system

Abstract

The system according to this embodiment aims to facilitate meetings and reach conclusions in a short amount of time. [Solution] The system according to the embodiment comprises an agenda organization unit, a discussion activation unit, a recording unit, an aggregation unit, and a summary unit. The agenda organization unit organizes the agenda items. The discussion activation unit activates the discussion based on the agenda items organized by the agenda organization unit. The recording unit records the progress of the discussion activated by the discussion activation unit in real time. The aggregation unit aggregates and summarizes the opinions of the participants based on the content recorded by the recording unit. The summary unit extracts the essence of the discussion based on the opinions aggregated by the aggregation unit and summarizes it effectively.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] [[ID=3^4]] In the conventional technology, meetings may be prolonged and take a lot of time to reach a conclusion, which may cause dissatisfaction among participants.

[0005] The system according to the embodiment aims to efficiently conduct a meeting and reach a conclusion in a short time.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an agenda organization unit, a discussion activation unit, a recording unit, an aggregation unit, and a summary unit. The agenda organization unit organizes the agenda items. The discussion activation unit activates the discussion based on the agenda items organized by the agenda organization unit. The recording unit records the progress of the discussion activated by the discussion activation unit in real time. The aggregation unit aggregates and summarizes the opinions of the participants based on the content recorded by the recording unit. The summary unit extracts the essence of the discussion based on the opinions aggregated by the aggregation unit and summarizes it effectively. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently conduct meetings and reach conclusions in a short amount of time. [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 labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 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 meeting efficiency system according to an embodiment of the present invention is a system using an AI agent aimed at improving the efficiency and quality of meetings. In this meeting efficiency system, first, the AI ​​agent organizes the meeting agenda and stimulates discussion. Next, the AI ​​agent records the progress of the discussion in real time and aggregates and summarizes the opinions of the participants. Furthermore, by extracting the essence of the discussion and summarizing it effectively, the AI ​​agent can reach a conclusion in a short time. This mechanism improves meeting performance and reduces participant dissatisfaction. For example, the AI ​​agent organizes the meeting agenda. In this process, the AI ​​agent clarifies the purpose and goals of the meeting and presents the agenda in an easy-to-understand manner. For example, before the start of the meeting, the AI ​​agent creates an agenda list and shares it with the participants, which helps the meeting proceed smoothly. Next, the AI ​​agent stimulates discussion. The AI ​​agent encourages participants to speak and supports the discussion to prevent it from stagnating. For example, by asking questions at appropriate times and indicating the direction of the discussion, the AI ​​agent stimulates the exchange of opinions among participants. Furthermore, the AI ​​agent records the progress of the discussion in real time. The AI ​​agent uses speech recognition technology to transcribe what is said during a meeting into text and automatically generates meeting minutes. This frees participants from the burden of manually compiling meeting minutes. The AI ​​agent also aggregates and summarizes participants' opinions. The AI ​​agent extracts the key points of each statement and summarizes the essence of the discussion. For example, the AI ​​agent highlights and shares important points of the discussion with participants, making it easy to follow the flow of the discussion. Finally, the AI ​​agent extracts the essence of the discussion and summarizes it effectively. The AI ​​agent organizes the results of the discussion and derives a conclusion. This allows for conclusions to be reached in a short time, improving meeting performance. This system achieves increased efficiency and improved quality in meetings, reducing participant dissatisfaction. For example, because conclusions are reached quickly without meetings running long, participants can experience stress-free meeting management. In addition, since the AI ​​agent automatically generates meeting minutes, the burden of manually compiling meeting minutes is reduced.Furthermore, the AI ​​agent extracts the essence of the discussion and summarizes it effectively, improving the quality of the meeting and increasing participant satisfaction. Thus, the meeting efficiency system can achieve both increased efficiency and improved quality in meetings, while reducing participant dissatisfaction.

[0029] The meeting efficiency system according to this embodiment comprises an agenda organization unit, a discussion activation unit, a recording unit, an aggregation unit, and a summary unit. The agenda organization unit organizes the agenda. For example, the agenda organization unit clarifies the purpose and objectives of the meeting and creates an agenda list. The agenda organization unit can organize the agenda based on a classification method and a method for prioritizing the agenda. The discussion activation unit activates the discussion based on the agenda organized by the agenda organization unit. For example, the discussion activation unit asks questions at appropriate times and indicates the direction of the discussion. The discussion activation unit can encourage participants to speak and support the discussion to prevent it from stagnating. The recording unit records the progress of the discussion activated by the discussion activation unit in real time. For example, the recording unit uses speech recognition technology to transcribe the content of speech during the meeting into text and automatically generates meeting minutes. The recording unit can perform recording based on a speech recognition algorithm and a method for processing speech data. The aggregation unit aggregates and summarizes the opinions of the participants based on the content recorded by the recording unit. The summarization unit extracts key points from each statement and highlights important aspects of the discussion. The summarization unit can consolidate opinions based on a method for classifying opinions and criteria for summarization. The concluding unit extracts the essence of the discussion based on the opinions consolidated by the summarization unit and summarizes them effectively. The concluding unit organizes the results of the discussion and draws conclusions. The concluding unit can summarize the discussion based on a method for extracting key points and criteria for summarization. As a result, the meeting efficiency system according to this embodiment can improve the efficiency and quality of meetings and reduce participant dissatisfaction.

[0030] The agenda planning team clarifies the purpose and objectives of the meeting and creates an agenda list. Specifically, the meeting organizer or facilitator sets the meeting's objectives and lists the agenda items based on those objectives. The agenda planning team can organize the agenda items based on classification and prioritization methods. For example, they can classify and prioritize items based on criteria such as "importance," "urgency," and "relevance." This ensures smooth meeting progress and prevents important agenda items from being overlooked. Furthermore, the agenda planning team can improve the selection and organization of agenda items by utilizing past meeting data and participant feedback. For example, they can improve the quality of meetings by prioritizing items that did not receive enough time in past meetings or items that were frequently requested by participants. In addition, the agenda planning team can use AI to automatically generate and classify agenda items. For example, they can use natural language processing technology to analyze the meeting's objectives and participants' opinions and automatically suggest appropriate agenda items. This improves the efficiency of agenda planning and reduces meeting preparation time.

[0031] The Discussion Activation Department activates discussions based on the agenda items organized by the Agenda Organization Department. Specifically, it asks questions at appropriate times and guides the direction of the discussion. For example, if the discussion is stalled or if the opinions of a particular participant are not being adequately reflected, the Discussion Activation Department intervenes and revitalizes the discussion by asking questions or making comments. The Discussion Activation Department can also encourage participants to speak up and support the discussion to prevent it from stagnating. For example, it can monitor the number of times and the duration of each participant's contributions to create an environment where specific participants feel comfortable speaking. Furthermore, the Discussion Activation Department can utilize AI to support the progress of discussions. For example, it can use natural language processing technology to analyze the content of the discussion in real time and automatically generate questions and comments at appropriate times. This improves the quality of the discussion and allows all participants to actively engage. In addition, the Discussion Activation Department can analyze past discussion data and understand discussion patterns and trends to improve how discussions are conducted. For example, it can optimize the progress of discussions by referring to questions and comments that were effective in past discussions. In this way, the Discussion Activation Department can improve the efficiency and quality of meetings and increase participant satisfaction.

[0032] The recording unit records the progress of discussions activated by the discussion activation unit in real time. Specifically, it uses speech recognition technology to transcribe the content of speeches during meetings into text and automatically generates meeting minutes. The speech recognition algorithm can recognize speeches during meetings with high accuracy and record them as text data. This allows for the creation of accurate meeting minutes without disrupting the flow of the meeting. The recording unit can also record based on how it processes the audio data. For example, by dividing the audio data by speaker and organizing the content of speeches, the readability of the meeting minutes can be improved. Furthermore, the recording unit can use AI to automatically summarize meeting minutes and extract keywords. For example, by using natural language processing technology to analyze the content of the meeting minutes and extract important points and keywords, it can automatically generate a summary of the meeting minutes. This allows participants to quickly grasp the main points of the meeting and facilitates follow-up after the meeting. In addition, the recording unit can use past meeting minute data to improve the method and content of creating meeting minutes. For example, it can enrich the content of meeting minutes based on information that was missing in past minutes or feedback from participants. This allows the recording department to improve the efficiency and quality of meetings, thereby increasing participant satisfaction.

[0033] The aggregation unit consolidates and summarizes participants' opinions based on the content recorded by the recording unit. Specifically, it extracts the key points of each statement and emphasizes the important points of the discussion. For example, by using natural language processing technology to analyze the content of statements and extract important keywords and phrases, the key points of the discussion can be organized. The aggregation unit can consolidate opinions based on classification methods and aggregation criteria. For example, by classifying opinions into categories such as "agree," "disagree," and "reserve," and organizing opinions within each category, it becomes easier to grasp the overall picture of the discussion. Furthermore, the aggregation unit can utilize AI to automatically aggregate and summarize opinions. For example, by using machine learning algorithms to analyze the content of statements and group similar opinions, the aggregation of opinions can be made more efficient. This allows the aggregation unit to quickly and accurately consolidate opinions and grasp the overall picture of the discussion. In addition, the aggregation unit can improve its opinion aggregation methods and criteria by utilizing past discussion data. For example, it can optimize opinion aggregation by referring to aggregation methods and criteria that were effective in past discussions. This allows the consolidation department to improve the efficiency and quality of meetings, thereby increasing participant satisfaction.

[0034] The summarizing team extracts the essence of the discussion based on the opinions aggregated by the summarizing team and summarizes them effectively. Specifically, it organizes the results of the discussion and derives conclusions. For example, by using natural language processing technology to analyze the aggregated opinions and extract key points and conclusions, the main points of the discussion can be organized. The summarizing team can summarize the discussion based on criteria for extracting key points and summarizing methods. For example, by classifying the main points of the discussion into categories such as "problems," "solutions," and "next steps," and organizing the key points for each category, it becomes easier to grasp the overall picture of the discussion. Furthermore, the summarizing team can also use AI to automatically summarize discussions and generate conclusions. For example, by using machine learning algorithms to analyze the content of the discussion and automatically generate key points and conclusions, the main points of the discussion can be grasped quickly. As a result, the summarizing team can summarize discussions quickly and accurately, improving the efficiency and quality of meetings. In addition, the summarizing team can use past discussion data to improve how discussions are summarized and how conclusions are drawn. For example, by referring to effective summarization methods and conclusion-reaching techniques from past discussions, the summarization process can be optimized. This allows the summarization team to improve the efficiency and quality of meetings, and increase participant satisfaction.

[0035] The recording unit can use speech recognition technology to transcribe the content of a meeting into text and automatically generate meeting minutes. For example, the recording unit can use a speech recognition algorithm to transcribe the content of a meeting into text in real time. The recording unit can also transcribe the content of a meeting into text based on a method for processing audio data. Furthermore, the recording unit can use speech recognition technology to automatically classify the content of a meeting and generate meeting minutes. This reduces the burden of manually organizing meeting minutes. Some or all of the above-described processes in the recording unit may be performed using AI, for example, or without AI. For example, the recording unit can input the content of a meeting into a generating AI and have the generating AI transcribe the content of the meeting into text.

[0036] The discussion activation unit can ask questions at appropriate times and guide the direction of the discussion. For example, the discussion activation unit can ask questions at appropriate times based on the interval between comments and the progress of the discussion. It can also guide the direction of the discussion based on how the discussion is progressing. Furthermore, the discussion activation unit can encourage participants to speak and support the discussion to prevent it from stagnating. This prevents the discussion from stalling and promotes active exchange of opinions. Some or all of the above processing in the discussion activation unit may be performed using AI, for example, or not using AI. For example, the discussion activation unit can input the progress of the discussion into a generating AI and cause the generating AI to ask questions at appropriate times.

[0037] The summarization unit can extract the main points of each statement and highlight the important points of the discussion. For example, the summarization unit can extract the main points and highlight the important points based on keyword extraction methods and highlighting methods. The summarization unit can also summarize opinions based on opinion classification methods and summarization criteria. Furthermore, the summarization unit can highlight the important points so that the flow of the discussion can be easily followed. This makes it easy to follow the flow of the discussion. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input the content of the statements into a generating AI and have the generating AI perform the extraction of main points and the highlighting of important points.

[0038] The summarizing unit can organize the results of a discussion and draw conclusions. For example, the summarizing unit can organize the results of a discussion and draw conclusions based on methods for classifying results and methods for deriving conclusions. The summarizing unit can also summarize the discussion based on methods for extracting key points and criteria for summarization. Furthermore, the summarizing unit can extract the essence of the discussion and summarize it effectively. This allows for conclusions to be reached in a short time, improving the performance of the meeting. Some or all of the above-described processes in the summarizing unit may be performed using AI, for example, or not. For example, the summarizing unit can input the results of the discussion into a generating AI and have the generating AI derive conclusions.

[0039] The agenda planning unit can clarify the purpose and objectives of a meeting and create an agenda list. For example, the agenda planning unit can clarify the purpose and objectives of a meeting and create an agenda list based on methods for setting objectives and creating agenda lists. The agenda planning unit can also organize the agenda based on methods for classifying and prioritizing agenda items. Furthermore, the agenda planning unit can share the agenda list with participants to ensure the smooth progress of the meeting. This ensures the smooth progress of the meeting. Some or all of the above processes in the agenda planning unit may be performed using AI, for example, or not using AI. For example, the agenda planning unit can input the purpose and objectives of the meeting into a generating AI and have the generating AI create the agenda list.

[0040] The agenda organization unit can analyze past meeting data and automatically group similar agenda items. For example, it can extract and group agenda items on the same theme from past meeting data. It can also treat similar agenda items as a single item to facilitate discussion. Furthermore, it can automatically link related agenda items based on past meeting data to streamline the flow of discussion. This allows for efficient discussion of similar agenda items. Some or all of the above processing in the agenda organization unit may be performed using AI, for example, or without AI. For example, the agenda organization unit can input past meeting data into a generating AI and have the generating AI perform the grouping of similar agenda items.

[0041] The agenda planning unit can dynamically adjust the level of detail of the agenda items according to the purpose of the meeting. For example, if the purpose of the meeting is to reach a conclusion in a short time, the agenda planning unit will reduce the level of detail of the agenda items and present only the key points. Conversely, if the purpose of the meeting is to have an in-depth discussion, the agenda planning unit can increase the level of detail of the agenda items and provide detailed information. Furthermore, the agenda planning unit can adjust the level of detail of the agenda items in real time according to the progress of the meeting, thereby smoothing the flow of discussion. This ensures a smooth discussion flow by providing an agenda level of detail appropriate to the purpose of the meeting. Some or all of the above processing in the agenda planning unit may be performed using AI, for example, or not using AI. For example, the agenda planning unit can input the purpose of the meeting into a generating AI and have the generating AI perform the adjustment of the level of detail of the agenda items.

[0042] The agenda planning unit can automatically provide relevant information on the agenda based on the participants' areas of expertise. For example, the agenda planning unit can automatically collect information related to the participants' areas of expertise and provide it in relation to the agenda. The agenda planning unit can also provide background information on the agenda based on the participants' areas of expertise to deepen the discussion. Furthermore, the agenda planning unit can refer to past meeting data related to the participants' areas of expertise and provide it in relation to the agenda. This deepens the discussion by providing information related to the participants' areas of expertise. Some or all of the above processing in the agenda planning unit may be performed using AI, for example, or without AI. For example, the agenda planning unit can input participants' areas of expertise data into a generating AI and have the generating AI perform the provision of relevant information.

[0043] The agenda planning unit can adjust the order of agenda items in real time according to the progress of the meeting. For example, the agenda planning unit can prioritize important agenda items depending on the progress of the meeting. The agenda planning unit can also flexibly adjust the order of agenda items according to the progress of the meeting to ensure a smooth flow of discussion. Furthermore, the agenda planning unit can postpone time-consuming agenda items and prioritize those that can be resolved quickly, depending on the progress of the meeting. This ensures a smooth flow of discussion by providing an agenda order that is appropriate to the progress of the meeting. Some or all of the above processes in the agenda planning unit may be performed using AI, for example, or not. For example, the agenda planning unit can input meeting progress data into a generating AI and have the generating AI perform the adjustment of the agenda order.

[0044] The discussion activation unit can analyze past discussion data, predict points where discussions are likely to stall, and take countermeasures. For example, the discussion activation unit can extract points where discussions are likely to stall from past discussion data and take countermeasures. The discussion activation unit can also predict points where discussions are likely to stall and ask questions at the appropriate time. Furthermore, the discussion activation unit can predict points where discussions are likely to stall and indicate the direction of the discussion. In this way, by predicting points where discussions are likely to stall and taking countermeasures, the flow of discussion becomes smoother. Some or all of the above processing in the discussion activation unit may be performed using AI, for example, or not using AI. For example, the discussion activation unit can input past discussion data into a generating AI and have the generating AI predict stall points and take countermeasures.

[0045] The discussion activation unit can automatically generate appropriate questions based on the participants' speaking history. For example, the discussion activation unit can analyze the participants' speaking history and automatically generate relevant questions. It can also automatically generate questions to deepen the discussion based on the participants' speaking history. Furthermore, it can automatically generate questions that indicate the direction of the discussion based on the participants' speaking history. In this way, the discussion is deepened by providing questions based on the participants' speaking history. Some or all of the above processing in the discussion activation unit may be performed using AI, for example, or without AI. For example, the discussion activation unit can input the participants' speaking history data into a generating AI and have the generating AI perform the automatic generation of questions.

[0046] The discussion activation unit can adjust the depth of the discussion based on the participants' expertise. For example, the discussion activation unit can deepen the discussion based on the participants' expertise. It can also shallow the discussion based on the participants' expertise. Furthermore, the discussion activation unit can adjust the depth of the discussion based on the participants' expertise to make the flow of the discussion smoother. This deepens the discussion by providing a depth of discussion appropriate to the participants' expertise. Some or all of the above processing in the discussion activation unit may be performed using AI, for example, or without AI. For example, the discussion activation unit can input participant expertise data into a generating AI and have the generating AI perform the adjustment of the discussion depth.

[0047] The discussion activation unit can dynamically change the discussion topics according to the progress of the meeting. For example, the discussion activation unit can change the discussion topics according to the progress of the meeting to make the discussion flow smoothly. The discussion activation unit can also prioritize discussion of important topics according to the progress of the meeting. Furthermore, the discussion activation unit can flexibly change the discussion topics according to the progress of the meeting to prevent the discussion from stagnating. In this way, by providing discussion topics that are appropriate to the progress of the meeting, the flow of the discussion becomes smoother. Some or all of the above processing in the discussion activation unit may be performed using AI, for example, or without using AI. For example, the discussion activation unit can input meeting progress data into a generating AI and cause the generating AI to change the discussion topics.

[0048] The recording unit can use speech recognition technology to generate records in different formats for each speaker. For example, the recording unit can generate records in different formats for each speaker to improve readability. The recording unit can also generate records in different formats for each speaker to smooth the flow of the discussion. Furthermore, the recording unit can generate records in different formats for each speaker to highlight the main points of the discussion. As a result, generating records in different formats for each speaker improves readability and makes the flow of the discussion smoother. Some or all of the above processing in the recording unit may be performed using AI, for example, or without AI. For example, the recording unit can input the content of the speech into a generation AI and have the generation AI perform the generation of records in a format specific to each speaker.

[0049] The recording unit can highlight key points of the meeting in real time according to the progress of the meeting. For example, the recording unit can highlight important points in real time according to the progress of the meeting. The recording unit can also highlight key points of the discussion in real time according to the progress of the meeting, thereby smoothing the flow of the discussion. Furthermore, the recording unit can highlight key points in real time according to the progress of the meeting, thereby preventing stagnation in the discussion. In this way, by providing highlighting of key points according to the progress of the meeting, the flow of the discussion becomes smoother. Some or all of the above processing in the recording unit may be performed using AI, for example, or without using AI. For example, the recording unit can input meeting progress data into a generating AI and have the generating AI perform the highlighting of key points.

[0050] The recording unit can automatically summarize the recorded content and provide it to participants in real time. For example, the recording unit can automatically summarize the recorded content and provide it to participants in real time. Furthermore, the recording unit can automatically summarize the recorded content and highlight the key points of the discussion. In addition, the recording unit can automatically summarize the recorded content and smooth the flow of the discussion. This means that by automatically summarizing the recorded content, the key points of the discussion are highlighted and the flow of the discussion becomes smoother. Some or all of the above processing in the recording unit may be performed using AI, for example, or without AI. For example, the recording unit can input the recorded content into a generating AI and have the generating AI perform the generation of the summary.

[0051] The recording unit can save the recorded content to the cloud, making it accessible to participants at any time. For example, the recording unit can save the recorded content to the cloud, making it accessible to participants at any time. The recording unit can also save the recorded content to the cloud and highlight the key points of the discussion. Furthermore, the recording unit can save the recorded content to the cloud and streamline the flow of the discussion. This allows participants to access the recorded content at any time and facilitates a smoother discussion flow. Some or all of the above-described processes in the recording unit may be performed using AI, or not. For example, the recording unit can input the recorded content into a generating AI and have the generating AI perform the task of saving it to the cloud.

[0052] The aggregation unit can automatically evaluate the importance of each statement and prioritize the aggregation of important opinions. For example, the aggregation unit can automatically evaluate the importance of each statement and prioritize the aggregation of important opinions. The aggregation unit can also emphasize the main points of the discussion based on the importance of the statements. Furthermore, the aggregation unit can also smooth the flow of the discussion based on the importance of the statements. As a result, by prioritizing the aggregation of important opinions, the main points of the discussion are emphasized and the flow of the discussion becomes smoother. Some or all of the above processing in the aggregation unit may be performed using AI, for example, or without AI. For example, the aggregation unit can input the content of the statements into a generating AI and have the generating AI perform the evaluation of importance and the aggregation of opinions.

[0053] The aggregation unit can automatically group similar opinions by referring to past meeting data. For example, the aggregation unit can automatically group similar opinions by referring to past meeting data. The aggregation unit can also treat similar opinions as a single opinion and proceed with the discussion efficiently. Furthermore, the aggregation unit can automatically link related opinions based on past meeting data to smooth the flow of the discussion. This allows for the efficient discussion by grouping similar opinions. Some or all of the above processing in the aggregation unit may be performed using AI, for example, or without AI. For example, the aggregation unit can input past meeting data into a generating AI and have the generating AI perform the grouping of similar opinions.

[0054] The aggregation unit can automatically summarize the aggregated opinions and provide them to participants in real time. For example, the aggregation unit can automatically summarize the aggregated opinions and provide them to participants in real time. The aggregation unit can also automatically summarize the aggregated opinions and highlight the key points of the discussion. Furthermore, the aggregation unit can automatically summarize the aggregated opinions and smooth the flow of the discussion. By automatically summarizing the aggregated opinions, the key points of the discussion are highlighted and the flow of the discussion becomes smoother. Some or all of the above processing in the aggregation unit may be performed using AI, for example, or without AI. For example, the aggregation unit can input the aggregated opinions into a generating AI and have the generating AI perform the generation of the summary.

[0055] The aggregation unit can store the aggregated opinions on the cloud, making them accessible to participants at any time. For example, the aggregation unit can store the aggregated opinions on the cloud, making them accessible to participants at any time. The aggregation unit can also store the aggregated opinions on the cloud and highlight the key points of the discussion. Furthermore, the aggregation unit can store the aggregated opinions on the cloud and streamline the flow of the discussion. This allows participants to access the aggregated opinions at any time and streamlines the flow of the discussion. Some or all of the above-described processes in the aggregation unit may be performed using AI, for example, or without AI. For example, the aggregation unit can input the aggregated opinions into a generating AI and have the generating AI perform the task of saving them to the cloud.

[0056] The summarizing unit can automatically derive the optimal conclusion by referring to past meeting data. For example, the summarizing unit can automatically derive the optimal conclusion by referring to past meeting data. Furthermore, the summarizing unit can automatically link related conclusions based on past meeting data, making the flow of discussion smoother. In addition, the summarizing unit can derive the optimal conclusion based on past meeting data and highlight the key points of the discussion. This makes the flow of discussion smoother by deriving the optimal conclusion based on past meeting data. Some or all of the above processing in the summarizing unit may be performed using AI, for example, or without AI. For example, the summarizing unit can input past meeting data into a generating AI and have the generating AI derive the optimal conclusion.

[0057] The summarizing unit can dynamically adjust the level of detail of the conclusions according to the progress of the meeting. For example, the summarizing unit can dynamically adjust the level of detail of the conclusions according to the progress of the meeting to ensure a smooth flow of discussion. The summarizing unit can also prioritize and present important conclusions according to the progress of the meeting. Furthermore, the summarizing unit can flexibly adjust the level of detail of the conclusions according to the progress of the meeting to prevent stagnation of discussion. This ensures a smooth flow of discussion by providing a level of detail of conclusions that is appropriate to the progress of the meeting. Some or all of the above processing in the summarizing unit may be performed using AI, for example, or without AI. For example, the summarizing unit can input meeting progress data into a generating AI and have the generating AI perform the adjustment of the level of detail of the conclusions.

[0058] The summarizing unit can automatically summarize the conclusions and provide them to participants in real time. For example, the summarizing unit can automatically summarize the conclusions and provide them to participants in real time. The summarizing unit can also automatically summarize the conclusions and highlight the key points of the discussion. Furthermore, the summarizing unit can automatically summarize the conclusions and smooth the flow of the discussion. By automatically summarizing the conclusions, the key points of the discussion are highlighted and the flow of the discussion becomes smoother. Some or all of the above processing in the summarizing unit may be performed using AI, for example, or not using AI. For example, the summarizing unit can input the conclusions into a generating AI and have the generating AI perform the generation of the summary.

[0059] The summarizing unit can save the conclusions to the cloud, making them accessible to participants at any time. For example, the summarizing unit can save the conclusions to the cloud, making them accessible to participants at any time. The summarizing unit can also save the conclusions to the cloud and highlight the key points of the discussion. Furthermore, the summarizing unit can save the conclusions to the cloud and streamline the flow of the discussion. This allows participants to access the conclusions at any time and streamlines the flow of the discussion. Some or all of the above processing in the summarizing unit may be performed using AI, for example, or not. For example, the summarizing unit can input the conclusions into a generating AI and have the generating AI perform the task of saving them to the cloud.

[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] The meeting efficiency system can also include a feedback function. This function collects feedback from participants after the meeting and identifies areas for improvement for future meetings. For example, it can send questionnaires to participants to gather opinions on the meeting's progress and content. It can also analyze the collected feedback and generate suggestions for improving meeting procedures and agenda setting. Furthermore, the feedback function can adjust the meeting's progress in real time based on participant feedback. This ensures that meetings reflect participant opinions and improve their quality.

[0062] The meeting efficiency system can also be equipped with a notification function. This notification function can inform participants in real time about the meeting's progress and any changes to important agenda items. For example, it can notify participants when it's time to move on to the next agenda item, depending on the meeting's progress. It can also notify participants of any changes to important agenda items. Furthermore, if the meeting is falling behind schedule, it can notify participants and encourage them to speed up the discussion. This makes it easier for participants to understand the meeting's progress and improves meeting efficiency.

[0063] The meeting efficiency system can also include a translation function. This function can translate speech in real time to facilitate communication between participants who speak different languages. For example, it can automatically translate and display speech during a meeting. It can also generate meeting minutes in multiple languages ​​and provide them to participants. Furthermore, if a participant speaks in a different language, the translation function can translate that speech in real time and share it with other participants. This improves communication between participants who speak different languages ​​and increases meeting efficiency.

[0064] The meeting efficiency system can also include a time management unit. This unit manages meeting time and adjusts the time allocation for each agenda item. For example, it monitors the time allotted for each agenda item and notifies participants to move on to the next item when the time limit has expired. It can also adjust the time allocation for each agenda item in real time according to the progress of the meeting. Furthermore, to ensure the meeting ends on time, the unit can notify participants if discussions are running long and encourage them to summarize. This ensures thorough time management and improves meeting efficiency.

[0065] The meeting efficiency system can also include a reminder function. This function can send reminders to participants before and after meetings to encourage preparation and follow-up. For example, it can send participants an agenda list and relevant materials the day before the meeting to encourage preparation. It can also notify participants of follow-up tasks and the date of the next meeting after the meeting has ended. Furthermore, it can notify participants when deadlines for important tasks are approaching, encouraging them to complete the tasks. This allows participants to prepare for and follow up on meetings more efficiently, improving the quality of the meetings.

[0066] The following briefly describes the processing flow for example form 1.

[0067] Step 1: The agenda planning team organizes the agenda. For example, the agenda planning team clarifies the purpose and objectives of the meeting and creates an agenda list. The agenda planning team can organize the agenda based on classification methods and prioritization methods. Step 2: The discussion activation team activates the discussion based on the agenda organized by the agenda organization team. For example, the discussion activation team can ask questions at appropriate times and guide the direction of the discussion. The discussion activation team can encourage participants to speak and support the discussion to prevent it from stagnating. Step 3: The recording unit records the progress of the discussion, which has been activated by the discussion activation unit, in real time. The recording unit can, for example, use speech recognition technology to transcribe the content of the discussion into text and automatically generate meeting minutes. The recording unit can perform recording based on speech recognition algorithms and methods for processing audio data. Step 4: The summarizing team consolidates and summarizes the participants' opinions based on the content recorded by the recording team. For example, the summarizing team extracts the main points of each statement and highlights the important points of the discussion. The summarizing team can consolidate opinions based on a method of classifying opinions and criteria for summarization. Step 5: The summarizing section extracts the essence of the discussion based on the opinions summarized by the aggregation section and summarizes them effectively. For example, the summarizing section organizes the results of the discussion and draws conclusions. The summarizing section can summarize the discussion based on criteria for extracting key points and summarizing methods.

[0068] (Example of form 2) The meeting efficiency system according to an embodiment of the present invention is a system using an AI agent aimed at improving the efficiency and quality of meetings. In this meeting efficiency system, first, the AI ​​agent organizes the meeting agenda and stimulates discussion. Next, the AI ​​agent records the progress of the discussion in real time and aggregates and summarizes the opinions of the participants. Furthermore, by extracting the essence of the discussion and summarizing it effectively, the AI ​​agent can reach a conclusion in a short time. This mechanism improves meeting performance and reduces participant dissatisfaction. For example, the AI ​​agent organizes the meeting agenda. In this process, the AI ​​agent clarifies the purpose and goals of the meeting and presents the agenda in an easy-to-understand manner. For example, before the start of the meeting, the AI ​​agent creates an agenda list and shares it with the participants, which helps the meeting proceed smoothly. Next, the AI ​​agent stimulates discussion. The AI ​​agent encourages participants to speak and supports the discussion to prevent it from stagnating. For example, by asking questions at appropriate times and indicating the direction of the discussion, the AI ​​agent stimulates the exchange of opinions among participants. Furthermore, the AI ​​agent records the progress of the discussion in real time. The AI ​​agent uses speech recognition technology to transcribe what is said during a meeting into text and automatically generates meeting minutes. This frees participants from the burden of manually compiling meeting minutes. The AI ​​agent also aggregates and summarizes participants' opinions. The AI ​​agent extracts the key points of each statement and summarizes the essence of the discussion. For example, the AI ​​agent highlights and shares important points of the discussion with participants, making it easy to follow the flow of the discussion. Finally, the AI ​​agent extracts the essence of the discussion and summarizes it effectively. The AI ​​agent organizes the results of the discussion and derives a conclusion. This allows for conclusions to be reached in a short time, improving meeting performance. This system achieves increased efficiency and improved quality in meetings, reducing participant dissatisfaction. For example, because conclusions are reached quickly without meetings running long, participants can experience stress-free meeting management. In addition, since the AI ​​agent automatically generates meeting minutes, the burden of manually compiling meeting minutes is reduced.Furthermore, the AI ​​agent extracts the essence of the discussion and summarizes it effectively, improving the quality of the meeting and increasing participant satisfaction. Thus, the meeting efficiency system can achieve both increased efficiency and improved quality in meetings, while reducing participant dissatisfaction.

[0069] The meeting efficiency system according to this embodiment comprises an agenda organization unit, a discussion activation unit, a recording unit, an aggregation unit, and a summary unit. The agenda organization unit organizes the agenda. For example, the agenda organization unit clarifies the purpose and objectives of the meeting and creates an agenda list. The agenda organization unit can organize the agenda based on a classification method and a method for prioritizing the agenda. The discussion activation unit activates the discussion based on the agenda organized by the agenda organization unit. For example, the discussion activation unit asks questions at appropriate times and indicates the direction of the discussion. The discussion activation unit can encourage participants to speak and support the discussion to prevent it from stagnating. The recording unit records the progress of the discussion activated by the discussion activation unit in real time. For example, the recording unit uses speech recognition technology to transcribe the content of speech during the meeting into text and automatically generates meeting minutes. The recording unit can perform recording based on a speech recognition algorithm and a method for processing speech data. The aggregation unit aggregates and summarizes the opinions of the participants based on the content recorded by the recording unit. The summarization unit extracts key points from each statement and highlights important aspects of the discussion. The summarization unit can consolidate opinions based on a method for classifying opinions and criteria for summarization. The concluding unit extracts the essence of the discussion based on the opinions consolidated by the summarization unit and summarizes them effectively. The concluding unit organizes the results of the discussion and draws conclusions. The concluding unit can summarize the discussion based on a method for extracting key points and criteria for summarization. As a result, the meeting efficiency system according to this embodiment can improve the efficiency and quality of meetings and reduce participant dissatisfaction.

[0070] The agenda planning team clarifies the purpose and objectives of the meeting and creates an agenda list. Specifically, the meeting organizer or facilitator sets the meeting's objectives and lists the agenda items based on those objectives. The agenda planning team can organize the agenda items based on classification and prioritization methods. For example, they can classify and prioritize items based on criteria such as "importance," "urgency," and "relevance." This ensures smooth meeting progress and prevents important agenda items from being overlooked. Furthermore, the agenda planning team can improve the selection and organization of agenda items by utilizing past meeting data and participant feedback. For example, they can improve the quality of meetings by prioritizing items that did not receive enough time in past meetings or items that were frequently requested by participants. In addition, the agenda planning team can use AI to automatically generate and classify agenda items. For example, they can use natural language processing technology to analyze the meeting's objectives and participants' opinions and automatically suggest appropriate agenda items. This improves the efficiency of agenda planning and reduces meeting preparation time.

[0071] The Discussion Activation Department activates discussions based on the agenda items organized by the Agenda Organization Department. Specifically, it asks questions at appropriate times and guides the direction of the discussion. For example, if the discussion is stalled or if the opinions of a particular participant are not being adequately reflected, the Discussion Activation Department intervenes and revitalizes the discussion by asking questions or making comments. The Discussion Activation Department can also encourage participants to speak up and support the discussion to prevent it from stagnating. For example, it can monitor the number of times and the duration of each participant's contributions to create an environment where specific participants feel comfortable speaking. Furthermore, the Discussion Activation Department can utilize AI to support the progress of discussions. For example, it can use natural language processing technology to analyze the content of the discussion in real time and automatically generate questions and comments at appropriate times. This improves the quality of the discussion and allows all participants to actively engage. In addition, the Discussion Activation Department can analyze past discussion data and understand discussion patterns and trends to improve how discussions are conducted. For example, it can optimize the progress of discussions by referring to questions and comments that were effective in past discussions. In this way, the Discussion Activation Department can improve the efficiency and quality of meetings and increase participant satisfaction.

[0072] The recording unit records the progress of discussions activated by the discussion activation unit in real time. Specifically, it uses speech recognition technology to transcribe the content of speeches during meetings into text and automatically generates meeting minutes. The speech recognition algorithm can recognize speeches during meetings with high accuracy and record them as text data. This allows for the creation of accurate meeting minutes without disrupting the flow of the meeting. The recording unit can also record based on how it processes the audio data. For example, by dividing the audio data by speaker and organizing the content of speeches, the readability of the meeting minutes can be improved. Furthermore, the recording unit can use AI to automatically summarize meeting minutes and extract keywords. For example, by using natural language processing technology to analyze the content of the meeting minutes and extract important points and keywords, it can automatically generate a summary of the meeting minutes. This allows participants to quickly grasp the main points of the meeting and facilitates follow-up after the meeting. In addition, the recording unit can use past meeting minute data to improve the method and content of creating meeting minutes. For example, it can enrich the content of meeting minutes based on information that was missing in past minutes or feedback from participants. This allows the recording department to improve the efficiency and quality of meetings, thereby increasing participant satisfaction.

[0073] The aggregation unit consolidates and summarizes participants' opinions based on the content recorded by the recording unit. Specifically, it extracts the key points of each statement and emphasizes the important points of the discussion. For example, by using natural language processing technology to analyze the content of statements and extract important keywords and phrases, the key points of the discussion can be organized. The aggregation unit can consolidate opinions based on classification methods and aggregation criteria. For example, by classifying opinions into categories such as "agree," "disagree," and "reserve," and organizing opinions within each category, it becomes easier to grasp the overall picture of the discussion. Furthermore, the aggregation unit can utilize AI to automatically aggregate and summarize opinions. For example, by using machine learning algorithms to analyze the content of statements and group similar opinions, the aggregation of opinions can be made more efficient. This allows the aggregation unit to quickly and accurately consolidate opinions and grasp the overall picture of the discussion. In addition, the aggregation unit can improve its opinion aggregation methods and criteria by utilizing past discussion data. For example, it can optimize opinion aggregation by referring to aggregation methods and criteria that were effective in past discussions. This allows the consolidation department to improve the efficiency and quality of meetings, thereby increasing participant satisfaction.

[0074] The summarizing team extracts the essence of the discussion based on the opinions aggregated by the summarizing team and summarizes them effectively. Specifically, it organizes the results of the discussion and derives conclusions. For example, by using natural language processing technology to analyze the aggregated opinions and extract key points and conclusions, the main points of the discussion can be organized. The summarizing team can summarize the discussion based on criteria for extracting key points and summarizing methods. For example, by classifying the main points of the discussion into categories such as "problems," "solutions," and "next steps," and organizing the key points for each category, it becomes easier to grasp the overall picture of the discussion. Furthermore, the summarizing team can also use AI to automatically summarize discussions and generate conclusions. For example, by using machine learning algorithms to analyze the content of the discussion and automatically generate key points and conclusions, the main points of the discussion can be grasped quickly. As a result, the summarizing team can summarize discussions quickly and accurately, improving the efficiency and quality of meetings. In addition, the summarizing team can use past discussion data to improve how discussions are summarized and how conclusions are drawn. For example, by referring to effective summarization methods and conclusion-reaching techniques from past discussions, the summarization process can be optimized. This allows the summarization team to improve the efficiency and quality of meetings, and increase participant satisfaction.

[0075] The recording unit can use speech recognition technology to transcribe the content of a meeting into text and automatically generate meeting minutes. For example, the recording unit can use a speech recognition algorithm to transcribe the content of a meeting into text in real time. The recording unit can also transcribe the content of a meeting into text based on a method for processing audio data. Furthermore, the recording unit can use speech recognition technology to automatically classify the content of a meeting and generate meeting minutes. This reduces the burden of manually organizing meeting minutes. Some or all of the above-described processes in the recording unit may be performed using AI, for example, or without AI. For example, the recording unit can input the content of a meeting into a generating AI and have the generating AI transcribe the content of the meeting into text.

[0076] The discussion activation unit can ask questions at appropriate times and guide the direction of the discussion. For example, the discussion activation unit can ask questions at appropriate times based on the interval between comments and the progress of the discussion. It can also guide the direction of the discussion based on how the discussion is progressing. Furthermore, the discussion activation unit can encourage participants to speak and support the discussion to prevent it from stagnating. This prevents the discussion from stalling and promotes active exchange of opinions. Some or all of the above processing in the discussion activation unit may be performed using AI, for example, or not using AI. For example, the discussion activation unit can input the progress of the discussion into a generating AI and cause the generating AI to ask questions at appropriate times.

[0077] The summarization unit can extract the main points of each statement and highlight the important points of the discussion. For example, the summarization unit can extract the main points and highlight the important points based on keyword extraction methods and highlighting methods. The summarization unit can also summarize opinions based on opinion classification methods and summarization criteria. Furthermore, the summarization unit can highlight the important points so that the flow of the discussion can be easily followed. This makes it easy to follow the flow of the discussion. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input the content of the statements into a generating AI and have the generating AI perform the extraction of main points and the highlighting of important points.

[0078] The summarizing unit can organize the results of a discussion and draw conclusions. For example, the summarizing unit can organize the results of a discussion and draw conclusions based on methods for classifying results and methods for deriving conclusions. The summarizing unit can also summarize the discussion based on methods for extracting key points and criteria for summarization. Furthermore, the summarizing unit can extract the essence of the discussion and summarize it effectively. This allows for conclusions to be reached in a short time, improving the performance of the meeting. Some or all of the above-described processes in the summarizing unit may be performed using AI, for example, or not. For example, the summarizing unit can input the results of the discussion into a generating AI and have the generating AI derive conclusions.

[0079] The agenda planning unit can clarify the purpose and objectives of a meeting and create an agenda list. For example, the agenda planning unit can clarify the purpose and objectives of a meeting and create an agenda list based on methods for setting objectives and creating agenda lists. The agenda planning unit can also organize the agenda based on methods for classifying and prioritizing agenda items. Furthermore, the agenda planning unit can share the agenda list with participants to ensure the smooth progress of the meeting. This ensures the smooth progress of the meeting. Some or all of the above processes in the agenda planning unit may be performed using AI, for example, or not using AI. For example, the agenda planning unit can input the purpose and objectives of the meeting into a generating AI and have the generating AI create the agenda list.

[0080] The agenda planning unit can estimate participants' emotions and adjust the priority of agenda items based on those estimated emotions. For example, if a participant is feeling stressed, the agenda planning unit can address important topics first and resolve them early. Conversely, if a participant is relaxed, the agenda planning unit can flexibly adjust the order of topics to ensure a smooth flow of discussion. Furthermore, if a participant is in a hurry, the agenda planning unit can postpone time-consuming topics and prioritize those that can be resolved quickly. This allows for smoother meeting progress by adjusting agenda priorities according to participants' emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the agenda planning unit may be performed using AI or not. For example, the agenda planning unit can input participant emotion data into a generative AI and have the generative AI adjust the agenda priorities.

[0081] The agenda organization unit can analyze past meeting data and automatically group similar agenda items. For example, it can extract and group agenda items on the same theme from past meeting data. It can also treat similar agenda items as a single item to facilitate discussion. Furthermore, it can automatically link related agenda items based on past meeting data to streamline the flow of discussion. This allows for efficient discussion of similar agenda items. Some or all of the above processing in the agenda organization unit may be performed using AI, for example, or without AI. For example, the agenda organization unit can input past meeting data into a generating AI and have the generating AI perform the grouping of similar agenda items.

[0082] The agenda planning unit can dynamically adjust the level of detail of the agenda items according to the purpose of the meeting. For example, if the purpose of the meeting is to reach a conclusion in a short time, the agenda planning unit will reduce the level of detail of the agenda items and present only the key points. Conversely, if the purpose of the meeting is to have an in-depth discussion, the agenda planning unit can increase the level of detail of the agenda items and provide detailed information. Furthermore, the agenda planning unit can adjust the level of detail of the agenda items in real time according to the progress of the meeting, thereby smoothing the flow of discussion. This ensures a smooth discussion flow by providing an agenda level of detail appropriate to the purpose of the meeting. Some or all of the above processing in the agenda planning unit may be performed using AI, for example, or not using AI. For example, the agenda planning unit can input the purpose of the meeting into a generating AI and have the generating AI perform the adjustment of the level of detail of the agenda items.

[0083] The agenda planning unit can estimate participants' emotions and adjust the presentation method based on the estimated emotions. For example, if a participant is nervous, the agenda planning unit can provide a simple and highly visible interface. If a participant is relaxed, it can also provide an interface with more detailed information. Furthermore, if a participant is in a hurry, it can provide a concise interface. This allows for a smoother flow of discussion by providing an agenda presentation method that is tailored to the participants' emotions. 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 agenda planning unit may be performed using AI or not. For example, the agenda planning unit can input participant emotion data into a generative AI and have the generative AI adjust the presentation method of the agenda.

[0084] The agenda planning unit can automatically provide relevant information on the agenda based on the participants' areas of expertise. For example, the agenda planning unit can automatically collect information related to the participants' areas of expertise and provide it in relation to the agenda. The agenda planning unit can also provide background information on the agenda based on the participants' areas of expertise to deepen the discussion. Furthermore, the agenda planning unit can refer to past meeting data related to the participants' areas of expertise and provide it in relation to the agenda. This deepens the discussion by providing information related to the participants' areas of expertise. Some or all of the above processing in the agenda planning unit may be performed using AI, for example, or without AI. For example, the agenda planning unit can input participants' areas of expertise data into a generating AI and have the generating AI perform the provision of relevant information.

[0085] The agenda planning unit can adjust the order of agenda items in real time according to the progress of the meeting. For example, the agenda planning unit can prioritize important agenda items depending on the progress of the meeting. The agenda planning unit can also flexibly adjust the order of agenda items according to the progress of the meeting to ensure a smooth flow of discussion. Furthermore, the agenda planning unit can postpone time-consuming agenda items and prioritize those that can be resolved quickly, depending on the progress of the meeting. This ensures a smooth flow of discussion by providing an agenda order that is appropriate to the progress of the meeting. Some or all of the above processes in the agenda planning unit may be performed using AI, for example, or not. For example, the agenda planning unit can input meeting progress data into a generating AI and have the generating AI perform the adjustment of the agenda order.

[0086] The discussion activation unit can estimate the emotions of participants and adjust the timing of prompting them to speak based on the estimated emotions. For example, if a participant is tense, the discussion activation unit will prompt them to speak at a time when they are relaxed. It can also proactively encourage participation if the participant is relaxed. Furthermore, if a participant is in a hurry, the discussion activation unit can prompt them to speak quickly. This provides appropriate timing for participation according to the participants' emotions, thereby stimulating the discussion. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the discussion activation unit may be performed using AI, or not. For example, the discussion activation unit can input participant emotion data into a generative AI and have the generative AI adjust the timing of participation.

[0087] The discussion activation unit can analyze past discussion data, predict points where discussions are likely to stall, and take countermeasures. For example, the discussion activation unit can extract points where discussions are likely to stall from past discussion data and take countermeasures. The discussion activation unit can also predict points where discussions are likely to stall and ask questions at the appropriate time. Furthermore, the discussion activation unit can predict points where discussions are likely to stall and indicate the direction of the discussion. In this way, by predicting points where discussions are likely to stall and taking countermeasures, the flow of discussion becomes smoother. Some or all of the above processing in the discussion activation unit may be performed using AI, for example, or not using AI. For example, the discussion activation unit can input past discussion data into a generating AI and have the generating AI predict stall points and take countermeasures.

[0088] The discussion activation unit can automatically generate appropriate questions based on the participants' speaking history. For example, the discussion activation unit can analyze the participants' speaking history and automatically generate relevant questions. It can also automatically generate questions to deepen the discussion based on the participants' speaking history. Furthermore, it can automatically generate questions that indicate the direction of the discussion based on the participants' speaking history. In this way, the discussion is deepened by providing questions based on the participants' speaking history. Some or all of the above processing in the discussion activation unit may be performed using AI, for example, or without AI. For example, the discussion activation unit can input the participants' speaking history data into a generating AI and have the generating AI perform the automatic generation of questions.

[0089] The discussion activation unit can estimate the emotions of the participants and adjust the direction of the discussion based on the estimated emotions. For example, if a participant is tense, the discussion activation unit can suggest a relaxed direction for the discussion. If a participant is relaxed, the discussion activation unit can also suggest a more proactive direction for the discussion. Furthermore, if a participant is in a hurry, the discussion activation unit can suggest a direction that leads to a quick conclusion. This makes the discussion smoother by providing a direction for discussion that is appropriate to the emotions of the participants. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the discussion activation unit may be performed using AI, for example, or without AI. For example, the discussion activation unit can input participant emotion data into a generative AI and have the generative AI adjust the direction of the discussion.

[0090] The discussion activation unit can adjust the depth of the discussion based on the participants' expertise. For example, the discussion activation unit can deepen the discussion based on the participants' expertise. It can also shallow the discussion based on the participants' expertise. Furthermore, the discussion activation unit can adjust the depth of the discussion based on the participants' expertise to make the flow of the discussion smoother. This deepens the discussion by providing a depth of discussion appropriate to the participants' expertise. Some or all of the above processing in the discussion activation unit may be performed using AI, for example, or without AI. For example, the discussion activation unit can input participant expertise data into a generating AI and have the generating AI perform the adjustment of the discussion depth.

[0091] The discussion activation unit can dynamically change the discussion topics according to the progress of the meeting. For example, the discussion activation unit can change the discussion topics according to the progress of the meeting to make the discussion flow smoothly. The discussion activation unit can also prioritize discussion of important topics according to the progress of the meeting. Furthermore, the discussion activation unit can flexibly change the discussion topics according to the progress of the meeting to prevent the discussion from stagnating. In this way, by providing discussion topics that are appropriate to the progress of the meeting, the flow of the discussion becomes smoother. Some or all of the above processing in the discussion activation unit may be performed using AI, for example, or without using AI. For example, the discussion activation unit can input meeting progress data into a generating AI and cause the generating AI to change the discussion topics.

[0092] The recording unit can estimate the emotions of participants and adjust the level of detail in the recording based on the estimated emotions. For example, if a participant is nervous, the recording unit can provide a simple and easy-to-read record. If a participant is relaxed, the recording unit can also provide a more detailed record. Furthermore, if a participant is in a hurry, the recording unit can provide a concise record. By providing a level of detail in the recording that matches the emotions of the participants, the flow of the discussion becomes smoother. Emotion estimation is achieved using an emotion estimation function, for example, with 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 recording unit may be performed using AI or not using AI. For example, the recording unit can input participant emotion data into a generative AI and have the generative AI adjust the level of detail in the recording.

[0093] The recording unit can use speech recognition technology to generate records in different formats for each speaker. For example, the recording unit can generate records in different formats for each speaker to improve readability. The recording unit can also generate records in different formats for each speaker to smooth the flow of the discussion. Furthermore, the recording unit can generate records in different formats for each speaker to highlight the main points of the discussion. As a result, generating records in different formats for each speaker improves readability and makes the flow of the discussion smoother. Some or all of the above processing in the recording unit may be performed using AI, for example, or without AI. For example, the recording unit can input the content of the speech into a generation AI and have the generation AI perform the generation of records in a format specific to each speaker.

[0094] The recording unit can highlight key points of the meeting in real time according to the progress of the meeting. For example, the recording unit can highlight important points in real time according to the progress of the meeting. The recording unit can also highlight key points of the discussion in real time according to the progress of the meeting, thereby smoothing the flow of the discussion. Furthermore, the recording unit can highlight key points in real time according to the progress of the meeting, thereby preventing stagnation in the discussion. In this way, by providing highlighting of key points according to the progress of the meeting, the flow of the discussion becomes smoother. Some or all of the above processing in the recording unit may be performed using AI, for example, or without using AI. For example, the recording unit can input meeting progress data into a generating AI and have the generating AI perform the highlighting of key points.

[0095] The recording unit can estimate the emotions of participants and adjust the way the recording is displayed based on the estimated emotions. For example, if a participant is nervous, the recording unit can provide a simple and easy-to-read display. If a participant is relaxed, the recording unit can also provide a display that includes detailed information. Furthermore, if a participant is in a hurry, the recording unit can provide a concise display. By providing a recording display method that is appropriate to the emotions of the participants, the flow of the discussion becomes smoother. 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 recording unit may be performed using AI or not using AI. For example, the recording unit can input participant emotion data into a generative AI and have the generative AI adjust the way the recording is displayed.

[0096] The recording unit can automatically summarize the recorded content and provide it to participants in real time. For example, the recording unit can automatically summarize the recorded content and provide it to participants in real time. Furthermore, the recording unit can automatically summarize the recorded content and highlight the key points of the discussion. In addition, the recording unit can automatically summarize the recorded content and smooth the flow of the discussion. This means that by automatically summarizing the recorded content, the key points of the discussion are highlighted and the flow of the discussion becomes smoother. Some or all of the above processing in the recording unit may be performed using AI, for example, or without AI. For example, the recording unit can input the recorded content into a generating AI and have the generating AI perform the generation of the summary.

[0097] The recording unit can save the recorded content to the cloud, making it accessible to participants at any time. For example, the recording unit can save the recorded content to the cloud, making it accessible to participants at any time. The recording unit can also save the recorded content to the cloud and highlight the key points of the discussion. Furthermore, the recording unit can save the recorded content to the cloud and streamline the flow of the discussion. This allows participants to access the recorded content at any time and facilitates a smoother discussion flow. Some or all of the above-described processes in the recording unit may be performed using AI, or not. For example, the recording unit can input the recorded content into a generating AI and have the generating AI perform the task of saving it to the cloud.

[0098] The aggregation unit can estimate the emotions of the participants and adjust the method of aggregating opinions based on the estimated emotions of the participants. For example, if a participant is tense, the aggregation unit can provide a simple and easy-to-understand aggregation method. If a participant is relaxed, the aggregation unit can also provide an aggregation method that includes detailed information. Furthermore, if a participant is in a hurry, the aggregation unit can provide an aggregation method that gets straight to the point. This allows for a smoother flow of discussion by providing an opinion aggregation method that is tailored to the emotions of the 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 aggregation unit may be performed using AI, for example, or not using AI. For example, the aggregation unit can input participant emotion data into a generative AI and have the generative AI adjust the method of aggregating opinions.

[0099] The aggregation unit can automatically evaluate the importance of each statement and prioritize the aggregation of important opinions. For example, the aggregation unit can automatically evaluate the importance of each statement and prioritize the aggregation of important opinions. The aggregation unit can also emphasize the main points of the discussion based on the importance of the statements. Furthermore, the aggregation unit can also smooth the flow of the discussion based on the importance of the statements. As a result, by prioritizing the aggregation of important opinions, the main points of the discussion are emphasized and the flow of the discussion becomes smoother. Some or all of the above processing in the aggregation unit may be performed using AI, for example, or without AI. For example, the aggregation unit can input the content of the statements into a generating AI and have the generating AI perform the evaluation of importance and the aggregation of opinions.

[0100] The aggregation unit can automatically group similar opinions by referring to past meeting data. For example, the aggregation unit can automatically group similar opinions by referring to past meeting data. The aggregation unit can also treat similar opinions as a single opinion and proceed with the discussion efficiently. Furthermore, the aggregation unit can automatically link related opinions based on past meeting data to smooth the flow of the discussion. This allows for the efficient discussion by grouping similar opinions. Some or all of the above processing in the aggregation unit may be performed using AI, for example, or without AI. For example, the aggregation unit can input past meeting data into a generating AI and have the generating AI perform the grouping of similar opinions.

[0101] The aggregation unit can estimate the emotions of participants and adjust the way opinions are displayed based on the estimated emotions. For example, if a participant is nervous, the aggregation unit can provide a simple and highly visible display method. If a participant is relaxed, the aggregation unit can also provide a display method that includes detailed information. Furthermore, if a participant is in a hurry, the aggregation unit can provide a concise display method. This allows for a smoother flow of discussion by providing an opinion display method that is appropriate to the emotions of the 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 aggregation unit may be performed using AI or not using AI. For example, the aggregation unit can input participant emotion data into a generative AI and have the generative AI adjust the way opinions are displayed.

[0102] The aggregation unit can automatically summarize the aggregated opinions and provide them to participants in real time. For example, the aggregation unit can automatically summarize the aggregated opinions and provide them to participants in real time. The aggregation unit can also automatically summarize the aggregated opinions and highlight the key points of the discussion. Furthermore, the aggregation unit can automatically summarize the aggregated opinions and smooth the flow of the discussion. By automatically summarizing the aggregated opinions, the key points of the discussion are highlighted and the flow of the discussion becomes smoother. Some or all of the above processing in the aggregation unit may be performed using AI, for example, or without AI. For example, the aggregation unit can input the aggregated opinions into a generating AI and have the generating AI perform the generation of the summary.

[0103] The aggregation unit can store the aggregated opinions on the cloud, making them accessible to participants at any time. For example, the aggregation unit can store the aggregated opinions on the cloud, making them accessible to participants at any time. The aggregation unit can also store the aggregated opinions on the cloud and highlight the key points of the discussion. Furthermore, the aggregation unit can store the aggregated opinions on the cloud and streamline the flow of the discussion. This allows participants to access the aggregated opinions at any time and streamlines the flow of the discussion. Some or all of the above-described processes in the aggregation unit may be performed using AI, for example, or without AI. For example, the aggregation unit can input the aggregated opinions into a generating AI and have the generating AI perform the task of saving them to the cloud.

[0104] The summarizing section can estimate the participants' emotions and adjust the way conclusions are presented based on those estimated emotions. For example, if a participant is tense, the summarizing section can provide a simple and easily understandable conclusion. If a participant is relaxed, it can also provide a conclusion with more detailed information. Furthermore, if a participant is in a hurry, it can provide a concise conclusion. This allows for a smoother flow of discussion by providing conclusions tailored to the participants' emotions. 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 summarizing section may be performed using AI or not. For example, the summarizing section can input participant emotion data into a generative AI and have the generative AI adjust the way conclusions are presented.

[0105] The summarizing unit can automatically derive the optimal conclusion by referring to past meeting data. For example, the summarizing unit can automatically derive the optimal conclusion by referring to past meeting data. Furthermore, the summarizing unit can automatically link related conclusions based on past meeting data, making the flow of discussion smoother. In addition, the summarizing unit can derive the optimal conclusion based on past meeting data and highlight the key points of the discussion. This makes the flow of discussion smoother by deriving the optimal conclusion based on past meeting data. Some or all of the above processing in the summarizing unit may be performed using AI, for example, or without AI. For example, the summarizing unit can input past meeting data into a generating AI and have the generating AI derive the optimal conclusion.

[0106] The summarizing unit can dynamically adjust the level of detail of the conclusions according to the progress of the meeting. For example, the summarizing unit can dynamically adjust the level of detail of the conclusions according to the progress of the meeting to ensure a smooth flow of discussion. The summarizing unit can also prioritize and present important conclusions according to the progress of the meeting. Furthermore, the summarizing unit can flexibly adjust the level of detail of the conclusions according to the progress of the meeting to prevent stagnation of discussion. This ensures a smooth flow of discussion by providing a level of detail of conclusions that is appropriate to the progress of the meeting. Some or all of the above processing in the summarizing unit may be performed using AI, for example, or without AI. For example, the summarizing unit can input meeting progress data into a generating AI and have the generating AI perform the adjustment of the level of detail of the conclusions.

[0107] The summary section can estimate the participants' emotions and adjust how the conclusions are displayed based on those estimated emotions. For example, if a participant is nervous, the summary section can provide a simple and easily readable display. If a participant is relaxed, it can also provide a display that includes detailed information. Furthermore, if a participant is in a hurry, it can provide a concise display. This allows for a smoother flow of discussion by providing a conclusion display method that is tailored to the participants' emotions. 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 summary section may be performed using AI or not. For example, the summary section can input participant emotion data into a generative AI and have the generative AI adjust how the conclusions are displayed.

[0108] The summarizing unit can automatically summarize the conclusions and provide them to participants in real time. For example, the summarizing unit can automatically summarize the conclusions and provide them to participants in real time. The summarizing unit can also automatically summarize the conclusions and highlight the key points of the discussion. Furthermore, the summarizing unit can automatically summarize the conclusions and smooth the flow of the discussion. By automatically summarizing the conclusions, the key points of the discussion are highlighted and the flow of the discussion becomes smoother. Some or all of the above processing in the summarizing unit may be performed using AI, for example, or not using AI. For example, the summarizing unit can input the conclusions into a generating AI and have the generating AI perform the generation of the summary.

[0109] The summarizing unit can save the conclusions to the cloud, making them accessible to participants at any time. For example, the summarizing unit can save the conclusions to the cloud, making them accessible to participants at any time. The summarizing unit can also save the conclusions to the cloud and highlight the key points of the discussion. Furthermore, the summarizing unit can save the conclusions to the cloud and streamline the flow of the discussion. This allows participants to access the conclusions at any time and streamlines the flow of the discussion. Some or all of the above processing in the summarizing unit may be performed using AI, for example, or not. For example, the summarizing unit can input the conclusions into a generating AI and have the generating AI perform the task of saving them to the cloud.

[0110] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0111] The meeting efficiency system can also include a feedback function. This function collects feedback from participants after the meeting and identifies areas for improvement for future meetings. For example, it can send questionnaires to participants to gather opinions on the meeting's progress and content. It can also analyze the collected feedback and generate suggestions for improving meeting procedures and agenda setting. Furthermore, the feedback function can adjust the meeting's progress in real time based on participant feedback. This ensures that meetings reflect participant opinions and improve their quality.

[0112] The meeting efficiency system can also be equipped with a notification function. This notification function can inform participants in real time about the meeting's progress and any changes to important agenda items. For example, it can notify participants when it's time to move on to the next agenda item, depending on the meeting's progress. It can also notify participants of any changes to important agenda items. Furthermore, if the meeting is falling behind schedule, it can notify participants and encourage them to speed up the discussion. This makes it easier for participants to understand the meeting's progress and improves meeting efficiency.

[0113] The meeting efficiency system can also include a translation function. This function can translate speech in real time to facilitate communication between participants who speak different languages. For example, it can automatically translate and display speech during a meeting. It can also generate meeting minutes in multiple languages ​​and provide them to participants. Furthermore, if a participant speaks in a different language, the translation function can translate that speech in real time and share it with other participants. This improves communication between participants who speak different languages ​​and increases meeting efficiency.

[0114] The meeting efficiency system can also include a time management unit. This unit manages meeting time and adjusts the time allocation for each agenda item. For example, it monitors the time allotted for each agenda item and notifies participants to move on to the next item when the time limit has expired. It can also adjust the time allocation for each agenda item in real time according to the progress of the meeting. Furthermore, to ensure the meeting ends on time, the unit can notify participants if discussions are running long and encourage them to summarize. This ensures thorough time management and improves meeting efficiency.

[0115] The meeting efficiency system can also include a reminder function. This function can send reminders to participants before and after meetings to encourage preparation and follow-up. For example, it can send participants an agenda list and relevant materials the day before the meeting to encourage preparation. It can also notify participants of follow-up tasks and the date of the next meeting after the meeting has ended. Furthermore, it can notify participants when deadlines for important tasks are approaching, encouraging them to complete the tasks. This allows participants to prepare for and follow up on meetings more efficiently, improving the quality of the meetings.

[0116] The meeting efficiency system can also be equipped with an emotion analysis unit. This unit can estimate participants' emotions from their statements and facial expressions and reflect this in the meeting's progress. For example, it can estimate emotions from participants' statements and tone, and encourage calmer discussion if the debate is heated. It can also analyze participants' facial expressions and suggest ways to create a more relaxed atmosphere if they appear tense. Furthermore, based on participants' emotional data, the emotion analysis unit can adjust the meeting's progress and the prioritization of agenda items. This enables meetings that are considerate of participants' emotions, improving the quality of the meetings.

[0117] The meeting efficiency system can also be equipped with an emotional feedback function. This function collects participant feedback on their emotions after the meeting, which can then be used to improve future meetings. For example, it can send participants a questionnaire after the meeting to evaluate their emotions and stress levels during the meeting. Furthermore, it can analyze the collected emotional data and generate suggestions for improving meeting procedures and agenda setting. It can also adjust the flow of the next meeting in real time based on the participants' emotional data. This enables meeting management that considers participants' emotions, thereby improving the quality of meetings.

[0118] The meeting efficiency system can also be equipped with an emotion monitoring unit. This unit can monitor participants' emotions in real time during a meeting and reflect this in the meeting's progress. For example, it can analyze participants' facial expressions and statements to detect changes in their emotions. Furthermore, if a participant is feeling stressed, the unit can suggest slowing the pace of the discussion. Conversely, if a participant is relaxed, it can suggest ways to encourage more active discussion. This enables meeting management that responds to participants' emotions, improving the quality of the meeting.

[0119] The meeting efficiency system can also be equipped with an emotion reporting function. This function provides participants with emotional data as a report after the meeting, which can be used for reviewing the meeting. For example, the emotion reporting function can visualize changes in participants' emotions during the meeting using graphs and charts, and provide this information to participants. Furthermore, based on the emotional data, the emotion reporting function can also suggest improvements to meeting procedures and agenda setting. In addition, based on the participants' emotional data, the emotion reporting function can adjust the flow of the next meeting in real time. This enables meeting management that takes participants' emotions into consideration, thereby improving the quality of meetings.

[0120] The meeting efficiency system can also include an emotional training section. This section can provide training to help participants better control their emotions. For example, it can teach participants breathing techniques for relaxation and stress relief methods. It can also offer advice to help participants relax if they are feeling anxious. Furthermore, it can provide training programs to help participants better control their emotions. This improves the quality of meetings by making it easier for participants to manage their emotions.

[0121] The following briefly describes the processing flow for example form 2.

[0122] Step 1: The agenda planning team organizes the agenda. For example, the agenda planning team clarifies the purpose and objectives of the meeting and creates an agenda list. The agenda planning team can organize the agenda based on classification methods and prioritization methods. Step 2: The discussion activation team activates the discussion based on the agenda organized by the agenda organization team. For example, the discussion activation team can ask questions at appropriate times and guide the direction of the discussion. The discussion activation team can encourage participants to speak and support the discussion to prevent it from stagnating. Step 3: The recording unit records the progress of the discussion, which has been activated by the discussion activation unit, in real time. The recording unit can, for example, use speech recognition technology to transcribe the content of the discussion into text and automatically generate meeting minutes. The recording unit can perform recording based on speech recognition algorithms and methods for processing audio data. Step 4: The summarizing team consolidates and summarizes the participants' opinions based on the content recorded by the recording team. For example, the summarizing team extracts the main points of each statement and highlights the important points of the discussion. The summarizing team can consolidate opinions based on a method of classifying opinions and criteria for summarization. Step 5: The summarizing section extracts the essence of the discussion based on the opinions summarized by the aggregation section and summarizes them effectively. For example, the summarizing section organizes the results of the discussion and draws conclusions. The summarizing section can summarize the discussion based on criteria for extracting key points and summarizing methods.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] Each of the multiple elements described above, including the agenda organization unit, discussion activation unit, recording unit, aggregation unit, and summary unit, is implemented by at least one of the smart device 14 and the data processing unit 12. For example, the agenda organization unit is implemented by the control unit 46A of the smart device 14, which clarifies the purpose and objectives of the meeting and creates an agenda list. The discussion activation unit is implemented by the control unit 46A of the smart device 14, which asks questions at appropriate times and indicates the direction of the discussion. The recording unit is implemented by the specific processing unit 290 of the data processing unit 12, which uses speech recognition technology to transcribe the content of statements made during the meeting into text and automatically generates meeting minutes. The aggregation unit is implemented by the specific processing unit 290 of the data processing unit 12, which extracts the main points of each statement and highlights the important points of the discussion. The summary unit is implemented by the specific processing unit 290 of the data processing unit 12, which organizes the results of the discussion and derives conclusions. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0127] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. 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.

[0132] 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).

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.).

[0139] 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.

[0140] 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.

[0141] 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.

[0142] Each of the multiple elements described above, including the agenda organization unit, discussion activation unit, recording unit, aggregation unit, and summary unit, is implemented by at least one of the smart glasses 214 and the data processing device 12. For example, the agenda organization unit is implemented by the control unit 46A of the smart glasses 214, which clarifies the purpose and objectives of the meeting and creates an agenda list. The discussion activation unit is implemented by the control unit 46A of the smart glasses 214, which asks questions at appropriate times and indicates the direction of the discussion. The recording unit is implemented by the specific processing unit 290 of the data processing device 12, which uses speech recognition technology to transcribe the content of statements made during the meeting into text and automatically generates meeting minutes. The aggregation unit is implemented by the specific processing unit 290 of the data processing device 12, which extracts the main points of each statement and highlights the important points of the discussion. The summary unit is implemented by the specific processing unit 290 of the data processing device 12, which organizes the results of the discussion and derives conclusions. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0143] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. 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.

[0148] 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).

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.).

[0155] 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.

[0156] 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.

[0157] 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.

[0158] Each of the multiple elements described above, including the agenda organization unit, discussion activation unit, recording unit, aggregation unit, and summary unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the agenda organization unit is implemented by the control unit 46A of the headset terminal 314, which clarifies the purpose and objectives of the meeting and creates an agenda list. The discussion activation unit is implemented by, for example, the control unit 46A of the headset terminal 314, which asks questions at appropriate times and indicates the direction of the discussion. The recording unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, which uses speech recognition technology to transcribe the content of statements made during the meeting into text and automatically generates meeting minutes. The aggregation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, which extracts the main points of each statement and highlights the important points of the discussion. The summary unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, which organizes the results of the discussion and derives conclusions. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0159] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. 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.

[0164] 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).

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.).

[0172] 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.

[0173] 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.

[0174] 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.

[0175] Each of the multiple elements described above, including the agenda organization unit, discussion activation unit, recording unit, aggregation unit, and summary unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the agenda organization unit is implemented by the control unit 46A of the robot 414, which clarifies the purpose and objectives of the meeting and creates an agenda list. The discussion activation unit is implemented by, for example, the control unit 46A of the robot 414, which asks questions at appropriate times and indicates the direction of the discussion. The recording unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, which uses speech recognition technology to transcribe the content of statements made during the meeting into text and automatically generates meeting minutes. The aggregation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, which extracts the main points of each statement and highlights the important points of the discussion. The summary unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, which organizes the results of the discussion and derives conclusions. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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."

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] (Note 1) The agenda organizing department is responsible for organizing the agenda items, A discussion activation unit that activates discussions based on the agenda items organized by the aforementioned agenda organization unit, A recording unit that records the progress of the discussion activated by the aforementioned discussion activation unit in real time, Based on the content recorded by the aforementioned recording unit, there is a summarization unit that collects and compiles the opinions of the participants, The system comprises a summarization unit that extracts the essence of the discussion based on the opinions aggregated by the aforementioned aggregation unit and summarizes it effectively. A system characterized by the following features. (Note 2) The recording unit is, Using speech recognition technology, the content of speech during meetings is converted into text, and meeting minutes are automatically generated. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned discussion activation unit is, Ask questions at the right time and guide the direction of the discussion. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned aggregation unit is Extract the key points from each statement and highlight the important aspects of the discussion. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned summary section is, Summarize the results of the discussion and draw a conclusion. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned agenda organizing department, Clarify the purpose and objectives of the meeting and create an agenda. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned agenda organizing department, Estimate the participants' emotions and adjust the agenda priorities based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned agenda organizing department, Analyze past meeting data and automatically group similar topics. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned agenda organizing department, The level of detail in the agenda is dynamically adjusted according to the purpose of the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned agenda organizing department, We estimate the participants' emotions and adjust the way the agenda is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned agenda organizing department, The system automatically provides relevant information on the agenda based on the participants' areas of expertise. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned agenda organizing department, The order of the agenda items will be adjusted in real time according to the progress of the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned discussion activation unit is, The system estimates the participants' emotions and adjusts the timing of prompting them to speak based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned discussion activation unit is, By analyzing past statements and predicting points where discussions are likely to stall, we can take countermeasures. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned discussion activation unit is, The system automatically generates appropriate questions based on the participants' speaking history. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned discussion activation unit is, The system estimates the emotions of the participants and adjusts the direction of the discussion based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned discussion activation unit is, Adjust the depth of the discussion based on the participants' expertise. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned discussion activation unit is, The discussion topics are dynamically changed according to the progress of the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 19) The recording unit is, The system estimates the participants' emotions and adjusts the level of detail in the recording based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The recording unit is, Using speech recognition technology, records are generated in a different format for each speaker. The system described in Appendix 1, characterized by the features described herein. (Note 21) The recording unit is, The system highlights key points of the meeting minutes in real time, according to the progress of the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 22) The recording unit is, The system estimates the participants' emotions and adjusts how the records are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The recording unit is, The recorded content is automatically summarized and provided to participants in real time. The system described in Appendix 1, characterized by the features described herein. (Note 24) The recording unit is, The recorded content will be saved to the cloud, allowing participants to access it at any time. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned aggregation unit is We estimate the emotions of the participants and adjust the method of aggregating opinions based on the estimated emotions of the participants. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned aggregation unit is The system automatically evaluates the importance of each statement and prioritizes and aggregates the most important opinions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned aggregation unit is Referencing past meeting data, similar opinions are automatically grouped together. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned aggregation unit is The system estimates the participants' emotions and adjusts how opinions are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned aggregation unit is The collected opinions are automatically summarized and provided to participants in real time. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned aggregation unit is The collected opinions will be stored in the cloud, allowing participants to access them at any time. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned summary section is, We estimate the participants' emotions and adjust the way conclusions are presented based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned summary section is, By referring to past meeting data, the system automatically derives the optimal conclusion. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned summary section is, The level of detail in the conclusions is dynamically adjusted according to the progress of the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned summary section is, We estimate the participants' emotions and adjust how conclusions are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned summary section is, The system automatically summarizes the conclusions and provides them to participants in real time. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned summary section is, The conclusions will be saved to the cloud so that participants can access them at any time. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0195] 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. The agenda organizing department is responsible for organizing the agenda items, A discussion activation unit that activates discussions based on the agenda items organized by the aforementioned agenda organization unit, A recording unit that records the progress of the discussion activated by the aforementioned discussion activation unit in real time, Based on the content recorded by the aforementioned recording unit, there is a summarization unit that collects and compiles the opinions of the participants, The system comprises a summarization unit that extracts the essence of the discussion based on the opinions aggregated by the aforementioned aggregation unit and summarizes it effectively. A system characterized by the following features.

2. The recording unit is, Using speech recognition technology, the content of speech during meetings is converted into text, and meeting minutes are automatically generated. The system according to feature 1.

3. The aforementioned discussion activation unit is, Ask questions at the right time and guide the direction of the discussion. The system according to feature 1.

4. The aforementioned aggregation unit is Extract the key points from each statement and highlight the important aspects of the discussion. The system according to feature 1.

5. The aforementioned summary section is, Summarize the results of the discussion and draw a conclusion. The system according to feature 1.

6. The aforementioned agenda organizing department, Clarify the purpose and objectives of the meeting and create an agenda. The system according to feature 1.

7. The aforementioned agenda organizing department, Estimate the participants' emotions and adjust the agenda priorities based on those estimated emotions. The system according to feature 1.

8. The aforementioned agenda organizing department, Analyze past meeting data and automatically group similar topics. The system according to feature 1.

Images