System

Abstract

To provide a system capable of automating and efficiently managing a schedule, recording and summarizing conference contents, and considering a time difference.SOLUTION: The system includes a calendar cooperation unit, a schedule proposal unit, a conference recording unit, an archive generation unit, a transcription unit, a minute memo generation unit, a time difference consideration unit, a subtitle generation unit, and a translation unit. The calendar cooperation unit cooperates with a calendar to manage a daily schedule. The schedule proposal unit proposes a schedule so that plans do not overlap. The conference recording unit records conference contents. The archive generation part generates the conference contents as an archive moving image. The transcription part transcribes conference contents. A minute memo generation part summarizes conference contents and automatically generates a minute memo. The time difference consideration section selects the conference holding time in consideration of the time difference. The subtitle generation unit displays the conversation content as subtitles. The translation unit translates the conversation content into multiple languages.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, tasks such as schedule management, recording and summarizing meeting content, and taking time differences into account are all done manually, which is inefficient and prone to errors.

[0005] The system according to the embodiment aims to automate and efficiently manage schedules, record and summarize meeting contents, and take time differences into consideration. [Means for solving the problem]

[0006] The system according to the embodiment includes a calendar linking unit, a schedule proposing unit, a meeting recording unit, an archive generating unit, a transcription unit, a minutes memo generating unit, a time difference consideration unit, a subtitle generating unit, and a translation unit. The calendar linking unit links with a calendar and manages daily schedules. The schedule proposing unit proposes schedules based on schedule information acquired by the calendar linking unit so that appointments do not overlap. The meeting recording unit records the meeting content. The archive generating unit generates archived videos of the meeting content recorded by the meeting recording unit. The transcription unit transcribes the meeting content from the archived videos generated by the archive generating unit. The minutes memo generating unit summarizes the meeting content transcribed by the transcription unit and automatically generates minutes memo. The time difference consideration unit selects the time of the meeting, taking time differences into account. The subtitle generating unit subtitles and displays the conversation content. The translation unit translates the conversation content into multiple languages. [Effects of the Invention]

[0007] The system according to the embodiment can automate and efficiently manage schedules, record and summarize meeting contents, and take time differences into consideration. [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) The scheduling assistance system according to an embodiment of the present invention is a system in which a generation AI works in conjunction with a calendar to manage daily schedules and propose schedules that avoid overlapping appointments. This allows the scheduling assistance system to improve the efficiency of users' schedule management and automate the arrangement and recording of meetings.

[0029] The scheduling assistance system according to the embodiment includes a calendar linking unit, a schedule proposing unit, a meeting recording unit, an archive generating unit, a transcription unit, a minutes memo generating unit, a time difference consideration unit, a subtitle generating unit, and a translation unit. The calendar linking unit links with a calendar to manage daily schedules. For example, it links with Google Calendar or Outlook Calendar to acquire the user's schedule. The schedule proposing unit proposes a schedule that avoids schedule overlaps based on the schedule information acquired by the calendar linking unit. For example, a generation AI analyzes the user's schedule and proposes an optimal schedule. The meeting recording unit records the contents of the meeting. For example, it records audio and video during the meeting and saves them as digital data. The archive generating unit generates an archived video of the meeting contents recorded by the meeting recording unit. For example, it edits the recorded data to create an archived video. The transcription unit transcribes the meeting contents from the archived video generated by the archive generating unit. For example, it converts the meeting contents into text data using speech recognition technology. The minutes memo generation unit summarizes the meeting content transcribed by the transcription unit and automatically generates minutes memos. For example, the generation AI analyzes the meeting content, extracts important points, and creates minutes memos. The time difference consideration unit selects the meeting time taking time differences into account. For example, it considers the time zones of each participant and suggests a time slot that is convenient for everyone to attend. The subtitle generation unit subtitles and displays the conversation content. For example, it uses voice recognition technology to subtitle the conversation content in real time. The translation unit translates the conversation content into multiple languages. For example, the generation AI analyzes the conversation content and translates it into different languages ​​for display. As a result, the scheduling assistance system according to the embodiment can improve the efficiency of users' schedule management and automate the arrangement and recording of meetings. For example, by utilizing the generation AI, users can easily manage their schedules and arrange meetings, and can smoothly record and share meeting content. In addition, global communication is possible, overcoming time differences and language barriers.

[0030] The calendar integration unit analyzes the user's past schedule data, learns the user's behavioral patterns, and can propose optimal schedules. For example, the generation AI in the calendar integration unit analyzes the user's schedule data from the past year to identify frequent event and meeting patterns. For example, it learns regular meetings every Monday and end-of-month briefings, and proposes a new schedule based on that. To learn the user's behavioral patterns, the generation AI compares past schedule data with actual behavioral history. For example, it analyzes the attendance rate and cancellation rate of scheduled meetings to identify time periods when the user is most likely to attend. The calendar integration unit also suggests avoiding concentrating appointments during specific time periods based on the user's past schedule data. For example, if the user tends to have lower concentration in the afternoon, it schedules important meetings in the morning. This enables optimal schedule proposals based on the user's behavioral patterns.

[0031] The calendar integration unit can suggest a healthy schedule by taking into account the user's health data. For example, the calendar integration unit uses the generation AI to analyze sleep data obtained from the user's wearable device and adjust the next day's schedule if the user has not gotten enough sleep. For example, it may suggest moving an important meeting to the afternoon. The calendar integration unit also uses the generation AI to incorporate appropriate rest and exercise times into the schedule based on the user's exercise data. For example, it supports a healthy lifestyle by suggesting a short walk after a long meeting. The calendar integration unit also uses the generation AI to comprehensively analyze the user's health data and add relaxation time to the schedule when stress levels are high. For example, it can suggest times for meditation or yoga to maintain the user's health. This makes it possible to suggest schedules based on the user's health status.

[0032] The calendar integration unit also integrates with the calendars of family and friends, making it possible to suggest schedules that take private plans into consideration. For example, the generation AI in the calendar integration unit integrates with the calendars of the user's family and friends to coordinate shared plans. For example, it could suggest weekend events that the whole family can attend. The calendar integration unit also adjusts the work schedule taking into consideration the user's private plans. For example, if there are plans to have dinner with friends, it would avoid important tasks before or after that time. The calendar integration unit also allows the generation AI to analyze the calendars of family and friends, find common free time, and suggest private plans. For example, it would suggest going to the movies at a time when all family members are free. This makes it possible to suggest schedules that take into consideration the plans of family and friends.

[0033] The calendar integration unit can obtain traffic information in real time and propose a schedule that optimizes travel time. For example, the generation AI in the calendar integration unit obtains real-time traffic information and proposes a schedule that takes travel time into consideration. For example, it may suggest traveling during times when congestion is expected to be avoided. The calendar integration unit also analyzes the user's travel route and proposes the optimal means of transportation. For example, it may suggest using a taxi or bicycle based on information about delays in public transportation. The calendar integration unit also adjusts the schedule to shorten travel time based on traffic information. For example, it may suggest ensuring ample travel time before an important meeting. This makes it possible to optimize travel time based on real-time traffic information.

[0034] The schedule proposal unit analyzes each participant's past meeting participation history and can propose the most efficient meeting time. For example, the generation AI in the schedule proposal unit analyzes each participant's meeting participation history over the past year and identifies time periods when participation rates are high. For example, the schedule proposal unit sets a meeting at a time when it is easy for everyone to participate. The generation AI in the schedule proposal unit also proposes the optimal meeting time based on each participant's meeting participation history. For example, it identifies the day of the week and time period when participants are most likely to participate based on past data. The generation AI in the schedule proposal unit also analyzes each participant's meeting participation history and proposes a meeting time that avoids time periods when participation rates are low. For example, it sets a meeting to avoid time periods when participants are busy. This makes it possible to propose efficient meeting times based on past meeting participation history.

[0035] The schedule proposal unit can propose a meeting time that maximizes work efficiency, taking into account the workload of each participant. In the schedule proposal unit, for example, the generation AI analyzes the workload data of each participant and proposes a meeting time that maximizes work efficiency. For example, the meeting is scheduled to avoid times when work is concentrated. In addition, the schedule proposal unit proposes the optimal meeting time based on the workload of each participant, using the generation AI. For example, scheduling a meeting during times when work is light improves work efficiency. In addition, the schedule proposal unit analyzes the workload data of each participant, using the generation AI to adjust the meeting time to maximize work efficiency. For example, scheduling a meeting to avoid times when work overlaps. This makes it possible to propose efficient meeting times that take work load into account.

[0036] The schedule proposal unit can propose a meeting time that maximizes work efficiency, taking into account the workload of each participant. In the schedule proposal unit, for example, the generation AI analyzes the workload data of each participant and proposes a meeting time that maximizes work efficiency. For example, the meeting is scheduled to avoid times when work is concentrated. In addition, the schedule proposal unit proposes the optimal meeting time based on the workload of each participant, using the generation AI. For example, scheduling a meeting during times when work is light improves work efficiency. In addition, the schedule proposal unit analyzes the workload data of each participant, using the generation AI to adjust the meeting time to maximize work efficiency. For example, scheduling a meeting to avoid times when work overlaps. This makes it possible to propose efficient meeting times that take work load into account.

[0037] The schedule proposal unit can propose the optimal meeting time according to the importance of the meeting. In the schedule proposal unit, for example, the generation AI analyzes the importance of the meeting and proposes a time period when all participants can attend for important meetings. For example, important meetings are set at a time period when it is easy for everyone to attend. In addition, the schedule proposal unit has the generation AI propose the optimal meeting time according to the importance of the meeting. For example, meetings with low importance are set flexibly to suit the convenience of the participants. In addition, the schedule proposal unit has the generation AI adjust the optimal meeting time based on the importance of the meeting. For example, important meetings are set at a time period when all participants can attend, and meetings with low importance are adjusted flexibly. This makes it possible to propose the optimal meeting time according to the importance of the meeting.

[0038] The schedule proposal unit can propose the optimal meeting format (online, offline, hybrid) depending on the purpose of the meeting. In the schedule proposal unit, for example, the generation AI analyzes the purpose of the meeting and proposes the optimal meeting format. For example, it proposes an online format for a brainstorming meeting. In addition, the schedule proposal unit proposes the optimal meeting format depending on the purpose of the meeting. For example, it proposes an offline format for a meeting where important decisions will be made. In addition, the schedule proposal unit adjusts the optimal meeting format based on the purpose of the meeting. For example, it proposes a hybrid format for a meeting where the main purpose is to share information. This makes it possible to propose the optimal meeting format depending on the purpose of the meeting.

[0039] The archive generation unit can automatically highlight important parts of a meeting and create a shortened archive video. For example, the generation AI analyzes the recorded meeting data and automatically highlights important parts. For example, it extracts parts where important decisions or discussions took place and creates a shortened archive video. The archive generation unit also identifies important parts based on the recorded meeting data and creates a shortened archive video. For example, it creates a shortened version summarizing the main points of the meeting and sends it to the participants. The archive generation unit also analyzes the recorded meeting data and highlights important parts to create a shortened archive video. For example, it creates a shortened version that emphasizes the important points of the meeting, making it easier to review later. This creates a shortened archive video that highlights the important parts of the meeting, making it possible to efficiently review the important parts later.

[0040] The archive generation unit can analyze meeting recording data and automatically attach relevant materials and links. In the archive generation unit, for example, the generation AI analyzes meeting recording data and automatically attaches materials and links related to the topics discussed. For example, it adds links to reports and websites mentioned during the meeting. The archive generation unit also identifies relevant materials and links based on the meeting recording data and attaches them to the archived video. For example, it automatically attaches presentation materials used in the meeting. The archive generation unit also builds a system in which the generation AI analyzes meeting recording data and automatically attaches relevant materials and links. For example, it adds links to literature and databases mentioned during the meeting. This automatically attaching relevant materials and links to meeting recording data deepens understanding of the meeting content.

[0041] The archive generation unit can analyze recorded meeting data and create an interactive archive that includes not only audio but also visual elements. For example, the generation AI in the archive generation unit analyzes recorded meeting data and creates an interactive archive that includes not only audio but also visual elements. For example, it integrates presentation slides and whiteboard content into videos. The archive generation unit also adds visual elements based on recorded meeting data to create an interactive archive. For example, it incorporates materials and charts used during the meeting into the video. The archive generation unit also builds a system in which the generation AI analyzes recorded meeting data and creates an interactive archive that includes visual elements. For example, it visually highlights important points during the meeting. This creates an interactive archive that includes not only audio but also visual elements, deepening understanding of the meeting content.

[0042] The archive generation unit can analyze recorded meeting data and make videos searchable based on specific keywords or topics. For example, the archive generation unit uses a generation AI to analyze recorded meeting data and make videos searchable based on specific keywords or topics. For example, it provides a search function based on keywords mentioned during a meeting. The archive generation unit also constructs a system in which the generation AI extracts specific keywords or topics from recorded meeting data and makes videos searchable. For example, it searches for videos based on topics discussed. The archive generation unit also provides a function in which the generation AI analyzes recorded meeting data and makes videos searchable based on specific keywords or topics. For example, it makes it possible to search for important comments made during a meeting. This makes it possible to search for videos based on specific keywords or topics, allowing users to quickly obtain necessary information.

[0043] The transcription unit can analyze meeting transcript data and automatically extract important action items. In the transcription unit, for example, a generation AI analyzes meeting transcript data and automatically extracts important action items. For example, it lists the tasks and people in charge that were decided during the meeting. The transcription unit also builds a system in which a generation AI identifies and automatically extracts important action items based on the meeting transcript data. For example, it automatically generates a to-do list for the meeting. The transcription unit also provides a function in which a generation AI analyzes meeting transcript data and automatically extracts important action items. For example, it lists important decisions made during the meeting. This automatically extracts important action items from the meeting transcript data, making the outcomes of the meeting clear.

[0044] The transcription unit can analyze meeting transcript data and automatically link related past meeting content and materials. For example, the transcription unit uses a generation AI to analyze meeting transcript data and automatically link related past meeting content and materials. For example, it links materials related to topics discussed in past meetings. The transcription unit also builds a system in which the generation AI identifies related past meeting content and materials based on the meeting transcript data and automatically links them. For example, it links minutes of past meetings. The transcription unit also provides a function in which the generation AI analyzes meeting transcript data and automatically links related past meeting content and materials. For example, it links presentation materials used in past meetings. This allows for a deeper understanding of the meeting content by automatically linking related past meeting content and materials from the meeting transcript data.

[0045] The transcription unit can analyze meeting transcript data and make it searchable based on specific keywords or topics. For example, the transcription unit uses a generation AI to analyze meeting transcript data and make it searchable based on specific keywords or topics. For example, it provides a search function based on keywords mentioned during a meeting. The transcription unit also builds a system in which the generation AI extracts specific keywords or topics based on the meeting transcript data and makes it searchable. For example, it searches based on the topics discussed. The transcription unit also provides a function in which the generation AI analyzes meeting transcript data and makes it searchable based on specific keywords or topics. For example, it makes it possible to search for important comments made during a meeting. This makes it possible to search meeting transcript data based on specific keywords or topics, allowing necessary information to be obtained quickly.

[0046] The transcription unit can analyze meeting transcript data and automatically generate not only summaries but also detailed minutes. For example, in the transcription unit, a generation AI analyzes meeting transcript data and automatically generates not only summaries but also detailed minutes. For example, it records the details of what was said during a meeting and provides them as minutes. The transcription unit also builds a system in which a generation AI automatically generates summaries and detailed minutes based on meeting transcript data. For example, it provides a summary that summarizes the main points of the meeting and minutes that record the details of what was said. The transcription unit also provides a function in which a generation AI analyzes meeting transcript data and automatically generates summaries and detailed minutes. For example, it summarizes the important points of the meeting and records the details of what was said as minutes. This allows the contents of a meeting to be recorded efficiently by automatically generating summaries and detailed minutes from the meeting transcript data.

[0047] The time difference consideration unit can take into account the time zone of each participant and propose the most efficient meeting time. In this case, for example, the generation AI analyzes the time zone of each participant and proposes a time period that is convenient for everyone to attend. For example, it identifies a time period when participants in different time zones can all attend. The time difference consideration unit also proposes the optimal meeting time based on each participant's time zone. For example, it selects a time period that allows everyone to attend without difficulty. The time difference consideration unit also builds a system in which the generation AI takes into account the time zone of each participant and proposes the most efficient meeting time. For example, it automatically calculates a time period that is convenient for everyone to attend. This makes it possible to propose efficient meeting times that take into account the time zones of each participant.

[0048] The translation unit can consider each participant's language settings and propose the optimal translation method. For example, the generation AI in the translation unit analyzes each participant's language settings and proposes the optimal translation method. For example, it provides real-time translation depending on the language used by the participant. The translation unit also considers each participant's language settings and proposes the optimal translation method using the generation AI. For example, if participants use different languages, it proposes simultaneous interpretation. The translation unit also considers each participant's language settings and builds a system in which the generation AI proposes the optimal translation method. For example, it improves translation accuracy depending on the language used by the participant. This makes it possible to propose the optimal translation method taking each participant's language settings into account.

[0049] The time difference consideration unit can propose the optimal meeting time according to the importance of the meeting. In this case, for example, the generation AI analyzes the importance of the meeting and proposes a time period when all participants can attend for important meetings. For example, important meetings are set at a time when it is easy for everyone to attend. The time difference consideration unit also proposes the optimal meeting time according to the importance of the meeting. For example, meetings with low importance are set flexibly to suit the convenience of the participants. The time difference consideration unit also adjusts the optimal meeting time based on the importance of the meeting. For example, important meetings are set at a time when all participants can attend, and meetings with low importance are adjusted flexibly. This makes it possible to propose the optimal meeting time according to the importance of the meeting.

[0050] The time difference consideration unit can suggest the optimal meeting format (online, offline, hybrid) depending on the purpose of the meeting. In the time difference consideration unit, for example, the generation AI analyzes the purpose of the meeting and suggests the optimal meeting format. For example, it would suggest an online format for a brainstorming meeting. In addition, the time difference consideration unit allows the generation AI to suggest the optimal meeting format depending on the purpose of the meeting. For example, it would suggest an offline format for a meeting where important decisions will be made. In addition, the time difference consideration unit allows the generation AI to adjust the optimal meeting format based on the purpose of the meeting. For example, it would suggest a hybrid format for a meeting where the main purpose is to share information. This makes it possible to suggest the optimal meeting format depending on the purpose of the meeting.

[0051] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0052] The schedule suggestion unit can suggest activities for refreshing yourself, taking into account the user's hobbies and interests. For example, if the user likes listening to music, it can provide information about music events and concerts during their free time. If the user likes sports, it can suggest nearby sporting events and gym opening times. If the user likes reading, it can suggest information about new book releases and library opening times. This makes it possible to suggest a schedule for refreshing yourself based on the user's hobbies and interests.

[0053] The calendar integration unit can suggest healthy eating schedules that take into account the user's meal times and nutritional balance. For example, the generation AI can analyze the user's eating history and suggest balanced meals. It can also suggest healthy meals that are easy to prepare when the user is busy. It can also suggest appropriate recipes and ingredients by taking into account the user's food preferences and allergy information. This makes it possible to suggest eating schedules based on the user's health condition.

[0054] The calendar integration unit can analyze the user's sleep patterns and suggest a schedule to ensure optimal sleep time. For example, the generation AI analyzes the user's sleep data and suggests going to bed earlier if they are not getting enough sleep. Also, if the user tends to stay up late, it can send a reminder to encourage them to go to bed earlier. Furthermore, it can provide advice on creating a relaxing environment to improve the quality of the user's sleep. This makes it possible to suggest an optimal sleep schedule based on the user's sleep patterns.

[0055] The calendar integration unit also integrates with the calendars of family and friends, making it possible to suggest schedules that take private plans into account. For example, the generation AI can integrate with the calendars of the user's family and friends to coordinate shared plans. For example, it can suggest weekend events that the whole family can attend. The calendar integration unit also adjusts the work schedule taking into account the user's private plans. For example, if there are plans to have dinner with friends, it can avoid important tasks before or after that time. The calendar integration unit also allows the generation AI to analyze the calendars of family and friends, find common free time, and suggest private plans. For example, it can suggest going to the movies at a time when all family members are free. This makes it possible to suggest schedules that take into account the plans of family and friends.

[0056] The calendar integration unit can obtain traffic information in real time and propose schedules that optimize travel time. For example, the generation AI obtains real-time traffic information and proposes a schedule that takes travel time into consideration. For example, it may suggest traveling during times when heavy traffic congestion is expected. The calendar integration unit also analyzes the user's travel route and proposes the optimal means of transportation. For example, it may suggest using a taxi or bicycle based on information about delays in public transportation. The calendar integration unit also adjusts the schedule to shorten travel time based on traffic information, allowing the generation AI to ensure ample travel time before an important meeting. This makes it possible to optimize travel time based on real-time traffic information.

[0057] The schedule suggestion unit analyzes each participant's past meeting participation history and can propose the most efficient meeting time. For example, the generation AI analyzes each participant's meeting participation history over the past year and identifies time periods when participation rates are high. For example, the meeting is scheduled for a time period when it is easiest for everyone to attend. The schedule suggestion unit also proposes the optimal meeting time based on each participant's meeting participation history. For example, it identifies the day of the week and time period when participants are most likely to attend from past data. The schedule suggestion unit also analyzes each participant's meeting participation history and proposes meeting times that avoid time periods when participation rates are low. For example, the meeting is scheduled to avoid time periods when participants are busy. This makes it possible to propose efficient meeting times based on past meeting participation history.

[0058] The schedule proposal unit can consider the workload of each participant and propose a meeting time that maximizes work efficiency. For example, the generation AI analyzes the workload data of each participant and proposes a meeting time that maximizes work efficiency. For example, the meeting is scheduled to avoid times when work is concentrated. The schedule proposal unit also proposes the optimal meeting time based on the workload of each participant. For example, scheduling a meeting during times when work is light improves work efficiency. The schedule proposal unit also proposes the optimal meeting time based on the workload of each participant. For example, scheduling a meeting to avoid times when work overlaps. The schedule proposal unit also proposes the optimal meeting time based on the workload of each participant. For example, scheduling a meeting to avoid times when work overlaps.

[0059] The processing flow of the first embodiment will be briefly explained below.

[0060] Step 1: The calendar integration unit integrates with a calendar and manages daily schedules. For example, it integrates with Google Calendar or Outlook Calendar to obtain the user's schedule. Step 2: The schedule suggestion unit proposes a schedule that avoids overlapping appointments based on the schedule information obtained by the calendar linkage unit. For example, the generation AI analyzes the user's schedule and proposes the optimal schedule. Step 3: The conference recording unit records the contents of the conference, for example, recording the audio and video during the conference and saving it as digital data. Step 4: The archive generating unit generates an archive video from the conference content recorded by the conference recording unit, for example, by editing the recorded data to create an archive video. Step 5: The transcription unit transcribes the meeting content from the archived video generated by the archive generation unit. For example, the transcription unit converts the meeting content into text data using voice recognition technology. Step 6: The minutes generation unit summarizes the meeting content transcribed by the transcription unit and automatically generates minutes. For example, the generation AI analyzes the meeting content, extracts important points, and creates minutes. Step 7: The time zone difference consideration unit selects the meeting time taking into account the time difference. For example, it considers the time zones of each participant and proposes a time slot that is convenient for everyone to participate. Step 8: The subtitle generator subtitles the conversation content and displays it. For example, it uses voice recognition technology to subtitle the conversation content in real time. Step 9: The translation unit translates the conversation into multiple languages. For example, the generation AI analyzes the conversation, translates it into different languages, and displays it.

[0061] (Example 2) The scheduling assistance system according to an embodiment of the present invention is a system in which a generation AI works in conjunction with a calendar to manage daily schedules and propose schedules that avoid overlapping appointments. This allows the scheduling assistance system to improve the efficiency of users' schedule management and automate the arrangement and recording of meetings.

[0062] The scheduling assistance system according to the embodiment includes a calendar linking unit, a schedule proposing unit, a meeting recording unit, an archive generating unit, a transcription unit, a minutes memo generating unit, a time difference consideration unit, a subtitle generating unit, and a translation unit. The calendar linking unit links with a calendar to manage daily schedules. For example, it links with Google Calendar or Outlook Calendar to acquire the user's schedule. The schedule proposing unit proposes a schedule that avoids schedule overlaps based on the schedule information acquired by the calendar linking unit. For example, a generation AI analyzes the user's schedule and proposes an optimal schedule. The meeting recording unit records the contents of the meeting. For example, it records audio and video during the meeting and saves them as digital data. The archive generating unit generates an archived video of the meeting contents recorded by the meeting recording unit. For example, it edits the recorded data to create an archived video. The transcription unit transcribes the meeting contents from the archived video generated by the archive generating unit. For example, it converts the meeting contents into text data using speech recognition technology. The minutes memo generation unit summarizes the meeting content transcribed by the transcription unit and automatically generates minutes memos. For example, the generation AI analyzes the meeting content, extracts important points, and creates minutes memos. The time difference consideration unit selects the meeting time taking time differences into account. For example, it considers the time zones of each participant and suggests a time slot that is convenient for everyone to attend. The subtitle generation unit subtitles and displays the conversation content. For example, it uses voice recognition technology to subtitle the conversation content in real time. The translation unit translates the conversation content into multiple languages. For example, the generation AI analyzes the conversation content and translates it into different languages ​​for display. As a result, the scheduling assistance system according to the embodiment can improve the efficiency of users' schedule management and automate the arrangement and recording of meetings. For example, by utilizing the generation AI, users can easily manage their schedules and arrange meetings, and can smoothly record and share meeting content. In addition, global communication is possible, overcoming time differences and language barriers.

[0063] The calendar integration unit analyzes the user's past schedule data, learns the user's behavioral patterns, and can propose optimal schedules. For example, the generation AI in the calendar integration unit analyzes the user's schedule data from the past year to identify frequent event and meeting patterns. For example, it learns regular meetings every Monday and end-of-month briefings, and proposes a new schedule based on that. To learn the user's behavioral patterns, the generation AI compares past schedule data with actual behavioral history. For example, it analyzes the attendance rate and cancellation rate of scheduled meetings to identify time periods when the user is most likely to attend. The calendar integration unit also suggests avoiding concentrating appointments during specific time periods based on the user's past schedule data. For example, if the user tends to have lower concentration in the afternoon, it schedules important meetings in the morning. This enables optimal schedule proposals based on the user's behavioral patterns.

[0064] The calendar integration unit can suggest a healthy schedule by taking into account the user's health data. For example, the calendar integration unit uses the generation AI to analyze sleep data obtained from the user's wearable device and adjust the next day's schedule if the user has not gotten enough sleep. For example, it may suggest moving an important meeting to the afternoon. The calendar integration unit also uses the generation AI to incorporate appropriate rest and exercise times into the schedule based on the user's exercise data. For example, it supports a healthy lifestyle by suggesting a short walk after a long meeting. The calendar integration unit also uses the generation AI to comprehensively analyze the user's health data and add relaxation time to the schedule when stress levels are high. For example, it can suggest times for meditation or yoga to maintain the user's health. This makes it possible to suggest schedules based on the user's health status.

[0065] The calendar linkage unit can use the emotion estimation function to analyze the user's emotional state and suggest a schedule to reduce stress. For example, if the generation AI analyzes the user's emotional state and determines that stress is high, the calendar linkage unit adds relaxing activities to the schedule. For example, it suggests time to listen to music or read. The calendar linkage unit also uses the emotion estimation function to identify the time of day when the user is most relaxed and adjusts the schedule to avoid important meetings or tasks during that time. For example, if the user finds it easier to relax in the evening, it schedules important meetings for the morning. The calendar linkage unit also incorporates break times to reduce stress into the schedule based on the user's emotional data. For example, it suggests a short break after a long period of work, ensuring time to refresh. This makes it possible to suggest a schedule to reduce stress based on the user's emotional state.

[0066] The calendar integration unit also integrates with the calendars of family and friends, making it possible to suggest schedules that take private plans into consideration. For example, the generation AI in the calendar integration unit integrates with the calendars of the user's family and friends to coordinate shared plans. For example, it could suggest weekend events that the whole family can attend. The calendar integration unit also adjusts the work schedule taking into consideration the user's private plans. For example, if there are plans to have dinner with friends, it would avoid important tasks before or after that time. The calendar integration unit also allows the generation AI to analyze the calendars of family and friends, find common free time, and suggest private plans. For example, it would suggest going to the movies at a time when all family members are free. This makes it possible to suggest schedules that take into consideration the plans of family and friends.

[0067] The calendar integration unit can obtain traffic information in real time and propose a schedule that optimizes travel time. For example, the generation AI in the calendar integration unit obtains real-time traffic information and proposes a schedule that takes travel time into consideration. For example, it may suggest traveling during times when congestion is expected to be avoided. The calendar integration unit also analyzes the user's travel route and proposes the optimal means of transportation. For example, it may suggest using a taxi or bicycle based on information about delays in public transportation. The calendar integration unit also adjusts the schedule to shorten travel time based on traffic information. For example, it may suggest ensuring ample travel time before an important meeting. This makes it possible to optimize travel time based on real-time traffic information.

[0068] The calendar linkage unit can use the emotion estimation function to set reminders for times when the user is most relaxed. For example, the calendar linkage unit uses the emotion estimation function to identify times when the user is relaxed and set reminders for those times. For example, if the user is relaxing in the evening, a reminder is sent for that time. The calendar linkage unit also uses the generation AI to analyze the user's emotion data and set reminders for times when stress is low. For example, if the user is relaxing in the morning, a reminder for an important task is sent for that time. The calendar linkage unit also uses the emotion estimation function to set reminders for times when the user is relaxed, thereby reducing stress. For example, a reminder for a break or refreshment is sent for times when the user is relaxing. In this way, setting reminders for times when the user is relaxed reduces stress.

[0069] The schedule proposal unit analyzes each participant's past meeting participation history and can propose the most efficient meeting time. For example, the generation AI in the schedule proposal unit analyzes each participant's meeting participation history over the past year and identifies time periods when participation rates are high. For example, the schedule proposal unit sets a meeting at a time when it is easy for everyone to participate. The generation AI in the schedule proposal unit also proposes the optimal meeting time based on each participant's meeting participation history. For example, it identifies the day of the week and time period when participants are most likely to participate based on past data. The generation AI in the schedule proposal unit also analyzes each participant's meeting participation history and proposes a meeting time that avoids time periods when participation rates are low. For example, it sets a meeting to avoid time periods when participants are busy. This makes it possible to propose efficient meeting times based on past meeting participation history.

[0070] The schedule proposal unit can propose a meeting time that maximizes work efficiency, taking into account the workload of each participant. In the schedule proposal unit, for example, the generation AI analyzes the workload data of each participant and proposes a meeting time that maximizes work efficiency. For example, the meeting is scheduled to avoid times when work is concentrated. In addition, the schedule proposal unit proposes the optimal meeting time based on the workload of each participant, using the generation AI. For example, scheduling a meeting during times when work is light improves work efficiency. In addition, the schedule proposal unit analyzes the workload data of each participant, using the generation AI to adjust the meeting time to maximize work efficiency. For example, scheduling a meeting to avoid times when work overlaps. This makes it possible to propose efficient meeting times that take work load into account.

[0071] The schedule proposal unit can propose a meeting time that maximizes work efficiency, taking into account the workload of each participant. In the schedule proposal unit, for example, the generation AI analyzes the workload data of each participant and proposes a meeting time that maximizes work efficiency. For example, the meeting is scheduled to avoid times when work is concentrated. In addition, the schedule proposal unit proposes the optimal meeting time based on the workload of each participant, using the generation AI. For example, scheduling a meeting during times when work is light improves work efficiency. In addition, the schedule proposal unit analyzes the workload data of each participant, using the generation AI to adjust the meeting time to maximize work efficiency. For example, scheduling a meeting to avoid times when work overlaps. This makes it possible to propose efficient meeting times that take work load into account.

[0072] The schedule proposal unit can use the emotion estimation function to schedule a meeting for a time period when all participants are most relaxed. For example, the schedule proposal unit uses the emotion estimation function to identify a time period when all participants are relaxed and schedules the meeting for that time period. For example, scheduling a meeting for a time period when all participants are relaxed improves the efficiency of the meeting. Furthermore, the schedule proposal unit uses the generation AI to analyze the emotion data of the participants and schedules the meeting for a time period when stress is low. For example, scheduling a meeting for a time period when participants are relaxed improves the atmosphere of the meeting. Furthermore, the schedule proposal unit uses the emotion estimation function to schedule a meeting for a time period when all participants are relaxed, thereby reducing stress. For example, scheduling a meeting for a time period when participants are relaxed improves the outcome of the meeting. As a result, scheduling a meeting for a time period when all participants are relaxed improves the efficiency of the meeting.

[0073] The schedule proposal unit can propose the optimal meeting time according to the importance of the meeting. In the schedule proposal unit, for example, the generation AI analyzes the importance of the meeting and proposes a time period when all participants can attend for important meetings. For example, important meetings are set at a time period when it is easy for everyone to attend. In addition, the schedule proposal unit has the generation AI propose the optimal meeting time according to the importance of the meeting. For example, meetings with low importance are set flexibly to suit the convenience of the participants. In addition, the schedule proposal unit has the generation AI adjust the optimal meeting time based on the importance of the meeting. For example, important meetings are set at a time period when all participants can attend, and meetings with low importance are adjusted flexibly. This makes it possible to propose the optimal meeting time according to the importance of the meeting.

[0074] The schedule proposal unit can propose the optimal meeting format (online, offline, hybrid) depending on the purpose of the meeting. In the schedule proposal unit, for example, the generation AI analyzes the purpose of the meeting and proposes the optimal meeting format. For example, it proposes an online format for a brainstorming meeting. In addition, the schedule proposal unit proposes the optimal meeting format depending on the purpose of the meeting. For example, it proposes an offline format for a meeting where important decisions will be made. In addition, the schedule proposal unit adjusts the optimal meeting format based on the purpose of the meeting. For example, it proposes a hybrid format for a meeting where the main purpose is to share information. This makes it possible to propose the optimal meeting format depending on the purpose of the meeting.

[0075] The schedule proposal unit can use the emotion estimation function to monitor the emotional states of participants in real time and adjust the progress of the meeting. For example, the schedule proposal unit uses the emotion estimation function to monitor the emotional states of participants in real time and adjust the progress of the meeting. For example, if a participant is feeling stressed, it suggests a break. The schedule proposal unit also adjusts the progress of the meeting by having the generation AI analyze the emotional data of the participants. For example, if participants are relaxed, it increases the time for in-depth discussion. The schedule proposal unit also uses the emotion estimation function to adjust the progress of the meeting based on the emotional states of the participants and reduce stress. For example, if a participant is tired, it ends the meeting early. In this way, by monitoring the emotional states of participants in real time and adjusting the progress of the meeting, the efficiency of the meeting is improved.

[0076] The archive generation unit can automatically highlight important parts of a meeting and create a shortened archive video. For example, the generation AI analyzes the recorded meeting data and automatically highlights important parts. For example, it extracts parts where important decisions or discussions took place and creates a shortened archive video. The archive generation unit also identifies important parts based on the recorded meeting data and creates a shortened archive video. For example, it creates a shortened version summarizing the main points of the meeting and sends it to the participants. The archive generation unit also analyzes the recorded meeting data and highlights important parts to create a shortened archive video. For example, it creates a shortened version that emphasizes the important points of the meeting, making it easier to review later. This creates a shortened archive video that highlights the important parts of the meeting, making it possible to efficiently review the important parts later.

[0077] The archive generation unit can analyze meeting recording data and automatically attach relevant materials and links. In the archive generation unit, for example, the generation AI analyzes meeting recording data and automatically attaches materials and links related to the topics discussed. For example, it adds links to reports and websites mentioned during the meeting. The archive generation unit also identifies relevant materials and links based on the meeting recording data and attaches them to the archived video. For example, it automatically attaches presentation materials used in the meeting. The archive generation unit also builds a system in which the generation AI analyzes meeting recording data and automatically attaches relevant materials and links. For example, it adds links to literature and databases mentioned during the meeting. This automatically attaching relevant materials and links to meeting recording data deepens understanding of the meeting content.

[0078] The archive generation unit can use the emotion estimation function to analyze changes in emotions during a meeting and emphasize emotionally important parts. For example, the archive generation unit uses the emotion estimation function to analyze changes in emotions during a meeting and emphasize emotionally important parts. For example, it highlights parts where participants showed strong emotions. The archive generation unit also uses the generation AI to analyze recorded meeting data and identify and emphasize important parts based on changes in emotions. For example, it highlights moments when emotions are heightened and reflects them in the archived video. The archive generation unit also uses the emotion estimation function to build a system that analyzes changes in emotions during a meeting and emphasizes emotionally important parts. For example, it highlights statements made at the peak of emotions. In this way, by analyzing changes in emotions during a meeting and emphasizing emotionally important parts, the important points of the meeting are clarified.

[0079] The archive generation unit can analyze recorded meeting data and create an interactive archive that includes not only audio but also visual elements. For example, the generation AI in the archive generation unit analyzes recorded meeting data and creates an interactive archive that includes not only audio but also visual elements. For example, it integrates presentation slides and whiteboard content into videos. The archive generation unit also adds visual elements based on recorded meeting data to create an interactive archive. For example, it incorporates materials and charts used during the meeting into the video. The archive generation unit also builds a system in which the generation AI analyzes recorded meeting data and creates an interactive archive that includes visual elements. For example, it visually highlights important points during the meeting. This creates an interactive archive that includes not only audio but also visual elements, deepening understanding of the meeting content.

[0080] The archive generation unit can analyze recorded meeting data and make videos searchable based on specific keywords or topics. For example, the archive generation unit uses a generation AI to analyze recorded meeting data and make videos searchable based on specific keywords or topics. For example, it provides a search function based on keywords mentioned during a meeting. The archive generation unit also constructs a system in which the generation AI extracts specific keywords or topics from recorded meeting data and makes videos searchable. For example, it searches for videos based on topics discussed. The archive generation unit also provides a function in which the generation AI analyzes recorded meeting data and makes videos searchable based on specific keywords or topics. For example, it makes it possible to search for important comments made during a meeting. This makes it possible to search for videos based on specific keywords or topics, allowing users to quickly obtain necessary information.

[0081] The archive generation unit can use the emotion estimation function to collect viewers' emotional reactions to the recorded conference data and provide feedback. For example, the archive generation unit uses the emotion estimation function to collect viewers' emotional reactions to the recorded conference data and provide feedback based on that data. For example, it identifies parts to which viewers reacted emotionally and suggests areas for improvement. The archive generation unit also builds a system in which the generation AI analyzes the recorded conference data, collects viewers' emotional reactions, and provides feedback. For example, it highlights parts to which viewers showed positive reactions. The archive generation unit also uses the emotion estimation function to collect viewers' emotional reactions to the recorded conference data and provides feedback based on that data. For example, it suggests improvements to parts to which viewers showed negative reactions. In this way, by collecting viewers' emotional reactions and providing feedback, areas for improvement in the conference are clarified.

[0082] The transcription unit can analyze meeting transcript data and automatically extract important action items. In the transcription unit, for example, a generation AI analyzes meeting transcript data and automatically extracts important action items. For example, it lists the tasks and people in charge that were decided during the meeting. The transcription unit also builds a system in which a generation AI identifies and automatically extracts important action items based on the meeting transcript data. For example, it automatically generates a to-do list for the meeting. The transcription unit also provides a function in which a generation AI analyzes meeting transcript data and automatically extracts important action items. For example, it lists important decisions made during the meeting. This automatically extracts important action items from the meeting transcript data, making the outcomes of the meeting clear.

[0083] The transcription unit can analyze meeting transcript data and automatically link related past meeting content and materials. For example, the transcription unit uses a generation AI to analyze meeting transcript data and automatically link related past meeting content and materials. For example, it links materials related to topics discussed in past meetings. The transcription unit also builds a system in which the generation AI identifies related past meeting content and materials based on the meeting transcript data and automatically links them. For example, it links minutes of past meetings. The transcription unit also provides a function in which the generation AI analyzes meeting transcript data and automatically links related past meeting content and materials. For example, it links presentation materials used in past meetings. This allows for a deeper understanding of the meeting content by automatically linking related past meeting content and materials from the meeting transcript data.

[0084] The transcription unit can use the emotion estimation function to analyze changes in emotions during a meeting and emphasize emotionally important parts. For example, the transcription unit uses the emotion estimation function to analyze changes in emotions during a meeting and emphasize emotionally important parts. For example, it highlights parts where participants showed strong emotions. The transcription unit also uses a generative AI to analyze the meeting transcript data and identify and emphasize important parts based on changes in emotions. For example, it highlights moments when emotions are heightened and reflects these in the meeting notes. The transcription unit also uses the emotion estimation function to build a system that analyzes changes in emotions during a meeting and emphasizes emotionally important parts. For example, it highlights statements made at the peak of emotions. In this way, the transcription unit analyzes changes in emotions during a meeting and emphasizes emotionally important parts, thereby clarifying the important points of the meeting.

[0085] The transcription unit can analyze meeting transcript data and make it searchable based on specific keywords or topics. For example, the transcription unit uses a generation AI to analyze meeting transcript data and make it searchable based on specific keywords or topics. For example, it provides a search function based on keywords mentioned during a meeting. The transcription unit also builds a system in which the generation AI extracts specific keywords or topics based on the meeting transcript data and makes it searchable. For example, it searches based on the topics discussed. The transcription unit also provides a function in which the generation AI analyzes meeting transcript data and makes it searchable based on specific keywords or topics. For example, it makes it possible to search for important comments made during a meeting. This makes it possible to search meeting transcript data based on specific keywords or topics, allowing necessary information to be obtained quickly.

[0086] The transcription unit can analyze meeting transcript data and automatically generate not only summaries but also detailed minutes. For example, in the transcription unit, a generation AI analyzes meeting transcript data and automatically generates not only summaries but also detailed minutes. For example, it records the details of what was said during a meeting and provides them as minutes. The transcription unit also builds a system in which a generation AI automatically generates summaries and detailed minutes based on meeting transcript data. For example, it provides a summary that summarizes the main points of the meeting and minutes that record the details of what was said. The transcription unit also provides a function in which a generation AI analyzes meeting transcript data and automatically generates summaries and detailed minutes. For example, it summarizes the important points of the meeting and records the details of what was said as minutes. This allows the contents of a meeting to be recorded efficiently by automatically generating summaries and detailed minutes from the meeting transcript data.

[0087] The transcription unit can use the emotion estimation function to collect users' emotional reactions to the meeting transcript data and provide feedback. For example, the transcription unit uses the emotion estimation function to collect users' emotional reactions to the meeting transcript data and provide feedback based on that data. For example, it identifies parts to which users reacted emotionally and suggests areas for improvement. The transcription unit also builds a system in which the generative AI analyzes the meeting transcript data, collects users' emotional reactions, and provides feedback. For example, it highlights parts to which users had positive reactions. The transcription unit also uses the emotion estimation function to collect users' emotional reactions to the meeting transcript data and provides feedback based on that data. For example, it suggests improvements to parts to which users had negative reactions. In this way, by collecting users' emotional reactions and providing feedback, areas for improvement in the meeting are clarified.

[0088] The time difference consideration unit can take into account the time zone of each participant and propose the most efficient meeting time. In this case, for example, the generation AI analyzes the time zone of each participant and proposes a time period that is convenient for everyone to attend. For example, it identifies a time period when participants in different time zones can all attend. The time difference consideration unit also proposes the optimal meeting time based on each participant's time zone. For example, it selects a time period that allows everyone to attend without difficulty. The time difference consideration unit also builds a system in which the generation AI takes into account the time zone of each participant and proposes the most efficient meeting time. For example, it automatically calculates a time period that is convenient for everyone to attend. This makes it possible to propose efficient meeting times that take into account the time zones of each participant.

[0089] The translation unit can consider each participant's language settings and propose the optimal translation method. For example, the generation AI in the translation unit analyzes each participant's language settings and proposes the optimal translation method. For example, it provides real-time translation depending on the language used by the participant. The translation unit also considers each participant's language settings and proposes the optimal translation method using the generation AI. For example, if participants use different languages, it proposes simultaneous interpretation. The translation unit also considers each participant's language settings and builds a system in which the generation AI proposes the optimal translation method. For example, it improves translation accuracy depending on the language used by the participant. This makes it possible to propose the optimal translation method taking each participant's language settings into account.

[0090] The time difference consideration unit can use the emotion estimation function to schedule a meeting for a time when all participants are most relaxed. For example, the time difference consideration unit uses the emotion estimation function to identify a time when all participants are relaxed and schedules the meeting for that time. For example, scheduling a meeting for a time when all participants are relaxed improves meeting efficiency. In addition, the time difference consideration unit uses the generation AI to analyze participants' emotion data and schedules the meeting for a time when stress is low. For example, scheduling a meeting for a time when participants are relaxed improves the atmosphere of the meeting. In addition, the time difference consideration unit uses the emotion estimation function to schedule a meeting for a time when all participants are relaxed, reducing stress. For example, scheduling a meeting for a time when participants are relaxed improves meeting outcomes. As a result, scheduling a meeting for a time when all participants are relaxed improves meeting efficiency.

[0091] The time difference consideration unit can propose the optimal meeting time according to the importance of the meeting. In this case, for example, the generation AI analyzes the importance of the meeting and proposes a time period when all participants can attend for important meetings. For example, important meetings are set at a time when it is easy for everyone to attend. The time difference consideration unit also proposes the optimal meeting time according to the importance of the meeting. For example, meetings with low importance are set flexibly to suit the convenience of the participants. The time difference consideration unit also adjusts the optimal meeting time based on the importance of the meeting. For example, important meetings are set at a time when all participants can attend, and meetings with low importance are adjusted flexibly. This makes it possible to propose the optimal meeting time according to the importance of the meeting.

[0092] The time difference consideration unit can suggest the optimal meeting format (online, offline, hybrid) depending on the purpose of the meeting. In the time difference consideration unit, for example, the generation AI analyzes the purpose of the meeting and suggests the optimal meeting format. For example, it would suggest an online format for a brainstorming meeting. In addition, the time difference consideration unit allows the generation AI to suggest the optimal meeting format depending on the purpose of the meeting. For example, it would suggest an offline format for a meeting where important decisions will be made. In addition, the time difference consideration unit allows the generation AI to adjust the optimal meeting format based on the purpose of the meeting. For example, it would suggest a hybrid format for a meeting where the main purpose is to share information. This makes it possible to suggest the optimal meeting format depending on the purpose of the meeting.

[0093] The time difference consideration unit can use the emotion estimation function to monitor the emotional states of participants in real time and adjust the progress of the meeting. For example, the time difference consideration unit uses the emotion estimation function to monitor the emotional states of participants in real time and adjust the progress of the meeting. For example, if a participant is feeling stressed, it suggests a break. The time difference consideration unit also adjusts the progress of the meeting by having the generation AI analyze the emotional data of the participants. For example, if participants are relaxed, it increases the time for in-depth discussion. The time difference consideration unit also uses the emotion estimation function to adjust the progress of the meeting based on the emotional states of the participants and reduce stress. For example, if a participant is tired, it ends the meeting early. In this way, by monitoring the emotional states of participants in real time and adjusting the progress of the meeting, the efficiency of the meeting is improved.

[0094] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0095] The schedule suggestion unit can suggest activities for refreshing yourself, taking into account the user's hobbies and interests. For example, if the user likes listening to music, it can provide information about music events and concerts during their free time. If the user likes sports, it can suggest nearby sporting events and gym opening times. If the user likes reading, it can suggest information about new book releases and library opening times. This makes it possible to suggest a schedule for refreshing yourself based on the user's hobbies and interests.

[0096] The calendar integration unit can suggest healthy eating schedules that take into account the user's meal times and nutritional balance. For example, the generation AI can analyze the user's eating history and suggest balanced meals. It can also suggest healthy meals that are easy to prepare when the user is busy. It can also suggest appropriate recipes and ingredients by taking into account the user's food preferences and allergy information. This makes it possible to suggest eating schedules based on the user's health condition.

[0097] The calendar integration unit can analyze the user's sleep patterns and suggest a schedule to ensure optimal sleep time. For example, the generation AI analyzes the user's sleep data and suggests going to bed earlier if they are not getting enough sleep. Also, if the user tends to stay up late, it can send a reminder to encourage them to go to bed earlier. Furthermore, it can provide advice on creating a relaxing environment to improve the quality of the user's sleep. This makes it possible to suggest an optimal sleep schedule based on the user's sleep patterns.

[0098] The calendar linkage unit can use the emotion estimation function to analyze the user's emotional state and suggest a schedule to improve motivation. For example, if the generation AI analyzes the user's emotional state and determines that motivation is declining, it will suggest encouraging messages and activities to increase motivation. It also maintains motivation by incorporating tasks into the schedule that are likely to give the user a sense of accomplishment. It also aims to improve motivation by suggesting refreshing activities during times when the user is able to relax. This makes it possible to suggest schedules to improve motivation based on the user's emotional state.

[0099] The calendar integration unit also integrates with the calendars of family and friends, making it possible to suggest schedules that take private plans into account. For example, the generation AI can integrate with the calendars of the user's family and friends to coordinate shared plans. For example, it can suggest weekend events that the whole family can attend. The calendar integration unit also adjusts the work schedule taking into account the user's private plans. For example, if there are plans to have dinner with friends, it can avoid important tasks before or after that time. The calendar integration unit also allows the generation AI to analyze the calendars of family and friends, find common free time, and suggest private plans. For example, it can suggest going to the movies at a time when all family members are free. This makes it possible to suggest schedules that take into account the plans of family and friends.

[0100] The calendar integration unit can obtain traffic information in real time and propose schedules that optimize travel time. For example, the generation AI obtains real-time traffic information and proposes a schedule that takes travel time into consideration. For example, it may suggest traveling during times when heavy traffic congestion is expected. The calendar integration unit also analyzes the user's travel route and proposes the optimal means of transportation. For example, it may suggest using a taxi or bicycle based on information about delays in public transportation. The calendar integration unit also adjusts the schedule to shorten travel time based on traffic information, allowing the generation AI to ensure ample travel time before an important meeting. This makes it possible to optimize travel time based on real-time traffic information.

[0101] The calendar linkage unit can use the emotion estimation function to set reminders for times when the user is most relaxed. For example, the emotion estimation function can be used to identify times when the user is relaxed and set reminders for those times. For example, if the user is relaxing in the evening, a reminder can be sent for that time. The calendar linkage unit also uses the generation AI to analyze the user's emotion data and set reminders for times when stress is low. For example, if the user is relaxing in the morning, a reminder for an important task can be sent for that time. The calendar linkage unit also uses the emotion estimation function to set reminders for times when the user is relaxed, thereby reducing stress. For example, a reminder for a break or refreshment can be sent for times when the user is relaxing. In this way, setting reminders for times when the user is relaxed reduces stress.

[0102] The schedule suggestion unit analyzes each participant's past meeting participation history and can propose the most efficient meeting time. For example, the generation AI analyzes each participant's meeting participation history over the past year and identifies time periods when participation rates are high. For example, the meeting is scheduled for a time period when it is easiest for everyone to attend. The schedule suggestion unit also proposes the optimal meeting time based on each participant's meeting participation history. For example, it identifies the day of the week and time period when participants are most likely to attend from past data. The schedule suggestion unit also analyzes each participant's meeting participation history and proposes meeting times that avoid time periods when participation rates are low. For example, the meeting is scheduled to avoid time periods when participants are busy. This makes it possible to propose efficient meeting times based on past meeting participation history.

[0103] The schedule proposal unit can consider the workload of each participant and propose a meeting time that maximizes work efficiency. For example, the generation AI analyzes the workload data of each participant and proposes a meeting time that maximizes work efficiency. For example, the meeting is scheduled to avoid times when work is concentrated. The schedule proposal unit also proposes the optimal meeting time based on the workload of each participant. For example, scheduling a meeting during times when work is light improves work efficiency. The schedule proposal unit also proposes the optimal meeting time based on the workload of each participant. For example, scheduling a meeting to avoid times when work overlaps. The schedule proposal unit also proposes the optimal meeting time based on the workload of each participant. For example, scheduling a meeting to avoid times when work overlaps.

[0104] The schedule proposal unit can use the emotion estimation function to schedule a meeting for a time period when all participants are most relaxed. For example, the emotion estimation function can be used to identify a time period when all participants are relaxed and schedule the meeting for that time period. For example, scheduling a meeting for a time period when all participants are relaxed improves the efficiency of the meeting. Furthermore, the schedule proposal unit uses the generation AI to analyze the emotion data of the participants and schedules the meeting for a time period when stress is low. For example, scheduling a meeting for a time period when participants are relaxed improves the atmosphere of the meeting. Furthermore, the schedule proposal unit uses the emotion estimation function to schedule a meeting for a time period when all participants are relaxed, thereby reducing stress. For example, scheduling a meeting for a time period when participants are relaxed improves the outcome of the meeting. As a result, scheduling a meeting for a time period when all participants are relaxed improves the efficiency of the meeting.

[0105] The processing flow of the second embodiment will be briefly explained below.

[0106] Step 1: The calendar integration unit integrates with a calendar and manages daily schedules. For example, it integrates with Google Calendar or Outlook Calendar to obtain the user's schedule. Step 2: The schedule suggestion unit proposes a schedule that avoids overlapping appointments based on the schedule information obtained by the calendar linkage unit. For example, the generation AI analyzes the user's schedule and proposes the optimal schedule. Step 3: The conference recording unit records the contents of the conference, for example, recording the audio and video during the conference and saving it as digital data. Step 4: The archive generating unit generates an archive video from the conference content recorded by the conference recording unit, for example, by editing the recorded data to create an archive video. Step 5: The transcription unit transcribes the meeting content from the archived video generated by the archive generation unit. For example, the transcription unit converts the meeting content into text data using voice recognition technology. Step 6: The minutes generation unit summarizes the meeting content transcribed by the transcription unit and automatically generates minutes. For example, the generation AI analyzes the meeting content, extracts important points, and creates minutes. Step 7: The time zone difference consideration unit selects the meeting time taking into account the time difference. For example, it considers the time zones of each participant and proposes a time slot that is convenient for everyone to participate. Step 8: The subtitle generator subtitles the conversation content and displays it. For example, it uses voice recognition technology to subtitle the conversation content in real time. Step 9: The translation unit translates the conversation into multiple languages. For example, the generation AI analyzes the conversation, translates it into different languages, and displays it.

[0107] 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.

[0108] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> 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.

[0109] 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.

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

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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).

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] In the headset type terminal 314, 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. 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 specific processing unit 290 using these models.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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).

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] In the robot 414, 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 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 processing similar to that of the specific processing unit 290 using these models.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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).

[0160] 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.

[0161] 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."

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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. [Explanation of symbols]

[0174] 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 calendar integration section that links with the calendar and manages daily schedules, a schedule suggestion unit that suggests a schedule so as not to overlap plans based on the schedule information acquired by the calendar linkage unit; a conference recording unit that records the contents of the conference; an archive generating unit that generates an archive video of the conference content recorded by the conference recording unit; a transcription unit that transcribes the contents of the conference from the archive video generated by the archive generation unit; a minutes memo generation unit that summarizes the contents of the meeting transcribed by the transcription unit and automatically generates minutes memos; a time difference consideration unit that selects a meeting time taking into consideration the time difference; a subtitle generation unit that subtitles and displays the conversation content; A translation unit that translates the conversation content into multiple languages. A system characterized by:

2. The calendar linkage unit Analyzes the user's past schedule data, learns the user's behavioral patterns, and proposes the optimal schedule 2. The system of claim 1.

3. The calendar linkage unit Taking into account the user's health data, it suggests a healthy schedule 2. The system of claim 1.

4. The calendar linkage unit Analyzes the user's emotional state and suggests a schedule to reduce stress 2. The system of claim 1.

5. The calendar linkage unit It also connects with the calendars of family and friends to suggest schedules that take private events into account.

2. The system of claim 1.

6. The calendar linkage unit Obtaining real-time traffic information and proposing schedules that optimize travel time 2. The system of claim 1.

7. The calendar linkage unit Set reminders for times when users are most relaxed 2. The system of claim 1.

8. The schedule proposal unit Analyze each participant's past meeting participation history and suggest the most efficient meeting time 2. The system of claim 1.

Images