system

Abstract

The system according to the embodiment aims to automate the creation of meeting minutes. [Solution] According to an embodiment, the system includes a notification receiving unit, a summarizing unit, and a calendar API adding unit. The notification receiving unit receives a transcription notification. The summarizing unit summarizes the transcription data based on the notification received by the notification receiving unit. The calendar API adding unit adds the summary created by the summarizing unit to the calendar API.

Description

[Technical Field]

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

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

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

[0004] Conventional techniques often require manual creation of meeting minutes, which can be inefficient.

[0005] The system according to the embodiment aims to automate the creation of meeting minutes. [Means for solving the problem]

[0006] According to an embodiment, the system includes a notification receiving unit, a summarizing unit, and a calendar API adding unit. The notification receiving unit receives a transcription notification. The summarizing unit summarizes the transcription data based on the notification received by the notification receiving unit. The calendar API adding unit adds the summary created by the summarizing unit to the calendar API. [Effects of the Invention]

[0007] The system according to the embodiment can automate the creation of meeting minutes. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may 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 a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) An online meeting minutes automation system according to an embodiment of the present invention automates the creation of online meeting minutes. The online meeting minutes automation system receives a notification when a transcription function for an online meeting is turned on, uses a generation AI to summarize the transcription data, and automatically adds the summarized minutes to the meeting schedule notes using a calendar API. For example, the online meeting minutes automation system receives a notification when a transcription function for an online meeting is turned on. For example, in an online meeting tool, the transcription function is turned on simultaneously with the start of the meeting. Next, the online meeting minutes automation system uses a generation AI to summarize the transcription data. The generation AI analyzes the content of the meeting, extracts key points, and creates a summary. For example, it summarizes the meeting agenda, decisions, action items, etc. Next, the online meeting minutes automation system uses a calendar API to automatically add the summarized minutes to the meeting schedule notes. For example, after the meeting ends, the summarized minutes are automatically added to the calendar schedule notes. This allows the online meeting minutes automation system to automate the creation of meeting minutes, saving time and effort, and facilitating the sharing of information. This allows the online meeting minutes automation system to automate the creation of meeting minutes, saving time and effort. For example, meeting participants no longer need to manually create minutes, and the contents of the meeting can be accurately recorded. In addition, the use of a calendar makes it easy to share minutes, ensuring that all meeting participants share the same information.

[0029] An online meeting minutes automation system according to an embodiment includes a notification receiving unit, a summarizing unit, and an adding unit. The notification receiving unit receives a notification when a transcription function for an online meeting is turned on. The notification receiving unit detects that the transcription function has been turned on, for example, using an API of an online meeting tool. The notification receiving unit can also be configured to automatically turn on the transcription function when a meeting starts. For example, the setting of the online meeting tool can be changed to turn on the transcription function when the meeting starts. The summarizing unit uses a generation AI to summarize the transcription data received by the notification receiving unit. The generation AI, for example, uses a text generation AI (e.g., LLM) to analyze the content of the meeting, extract key points, and create a summary. The summarizing unit can also use the generation AI to summarize the meeting agenda, decisions, action items, etc. For example, the generation AI receives a prompt such as, "Please summarize the main points of this meeting," and extracts the main points of the meeting to create a summary. The adding unit adds the summary created by the summarizing unit to a calendar API. The adding unit automatically adds the summarized minutes to the meeting appointment notes, for example, using the Google® Calendar API or the Microsoft® Outlook® Calendar API. For example, after the meeting ends, the adding unit automatically adds the summarized minutes to the calendar appointment notes. This allows the online meeting minutes automation system according to the embodiment to automate the creation of meeting minutes and reduce the effort required. For example, meeting participants no longer need to manually create minutes, allowing the contents of the meeting to be accurately recorded. Furthermore, using a calendar makes it easy to share the minutes, allowing all meeting participants to share the same information.

[0030] The notification receiving unit can receive a notification when the transcription function of the online conference tool is turned on. The notification receiving unit can detect that the transcription function is turned on, for example, using the API of the online conference tool. For example, the Zoom API can be used to set the transcription function to be turned on as soon as the conference starts. The notification receiving unit can also support other online conference tools such as Microsoft Teams (registered trademark) and Google Meet (registered trademark). For example, the Microsoft Teams API can be used to set the transcription function to be turned on as soon as the conference starts. This automatically turns on the transcription function as soon as the conference starts. Some or all of the above-described processing in the notification receiving unit can be performed, for example, using AI or without AI. For example, the notification receiving unit can input data obtained from the API of the online conference tool into the generation AI and cause the generation AI to execute processing to detect that the transcription function is turned on.

[0031] The summarization unit can analyze the content of a meeting, extract key points, and create a summary. The summarization unit can use a generation AI to analyze the content of the meeting, extract key points, and create a summary. The generation AI can, for example, use a text generation AI (e.g., LLM) to analyze the content of the meeting, extract key points, and create a summary. The summarization unit can also use a generation AI to summarize the meeting agenda, decisions, action items, etc. For example, the generation AI can receive a prompt such as, "Please summarize the main points of this meeting," and extract the main points of the meeting to create a summary. The summarization unit can also use a generation AI to analyze the content of the meeting in real time, extract key points, and create a summary. For example, the generation AI can analyze transcription data in real time while the meeting is in progress, extract key points, and create a summary. This makes it possible to summarize the meeting agenda, decisions, action items, etc. Some or all of the above-mentioned processing in the summarization unit can be performed, for example, using AI, or can be performed without using AI. For example, the summarization unit can input transcription data into the generation AI and have the generation AI generate a summary.

[0032] The adding unit can automatically add the summarized minutes to the meeting appointment notes using a calendar API. The adding unit automatically adds the summarized minutes to the meeting appointment notes using, for example, the Google Calendar API or the Microsoft Outlook Calendar API. For example, the adding unit automatically adds the summarized minutes to the calendar appointment notes after the meeting ends using the Google Calendar API. The adding unit can also automatically add the summarized minutes to the meeting appointment notes using the Microsoft Outlook Calendar API. For example, the adding unit automatically adds the summarized minutes to the calendar appointment notes after the meeting ends. This allows meeting participants to easily check the minutes on the calendar. Some or all of the above-described processing in the adding unit may be performed using, for example, AI, or may be performed without using AI. For example, the adding unit may input the summary created by the summarizing unit to a generating AI and cause the generating AI to perform processing to add the summary to the calendar API.

[0033] The summarization unit can summarize the meeting agenda, decisions, action items, etc. The summarization unit uses a generation AI to summarize the meeting agenda, decisions, action items, etc. The generation AI, for example, uses a text generation AI (e.g., LLM) to analyze the content of the meeting and extract key points to create a summary. The summarization unit can also use a generation AI to summarize the meeting agenda, decisions, action items, etc. For example, the generation AI receives a prompt such as "Please summarize the main points of this meeting" and extracts the main points of the meeting to create a summary. The summarization unit can also use a generation AI to analyze the content of the meeting in real time and extract key points to create a summary. For example, the generation AI can analyze transcription data in real time while the meeting is in progress, extract key points, and create a summary. This allows the content of the meeting to be accurately recorded. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can input transcription data to the generation AI and have the generation AI generate a summary.

[0034] The adding unit can automatically add summarized minutes to the calendar appointment notes after the meeting ends. The adding unit can automatically add the summarized minutes to the meeting appointment notes, for example, using the Google Calendar API or the Microsoft Outlook Calendar API. For example, the adding unit can automatically add the summarized minutes to the calendar appointment notes after the meeting ends using the Google Calendar API. The adding unit can also automatically add the summarized minutes to the meeting appointment notes using the Microsoft Outlook Calendar API. For example, the adding unit can automatically add the summarized minutes to the calendar appointment notes after the meeting ends. This allows all meeting participants to share the same information. Some or all of the above-described processing in the adding unit can be performed using, for example, AI, or can be performed without using AI. For example, the adding unit can input the summary created by the summarizing unit to the generating AI and cause the generating AI to perform processing to add the summary to the calendar API.

[0035] The notification receiving unit can determine the priority of notifications based on the importance of the meeting when receiving the notification. For example, the notification receiving unit determines the priority of notifications based on the importance of the meeting when receiving the notification. For example, the notification receiving unit considers the positions of participants and the content of the agenda to evaluate the importance of the meeting. For example, the notification receiving unit can set the notification to be received with the highest priority for a high-importance meeting. The notification receiving unit can also set the notification to be received later for a low-importance meeting. Furthermore, the notification receiving unit can adjust the volume and display method of notifications according to the importance. For example, for a high-importance meeting, the volume of the notification can be increased and a display method with high visibility can be provided. This makes it possible to adjust the priority of notifications according to the importance. Some or all of the above-described processing in the notification receiving unit can be performed using, or without, AI. For example, the notification receiving unit can input meeting importance data to a generation AI and have the generation AI determine the priority of notifications.

[0036] The notification receiving unit can customize the content of the notification by taking into account attribute information of the meeting participants when receiving the notification. For example, the notification receiving unit customizes the content of the notification by taking into account attribute information of the meeting participants when receiving the notification. The notification receiving unit considers attribute information such as the participants' job titles, fields of expertise, and past participation history. For example, if there are many participants, the notification content can include an overview of the meeting. Also, if there are few participants, the notification content can include a detailed agenda. Furthermore, the notification content can be customized according to the participants' job titles. For example, a notification that briefly summarizes the main points can be provided to senior managers, and a notification that includes detailed technical information can be provided to specialists. This allows the content of the notification to be optimized according to the participant's attribute information. Some or all of the above-mentioned processing in the notification receiving unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification receiving unit can input the participant's attribute information into a generation AI and have the generation AI customize the notification content.

[0037] The notification receiving unit can adjust the frequency of notifications according to the progress of the meeting when receiving a notification. For example, the notification receiving unit adjusts the frequency of notifications according to the progress of the meeting when receiving a notification. The notification receiving unit, for example, considers the frequency of comments and the progress of the agenda in order to grasp the progress of the meeting. For example, when the meeting is in progress, the notification receiving unit can reduce the frequency of notifications. Also, when the meeting is about to end, the notification frequency can be increased. Furthermore, the content of the notification can be updated according to the progress of the meeting. For example, the latest agenda and decisions can be included in the notification content according to the progress of the meeting. This makes it possible to optimize the frequency of notifications according to the progress of the meeting. Some or all of the above-mentioned processing in the notification receiving unit may be performed using AI, for example, or may be performed without using AI. For example, the notification receiving unit can input meeting progress data to a generation AI and cause the generation AI to adjust the frequency of notifications.

[0038] The notification receiving unit can customize the content of the notification taking into account the geographical distribution of the conference when receiving the notification. For example, the notification receiving unit customizes the content of the notification taking into account the geographical distribution of the conference when receiving the notification. The notification receiving unit takes into account, for example, the geographical distribution of participants, such as their locations and time zones. For example, if participants are in different regions, time zone information can be included in the notification content. Also, if participants are in the same region, local information can be included in the notification content. Furthermore, the timing of sending the notification can be adjusted according to the geographical distribution. For example, notifications can be sent at appropriate times to participants in different time zones. This allows the content of the notification to be optimized according to the geographical distribution. Some or all of the above-mentioned processing in the notification receiving unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification receiving unit can input participant geographical distribution data to a generation AI and cause the generation AI to customize the notification content.

[0039] The notification receiving unit can improve the accuracy of the notification by referring to related literature of the meeting when receiving the notification. For example, the notification receiving unit improves the accuracy of the notification by referring to related literature of the meeting when receiving the notification. The notification receiving unit, for example, refers to related literature such as past meeting records and related research papers. For example, literature related to the agenda of the meeting is included in the notification content. The notification content can also be customized by referring to past minutes of the meeting. Furthermore, the priority of the notification can be determined based on the related literature. For example, the priority of the notification can be adjusted according to the importance of the related literature. In this way, the accuracy of the notification can be improved by referring to the related literature. Some or all of the above-mentioned processing in the notification receiving unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification receiving unit can input related literature data into a generation AI and have the generation AI customize the notification content.

[0040] The notification receiving unit can adjust the content of the notification taking into account the market value of the conference when receiving the notification. For example, the notification receiving unit adjusts the content of the notification taking into account the market value of the conference when receiving the notification. The notification receiving unit evaluates market value, such as sales forecasts and market share. For example, for a conference with high market value, detailed information can be included in the notification content. Also, for a conference with low market value, the notification content can be simplified. Furthermore, the timing of sending the notification can be adjusted according to the market value. For example, for a conference with high market value, the notification is sent with the highest priority. This allows the content of the notification to be optimized according to the market value. Some or all of the above-mentioned processing in the notification receiving unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification receiving unit can input market value data into a generation AI and have the generation AI adjust the notification content.

[0041] The summarization unit can adjust the level of detail of the summary based on the importance of the meeting when generating the summary. The summarization unit uses the generation AI to adjust the level of detail of the summary based on the importance of the meeting when generating the summary. The summarization unit, for example, considers the participants' positions and the content of the agenda to evaluate the importance of the meeting. For example, for a highly important meeting, a detailed summary is provided. Also, for a low-importance meeting, a concise summary can be provided. Furthermore, the length of the summary can be adjusted based on the importance. For example, for a highly important meeting, the length of the summary is increased and more detailed information is included. In this way, the level of detail of the summary can be adjusted based on the importance. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can input meeting importance data to the generation AI and have the generation AI adjust the level of detail of the summary.

[0042] The summarization unit can apply different summarization algorithms depending on the category of the meeting when generating a summary. The summarization unit uses a generation AI to apply different summarization algorithms depending on the category of the meeting when generating a summary. For example, the summarization unit considers the content of the agenda and the participants' areas of expertise to evaluate the category of the meeting. For example, in the case of a technical meeting, a summarization algorithm that emphasizes technical key points can be applied. In addition, in the case of a marketing meeting, a summarization algorithm that emphasizes marketing strategies can be applied. Furthermore, in the case of a human resources meeting, a summarization algorithm that emphasizes human resources-related key points can be applied. This allows the optimal summarization algorithm to be applied depending on the category. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can input meeting category data into the generation AI and have the generation AI apply the summarization algorithm.

[0043] The summarization unit can improve the accuracy of the summary by referring to the user's past summarization results when generating a summary. The summarization unit uses the generation AI to improve the accuracy of the summary by referring to the user's past summarization results when generating a summary. The summarization unit references past summarization results, such as past meeting records and summary storage formats. For example, the summarization unit adjusts the style of the summary by referring to summaries created by the user in the past. It can also extract important points from the user's past summarization results. It can also adjust the length of the summary based on the user's past summarization results. In this way, the accuracy of the summary is improved by referring to the past summarization results. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can input past summarization result data into the generation AI and have the generation AI improve the accuracy of the summary.

[0044] The summarization unit can determine the priority of summaries based on the time of the meeting when generating summaries. The summarization unit uses the generation AI to determine the priority of summaries based on the time of the meeting when generating summaries. The summarization unit takes into account, for example, the time of the meeting, such as the schedule of the meeting and seasonal factors. For example, for the most recent meeting, the priority of the summary can be set high. Also, for past meetings, the priority of the summary can be set low. Furthermore, the level of detail of the summary can be adjusted depending on the time of the meeting. For example, for the most recent meeting, a detailed summary can be provided, and for past meetings, a concise summary can be provided. This makes it possible to adjust the priority of the summary depending on the time of the meeting. Some or all of the above-mentioned processing in the summarization unit can be performed using, for example, AI, or can be performed without using AI. For example, the summarization unit can input data on the time of the meeting to the generation AI and have the generation AI determine the priority of the summaries.

[0045] The summarization unit can adjust the order of summaries based on the relevance of the meetings when generating summaries. The summarization unit uses a generation AI to adjust the order of summaries based on the relevance of the meetings when generating summaries. The summarization unit considers the relevance of the meetings, such as commonalities in agendas and overlapping participants. For example, for highly relevant meetings, the order of summaries can be set to a higher priority. Also, for less relevant meetings, the order of summaries can be postponed. Furthermore, the content of the summaries can be adjusted according to the relevance of the meetings. For example, for highly relevant meetings, a detailed summary can be provided, and for less relevant meetings, a concise summary can be provided. This makes it possible to optimize the order of summaries according to their relevance. Some or all of the above-described processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can input meeting relevance data into the generation AI and have the generation AI adjust the order of summaries.

[0046] The summarization unit can adjust the use of technical terms in the summary according to the user's level of expertise when generating a summary. The summarization unit uses a generation AI to adjust the use of technical terms in the summary according to the user's level of expertise when generating a summary. The summarization unit considers the level of expertise, such as qualifications and past work experience. For example, a user with high expertise can be provided with a summary that uses a lot of technical terms. A user with low expertise can also be provided with a concise and easy-to-understand summary. Furthermore, the content of the summary can be adjusted according to the user's level of expertise. For example, a user with high expertise can be provided with a summary that includes detailed technical information, while a user with low expertise can be provided with a summary that includes basic information. This allows the provision of an optimal summary according to the level of expertise. Some or all of the above-described processing in the summarization unit can be performed using AI, for example, or without AI. For example, the summarization unit can input the user's level of expertise data into the generation AI and have the generation AI execute the use of technical terms in the summary.

[0047] The adding unit can improve the accuracy of adding summaries by taking into account the interrelationships between meetings when adding summaries. The adding unit uses the generating AI to improve the accuracy of adding summaries by taking into account the interrelationships between meetings when adding summaries. The adding unit considers the interrelationships between meetings, such as the relevance of agenda items and overlapping participants. For example, the adding unit adds summaries of related meetings together. The order of summaries can also be adjusted based on the interrelationships between meetings. Furthermore, the content of the summaries can be adjusted by taking into account the interrelationships between meetings. For example, summaries of related meetings can be integrated to provide consistent content. This makes it possible to adjust the order of summaries based on the interrelationships between meetings. Some or all of the above-mentioned processing in the adding unit may be performed using AI, for example, or may be performed without using AI. For example, the adding unit can input meeting interrelationship data to the generating AI and cause the generating AI to adjust the order of summaries.

[0048] The adding unit can add a summary while taking into consideration attribute information of the participants in the meeting. The adding unit uses the generating AI to add a summary while taking into consideration attribute information of the participants in the meeting. The adding unit considers attribute information such as the participants' job titles, fields of expertise, and past participation history. For example, the adding unit adjusts the content of the summary according to the participants' job titles. The adding unit can also adjust the content of the summary according to the participants' level of expertise. The adding unit can also adjust the content of the summary based on the participants' interests. For example, a summary that highlights relevant information based on the participants' interests can be provided. This allows the content of the summary to be optimized according to the participants' attribute information. Some or all of the above-mentioned processing in the adding unit can be performed using AI, for example, or without AI. For example, the adding unit can input participant attribute information data to the generating AI and cause the generating AI to adjust the content of the summary.

[0049] The adding unit can perform additional weighting based on the frequency of the meeting when adding a summary. The adding unit uses the generating AI to perform additional weighting based on the frequency of the meeting when adding a summary. The adding unit takes into account, for example, the frequency of meetings, such as weekly meetings or monthly meetings. For example, for meetings that are held frequently, the weighting of the summary can be set high. Also, for meetings that are held infrequently, the weighting of the summary can be set low. Furthermore, the content of the summary can be adjusted according to the frequency of the meeting. For example, for meetings that are held frequently, a detailed summary can be provided, and for meetings that are held infrequently, a concise summary can be provided. In this way, the weighting of the summary can be adjusted according to the frequency of the meeting. Some or all of the above-mentioned processing in the adding unit may be performed using, for example, AI, or may be performed without using AI. For example, the adding unit can input meeting frequency data to the generating AI and cause the generating AI to adjust the weighting of the summary.

[0050] The adding unit can add a summary while taking into account the geographical distribution of the conference. The adding unit uses the generating AI to add a summary while taking into account the geographical distribution of the conference. The adding unit considers, for example, the geographical distribution of participants, such as their locations and time zones. For example, if participants are in different regions, time zone information can be included in the summary content. Also, if participants are in the same region, local information can be included in the summary content. Furthermore, the timing of sending the summary can be adjusted according to the geographical distribution. For example, a summary can be sent at an appropriate time to participants in different time zones. This allows the content of the summary to be optimized according to the geographical distribution. Some or all of the above-mentioned processing in the adding unit can be performed using, for example, AI, or can be performed without using AI. For example, the adding unit can input participant geographical distribution data to the generating AI and cause the generating AI to adjust the content of the summary.

[0051] The adding unit can improve the accuracy of the addition by referring to related literature from the conference when adding a summary. The adding unit uses the generating AI to improve the accuracy of the addition by referring to related literature from the conference when adding a summary. The adding unit, for example, refers to related literature such as past meeting records and related research papers. For example, literature related to the conference agenda is included in the summary content. The summary content can also be customized by referring to past minutes of the meeting. Furthermore, the priority of the summary can be determined based on the related literature. For example, the priority of the summary can be adjusted according to the importance of the related literature. In this way, the accuracy of the summary can be improved by referring to the related literature. Some or all of the above-mentioned processing in the adding unit may be performed using, for example, AI, or may be performed without using AI. For example, the adding unit can input related literature data into the generating AI and cause the generating AI to customize the content of the summary.

[0052] The adding unit can add a summary taking into consideration the market value of the conference when adding the summary. The adding unit uses the generating AI to add a summary taking into consideration the market value of the conference when adding the summary. The adding unit evaluates market value, such as sales forecasts and market share. For example, for a conference with high market value, detailed information can be included in the summary content. Also, for a conference with low market value, the summary content can be made simple. Furthermore, the timing of sending the summary can be adjusted according to the market value. For example, for a conference with high market value, the summary can be sent with the highest priority. This allows the content of the summary to be optimized according to the market value. Some or all of the above-mentioned processing in the adding unit can be performed using, for example, AI, or can be performed without using AI. For example, the adding unit can input market value data into the generating AI and cause the generating AI to adjust the content of the summary.

[0053] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0054] The notification receiving unit can adjust the timing of notifications taking into account the free time in the user's calendar. For example, the notification receiving unit analyzes the user's calendar and sends notifications during times when the user has free time before or after a meeting. The notification receiving unit can also send notifications that avoid times when the user is busy. Furthermore, the notification receiving unit can determine the priority of notifications based on the user's calendar. For example, notifications can be sent preferentially before an important meeting, and notifications can be sent later before a less important meeting. This allows the user to receive notifications at the optimal time according to their schedule.

[0055] The summarizer can automatically generate action items based on the content of the meeting and assign them to responsible parties. For example, the summarizer can extract action items from meeting minutes and identify responsible parties. The summarizer can also set deadlines for action items. Furthermore, the summarizer can track the progress of action items and send periodic reminders. This allows for efficient management of action items based on the content of the meeting.

[0056] The adding unit can provide a summary of the meeting in multiple languages. For example, the adding unit can use generative AI to translate the summary into multiple languages, such as English, Japanese, and Spanish. The adding unit can also provide the summary in an appropriate language based on a user's language settings. Furthermore, the adding unit can automatically select the language of the summary depending on the language of the meeting participants. This allows participants who speak different languages ​​to share the same information.

[0057] The summarization unit can automatically generate follow-up emails based on the content of the meeting and send them to participants. For example, the summarization unit can extract important points from the meeting minutes and create a follow-up email. The summarization unit can also include action items and the schedule for the next meeting in the follow-up email. Furthermore, the summarization unit can adjust the timing of sending the follow-up email. This allows for efficient follow-up of the content of the meeting.

[0058] The summarization unit can automatically generate reports based on the contents of the meeting and send them to superiors and other relevant parties. For example, the summarization unit can extract important points from the minutes of a meeting and create a report. The summarization unit can also include graphs and charts in the report. Furthermore, the summarization unit can adjust the timing of sending the report. This allows the contents of the meeting to be reported efficiently.

[0059] The summarizing unit can automatically generate a task list based on the content of the meeting and add it to the project management tool. For example, the summarizing unit can extract tasks from the minutes of the meeting and add them to the project management tool. The summarizing unit can also set deadlines and assignees for the tasks. Furthermore, the summarizing unit can track the progress of the tasks and send periodic reminders. This allows for efficient task management based on the content of the meeting.

[0060] The processing flow of the first embodiment will be briefly explained below.

[0061] Step 1: The notification receiver receives a notification when the transcription function for an online meeting is turned on. For example, it can detect that the transcription function has been turned on using the API of the online meeting tool. It can also be set to automatically turn on the transcription function when the meeting starts. Step 2: The summarization unit uses a generation AI to summarize the transcription data received by the notification receiving unit. The generation AI, for example, uses a text generation AI (e.g., LLM) to analyze the content of the meeting, extract key points, and create a summary. It can also summarize the meeting agenda, decisions, action items, etc. Step 3: The adding unit adds the summary created by the summarizing unit to a calendar API. For example, the summarizing minutes are automatically added to the notes of the meeting appointment using Google Calendar API or Microsoft Outlook Calendar API. After the meeting ends, the summarizing minutes are automatically added to the notes of the calendar appointment.

[0062] (Example 2) An online meeting minutes automation system according to an embodiment of the present invention automates the creation of online meeting minutes. The online meeting minutes automation system receives a notification when a transcription function for an online meeting is turned on, uses a generation AI to summarize the transcription data, and automatically adds the summarized minutes to the meeting schedule notes using a calendar API. For example, the online meeting minutes automation system receives a notification when a transcription function for an online meeting is turned on. For example, in an online meeting tool, the transcription function is turned on simultaneously with the start of the meeting. Next, the online meeting minutes automation system uses a generation AI to summarize the transcription data. The generation AI analyzes the content of the meeting, extracts key points, and creates a summary. For example, it summarizes the meeting agenda, decisions, action items, etc. Next, the online meeting minutes automation system uses a calendar API to automatically add the summarized minutes to the meeting schedule notes. For example, after the meeting ends, the summarized minutes are automatically added to the calendar schedule notes. This allows the online meeting minutes automation system to automate the creation of meeting minutes, saving time and effort, and facilitating the sharing of information. This allows the online meeting minutes automation system to automate the creation of meeting minutes, saving time and effort. For example, meeting participants no longer need to manually create minutes, and the contents of the meeting can be accurately recorded. In addition, the use of a calendar makes it easy to share minutes, ensuring that all meeting participants share the same information.

[0063] An online meeting minutes automation system according to an embodiment includes a notification receiving unit, a summarizing unit, and an adding unit. The notification receiving unit receives a notification when a transcription function for an online meeting is turned on. The notification receiving unit detects that the transcription function has been turned on, for example, using an API of an online meeting tool. The notification receiving unit can also be configured to automatically turn on the transcription function when a meeting starts. For example, the setting of the online meeting tool can be changed to turn on the transcription function when the meeting starts. The summarizing unit uses a generation AI to summarize the transcription data received by the notification receiving unit. The generation AI, for example, uses a text generation AI (e.g., LLM) to analyze the content of the meeting, extract key points, and create a summary. The summarizing unit can also use the generation AI to summarize the meeting agenda, decisions, action items, etc. For example, the generation AI receives a prompt such as, "Please summarize the main points of this meeting," and extracts the main points of the meeting to create a summary. The adding unit adds the summary created by the summarizing unit to a calendar API. The adding unit automatically adds the summarized minutes to the meeting appointment notes, for example, using the Google Calendar API or the Microsoft Outlook Calendar API. For example, after the meeting ends, the adding unit automatically adds the summarized minutes to the calendar appointment notes. This allows the online meeting minutes automation system according to the embodiment to automate the creation of meeting minutes and reduce the effort required. For example, meeting participants no longer need to manually create minutes, allowing the contents of the meeting to be accurately recorded. Furthermore, using a calendar makes it easy to share the minutes, allowing all meeting participants to share the same information.

[0064] The notification receiving unit can receive a notification when the transcription function of the online conference tool is turned on. The notification receiving unit can detect that the transcription function is turned on, for example, using the API of the online conference tool. For example, the Zoom API can be used to set the transcription function to be turned on as soon as the conference starts. The notification receiving unit can also support other online conference tools such as Microsoft Teams and Google Meet. For example, the Microsoft Teams API can be used to set the transcription function to be turned on as soon as the conference starts. This automatically turns on the transcription function as soon as the conference starts. Some or all of the above-described processing in the notification receiving unit can be performed using, for example, AI or without AI. For example, the notification receiving unit can input data obtained from the API of the online conference tool into the generation AI and cause the generation AI to execute processing to detect that the transcription function is turned on.

[0065] The summarization unit can analyze the content of a meeting, extract key points, and create a summary. The summarization unit can use a generation AI to analyze the content of the meeting, extract key points, and create a summary. The generation AI can, for example, use a text generation AI (e.g., LLM) to analyze the content of the meeting, extract key points, and create a summary. The summarization unit can also use a generation AI to summarize the meeting agenda, decisions, action items, etc. For example, the generation AI can receive a prompt such as, "Please summarize the main points of this meeting," and extract the main points of the meeting to create a summary. The summarization unit can also use a generation AI to analyze the content of the meeting in real time, extract key points, and create a summary. For example, the generation AI can analyze transcription data in real time while the meeting is in progress, extract key points, and create a summary. This makes it possible to summarize the meeting agenda, decisions, action items, etc. Some or all of the above-mentioned processing in the summarization unit can be performed, for example, using AI, or can be performed without using AI. For example, the summarization unit can input transcription data into the generation AI and have the generation AI generate a summary.

[0066] The adding unit can automatically add the summarized minutes to the meeting appointment notes using a calendar API. The adding unit automatically adds the summarized minutes to the meeting appointment notes using, for example, the Google Calendar API or the Microsoft Outlook Calendar API. For example, the adding unit automatically adds the summarized minutes to the calendar appointment notes after the meeting ends using the Google Calendar API. The adding unit can also automatically add the summarized minutes to the meeting appointment notes using the Microsoft Outlook Calendar API. For example, the adding unit automatically adds the summarized minutes to the calendar appointment notes after the meeting ends. This allows meeting participants to easily check the minutes on the calendar. Some or all of the above-described processing in the adding unit may be performed using, for example, AI, or may be performed without using AI. For example, the adding unit may input the summary created by the summarizing unit to a generating AI and cause the generating AI to perform processing to add the summary to the calendar API.

[0067] The summarization unit can summarize the meeting agenda, decisions, action items, etc. The summarization unit uses a generation AI to summarize the meeting agenda, decisions, action items, etc. The generation AI, for example, uses a text generation AI (e.g., LLM) to analyze the content of the meeting and extract key points to create a summary. The summarization unit can also use a generation AI to summarize the meeting agenda, decisions, action items, etc. For example, the generation AI receives a prompt such as "Please summarize the main points of this meeting" and extracts the main points of the meeting to create a summary. The summarization unit can also use a generation AI to analyze the content of the meeting in real time and extract key points to create a summary. For example, the generation AI can analyze transcription data in real time while the meeting is in progress, extract key points, and create a summary. This allows the content of the meeting to be accurately recorded. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can input transcription data to the generation AI and have the generation AI generate a summary.

[0068] The adding unit can automatically add summarized minutes to the calendar appointment notes after the meeting ends. The adding unit can automatically add the summarized minutes to the meeting appointment notes, for example, using the Google Calendar API or the Microsoft Outlook Calendar API. For example, the adding unit can automatically add the summarized minutes to the calendar appointment notes after the meeting ends using the Google Calendar API. The adding unit can also automatically add the summarized minutes to the meeting appointment notes using the Microsoft Outlook Calendar API. For example, the adding unit can automatically add the summarized minutes to the calendar appointment notes after the meeting ends. This allows all meeting participants to share the same information. Some or all of the above-described processing in the adding unit can be performed using, for example, AI, or can be performed without using AI. For example, the adding unit can input the summary created by the summarizing unit to the generating AI and cause the generating AI to perform processing to add the summary to the calendar API.

[0069] The online meeting minutes automation system includes a notification receiving unit that estimates a user's emotion and adjusts the timing of notification reception based on the estimated user emotion. The notification receiving unit, for example, estimates the user's emotion and adjusts the timing of notification reception based on the estimated user emotion. The notification receiving unit estimates the user's emotion using, for example, facial expression recognition technology. For example, the notification receiving unit analyzes the user's facial expression data captured by a camera to estimate the user's emotion. The notification receiving unit can also estimate the user's emotion using voice analysis technology. For example, the notification receiving unit analyzes the user's voice data and estimates the emotion based on the tone and speed of the voice. Furthermore, the notification receiving unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor and estimate the emotion. For example, the notification receiving unit estimates the emotion based on heart rate fluctuations. This allows notifications to be received at the optimal timing depending on the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation 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 processing in the notification receiving unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the notification receiving unit may input user emotion data into the generation AI and cause the generation AI to adjust the timing of notification reception.

[0070] The notification receiving unit can determine the priority of notifications based on the importance of the meeting when receiving the notification. For example, the notification receiving unit determines the priority of notifications based on the importance of the meeting when receiving the notification. For example, the notification receiving unit considers the positions of participants and the content of the agenda to evaluate the importance of the meeting. For example, the notification receiving unit can set the notification to be received with the highest priority for a high-importance meeting. The notification receiving unit can also set the notification to be received later for a low-importance meeting. Furthermore, the notification receiving unit can adjust the volume and display method of notifications according to the importance. For example, for a high-importance meeting, the volume of the notification can be increased and a display method with high visibility can be provided. This makes it possible to adjust the priority of notifications according to the importance. Some or all of the above-described processing in the notification receiving unit can be performed using, or without, AI. For example, the notification receiving unit can input meeting importance data to a generation AI and have the generation AI determine the priority of notifications.

[0071] The notification receiving unit can customize the content of the notification by taking into account attribute information of the meeting participants when receiving the notification. For example, the notification receiving unit customizes the content of the notification by taking into account attribute information of the meeting participants when receiving the notification. The notification receiving unit considers attribute information such as the participants' job titles, fields of expertise, and past participation history. For example, if there are many participants, the notification content can include an overview of the meeting. Also, if there are few participants, the notification content can include a detailed agenda. Furthermore, the notification content can be customized according to the participants' job titles. For example, a notification that briefly summarizes the main points can be provided to senior managers, and a notification that includes detailed technical information can be provided to specialists. This allows the content of the notification to be optimized according to the participant's attribute information. Some or all of the above-mentioned processing in the notification receiving unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification receiving unit can input the participant's attribute information into a generation AI and have the generation AI customize the notification content.

[0072] The notification receiving unit can adjust the frequency of notifications according to the progress of the meeting when receiving a notification. For example, the notification receiving unit adjusts the frequency of notifications according to the progress of the meeting when receiving a notification. The notification receiving unit, for example, considers the frequency of comments and the progress of the agenda in order to grasp the progress of the meeting. For example, when the meeting is in progress, the notification receiving unit can reduce the frequency of notifications. Also, when the meeting is about to end, the notification frequency can be increased. Furthermore, the content of the notification can be updated according to the progress of the meeting. For example, the latest agenda and decisions can be included in the notification content according to the progress of the meeting. This makes it possible to optimize the frequency of notifications according to the progress of the meeting. Some or all of the above-mentioned processing in the notification receiving unit may be performed using AI, for example, or may be performed without using AI. For example, the notification receiving unit can input meeting progress data to a generation AI and cause the generation AI to adjust the frequency of notifications.

[0073] The notification receiving unit can estimate the user's emotion and adjust the notification display method based on the estimated user's emotion. The notification receiving unit, for example, estimates the user's emotion and adjusts the notification display method based on the estimated user's emotion. The notification receiving unit, for example, estimates the user's emotion using facial expression recognition technology. For example, the notification receiving unit analyzes the user's facial expression data captured by a camera to estimate the user's emotion. The notification receiving unit can also estimate the user's emotion using voice analysis technology. For example, the notification receiving unit analyzes the user's voice data and estimates the emotion based on the tone and speed of the voice. Furthermore, the notification receiving unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor and estimate the emotion. For example, the notification receiving unit estimates the emotion based on heart rate fluctuations. This allows the user to receive notifications in the optimal display method depending on the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generation 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 processing in the notification receiving unit may be performed using AI, or may be performed without using AI. For example, the notification receiving unit may input user emotion data into the generation AI and cause the generation AI to adjust the notification display method.

[0074] The notification receiving unit can customize the content of the notification taking into account the geographical distribution of the conference when receiving the notification. For example, the notification receiving unit customizes the content of the notification taking into account the geographical distribution of the conference when receiving the notification. The notification receiving unit takes into account, for example, the geographical distribution of participants, such as their locations and time zones. For example, if participants are in different regions, time zone information can be included in the notification content. Also, if participants are in the same region, local information can be included in the notification content. Furthermore, the timing of sending the notification can be adjusted according to the geographical distribution. For example, notifications can be sent at appropriate times to participants in different time zones. This allows the content of the notification to be optimized according to the geographical distribution. Some or all of the above-mentioned processing in the notification receiving unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification receiving unit can input participant geographical distribution data to a generation AI and cause the generation AI to customize the notification content.

[0075] The notification receiving unit can improve the accuracy of the notification by referring to related literature of the meeting when receiving the notification. For example, the notification receiving unit improves the accuracy of the notification by referring to related literature of the meeting when receiving the notification. The notification receiving unit, for example, refers to related literature such as past meeting records and related research papers. For example, literature related to the agenda of the meeting is included in the notification content. The notification content can also be customized by referring to past minutes of the meeting. Furthermore, the priority of the notification can be determined based on the related literature. For example, the priority of the notification can be adjusted according to the importance of the related literature. In this way, the accuracy of the notification can be improved by referring to the related literature. Some or all of the above-mentioned processing in the notification receiving unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification receiving unit can input related literature data into a generation AI and have the generation AI customize the notification content.

[0076] The notification receiving unit can adjust the content of the notification taking into account the market value of the conference when receiving the notification. For example, the notification receiving unit adjusts the content of the notification taking into account the market value of the conference when receiving the notification. The notification receiving unit evaluates market value, such as sales forecasts and market share. For example, for a conference with high market value, detailed information can be included in the notification content. Also, for a conference with low market value, the notification content can be simplified. Furthermore, the timing of sending the notification can be adjusted according to the market value. For example, for a conference with high market value, the notification is sent with the highest priority. This allows the content of the notification to be optimized according to the market value. Some or all of the above-mentioned processing in the notification receiving unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification receiving unit can input market value data into a generation AI and have the generation AI adjust the notification content.

[0077] The summarization unit can estimate the user's emotion and adjust the presentation method of the summary based on the estimated user's emotion. The summarization unit can estimate the user's emotion using a generation AI and adjust the presentation method of the summary based on the estimated user's emotion. The summarization unit can estimate the user's emotion using, for example, facial expression recognition technology. For example, the summarization unit can analyze the user's facial expression data captured by a camera to estimate the user's emotion. The summarization unit can also estimate the user's emotion using voice analysis technology. For example, the summarization unit can analyze the user's voice data and estimate the emotion based on the tone and speed of the voice. Furthermore, the summarization unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor and estimate the emotion. For example, the summarization unit can estimate the emotion based on heart rate fluctuations. This allows the summary to be provided in an optimal presentation method depending on the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can 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 processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit may input user emotion data into the generation AI and have the generation AI adjust the way the summary is expressed.

[0078] The summarization unit can adjust the level of detail of the summary based on the importance of the meeting when generating the summary. The summarization unit uses the generation AI to adjust the level of detail of the summary based on the importance of the meeting when generating the summary. The summarization unit, for example, considers the participants' positions and the content of the agenda to evaluate the importance of the meeting. For example, for a highly important meeting, a detailed summary is provided. Also, for a low-importance meeting, a concise summary can be provided. Furthermore, the length of the summary can be adjusted based on the importance. For example, for a highly important meeting, the length of the summary is increased and more detailed information is included. In this way, the level of detail of the summary can be adjusted based on the importance. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can input meeting importance data to the generation AI and have the generation AI adjust the level of detail of the summary.

[0079] The summarization unit can apply different summarization algorithms depending on the category of the meeting when generating a summary. The summarization unit uses a generation AI to apply different summarization algorithms depending on the category of the meeting when generating a summary. For example, the summarization unit considers the content of the agenda and the participants' areas of expertise to evaluate the category of the meeting. For example, in the case of a technical meeting, a summarization algorithm that emphasizes technical key points can be applied. In addition, in the case of a marketing meeting, a summarization algorithm that emphasizes marketing strategies can be applied. Furthermore, in the case of a human resources meeting, a summarization algorithm that emphasizes human resources-related key points can be applied. This allows the optimal summarization algorithm to be applied depending on the category. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can input meeting category data into the generation AI and have the generation AI apply the summarization algorithm.

[0080] The summarization unit can improve the accuracy of the summary by referring to the user's past summarization results when generating a summary. The summarization unit uses the generation AI to improve the accuracy of the summary by referring to the user's past summarization results when generating a summary. The summarization unit references past summarization results, such as past meeting records and summary storage formats. For example, the summarization unit adjusts the style of the summary by referring to summaries created by the user in the past. It can also extract important points from the user's past summarization results. It can also adjust the length of the summary based on the user's past summarization results. In this way, the accuracy of the summary is improved by referring to the past summarization results. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can input past summarization result data into the generation AI and have the generation AI improve the accuracy of the summary.

[0081] The summarization unit can estimate the user's emotion and adjust the length of the summary based on the estimated user emotion. The summarization unit can estimate the user's emotion using a generation AI and adjust the length of the summary based on the estimated user emotion. The summarization unit can estimate the user's emotion using, for example, facial expression recognition technology. For example, the summarization unit can analyze the user's facial expression data captured by a camera to estimate the user's emotion. The summarization unit can also estimate the user's emotion using voice analysis technology. For example, the summarization unit can analyze the user's voice data and estimate the emotion based on the tone and speed of the voice. Furthermore, the summarization unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor to estimate the emotion. For example, the summarization unit can estimate the emotion based on heart rate fluctuations. This allows the summary to be provided with an optimal length depending on the user's emotion. Emotion estimation is achieved using, for example, an emotion engine or generation AI, using an emotion estimation function. The generation AI can 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 processing in the summarization unit may be performed using AI, or may be performed without AI. For example, the summarization unit may input user emotion data into the generation AI and have the generation AI adjust the length of the summary.

[0082] The summarization unit can determine the priority of summaries based on the time of the meeting when generating summaries. The summarization unit uses the generation AI to determine the priority of summaries based on the time of the meeting when generating summaries. The summarization unit takes into account, for example, the time of the meeting, such as the schedule of the meeting and seasonal factors. For example, for the most recent meeting, the priority of the summary can be set high. Also, for past meetings, the priority of the summary can be set low. Furthermore, the level of detail of the summary can be adjusted depending on the time of the meeting. For example, for the most recent meeting, a detailed summary can be provided, and for past meetings, a concise summary can be provided. This makes it possible to adjust the priority of the summary depending on the time of the meeting. Some or all of the above-mentioned processing in the summarization unit can be performed using, for example, AI, or can be performed without using AI. For example, the summarization unit can input data on the time of the meeting to the generation AI and have the generation AI determine the priority of the summaries.

[0083] The summarization unit can adjust the order of summaries based on the relevance of the meetings when generating summaries. The summarization unit uses a generation AI to adjust the order of summaries based on the relevance of the meetings when generating summaries. The summarization unit considers the relevance of the meetings, such as commonalities in agendas and overlapping participants. For example, for highly relevant meetings, the order of summaries can be set to a higher priority. Also, for less relevant meetings, the order of summaries can be postponed. Furthermore, the content of the summaries can be adjusted according to the relevance of the meetings. For example, for highly relevant meetings, a detailed summary can be provided, and for less relevant meetings, a concise summary can be provided. This makes it possible to optimize the order of summaries according to their relevance. Some or all of the above-described processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can input meeting relevance data into the generation AI and have the generation AI adjust the order of summaries.

[0084] The summarization unit can adjust the use of technical terms in the summary according to the user's level of expertise when generating a summary. The summarization unit uses a generation AI to adjust the use of technical terms in the summary according to the user's level of expertise when generating a summary. The summarization unit considers the level of expertise, such as qualifications and past work experience. For example, a user with high expertise can be provided with a summary that uses a lot of technical terms. A user with low expertise can also be provided with a concise and easy-to-understand summary. Furthermore, the content of the summary can be adjusted according to the user's level of expertise. For example, a user with high expertise can be provided with a summary that includes detailed technical information, while a user with low expertise can be provided with a summary that includes basic information. This allows the provision of an optimal summary according to the level of expertise. Some or all of the above-described processing in the summarization unit can be performed using AI, for example, or without AI. For example, the summarization unit can input the user's level of expertise data into the generation AI and have the generation AI execute the use of technical terms in the summary.

[0085] The adding unit can estimate the user's emotion and determine the priority of summaries to be added based on the estimated user's emotion. The adding unit can estimate the user's emotion using a generation AI and determine the priority of summaries to be added based on the estimated user's emotion. The adding unit can estimate the user's emotion using, for example, facial expression recognition technology. For example, the adding unit can analyze the user's facial expression data captured by a camera and estimate the user's emotion. The adding unit can also estimate the user's emotion using voice analysis technology. For example, the adding unit can analyze the user's voice data and estimate the emotion based on the tone and speed of the voice. Furthermore, the adding unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor and estimate the emotion. For example, the adding unit can estimate the emotion based on heart rate fluctuations. This allows summaries to be added in the optimal priority order according to the user's emotion. Emotion estimation is realized using, for example, an emotion estimation function using an emotion engine or a generation AI. The generation 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 processing in the addition unit may be performed using AI, or may be performed without using AI. For example, the addition unit may input user emotion data into the generation AI and cause the generation AI to determine the priority of summaries.

[0086] The adding unit can improve the accuracy of adding summaries by taking into account the interrelationships between meetings when adding summaries. The adding unit uses the generating AI to improve the accuracy of adding summaries by taking into account the interrelationships between meetings when adding summaries. The adding unit considers the interrelationships between meetings, such as the relevance of agenda items and overlapping participants. For example, the adding unit adds summaries of related meetings together. The order of summaries can also be adjusted based on the interrelationships between meetings. Furthermore, the content of the summaries can be adjusted by taking into account the interrelationships between meetings. For example, summaries of related meetings can be integrated to provide consistent content. This makes it possible to adjust the order of summaries based on the interrelationships between meetings. Some or all of the above-mentioned processing in the adding unit may be performed using AI, for example, or may be performed without using AI. For example, the adding unit can input meeting interrelationship data to the generating AI and cause the generating AI to adjust the order of summaries.

[0087] The adding unit can add a summary while taking into consideration attribute information of the participants in the meeting. The adding unit uses the generating AI to add a summary while taking into consideration attribute information of the participants in the meeting. The adding unit considers attribute information such as the participants' job titles, fields of expertise, and past participation history. For example, the adding unit adjusts the content of the summary according to the participants' job titles. The adding unit can also adjust the content of the summary according to the participants' level of expertise. The adding unit can also adjust the content of the summary based on the participants' interests. For example, a summary that highlights relevant information based on the participants' interests can be provided. This allows the content of the summary to be optimized according to the participants' attribute information. Some or all of the above-mentioned processing in the adding unit can be performed using AI, for example, or without AI. For example, the adding unit can input participant attribute information data to the generating AI and cause the generating AI to adjust the content of the summary.

[0088] The adding unit can perform additional weighting based on the frequency of the meeting when adding a summary. The adding unit uses the generating AI to perform additional weighting based on the frequency of the meeting when adding a summary. The adding unit takes into account, for example, the frequency of meetings, such as weekly meetings or monthly meetings. For example, for meetings that are held frequently, the weighting of the summary can be set high. Also, for meetings that are held infrequently, the weighting of the summary can be set low. Furthermore, the content of the summary can be adjusted according to the frequency of the meeting. For example, for meetings that are held frequently, a detailed summary can be provided, and for meetings that are held infrequently, a concise summary can be provided. In this way, the weighting of the summary can be adjusted according to the frequency of the meeting. Some or all of the above-mentioned processing in the adding unit may be performed using, for example, AI, or may be performed without using AI. For example, the adding unit can input meeting frequency data to the generating AI and cause the generating AI to adjust the weighting of the summary.

[0089] The adding unit can estimate the user's emotion and adjust the display method of the summary to be added based on the estimated user's emotion. The adding unit can estimate the user's emotion using a generation AI and adjust the display method of the summary to be added based on the estimated user's emotion. The adding unit can estimate the user's emotion using, for example, facial expression recognition technology. For example, the adding unit can analyze the user's facial expression data captured by a camera and estimate the user's emotion. The adding unit can also estimate the user's emotion using voice analysis technology. For example, the adding unit can analyze the user's voice data and estimate the emotion based on the tone and speed of the voice. Furthermore, the adding unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor and estimate the emotion. For example, the adding unit can estimate the emotion based on heart rate fluctuations. This allows the summary to be added in an optimal display method depending on the user's emotion. Emotion estimation is achieved using, for example, an emotion estimation function using an emotion engine or a generation AI. The generation 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 processing in the addition unit may be performed using AI, or may be performed without using AI. For example, the addition unit may input user emotion data into the generation AI and cause the generation AI to adjust the display method of the summary.

[0090] The adding unit can add a summary while taking into account the geographical distribution of the conference. The adding unit uses the generating AI to add a summary while taking into account the geographical distribution of the conference. The adding unit considers, for example, the geographical distribution of participants, such as their locations and time zones. For example, if participants are in different regions, time zone information can be included in the summary content. Also, if participants are in the same region, local information can be included in the summary content. Furthermore, the timing of sending the summary can be adjusted according to the geographical distribution. For example, a summary can be sent at an appropriate time to participants in different time zones. This allows the content of the summary to be optimized according to the geographical distribution. Some or all of the above-mentioned processing in the adding unit can be performed using, for example, AI, or can be performed without using AI. For example, the adding unit can input participant geographical distribution data to the generating AI and cause the generating AI to adjust the content of the summary.

[0091] The adding unit can improve the accuracy of the addition by referring to related literature from the conference when adding a summary. The adding unit uses the generating AI to improve the accuracy of the addition by referring to related literature from the conference when adding a summary. The adding unit, for example, refers to related literature such as past meeting records and related research papers. For example, literature related to the conference agenda is included in the summary content. The summary content can also be customized by referring to past minutes of the meeting. Furthermore, the priority of the summary can be determined based on the related literature. For example, the priority of the summary can be adjusted according to the importance of the related literature. In this way, the accuracy of the summary can be improved by referring to the related literature. Some or all of the above-mentioned processing in the adding unit may be performed using, for example, AI, or may be performed without using AI. For example, the adding unit can input related literature data into the generating AI and cause the generating AI to customize the content of the summary.

[0092] The adding unit can add a summary taking into consideration the market value of the conference when adding the summary. The adding unit uses the generating AI to add a summary taking into consideration the market value of the conference when adding the summary. The adding unit evaluates market value, such as sales forecasts and market share. For example, for a conference with high market value, detailed information can be included in the summary content. Also, for a conference with low market value, the summary content can be made simple. Furthermore, the timing of sending the summary can be adjusted according to the market value. For example, for a conference with high market value, the summary can be sent with the highest priority. This allows the content of the summary to be optimized according to the market value. Some or all of the above-mentioned processing in the adding unit can be performed using, for example, AI, or can be performed without using AI. For example, the adding unit can input market value data into the generating AI and cause the generating AI to adjust the content of the summary. === Hard Collateral 1-1 === Each of the multiple elements, including the notification receiving unit, summarizing unit, and adding unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the notification receiving unit is realized by the control unit 46A of the smart device 14 and receives a notification when a transcription function for an online meeting is turned on. The summarizing unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and summarizes the transcription data using a generation AI. The adding unit is realized, for example, by the control unit 46A of the smart device 14 and automatically adds the summarized minutes to the meeting schedule notes using a calendar API. === Hard Collateral 1-2 === Each of the multiple elements, including the notification receiving unit, the summarizing unit, and the adding unit, described above, is implemented, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the notification receiving unit is implemented by the control unit 46A of the smart glasses 214 and receives a notification when a transcription function for an online meeting is turned on. The summarizing unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and summarizes the transcription data using a generation AI. The adding unit is implemented, for example, by the control unit 46A of the smart glasses 214 and automatically adds the summarized minutes to the meeting schedule notes using a calendar API. === Hard Collateral 1-3 === Each of the multiple elements including the notification receiving unit, summarizing unit, and adding unit described above is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the notification receiving unit is realized by the control unit 46A of the headset type terminal 314 and receives a notification when the transcription function of an online meeting is turned on. The summarizing unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and summarizes the transcription data using a generation AI. The adding unit is realized, for example, by the control unit 46A of the headset type terminal 314 and automatically adds the summarized minutes to the notes of the meeting schedule using a calendar API. === Hard Collateral 1-4 === Each of the multiple elements including the notification receiving unit, the summarizing unit, and the adding unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the notification receiving unit is realized by the control unit 46A of the robot 414 and receives a notification when the transcription function of an online meeting is turned on. The summarizing unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and summarizes the transcription data using a generation AI. The adding unit is realized, for example, by the control unit 46A of the robot 414 and automatically adds the summarized minutes to the notes of the meeting schedule using a calendar API.

[0093] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0094] The notification receiving unit can adjust the timing of notifications taking into account the free time in the user's calendar. For example, the notification receiving unit analyzes the user's calendar and sends notifications during times when the user has free time before or after a meeting. The notification receiving unit can also send notifications that avoid times when the user is busy. Furthermore, the notification receiving unit can determine the priority of notifications based on the user's calendar. For example, notifications can be sent preferentially before an important meeting, and notifications can be sent later before a less important meeting. This allows the user to receive notifications at the optimal time according to their schedule.

[0095] The summarizer can automatically generate action items based on the content of the meeting and assign them to responsible parties. For example, the summarizer can extract action items from meeting minutes and identify responsible parties. The summarizer can also set deadlines for action items. Furthermore, the summarizer can track the progress of action items and send periodic reminders. This allows for efficient management of action items based on the content of the meeting.

[0096] The adding unit can provide a summary of the meeting in multiple languages. For example, the adding unit can use generative AI to translate the summary into multiple languages, such as English, Japanese, and Spanish. The adding unit can also provide the summary in an appropriate language based on a user's language settings. Furthermore, the adding unit can automatically select the language of the summary depending on the language of the meeting participants. This allows participants who speak different languages ​​to share the same information.

[0097] The notification receiving unit can estimate the user's emotions and adjust the content of the notification based on the estimated user's emotions. For example, the notification receiving unit can simplify the content of the notification if the user is feeling stressed, and provide detailed information if the user is feeling relaxed. The notification receiving unit can also adjust the tone of the notification according to the user's emotions. For example, if the user is tired, the notification can be sent in a gentle tone. This allows the optimal notification to be provided according to the user's emotions.

[0098] The summarization unit can automatically generate follow-up emails based on the content of the meeting and send them to participants. For example, the summarization unit can extract important points from the meeting minutes and create a follow-up email. The summarization unit can also include action items and the schedule for the next meeting in the follow-up email. Furthermore, the summarization unit can adjust the timing of sending the follow-up email. This allows for efficient follow-up of the content of the meeting.

[0099] The notification receiving unit can estimate the user's emotions and adjust the frequency of notifications based on the estimated user's emotions. For example, the notification receiving unit can reduce the frequency of notifications when the user is feeling stressed and increase the frequency of notifications when the user is relaxed. The notification receiving unit can also adjust the timing of notifications according to the user's emotions. For example, if the user is concentrating, notifications can be delayed. This allows the user to receive notifications at an optimal frequency according to the user's emotions.

[0100] The summarization unit can automatically generate reports based on the contents of the meeting and send them to superiors and other relevant parties. For example, the summarization unit can extract important points from the minutes of a meeting and create a report. The summarization unit can also include graphs and charts in the report. Furthermore, the summarization unit can adjust the timing of sending the report. This allows the contents of the meeting to be reported efficiently.

[0101] The notification receiving unit can estimate the user's emotions and adjust the notification display method based on the estimated user's emotions. For example, if the user is feeling stressed, the notification receiving unit displays the notification as a pop-up, and if the user is feeling relaxed, the notification receiving unit displays the notification as a banner. The notification receiving unit can also adjust the color and font of the notification according to the user's emotions. For example, if the user is tired, the notification color can be changed to a calm color. This allows the user to receive notifications in the optimal display method according to their emotions.

[0102] The summarizing unit can automatically generate a task list based on the content of the meeting and add it to the project management tool. For example, the summarizing unit can extract tasks from the minutes of the meeting and add them to the project management tool. The summarizing unit can also set deadlines and assignees for the tasks. Furthermore, the summarizing unit can track the progress of the tasks and send periodic reminders. This allows for efficient task management based on the content of the meeting.

[0103] The notification receiving unit can estimate the user's emotion and adjust the notification volume based on the estimated user's emotion. For example, the notification receiving unit can lower the notification volume when the user is feeling stressed and increase the notification volume when the user is relaxed. The notification receiving unit can also change the type of notification sound depending on the user's emotion. For example, if the user is tired, the notification sound can be changed to a gentler sound. This allows the user to receive notifications at an optimal volume depending on the user's emotion.

[0104] The processing flow of the second embodiment will be briefly explained below.

[0105] Step 1: The notification receiver receives a notification when the transcription function for an online meeting is turned on. For example, it can detect that the transcription function has been turned on using the API of the online meeting tool. It can also be set to automatically turn on the transcription function when the meeting starts. Step 2: The summarization unit uses a generation AI to summarize the transcription data received by the notification receiving unit. The generation AI, for example, uses a text generation AI (e.g., LLM) to analyze the content of the meeting, extract key points, and create a summary. It can also summarize the meeting agenda, decisions, action items, etc. Step 3: The adding unit adds the summary created by the summarizing unit to a calendar API. For example, the summarizing minutes are automatically added to the notes of the meeting appointment using Google Calendar API or Microsoft Outlook Calendar API. After the meeting ends, the summarizing minutes are automatically added to the notes of the calendar appointment.

[0106] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0107] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0108] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, 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.

[0109] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0110] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0111] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0112] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0113] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0114] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0115] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0116] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0117] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0118] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0119] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0120] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0121] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0122] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0123] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0124] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0125] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0126] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0127] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0128] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0129] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0130] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0131] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0132] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0133] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0134] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0135] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0136] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0137] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0138] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0139] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0140] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0141] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0142] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0143] 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.

[0144] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0145] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0146] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0147] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0148] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0149] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0150] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0151] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0152] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0153] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0154] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0155] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0156] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0157] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0158] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0159] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0160] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0161] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0162] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0163] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0164] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0165] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0166] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0167] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0168] 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.

[0169] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0170] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0171] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0172] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0173] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0174] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0175] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0176] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0177] [Explanation of symbols]

[0178] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a notification receiving unit that receives a transcription notification; a summarizing unit that summarizes the transcription data based on the notification received by the notification receiving unit; a unit for adding the summary created by the summarizing unit to a calendar API; A system characterized by:

2. The notification receiving unit Get notified when transcription is enabled in your online meeting tool 2. The system of claim 1.

3. The summary section Analyze meeting content, extract key points, and create a summary 2. The system of claim 1.

4. The adding unit Automatically add summarized meeting minutes to meeting appointment notes using the Calendar API 2. The system of claim 1.

5. The summary section Summarize meeting agendas, decisions, and action items 2. The system of claim 1.

6. The adding unit After a meeting, automatically add a summary of the meeting minutes to the calendar event notes 2. The system of claim 1.

7. The notification receiving unit Estimate the user's emotions and adjust the timing of notification reception based on the estimated user emotions 2. The system of claim 1.

8. The notification receiving unit Prioritize notifications based on meeting importance when notifications arrive 2. The system of claim 1.

Images