The AI ​​agent system for facilitating meetings according to an embodiment of the present invention is a system for solving meeting-related challenges faced by companies and organizations. This system creates an environment in which both in-person and online participants can efficiently participate in meetings. The AI ​​agent system for facilitating meetings is equipped with a casual conversation detection function, and if casual conversation escalates during a meeting, it automatically displays a summary of the minutes on a whiteboard or online meeting tool and navigates the meeting towards its goal. For example, if the topic deviates during a meeting, the AI ​​agent detects this and displays a summary of the minutes to encourage the meeting to proceed. Next, it is equipped with a progress monitoring function, constantly keeping track of meeting time, agenda, and meeting goals, and prompting progress with voice and text when the meeting stalls. For example, if the meeting is running behind schedule, the AI ​​agent prompts progress with voice alerts and text messages to improve meeting efficiency. Furthermore, it is equipped with a real-time monitoring function, detecting casual conversation and deviations from the agenda through audio analysis during the meeting. For example, if the topic deviates during a meeting, the AI ​​agent detects this in real time and takes appropriate action. Furthermore, it features a meeting summary display function, showing meeting minutes and progress on a whiteboard or online tool. For example, displaying the meeting progress in real time makes it easier for all participants to understand the current status. Finally, it has a progress support function, prompting progress with audio alerts and text messages when the meeting progress stalls, leading to a more productive meeting. For example, if the meeting is stalled, the AI ​​agent prompts progress with audio alerts and text messages to improve meeting efficiency. In this way, the AI ​​agent system that facilitates meetings can improve meeting efficiency and productivity, creating an environment where each employee can generate creative ideas. This will further promote work style reform and aim to achieve employee satisfaction, happiness, and corporate growth simultaneously. Thus, the AI ​​agent system that facilitates meetings can improve meeting efficiency and productivity.

[0071] The AI ​​agent system for facilitating a meeting according to this embodiment comprises a casual conversation detection unit, a display unit, a progress monitoring unit, a real-time monitoring unit, and a progress support unit. The casual conversation detection unit analyzes audio data during the meeting in real time and detects casual conversation. The casual conversation detection unit analyzes audio data during the meeting using, for example, speech recognition technology to distinguish between casual conversation and statements related to the agenda. The casual conversation detection unit can also detect casual conversation using keyword matching or contextual analysis. Furthermore, the casual conversation detection unit can learn the speaking patterns of meeting participants to improve the accuracy of casual conversation detection. For example, the casual conversation detection unit learns past meeting data to more accurately distinguish between casual conversation and statements related to the agenda. The display unit displays a meeting summary based on the casual conversation detected by the casual conversation detection unit. The display unit displays the meeting summary on, for example, a whiteboard or an online meeting tool. The display unit can also display the progress of the meeting in real time. Furthermore, the display unit can estimate the emotions of meeting participants and adjust the display method of the meeting summary based on the estimated emotions. For example, the display unit shows a detailed meeting summary when meeting participants are relaxed, and a concise summary when they are tense. The progress monitoring unit constantly monitors the meeting time, agenda, and goals, and prompts progress with voice and text when stalls occur. The progress monitoring unit can, for example, pre-set the meeting agenda and goals and monitor the progress in real time. It can also estimate the emotions of meeting participants and adjust the monitoring method based on the estimated emotions. For example, it can monitor the progress more loosely when meeting participants are relaxed and more strictly when they are tense. The real-time monitoring unit analyzes audio data during the meeting to detect deviations from the agenda. For example, it can use speech recognition technology to analyze audio data during the meeting and detect statements unrelated to the agenda. It can also learn the speech patterns of meeting participants to more accurately detect deviations from the agenda. Furthermore, the real-time monitoring unit can estimate the emotions of meeting participants and adjust the accuracy of agenda deviation detection based on the estimated emotions.For example, the real-time monitoring unit sets a lower accuracy for detecting deviations from the agenda when meeting participants are relaxed, and a higher accuracy when they are tense. The progress support unit guides the meeting based on the deviations from the agenda detected by the real-time monitoring unit. The progress support unit guides the meeting using, for example, voice alerts or text messages. The progress support unit can also estimate the emotions of meeting participants and adjust its progress support methods based on the estimated emotions. For example, the progress support unit provides gentle progress support when meeting participants are relaxed, and provides quick and clear progress support when they are tense. As a result, the AI ​​agent system facilitating meetings according to this embodiment can achieve increased meeting efficiency and productivity.

[0072] The casual conversation detection unit analyzes audio data during meetings in real time to detect casual conversation. For example, it uses speech recognition technology to analyze the audio data during meetings and distinguish between casual conversation and statements related to the agenda. Specifically, speech recognition technology converts the audio data into text, and then analyzes that text using natural language processing technology. The casual conversation detection unit can also detect casual conversation using keyword matching and contextual analysis. For example, if a particular keyword or phrase appears frequently, it is determined that it is likely to be casual conversation. Furthermore, by using contextual analysis, it is possible to understand the context and flow of the topic, and distinguish between casual conversation and statements related to the agenda more accurately. In addition, the casual conversation detection unit can learn the speaking patterns of meeting participants to improve the accuracy of casual conversation detection. For example, by learning past meeting data and understanding the tendency of certain participants to make certain statements, the accuracy of casual conversation detection can be improved. As a result, the casual conversation detection unit can quickly and accurately detect casual conversation during meetings, contributing to the efficiency of meetings.

[0073] The display unit shows a meeting summary based on the casual conversation detected by the casual conversation detection unit. The display unit displays the meeting summary on a whiteboard or online meeting tool, for example. Specifically, it excludes casual conversation detected by the casual conversation detection unit and extracts only statements related to the agenda to create a summary. The display unit can also display the progress of the meeting in real time. For example, it can display the current agenda, progress, and remaining time to make it easier for participants to understand the progress of the meeting. In addition, the display unit can estimate the emotions of meeting participants and adjust how the meeting summary is displayed based on the estimated emotions. For example, if meeting participants are relaxed, the display unit will display a detailed meeting summary, and if they are tense, it will display a concise meeting summary. In this way, the display unit can support the progress of the meeting and enable participants to efficiently grasp information. Furthermore, the display unit can dynamically update the displayed content according to the progress of the meeting, always providing the latest information. In this way, the display unit can contribute to the efficiency and productivity of meetings.

[0074] The progress monitoring unit constantly keeps track of meeting time, agenda, and goals, and prompts progress via voice and text when stalls occur. For example, the progress monitoring unit pre-sets the meeting agenda and goals and monitors the progress in real time. Specifically, it inputs the agenda and goals into the system before the meeting starts and tracks the progress in real time. The progress monitoring unit analyzes the statements and actions of meeting participants and prompts progress via voice and text if progress stalls. The progress monitoring unit can also estimate the emotions of meeting participants and adjust the monitoring method based on the estimated emotions. For example, if meeting participants are relaxed, the monitoring will be less strict, and if they are tense, it will be more strict. In this way, the progress monitoring unit can ensure smooth meeting progress and support efficient meeting management. Furthermore, the progress monitoring unit can record the progress of the meeting and provide data for later analysis. In this way, the progress monitoring unit can contribute to increased meeting efficiency and productivity.

[0075] The real-time monitoring unit analyzes audio data during meetings to detect deviations from the agenda. For example, it uses speech recognition technology to analyze audio data during meetings and detect statements unrelated to the agenda. Specifically, it uses speech recognition technology to convert audio data into text, and then analyzes that text using natural language processing technology. The real-time monitoring unit can also learn the speaking patterns of meeting participants to more accurately detect deviations from the agenda. For example, by learning past meeting data and understanding the tendency of certain participants to speak, it can more accurately detect deviations from the agenda. Furthermore, the real-time monitoring unit can estimate the emotions of meeting participants and adjust the accuracy of agenda deviation detection based on the estimated emotions. For example, if meeting participants are relaxed, the accuracy of agenda deviation detection is set low, and if they are tense, it is set high. In this way, the real-time monitoring unit can quickly and accurately detect deviations from the agenda during meetings, contributing to the efficiency of meetings.

[0076] The meeting support unit facilitates the meeting based on deviations from the agenda detected by the real-time monitoring unit. The support unit uses methods such as audio alerts and text messages to guide the meeting. Specifically, if the real-time monitoring unit detects a deviation from the agenda, the support unit issues an audio alert to prompt participants to return to the topic. It can also provide specific instructions and advice via text messages. The support unit can also estimate the emotions of meeting participants and adjust its support methods based on these estimations. For example, if participants are relaxed, it provides gentle support; if they are tense, it provides quick and clear support. This allows the support unit to ensure a smooth meeting and support efficient meeting management. Furthermore, the support unit can record the meeting's progress and provide data for later analysis. This allows the support unit to contribute to increased meeting efficiency and productivity.

[0077] The casual conversation detection unit can analyze audio data during a meeting in real time and distinguish between casual conversation and statements related to the agenda. For example, the casual conversation detection unit can analyze the audio data during the meeting using speech recognition technology to distinguish between casual conversation and statements related to the agenda. The casual conversation detection unit can also detect casual conversation using keyword matching and contextual analysis. Furthermore, the casual conversation detection unit can learn the speaking patterns of meeting participants to improve the accuracy of casual conversation detection. For example, the casual conversation detection unit can learn from past meeting data to more accurately distinguish between casual conversation and statements related to the agenda. This makes it possible to make the meeting proceed more smoothly by distinguishing between casual conversation and statements related to the agenda. Some or all of the above processing in the casual conversation detection unit may be performed using AI, for example, or without AI. For example, the casual conversation detection unit can input the audio data during the meeting into a generating AI and have the generating AI perform the distinction between casual conversation and statements related to the agenda.

[0078] The progress monitoring unit can pre-set the meeting agenda and goals and monitor the progress in real time. For example, the progress monitoring unit can pre-set the meeting agenda and goals and monitor the progress in real time. The progress monitoring unit can also estimate the emotions of meeting participants and adjust the monitoring method based on the estimated emotions. For example, if meeting participants are relaxed, the progress monitoring unit will monitor the progress loosely, and if they are tense, it will monitor strictly. Furthermore, the progress monitoring unit can dynamically change the priority of the agenda and goals according to the progress of the meeting. For example, if the progress monitoring unit is behind schedule, it will prioritize important agendas and goals, and if it is on track, it will proceed with detailed agendas and goals. This allows for efficient management of the meeting by pre-setting the agenda and goals and monitoring the progress in real time. Some or all of the above processes in the progress monitoring unit may be performed using AI, for example, or not. For example, the progress monitoring unit can input the meeting agenda and goals into a generation AI and have the generation AI monitor the progress.

[0079] The real-time monitoring unit can analyze audio data to detect deviations from the agenda. For example, the real-time monitoring unit can use speech recognition technology to analyze audio data during a meeting and detect statements unrelated to the agenda. The real-time monitoring unit can also learn the speaking patterns of meeting participants to more accurately detect deviations from the agenda. Furthermore, the real-time monitoring unit can estimate the emotions of meeting participants and adjust the accuracy of agenda deviation detection based on the estimated emotions. For example, the real-time monitoring unit can set the accuracy of agenda deviation detection lower when meeting participants are relaxed and higher when they are tense. This allows for appropriate support of the meeting's progress by analyzing audio data and detecting deviations from the agenda. Some or all of the above processing in the real-time monitoring unit may be performed using AI, for example, or without AI. For example, the real-time monitoring unit can input audio data from the meeting into a generating AI and have the generating AI perform the detection of deviations from the agenda.

[0080] The display unit can display meeting minutes and meeting progress on a whiteboard or online tool. For example, it can display a meeting summary on a whiteboard or online meeting tool. The display unit can also display the meeting progress in real time. Furthermore, the display unit can estimate the emotions of meeting participants and adjust how the meeting summary is displayed based on the estimated emotions. For example, if meeting participants are relaxed, the display unit will display a detailed meeting summary, and if they are tense, it will display a concise summary. This makes it easier for all participants to understand the current progress by displaying the meeting minutes and meeting progress. Some or all of the above processing in the display unit may be performed using AI, for example, or not using AI. For example, the display unit can input the meeting progress into a generating AI and have the generating AI perform the display of the meeting summary.

[0081] The meeting support unit can prompt progress with audio alerts and text messages when the meeting is stalled. For example, the meeting support unit can use audio alerts and text messages to encourage the meeting to continue. The meeting support unit can also estimate the emotions of meeting participants and adjust its support methods based on those estimates. For example, if participants are relaxed, the support unit will provide gentle support; if they are tense, it will provide quick and clear support. Furthermore, the meeting support unit can dynamically change the content of audio alerts and text messages according to the progress of the meeting. For example, if the meeting is behind schedule, the support unit will send urgent audio alerts and text messages; if it is progressing smoothly, it will send gentle audio alerts and text messages. This allows for more productive meetings by prompting progress when the meeting stalls. Some or all of the above processes in the meeting support unit may be performed using AI, for example, or not. For example, the meeting support unit can input the progress of the meeting into a generating AI and have the generating AI execute the methods of support.

[0082] The casual conversation detection unit can estimate the emotions of meeting participants and adjust the accuracy of casual conversation detection based on the estimated emotions. For example, if meeting participants are relaxed, the casual conversation detection unit can set the accuracy of casual conversation detection low, broadening the range of acceptable casual conversation. Conversely, if meeting participants are tense, the casual conversation detection unit can set the accuracy of casual conversation detection high, detecting casual conversation early to facilitate the progress of the meeting. Furthermore, if meeting participants are tired, the casual conversation detection unit can set the accuracy of casual conversation detection to a medium level, allowing for a moderate amount of casual conversation while maintaining the progress of the meeting. In this way, adjusting the accuracy of casual conversation detection according to the emotions of meeting participants enables more appropriate casual conversation detection. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the casual conversation detection unit may be performed using AI, for example, or without using AI. For example, the casual conversation detection unit can input emotional data of meeting participants into a generating AI, which can then adjust the accuracy of the casual conversation detection.

[0083] The casual conversation detection unit, upon detecting casual conversation, can evaluate its importance according to the progress of the meeting and issue a warning as necessary. For example, if the meeting is progressing smoothly, the casual conversation detection unit may evaluate the importance of the casual conversation low and not issue a warning. Conversely, if the meeting is behind schedule, the casual conversation detection unit may evaluate the importance of the casual conversation high and issue a warning. Furthermore, if the meeting is stalled, the casual conversation detection unit may evaluate the importance of the casual conversation to a moderate level and issue an appropriate warning. In this way, by evaluating the importance of casual conversation according to the progress of the meeting and issuing warnings as necessary, the progress of the meeting can be appropriately managed. Some or all of the above processing in the casual conversation detection unit may be performed using AI, for example, or not using AI. For example, the casual conversation detection unit can input meeting progress data into a generating AI and have the generating AI perform the evaluation of the importance of casual conversation and issue warnings.

[0084] The casual conversation detection unit learns the speaking patterns of meeting participants when it detects casual conversation, enabling it to more accurately distinguish between casual conversation and statements related to the agenda. For example, the casual conversation detection unit learns the past speaking patterns of meeting participants to distinguish between casual conversation and statements related to the agenda. It can also analyze the frequency and content of meeting participants' statements to distinguish between casual conversation and statements related to the agenda. Furthermore, the casual conversation detection unit can analyze the tone and emotion of meeting participants' statements to distinguish between casual conversation and statements related to the agenda. In this way, by learning the speaking patterns of meeting participants, it can more accurately distinguish between casual conversation and statements related to the agenda. Some or all of the above processing in the casual conversation detection unit may be performed using AI, for example, or without AI. For example, the casual conversation detection unit can input meeting participants' speaking data into a generating AI and have the generating AI perform the distinction between casual conversation and statements related to the agenda.

[0085] The casual conversation detection unit can estimate the emotions of meeting participants and adjust the timing of casual conversation detection based on the estimated emotions. For example, if meeting participants are relaxed, the casual conversation detection unit can delay the timing of casual conversation detection and allow it to continue. Conversely, if meeting participants are tense, the casual conversation detection unit can advance the timing of casual conversation detection to detect it earlier. Furthermore, if meeting participants are tired, the casual conversation detection unit can set the timing of casual conversation detection to a moderate level and allow a moderate amount of casual conversation. By adjusting the timing of casual conversation detection according to the emotions of meeting participants, more appropriate casual conversation detection becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the casual conversation detection unit may be performed using AI, for example, or without using AI. For example, the casual conversation detection unit can input emotional data of meeting participants into a generating AI, which can then adjust the timing of casual conversation detection.

[0086] The casual conversation detection unit can evaluate the impact of casual conversation based on the meeting participants' positions and areas of expertise when it detects it. For example, if a meeting participant has a high position, the casual conversation detection unit may evaluate the impact of casual conversation as low and allow it. The casual conversation detection unit may also evaluate the impact of casual conversation as low and allow it if the meeting participant's area of ​​expertise is related to the meeting agenda. Furthermore, if a meeting participant has a low position, the casual conversation detection unit may evaluate the impact of casual conversation as high and detect it early. This allows for appropriate management of the meeting's progress by evaluating the impact of casual conversation based on the meeting participants' positions and areas of expertise. Some or all of the above processing in the casual conversation detection unit may be performed using AI, for example, or without AI. For example, the casual conversation detection unit can input meeting participants' position and area of ​​expertise data into a generating AI and have the generating AI perform the evaluation of the impact of casual conversation.

[0087] The casual conversation detection unit can dynamically set the acceptable range of casual conversation according to the meeting's theme and purpose when it detects casual conversation. For example, if the meeting's theme is important, the casual conversation detection unit can set a narrower acceptable range of casual conversation to detect it early. Conversely, if the meeting's theme is light, the casual conversation detection unit can set a wider acceptable range of casual conversation to allow it. Furthermore, if the meeting's purpose is clear, the casual conversation detection unit can set a moderate acceptable range of casual conversation to allow a reasonable amount of casual conversation. In this way, by dynamically setting the acceptable range of casual conversation according to the meeting's theme and purpose, the progress of the meeting can be appropriately managed. Some or all of the above processing in the casual conversation detection unit may be performed using AI, for example, or without AI. For example, the casual conversation detection unit can input meeting theme and purpose data into a generating AI and have the generating AI set the acceptable range of casual conversation.

[0088] The display unit can estimate the emotions of meeting participants and adjust the display method of the meeting minutes summary based on the estimated emotions. For example, if a meeting participant is relaxed, the display unit can display a detailed meeting minutes summary. If a meeting participant is tense, the display unit can also display a concise meeting minutes summary. Furthermore, if a meeting participant is tired, the display unit can display a highly legible meeting minutes summary. By adjusting the display method of the meeting minutes summary according to the emotions of the meeting participants, a more appropriate meeting minutes summary is displayed. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the display unit may be performed using AI, or not using AI. For example, the display unit can input the emotion data of meeting participants into the generative AI and have the generative AI adjust the display method of the meeting minutes summary.

[0089] The display unit can dynamically update its content according to the progress of the meeting. For example, the display unit can update the meeting minutes summary in real time according to the progress of the meeting. The display unit can also highlight important meeting minutes summaries if the meeting is behind schedule. Furthermore, if the meeting is progressing smoothly, the display unit can display a detailed meeting minutes summary. This allows all participants to stay informed of the latest information by dynamically updating the display content according to the progress of the meeting. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input meeting progress data into a generating AI and have the generating AI perform the dynamic updating of the display content.

[0090] The display unit can customize the displayed content according to the position and area of ​​expertise of the meeting participants. For example, if a meeting participant holds a high position, the display unit will highlight and display important minutes summaries. The display unit can also display detailed minutes summaries if the meeting participant's area of ​​expertise is related to the meeting agenda. Furthermore, if a meeting participant holds a low position, the display unit can display a concise minutes summary. In this way, more appropriate information is provided by customizing the displayed content according to the position and area of ​​expertise of the meeting participants. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input meeting participant position and area of ​​expertise data into a generating AI and have the generating AI perform the customization of the displayed content.

[0091] The display unit can estimate the emotions of meeting participants and determine the priority of information to display based on the estimated emotions. For example, if a meeting participant is relaxed, the display unit may prioritize displaying detailed information. It can also prioritize displaying important information if the participant is tense. Furthermore, if the participant is tired, the display unit may prioritize displaying highly visible information. This ensures that more appropriate information is provided by prioritizing the information displayed according to the emotions of the meeting participants. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the display unit may be performed using AI, or not. For example, the display unit can input the emotion data of meeting participants into a generative AI and have the generative AI determine the priority of information.

[0092] The display unit can select the optimal display method based on the device information of the meeting participants when displaying information. For example, if a meeting participant is using a smartphone, the display unit can provide a display method that matches the screen size. Furthermore, if a meeting participant is using a tablet, the display unit can provide a display method optimized for a larger screen. In addition, if a meeting participant is using a smartwatch, the display unit can provide a concise and highly visible display method. This ensures that more relevant information is provided by selecting the optimal display method based on the device information of the meeting participants. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input the device information of the meeting participants into a generating AI and have the generating AI select the optimal display method.

[0093] The display unit can dynamically change its display content according to the meeting's theme and purpose. For example, if the meeting's theme is important, the display unit will highlight important information. If the meeting's theme is less important, the display unit can also display detailed information. Furthermore, if the meeting's purpose is clear, the display unit can display information tailored to that purpose. This dynamic change in display content according to the meeting's theme and purpose provides more appropriate information. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input meeting theme and purpose data into a generating AI, and have the generating AI dynamically change the display content.

[0094] The progress monitoring unit can estimate the emotions of meeting participants and adjust the method of monitoring the progress based on the estimated emotions. For example, if meeting participants are relaxed, the progress monitoring unit will monitor the progress more gently. Conversely, if meeting participants are tense, the progress monitoring unit can monitor the progress more strictly. Furthermore, if meeting participants are tired, the progress monitoring unit can monitor the progress to a moderate degree. This allows for more appropriate progress management by adjusting the method of monitoring the progress according to the emotions of the meeting participants. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the progress monitoring unit may be performed using AI, or not using AI. For example, the progress monitoring unit can input the emotion data of meeting participants into the generative AI and have the generative AI adjust the method of monitoring the progress.

[0095] The progress monitoring unit can dynamically change the priority of agendas and goals according to the progress of the meeting during progress monitoring. For example, if the meeting is behind schedule, the progress monitoring unit will prioritize important agendas and goals. If the meeting is progressing smoothly, the progress monitoring unit can also proceed with detailed agendas and goals. Furthermore, if the meeting is stalled, the progress monitoring unit can re-evaluate important agendas and goals and proceed accordingly. This allows for efficient management of the meeting by dynamically changing the priority of agendas and goals according to the progress of the meeting. Some or all of the above processing in the progress monitoring unit may be performed using AI, for example, or without AI. For example, the progress monitoring unit can input meeting progress data into a generating AI and have the generating AI execute dynamic changes to the priority of agendas and goals.

[0096] The progress monitoring unit can learn the speaking patterns of meeting participants during progress monitoring to improve the accuracy of monitoring the progress. For example, the progress monitoring unit can learn the past speaking patterns of meeting participants to improve the accuracy of monitoring the progress. The progress monitoring unit can also analyze the frequency and content of meeting participants' statements to improve the accuracy of monitoring the progress. Furthermore, the progress monitoring unit can analyze the tone and emotion of meeting participants' statements to improve the accuracy of monitoring the progress. In this way, by learning the speaking patterns of meeting participants, the accuracy of monitoring the progress can be improved. Some or all of the above processing in the progress monitoring unit may be performed using AI, for example, or without using AI. For example, the progress monitoring unit can input meeting participants' speaking data into a generating AI and have the generating AI perform the improvement of the accuracy of monitoring the progress.

[0097] The progress monitoring unit can estimate the emotions of meeting participants and adjust the frequency of monitoring the progress based on the estimated emotions. For example, if a meeting participant is relaxed, the progress monitoring unit can set the monitoring frequency low. Conversely, if a meeting participant is tense, the progress monitoring unit can set the monitoring frequency high. Furthermore, if a meeting participant is tired, the progress monitoring unit can set the monitoring frequency to a moderate level. This allows for more appropriate progress management by adjusting the monitoring frequency according to the emotions of the meeting participants. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the progress monitoring unit may be performed using AI, or not using AI. For example, the progress monitoring unit can input the emotion data of meeting participants into the generative AI and have the generative AI adjust the monitoring frequency.

[0098] The progress monitoring unit can set evaluation criteria for the progress of a meeting based on the roles and areas of expertise of the meeting participants during progress monitoring. For example, if a meeting participant holds a high-ranking position, the progress monitoring unit can set the evaluation criteria for the progress more leniently. It can also set the evaluation criteria for the progress more leniently if the meeting participant's area of ​​expertise is related to the meeting agenda. Furthermore, if a meeting participant holds a low-ranking position, the progress monitoring unit can set the evaluation criteria for the progress more strictly. This allows for more appropriate progress management by setting evaluation criteria based on the roles and areas of expertise of the meeting participants. Some or all of the above processing in the progress monitoring unit may be performed using AI, for example, or not using AI. For example, the progress monitoring unit can input meeting participant role and area of ​​expertise data into a generating AI and have the generating AI set the evaluation criteria for the progress.

[0099] The progress monitoring unit can dynamically change its monitoring method according to the meeting's theme and objectives during progress monitoring. For example, if the meeting's theme is important, the progress monitoring unit will strictly monitor the progress. Conversely, if the meeting's theme is less important, the progress monitoring unit can also monitor the progress more loosely. Furthermore, if the meeting's objective is clear, the progress monitoring unit can monitor the progress in a way that aligns with that objective. This allows for more appropriate progress management by dynamically changing the monitoring method according to the meeting's theme and objectives. Some or all of the above processing in the progress monitoring unit may be performed using AI, for example, or without AI. For example, the progress monitoring unit can input meeting theme and objective data into a generating AI and have the generating AI dynamically change the monitoring method.

[0100] The real-time monitoring unit can estimate the emotions of meeting participants and adjust the accuracy of agenda deviation detection based on the estimated emotions. For example, if meeting participants are relaxed, the real-time monitoring unit can set the agenda deviation detection accuracy low and tolerate deviations. Conversely, if meeting participants are tense, the real-time monitoring unit can set the agenda deviation detection accuracy high and detect deviations early. Furthermore, if meeting participants are tired, the real-time monitoring unit can set the agenda deviation detection accuracy to a moderate level and tolerate a moderate amount of deviation. By adjusting the agenda deviation detection accuracy according to the emotions of meeting participants, more appropriate agenda deviation detection becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the real-time monitoring unit may be performed using AI, for example, or without AI. For example, the real-time monitoring unit can input emotional data of meeting participants into a generating AI and have the generating AI adjust the accuracy of detecting deviations from the agenda.

[0101] The real-time monitoring unit can evaluate the importance of deviations from the agenda according to the progress of the meeting during real-time monitoring. For example, if the meeting is progressing smoothly, the real-time monitoring unit may evaluate the importance of deviations from the agenda at a low level and tolerate them. Conversely, if the meeting is behind schedule, the real-time monitoring unit may evaluate the importance of deviations from the agenda at a high level and detect them early. Furthermore, if the meeting is stalled, the real-time monitoring unit may evaluate the importance of deviations from the agenda at a moderate level and tolerate a moderate degree of deviation. This enables more appropriate management of deviations from the agenda by evaluating the importance of deviations from the agenda according to the progress of the meeting. Some or all of the above processing in the real-time monitoring unit may be performed using AI, for example, or without AI. For example, the real-time monitoring unit can input meeting progress data into a generating AI and have the generating AI perform the evaluation of the importance of deviations from the agenda.

[0102] The real-time monitoring unit can learn the speaking patterns of meeting participants during real-time monitoring, enabling more accurate detection of deviations from the agenda. For example, the real-time monitoring unit can learn the past speaking patterns of meeting participants to accurately detect deviations from the agenda. Furthermore, the real-time monitoring unit can analyze the frequency and content of participants' statements to accurately detect deviations from the agenda. In addition, the real-time monitoring unit can analyze the tone and emotion of participants' statements to accurately detect deviations from the agenda. This allows for more accurate detection of deviations from the agenda by learning the speaking patterns of meeting participants. Some or all of the above processing in the real-time monitoring unit may be performed using AI, for example, or without AI. For example, the real-time monitoring unit can input meeting participant speech data into a generating AI and have the generating AI perform the detection of deviations from the agenda.

[0103] The real-time monitoring unit can estimate the emotions of meeting participants and adjust the timing of agenda deviation detection based on the estimated emotions. For example, if meeting participants are relaxed, the real-time monitoring unit can delay the timing of agenda deviation detection and allow for deviations. Conversely, if meeting participants are tense, the real-time monitoring unit can advance the timing of agenda deviation detection to detect deviations earlier. Furthermore, if meeting participants are tired, the real-time monitoring unit can set the timing of agenda deviation detection to a moderate level and allow for a moderate degree of deviation. By adjusting the timing of agenda deviation detection according to the emotions of meeting participants, more appropriate detection of agenda deviations becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the real-time monitoring unit may be performed using AI, for example, or without AI. For example, the real-time monitoring unit can input emotional data of meeting participants into a generating AI and have the generating AI adjust the timing of detecting deviations from the agenda.

[0104] The real-time monitoring unit can evaluate the impact of agenda deviations based on the positions and areas of expertise of meeting participants during real-time monitoring. For example, if a meeting participant holds a high position, the real-time monitoring unit may evaluate the impact of agenda deviations as low and tolerate the deviation. Furthermore, if a meeting participant's area of ​​expertise is related to the meeting agenda, the real-time monitoring unit may also evaluate the impact of agenda deviations as low and tolerate the deviation. Additionally, if a meeting participant holds a low position, the real-time monitoring unit may evaluate the impact of agenda deviations as high and detect the deviation early. This enables more appropriate agenda deviation management by evaluating the impact of agenda deviations based on the positions and areas of expertise of meeting participants. Some or all of the above processing in the real-time monitoring unit may be performed using AI, or not. For example, the real-time monitoring unit can input meeting participant position and area of ​​expertise data into a generating AI and have the generating AI perform the evaluation of the impact of agenda deviations.

[0105] The real-time monitoring unit can dynamically set the acceptable range of deviation from the agenda according to the meeting's theme and objectives during real-time monitoring. For example, if the meeting's theme is important, the real-time monitoring unit can set a narrower acceptable range of deviation to detect deviations early. Conversely, if the meeting's theme is less important, the real-time monitoring unit can set a wider acceptable range of deviation to allow deviations. Furthermore, if the meeting's objective is clear, the real-time monitoring unit can set a moderate acceptable range of deviation to allow a moderate amount of deviation. This allows for more appropriate management of agenda deviations by dynamically setting the acceptable range of deviation according to the meeting's theme and objectives. Some or all of the above processing in the real-time monitoring unit may be performed using AI, for example, or without AI. For example, the real-time monitoring unit can input meeting theme and objective data into a generating AI and have the generating AI set the acceptable range of deviation from the agenda.

[0106] The meeting support unit can estimate the emotions of meeting participants and adjust its support methods based on the estimated emotions. For example, if meeting participants are relaxed, the support unit will provide gentle support. If meeting participants are tense, the support unit can also provide quick and clear support. Furthermore, if meeting participants are tired, the support unit can provide support while suggesting appropriate breaks. By adjusting the support methods according to the emotions of meeting participants, more appropriate support becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the meeting support unit may be performed using AI, or not using AI. For example, the meeting support unit can input the emotional data of meeting participants into a generative AI and have the generative AI adjust the support methods.

[0107] The progress support unit can dynamically change the content of audio alerts and text messages according to the progress of the meeting during progress support. For example, if the meeting is behind schedule, the progress support unit can send urgent audio alerts and text messages. It can also send calm audio alerts and text messages if the meeting is progressing smoothly. Furthermore, if the meeting is stalled, the progress support unit can send audio alerts and text messages to encourage progress. By dynamically changing the content of audio alerts and text messages according to the progress of the meeting, more appropriate progress support becomes possible. Some or all of the above processing in the progress support unit may be performed using AI, for example, or not using AI. For example, the progress support unit can input meeting progress data into a generating AI and have the generating AI dynamically change the content of audio alerts and text messages.

[0108] The progress support unit can improve the accuracy of its progress support by learning the speaking patterns of meeting participants during progress support. For example, the progress support unit can improve the accuracy of its progress support by learning the past speaking patterns of meeting participants. It can also improve the accuracy of its progress support by analyzing the frequency and content of meeting participants' statements. Furthermore, it can improve the accuracy of its progress support by analyzing the tone and emotion of meeting participants' statements. In this way, the accuracy of progress support can be improved by learning the speaking patterns of meeting participants. Some or all of the above processing in the progress support unit may be performed using AI, for example, or without AI. For example, the progress support unit can input meeting participant statement data into a generating AI and have the generating AI perform the improvement of progress support accuracy.

[0109] The meeting support unit can estimate the emotions of meeting participants and determine the priority of meeting support based on the estimated emotions. For example, if a meeting participant is relaxed, the meeting support unit may set a low priority for meeting support. Conversely, if a meeting participant is tense, the meeting support unit may set a high priority for meeting support. Furthermore, if a meeting participant is tired, the meeting support unit may set a medium priority for meeting support. This allows for more appropriate meeting support by determining the priority of meeting support according to the emotions of the meeting participants. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the meeting support unit may be performed using AI, or not using AI. For example, the meeting support unit can input the emotional data of meeting participants into a generative AI and have the generative AI determine the priority of meeting support.

[0110] The progress support unit can customize the content of its progress support based on the roles and areas of expertise of the meeting participants. For example, if a meeting participant holds a high-ranking position, the progress support unit can provide important progress support. Furthermore, if a meeting participant's area of ​​expertise is relevant to the meeting agenda, the progress support unit can provide detailed progress support. Additionally, if a meeting participant holds a low-ranking position, the progress support unit can provide concise progress support. This allows for more appropriate progress support by customizing the content based on the roles and areas of expertise of the meeting participants. Some or all of the above processing in the progress support unit may be performed using AI, or not. For example, the progress support unit can input meeting participant role and area of ​​expertise data into a generating AI and have the generating AI customize the content of the progress support.

[0111] The progress support unit can dynamically change its method of progress support depending on the theme and purpose of the meeting. For example, if the meeting theme is important, the progress support unit can provide strict progress support. If the meeting theme is light, the progress support unit can also provide relaxed progress support. Furthermore, if the purpose of the meeting is clear, the progress support unit can provide progress support tailored to that purpose. By dynamically changing the method of progress support according to the theme and purpose of the meeting, more appropriate progress support becomes possible. Some or all of the above processing in the progress support unit may be performed using AI, for example, or not using AI. For example, the progress support unit can input meeting theme and purpose data into a generating AI and have the generating AI execute the dynamic change in the method of progress support.

[0112] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0113] An AI agent system for facilitating meetings can also be equipped with the ability to analyze the content of participants' remarks and evaluate the importance of those remarks. For example, if a remark is directly related to the meeting's goals, it will be highly rated and reflected in the meeting minutes. Conversely, if a remark does not contribute to the progress of the meeting, it will be lowly rated and not reflected in the minutes. Furthermore, if a remark hinders the progress of the meeting, it can be displayed as a warning to encourage the meeting to proceed smoothly. In this way, by evaluating the content of participants' remarks, the progress of the meeting can be managed more efficiently.

[0114] AI agent systems for facilitating meetings can also include features to monitor the frequency of participation and ensure equal opportunities for speaking. For example, if a particular participant speaks too much, the system can prompt that participant to reduce their participation. It can also display messages encouraging participants who speak less to speak up. Furthermore, to ensure equal opportunities for speaking, the system can display the number of times each participant has spoken in real time, allowing all participants to understand the speaking situation. This equalization of speaking opportunities can lead to smoother meeting progress.

[0115] AI agent systems for facilitating meetings can also have the ability to summarize participants' statements and extract key points. For example, they can analyze statements in real time and extract important keywords and phrases. They can also automatically generate meeting minutes summaries based on the extracted keywords and phrases. Furthermore, they can highlight important points to make them easy for all participants to understand. This allows for more efficient management of meeting progress by summarizing statements and extracting key points.

[0116] AI agent systems for facilitating meetings can also be equipped with the ability to analyze the content of participants' statements and evaluate the emotional tone of those statements. For example, if a statement has a positive tone, it will be highly rated and reflected in the meeting minutes. Conversely, if a statement has a negative tone, it will be lowly rated and not reflected in the meeting minutes. Furthermore, if a statement has a neutral tone, it can be moderately rated and reflected in the meeting minutes. By evaluating the emotional tone of statements, this can lead to smoother meeting progress.

[0117] AI agent systems for facilitating meetings can also be equipped with the ability to analyze the content of participants' statements and evaluate the reliability of those statements. For example, if a statement is based on a highly reliable source, it will be highly rated and reflected in the meeting minutes. Conversely, if a statement is based on a less reliable source, it will be lowly rated and not reflected in the meeting minutes. Furthermore, if a statement is based on a moderately reliable source, it can be moderately rated and reflected in the meeting minutes. This allows for more efficient management of meeting progress by evaluating the reliability of statements.

[0118] An AI agent system for facilitating meetings can also be equipped with the ability to analyze the content of participants' remarks and evaluate their relevance. For example, if a remark is directly related to the meeting agenda, it will be highly rated and reflected in the meeting minutes. Conversely, if a remark is not related to the agenda, it will be lowly rated and not reflected in the minutes. Furthermore, if a remark is partially related to the agenda, it can be moderately rated and reflected in the minutes. This allows for more efficient management of the meeting's progress by evaluating the relevance of remarks.

[0119] AI agent systems for facilitating meetings can also be equipped with the ability to analyze the content of participants' statements and evaluate the emotional tone of those statements. For example, if a statement has a positive tone, it will be highly rated and reflected in the meeting minutes. Conversely, if a statement has a negative tone, it will be lowly rated and not reflected in the meeting minutes. Furthermore, if a statement has a neutral tone, it can be moderately rated and reflected in the meeting minutes. By evaluating the emotional tone of statements, this can lead to smoother meeting progress.

[0120] AI agent systems for facilitating meetings can also be equipped with the ability to analyze the content of participants' statements and evaluate the reliability of those statements. For example, if a statement is based on a highly reliable source, it will be highly rated and reflected in the meeting minutes. Conversely, if a statement is based on a less reliable source, it will be lowly rated and not reflected in the meeting minutes. Furthermore, if a statement is based on a moderately reliable source, it can be moderately rated and reflected in the meeting minutes. This allows for more efficient management of meeting progress by evaluating the reliability of statements.

[0121] An AI agent system for facilitating meetings can also be equipped with the ability to analyze the content of participants' remarks and evaluate their relevance. For example, if a remark is directly related to the meeting agenda, it will be highly rated and reflected in the meeting minutes. Conversely, if a remark is not related to the agenda, it will be lowly rated and not reflected in the minutes. Furthermore, if a remark is partially related to the agenda, it can be moderately rated and reflected in the minutes. This allows for more efficient management of the meeting's progress by evaluating the relevance of remarks.

[0122] AI agent systems for facilitating meetings can also be equipped with the ability to analyze the content of participants' statements and evaluate the emotional tone of those statements. For example, if a statement has a positive tone, it will be highly rated and reflected in the meeting minutes. Conversely, if a statement has a negative tone, it will be lowly rated and not reflected in the meeting minutes. Furthermore, if a statement has a neutral tone, it can be moderately rated and reflected in the meeting minutes. By evaluating the emotional tone of statements, this can lead to smoother meeting progress.

[0123] The following briefly describes the processing flow for example form 2.

[0124] Step 1: The chat detection unit analyzes the audio data during the meeting in real time to detect chatter. The chat detection unit uses speech recognition technology to analyze the audio data during the meeting and distinguishes between chatter and statements related to the agenda. It can also detect chatter using keyword matching and contextual analysis. Furthermore, the chat detection unit can learn the speaking patterns of meeting participants to improve the accuracy of chatter detection. Step 2: The display unit displays a meeting summary based on the casual conversation detected by the casual conversation detection unit. The display unit displays the meeting summary on a whiteboard or online meeting tool. It can also display the progress of the meeting in real time. Furthermore, it can estimate the emotions of meeting participants and adjust the way the meeting summary is displayed based on the estimated emotions. Step 3: The progress monitoring unit keeps track of meeting time, agenda, and goals, and prompts progress via voice and text when stalls occur. The progress monitoring unit pre-sets the meeting agenda and goals and monitors progress in real time. It can also estimate the emotions of meeting participants and adjust the progress monitoring method based on the estimated emotions. Step 4: The real-time monitoring unit analyzes the audio data during the meeting to detect deviations from the agenda. The real-time monitoring unit uses speech recognition technology to analyze the audio data during the meeting and detect statements unrelated to the agenda. It can also learn the speaking patterns of meeting participants to more accurately detect deviations from the agenda. Furthermore, it can estimate the emotions of meeting participants and adjust the accuracy of agenda deviation detection based on the estimated emotions. Step 5: The meeting support unit prompts the meeting to proceed based on deviations from the agenda detected by the real-time monitoring unit. The meeting support unit prompts the meeting to proceed using voice alerts and text messages. It can also estimate the emotions of meeting participants and adjust the method of meeting support based on the estimated emotions.

[0125] 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.

[0126] Data generation model 58 is a form of 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> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. 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 (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0127] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0128] Each of the multiple elements described above, including the chat detection unit, display unit, progress monitoring unit, real-time monitoring unit, and progress support unit, is implemented, for example, by at least one of the smart device 14 and the data processing unit 12. For example, the chat detection unit is implemented by the microphone 38B and control unit 46A of the smart device 14, which analyzes audio data during the meeting in real time and detects chatter. The display unit is implemented, for example, by the display 40A and control unit 46A of the smart device 14, which displays a summary of the meeting minutes. The progress monitoring unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, which constantly monitors the meeting time, agenda, and meeting goals, and prompts progress with voice and text when there is stagnation. The real-time monitoring unit is implemented, for example, by the microphone 38B and control unit 46A of the smart device 14, which analyzes audio data during the meeting and detects deviations from the agenda. The progress support unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, which prompts the progress of the meeting based on the deviations from the agenda detected by the real-time monitoring unit. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0129] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0130] 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.

[0131] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0132] 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.

[0133] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0134] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0135] 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.

[0136] 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 by the processor 28. The storage 32 stores the specific processing program 56.

[0137] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0138] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0139] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0140] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0141] 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.

[0142] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0143] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0144] Each of the multiple elements described above, including the chat detection unit, display unit, progress monitoring unit, real-time monitoring unit, and progress support unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the chat detection unit is implemented by the microphone 238 and control unit 46A of the smart glasses 214, which analyzes audio data during the meeting in real time and detects chatter. The display unit is implemented, for example, by the display and control unit 46A of the smart glasses 214, which displays a summary of the meeting minutes. The progress monitoring unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, which constantly monitors the meeting time, agenda, and meeting goals, and prompts progress with voice and text when there is stagnation. The real-time monitoring unit is implemented, for example, by the microphone 238 and control unit 46A of the smart glasses 214, which analyzes audio data during the meeting and detects deviations from the agenda. The progress support unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, which prompts the progress of the meeting based on the deviations from the agenda detected by the real-time monitoring unit. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0145] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0146] 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.

[0147] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0148] 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.

[0149] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0150] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0151] 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.

[0152] 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.

[0153] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0154] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0155] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0156] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0157] 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.

[0158] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0159] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0160] Each of the multiple elements described above, including the chat detection unit, display unit, progress monitoring unit, real-time monitoring unit, and progress support unit, is implemented, for example, by at least one of the headset terminal 314 and the data processing unit 12. For example, the chat detection unit is implemented by the microphone 238 and control unit 46A of the headset terminal 314, which analyzes audio data during the meeting in real time and detects chatter. The display unit is implemented, for example, by the display 343 and control unit 46A of the headset terminal 314, which displays a summary of the meeting minutes. The progress monitoring unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, which constantly monitors the meeting time, agenda, and meeting goals, and prompts progress with voice and text when there is stagnation. The real-time monitoring unit is implemented, for example, by the microphone 238 and control unit 46A of the headset terminal 314, which analyzes audio data during the meeting and detects deviations from the agenda. The progress support unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and facilitates the progress of the meeting based on deviations from the agenda detected by the real-time monitoring unit. The correspondence between each unit and the devices and control units is not limited to the example described above and can be modified in various ways.

[0161] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0162] 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.

[0163] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0164] 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.

[0165] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0166] 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 image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0167] 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.

[0168] 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. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0169] 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.

[0170] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0171] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0172] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0173] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0174] 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.

[0175] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0176] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0177] Each of the multiple elements described above, including the chat detection unit, display unit, progress monitoring unit, real-time monitoring unit, and progress support unit, is implemented, for example, by at least one of the robot 414 and the data processing unit 12. For example, the chat detection unit is implemented by the microphone 238 and control unit 46A of the robot 414, which analyzes audio data during the meeting in real time and detects chatter. The display unit is implemented, for example, by the display and control unit 46A of the robot 414, which displays a summary of the meeting minutes. The progress monitoring unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, which constantly monitors the meeting time, agenda, and meeting goals, and prompts progress with voice and text when there is stagnation. The real-time monitoring unit is implemented, for example, by the microphone 238 and control unit 46A of the robot 414, which analyzes audio data during the meeting to detect deviations from the agenda. The progress support unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, which prompts the progress of the meeting based on the deviations from the agenda detected by the real-time monitoring unit. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0178] 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.

[0179] Figure 9 shows the 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.

[0180] 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.

[0181] 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.

[0182] 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, and motorcycles, 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 based, for example, 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.

[0183] 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."

[0184] 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.

[0185] 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 method for the specific process may be used, which includes computer 22 and multiple other computers.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0194] 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 other things 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.

[0195] 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.

[0196] (Note 1) A chat detection unit analyzes audio data during meetings in real time to detect casual conversation, A display unit that displays a summary of the meeting minutes based on the casual conversation detected by the casual conversation detection unit, The progress monitoring department keeps track of meeting time, agenda, and goals, and prompts progress via voice and text when delays occur. A real-time monitoring unit analyzes audio data during meetings to detect deviations from the agenda, The system includes a progress support unit that facilitates the progress of the meeting based on deviations from the agenda detected by the real-time monitoring unit. A system characterized by the following features. (Note 2) The aforementioned casual conversation detection unit, The system analyzes audio data from meetings in real time to distinguish between casual conversation and statements related to the agenda. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned progress monitoring unit, Set the meeting agenda and goals in advance, and monitor the progress in real time. The system described in Appendix 1, characterized by the features described herein. (Note 4) The real-time monitoring unit described above is: Analyze audio data to detect deviations from the agenda. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned display unit is Display meeting minutes and progress on a whiteboard or online tool. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned progress support unit is: When the meeting stalls, audio alerts and text prompts will prompt progress. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned casual conversation detection unit, The system estimates the emotions of meeting participants and adjusts the accuracy of casual conversation detection based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned casual conversation detection unit, When casual conversation is detected, the importance of the conversation is evaluated according to the progress of the meeting, and a warning is issued if necessary. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned casual conversation detection unit, When detecting casual conversation, the system learns the speaking patterns of meeting participants to more accurately distinguish between casual conversation and discussion-related statements. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned casual conversation detection unit, The system estimates the emotions of meeting participants and adjusts the timing of casual conversation detection based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned casual conversation detection unit, When casual conversation is detected, the impact of the conversation is evaluated based on the roles and areas of expertise of the meeting participants. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned casual conversation detection unit, When casual conversation is detected, the system dynamically sets the acceptable level of casual conversation according to the meeting's theme and purpose. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned display unit is The system estimates the emotions of meeting participants and adjusts how the meeting minutes summary is displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned display unit is When displayed, the content is dynamically updated according to the progress of the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned display unit is When displaying information, the displayed content will be customized according to the role and area of ​​expertise of the meeting participants. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned display unit is The system estimates the emotions of meeting participants and prioritizes the information to display based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned display unit is When displaying information, the system selects the optimal display method based on the device information of the meeting participants. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned display unit is When displayed, the content is dynamically changed according to the meeting's theme and purpose. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned data transfer monitoring unit is Estimate the emotions of meeting participants and adjust the method of monitoring the progress based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned data transfer monitoring unit is During progress monitoring, the agenda and goal priorities are dynamically changed according to the meeting's progress. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned data transfer monitoring unit is During progress monitoring, the system learns the speaking patterns of meeting participants to improve the accuracy of monitoring the progress. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned data transfer monitoring unit is The system estimates the emotions of meeting participants and adjusts the frequency of monitoring the meeting's progress based on these estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned data transfer monitoring unit is When monitoring progress, set evaluation criteria for the meeting based on the roles and areas of expertise of the meeting participants. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned data transfer monitoring unit is During progress monitoring, the method of monitoring progress is dynamically changed according to the meeting's theme and objectives. The system described in Appendix 1, characterized by the features described herein. (Note 25) The real-time monitoring unit described above is: The system estimates the emotions of meeting participants and adjusts the accuracy of agenda deviation detection based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The real-time monitoring unit described above is: During real-time monitoring, the importance of deviations from the agenda is evaluated according to the progress of the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 27) The real-time monitoring unit described above is: During real-time monitoring, the system learns the speaking patterns of meeting participants to more accurately detect deviations from the agenda. The system described in Appendix 1, characterized by the features described herein. (Note 28) The real-time monitoring unit described above is: The system estimates the emotions of meeting participants and adjusts the timing of agenda deviation detection based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The real-time monitoring unit described above is: During real-time monitoring, the impact of deviating from the agenda is assessed based on the roles and areas of expertise of meeting participants. The system described in Appendix 1, characterized by the features described herein. (Note 30) The real-time monitoring unit described above is: During real-time monitoring, the acceptable range for deviations from the agenda is dynamically set according to the meeting's theme and objectives. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned progress support unit is: The system estimates the emotions of meeting participants and adjusts the method of facilitating support based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned progress support unit is: During meeting progress support, the content of audio alerts and text messages is dynamically changed according to the progress of the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned progress support unit is: During meeting support, the system learns the speaking patterns of meeting participants to improve the accuracy of the support. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned progress support unit is: The system estimates the emotions of meeting participants and prioritizes facilitator support based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned progress support unit is: During meeting support, customize the support content based on the roles and areas of expertise of the meeting participants. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned progress support unit is: During meeting management support, the method of support is dynamically changed according to the meeting's theme and objectives. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0197] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A chat detection unit analyzes audio data during meetings in real time to detect casual conversation, A display unit that displays a summary of the meeting minutes based on the casual conversation detected by the casual conversation detection unit, The progress monitoring department keeps track of meeting time, agenda, and goals, and prompts progress via voice and text when delays occur. A real-time monitoring unit analyzes audio data during meetings to detect deviations from the agenda, The system includes a progress support unit that facilitates the progress of the meeting based on deviations from the agenda detected by the real-time monitoring unit. A system characterized by the following features.

2. The aforementioned casual conversation detection unit, The system analyzes audio data from meetings in real time to distinguish between casual conversation and statements related to the agenda. The system according to feature 1.

3. The aforementioned progress monitoring unit, Set the meeting agenda and goals in advance, and monitor the progress in real time. The system according to feature 1.

4. The real-time monitoring unit described above is: Analyze audio data to detect deviations from the agenda. The system according to feature 1.

5. The aforementioned display unit is Display meeting minutes and progress updates on a whiteboard or online tools. The system according to feature 1.

6. The aforementioned progress support unit is: When the meeting stalls, audio alerts and text prompts will guide the process forward. The system according to feature 1.

7. The aforementioned casual conversation detection unit, The system estimates the emotions of meeting participants and adjusts the accuracy of casual conversation detection based on the estimated emotions. The system according to feature 1.

8. The aforementioned casual conversation detection unit, When casual conversation is detected, the importance of the conversation is evaluated according to the progress of the meeting, and a warning is issued if necessary. The system according to feature 1.

9. The aforementioned casual conversation detection unit, When detecting casual conversation, the system learns the speaking patterns of meeting participants to more accurately distinguish between casual conversation and discussion-related statements. The system according to feature 1.

10. The aforementioned casual conversation detection unit, The system estimates the emotions of meeting participants and adjusts the timing of casual conversation detection based on the estimated emotions. The system according to feature 1.

Images