system

Abstract

The system according to this embodiment aims to efficiently create meeting minutes and follow up on meetings. [Solution] The system according to the embodiment comprises a minutes creation unit, a materials provision unit, and a follow-up unit. The minutes creation unit analyzes the audio of the meeting and generates minutes. The materials provision unit provides necessary materials based on the minutes generated by the minutes creation unit. The follow-up unit sends follow-up emails and notifications and creates a to-do list based on the minutes generated by the minutes creation unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that creating meeting minutes and following up are laborious and time-consuming, and it is difficult to perform them efficiently.

[0005] The system according to the embodiment aims to efficiently create meeting minutes and follow up.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a minutes creation unit, a materials provision unit, and a follow-up unit. The minutes creation unit analyzes the audio of the meeting and generates minutes. The materials provision unit provides necessary materials based on the minutes generated by the minutes creation unit. The follow-up unit sends follow-up emails and notifications and creates a to-do list based on the minutes generated by the minutes creation unit. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently create meeting minutes and follow up on meetings. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

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

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

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

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

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

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

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

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

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

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

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

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

[0028] (Example of form 1) The meeting support system according to an embodiment of the present invention is a system in which AI automatically creates meeting minutes during a meeting and understands their contents. This meeting support system analyzes the meeting audio in real time and generates meeting minutes. The generated meeting minutes are updated sequentially in accordance with the progress of the meeting and can be viewed in real time by all participants. The meeting support system has a function to immediately provide necessary materials during the meeting. The AI ​​understands the content of the meeting and automatically searches for and generates the necessary materials. This makes the meeting proceed smoothly and efficiently. Furthermore, the meeting support system also has a follow-up function. After the meeting ends, the AI ​​automatically sends follow-up emails and notifications to people who need to be contacted. It also creates a to-do list for each meeting participant, clarifying the tasks decided in the meeting. With this system, the preparation, progress, and follow-up of meetings are automated, maximizing work efficiency. The quality of meetings is also improved, and their role as a place for decision-making is strengthened. In today's world, where efficient meeting management is required due to the spread of remote work, this system is extremely useful. For example, the meeting support system analyzes the meeting audio in real time and generates meeting minutes. The generated meeting minutes are updated sequentially in line with the progress of the meeting, and all participants can view them in real time. The meeting support system has the function of instantly providing necessary materials during the meeting. AI understands the content of the meeting and automatically searches for and generates the necessary materials. This makes the meeting proceed smoothly and efficiently. Furthermore, the meeting support system also has a follow-up function. After the meeting ends, the AI ​​automatically sends follow-up emails and notifications to people who need to be contacted. It also creates a to-do list for each meeting participant, clarifying the tasks decided at the meeting. This system automates meeting preparation, progress, and follow-up, maximizing work efficiency. The quality of meetings is also improved, and their role as a forum for decision-making is strengthened. In today's world, where efficient meeting management is required due to the spread of remote work, this system is extremely useful. As a result, the meeting support system can automate meeting preparation, progress, and follow-up, maximizing work efficiency.

[0029] The meeting support system according to this embodiment comprises a minutes creation unit, a materials provision unit, and a follow-up unit. The minutes creation unit analyzes the audio of the meeting and generates minutes. The minutes creation unit converts the audio of the meeting into text data using, for example, speech recognition technology. The minutes creation unit can also summarize the content of the meeting and generate minutes using natural language processing technology. The minutes creation unit converts the audio of the meeting into text data in real time using, for example, speech recognition technology. The minutes creation unit can also summarize the content of the meeting and generate minutes using natural language processing technology. The minutes creation unit converts the audio of the meeting into text data in real time using, for example, speech recognition technology. The minutes creation unit can also summarize the content of the meeting and generate minutes using natural language processing technology. The materials provision unit provides necessary materials based on the minutes generated by the minutes creation unit. The materials provision unit understands the content of the meeting and automatically searches for and generates necessary materials. The document provision unit, for example, understands the content of the meeting and automatically searches for and generates the necessary documents. The document provision unit, for example, understands the content of the meeting and automatically searches for and generates the necessary documents. The follow-up unit, based on the minutes generated by the minutes creation unit, sends follow-up emails and notifications and creates to-do lists. The follow-up unit, for example, sends follow-up emails and notifications to people who need to be contacted. The follow-up unit, for example, creates to-do lists for each meeting participant. The follow-up unit, for example, sends follow-up emails and notifications to people who need to be contacted. The follow-up unit, for example, creates to-do lists for each meeting participant. As a result, the meeting support system according to the embodiment can improve the efficiency of meetings by analyzing meeting audio, generating minutes, providing necessary documents, and performing follow-up.

[0030] The minutes creation department analyzes the audio of meetings and generates meeting minutes. Specifically, the minutes creation department uses speech recognition technology to convert the meeting audio into text data. This speech recognition technology can capture speech during the meeting in real time and transcribe it into text for each speaker. For example, what is said during the meeting is immediately displayed as text, allowing participants to review it on the spot. Furthermore, the minutes creation department uses natural language processing technology to summarize the meeting content and extract key points. This natural language processing technology understands the context and meaning of speech, and can summarize the main points while eliminating redundant parts. For example, even in long meetings, it can generate minutes that concisely summarize the important points of discussion and decisions. By combining these technologies, the minutes creation department converts the meeting audio into text data in real time and then summarizes its content to generate meeting minutes. This allows for the rapid and accurate creation of meeting records, and participants can review the minutes after the meeting to grasp important information without missing anything.

[0031] The document provision department provides necessary materials based on the meeting minutes generated by the meeting minutes creation department. Specifically, the document provision department has the function to understand the content of the meeting and automatically search for and generate relevant materials. For example, it can automatically search for past meeting materials and references related to topics discussed during the meeting and provide them to participants. The document provision department can also generate new materials based on the content of the meeting. For example, it can automatically document action plans and schedules decided at the meeting and distribute them to participants. Through these functions, the document provision department improves the efficiency of meetings by gaining a deeper understanding of the content and quickly providing necessary information. Furthermore, the document provision department can store the generated materials in the cloud, making them accessible to participants at any time. This allows for easy reference of necessary materials after the meeting, promoting information sharing and utilization. By understanding the content of the meeting and automatically searching for and generating necessary materials, the document provision department supports participants in efficiently obtaining information.

[0032] The Follow-up Department sends follow-up emails and notifications and creates to-do lists based on the meeting minutes generated by the Minutes Creation Department. Specifically, the Follow-up Department identifies action items and assignees decided at the meeting and automatically sends follow-up emails and notifications based on that. For example, it can send follow-up emails containing deadlines and detailed instructions to those responsible for tasks decided at the meeting. The Follow-up Department also has the function of creating to-do lists for each meeting participant and managing their progress. For example, it can list the tasks decided at the meeting and update the progress for each person in charge. This streamlines task management after the meeting, and allows those in charge to clearly understand their role and progress. Furthermore, the Follow-up Department has a reminder function and can send notifications to those in charge of tasks as the deadline approaches. This prevents task delays and supports smooth progress. By automating post-meeting follow-up and streamlining task management, the Follow-up Department can maximize the results of the meeting.

[0033] The meeting minutes creation unit can analyze meeting audio in real time and generate meeting minutes. For example, the meeting minutes creation unit can use speech recognition technology to convert meeting audio into text data in real time. The meeting minutes creation unit can also use natural language processing technology to summarize the meeting content and generate meeting minutes. This allows for the immediate generation of meeting minutes by analyzing meeting audio in real time. The specific definition and criteria of "real time" need to be clarified, for example, by considering latency and processing speed. Some or all of the above-described processes in the meeting minutes creation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the meeting minutes creation unit can input meeting audio data into a generation AI and generate meeting minutes in real time.

[0034] The document provision department can understand the content of a meeting and automatically search for and generate the necessary documents. For example, the document provision department can analyze the content of a meeting using natural language processing technology and automatically search for and generate the necessary documents. For example, the document provision department can understand the content of a meeting using machine learning technology and automatically search for and generate the necessary documents. For example, the document provision department can analyze the content of a meeting using natural language processing technology and automatically search for and generate the necessary documents. For example, the document provision department can understand the content of a meeting using machine learning technology and automatically search for and generate the necessary documents. This allows the meeting to proceed smoothly by understanding the content and automatically providing the necessary documents. The specific methods and criteria for understanding need to be clearly defined, for example, using natural language processing technology or machine learning technology. The specific methods and criteria for automatic searching and generation need to be clearly defined, for example, using search algorithms or generation algorithms. Some or all of the above-described processes in the document provision department may be performed using, for example, a generation AI, or not using a generation AI. For example, the document provision department can input meeting content data into a generation AI and have the generation AI search for and generate the necessary documents.

[0035] The follow-up department can send follow-up emails or notifications to individuals who need to be contacted. For example, the follow-up department can analyze meeting minutes to identify individuals who need to be contacted. The follow-up department can identify meeting speakers and task assignees and send follow-up emails or notifications. This streamlines post-meeting follow-up by sending follow-up emails or notifications to those who need to be contacted. The specific method for identifying individuals who need to be contacted should be clearly defined, for example, by identifying meeting speakers or task assignees. Some or all of the above-described processes in the follow-up department may be performed using, for example, a generative AI, or not. For example, the follow-up department can input meeting minutes data into a generative AI and have the AI ​​identify individuals who need to be contacted and send follow-up emails or notifications.

[0036] The follow-up unit can create a to-do list for each meeting participant. The follow-up unit can, for example, analyze the meeting minutes and identify the tasks of each meeting participant. The follow-up unit can, for example, analyze the meeting's speaking history and create a to-do list for each meeting participant. The follow-up unit can, for example, analyze the meeting minutes and identify the tasks of each meeting participant. The follow-up unit can, for example, analyze the meeting's speaking history and create a to-do list for each meeting participant. By creating a to-do list for each meeting participant, the tasks decided at the meeting can be clearly identified. The specific method for identifying each meeting participant needs to be clearly defined, for example, by using a participant list or speaking history. Some or all of the above processing in the follow-up unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the follow-up unit can input meeting minutes data into a generation AI and have the generation AI create a to-do list for each meeting participant.

[0037] The minutes creation unit can add a function to highlight important statements and discussions according to the progress of the meeting. For example, if the meeting is progressing quickly, the minutes creation unit can highlight important statements in bold or color. If the meeting is progressing slowly, the minutes creation unit can summarize and display important discussions. If the meeting is interrupted, the minutes creation unit can remind participants of important points when the meeting resumes. This ensures that important points are not missed by highlighting important statements and discussions according to the progress of the meeting. Specific criteria and methods according to the progress should be clearly defined, for example, by the phase of the meeting or the importance of the statements. Specific methods and criteria for highlighting should be clearly defined, for example, by the color of the text or the size of the font. Some or all of the above processing in the minutes creation unit may be performed using, for example, a generation AI, or not. For example, the minutes creation unit can input meeting progress data into a generation AI and have the generation AI perform the highlighting of important statements and discussions.

[0038] The minutes creation unit can analyze the audio data of a meeting and generate minutes by color-coding each speaker. For example, the minutes creation unit can display the minutes in different colors for each speaker to make them easier to distinguish visually. For example, the minutes creation unit can color-code according to the speaker's position or role to indicate importance. For example, the minutes creation unit can change the intensity of the color according to the frequency of a speaker's contributions to visualize the activity level of the discussion. In this way, by color-coding each speaker, it is possible to provide minutes that are easy to distinguish visually. The specific method and criteria for color-coding need to be clearly defined, for example, by the criteria for selecting colors for each speaker and the types of colors used. Some or all of the above processing in the minutes creation unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the minutes creation unit can input the audio data of the meeting into a generation AI and have the generation AI perform the color-coding for each speaker.

[0039] The meeting minutes creation unit can be equipped with a function to analyze meeting audio data and statistically display the frequency and duration of speeches. For example, the meeting minutes creation unit can display the frequency of speech for each speaker in a graph to visualize biases in the discussion. For example, the meeting minutes creation unit can display the duration of speeches in a timeline to make it easier to understand the progress of the meeting. For example, the meeting minutes creation unit can extract keywords from the content of speeches and statistically display frequently occurring keywords. This allows for the visualization of biases in the discussion by statistically displaying the frequency and duration of speeches. The specific methods and criteria for statistical display need to be clearly defined, for example, by the type of graph and the items to be displayed. Some or all of the above processing in the meeting minutes creation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the meeting minutes creation unit can input meeting audio data into a generative AI and have the generative AI perform the statistical display of the frequency and duration of speeches.

[0040] The minutes creation unit can analyze meeting audio data and automatically classify the minutes based on specific keywords. For example, the minutes creation unit can classify the minutes by meeting agenda items to make them easier to search. For example, the minutes creation unit can link related minutes based on keywords in the content of the speeches. For example, the minutes creation unit can automatically classify minutes related to specific projects or tasks to make them easier to manage. This makes it easier to search by classifying the minutes based on specific keywords. The specific selection method and criteria for these keywords need to be clearly defined, for example, by frequency or importance. Some or all of the above processing in the minutes creation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the minutes creation unit can input meeting audio data into a generative AI and have the generative AI classify the minutes based on specific keywords.

[0041] The document provisioning unit can add a function to automatically highlight relevant documents according to the progress of the meeting. For example, the document provisioning unit can automatically display relevant documents in accordance with the progress of the meeting to facilitate discussion. For example, if the meeting is progressing quickly, the document provisioning unit can highlight and display important documents. For example, if the meeting is progressing slowly, the document provisioning unit can display detailed documents to facilitate deeper discussion. This ensures that important documents are not missed by highlighting relevant documents according to the progress of the meeting. Specific criteria and methods for highlighting according to the progress should be clearly defined, for example, by the phase of the meeting or the importance of the statements. Specific methods and criteria for highlighting should be clearly defined, for example, by the color of the text or the size of the font. Some or all of the above processing in the document provisioning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the document provisioning unit can input meeting progress data into a generative AI and have the generative AI perform the highlighting of relevant documents.

[0042] The document provision department can automatically search for and provide past meeting materials and related literature based on the content of the meeting. For example, the document provision department can automatically search for and provide past meeting materials related to the agenda of the meeting. For example, the document provision department can automatically search for and provide related literature and research materials based on the content of the meeting. For example, the document provision department can support discussions by providing necessary materials in real time in accordance with the progress of the meeting. In this way, discussions can be supported by automatically providing past meeting materials and related literature. The specific types and search methods for past meeting materials need to be clarified, for example, in meeting minutes or presentation materials. The specific types and search methods for related literature need to be clarified, for example, in academic papers or technical documents. Some or all of the above processing in the document provision department may be performed using, for example, a generative AI, or not using a generative AI. For example, the document provision department can input meeting content data into a generative AI and have the generative AI perform the search and provision of past meeting materials and related literature.

[0043] The materials provision department can add a function to automatically provide relevant video and audio materials based on the meeting content. For example, the materials provision department can automatically search for and provide videos related to the meeting agenda. For example, the materials provision department can automatically search for and provide relevant audio materials based on the meeting content. For example, the materials provision department can support discussions by providing necessary video and audio materials in real time in accordance with the progress of the meeting. This allows for support of discussions by automatically providing relevant video and audio materials. The specific types and methods of providing relevant video and audio materials need to be clearly defined, for example, presentation videos or interview audio. Some or all of the above processing in the materials provision department may be performed using, for example, a generative AI, or without a generative AI. For example, the materials provision department can input meeting content data into a generative AI and have the generative AI provide relevant video and audio materials.

[0044] The document provision department can add multilingual support by translating documents in real time based on the meeting content. For example, the document provision department can translate and provide documents related to the meeting agenda in real time. For example, the document provision department can provide relevant documents in multiple languages ​​based on the meeting content to support international discussions. For example, the document provision department can translate necessary documents in real time in accordance with the progress of the meeting to facilitate discussions. In this way, international discussions can be supported by translating documents in real time. The specific methods and criteria for real-time translation need to be clearly defined, for example, in the translation algorithm and supported languages. Some or all of the above processing in the document provision department may be performed using, for example, generative AI, or not using generative AI. For example, the document provision department can input meeting content data into generative AI and have the generative AI perform real-time document translation.

[0045] The follow-up unit can be equipped with a function to automatically determine the priority of follow-ups based on the content of the meeting. For example, the follow-up unit can prioritize important follow-ups based on the meeting agenda. For example, the follow-up unit can automatically determine the priority of follow-ups based on the progress of the meeting. For example, the follow-up unit can evaluate the importance of follow-ups and determine their priority based on the content of the meeting. This allows important follow-ups to be prioritized by automatically determining the priority of follow-ups. The specific methods and criteria for automatically determining priorities need to be clearly defined, for example, by importance or urgency. Some or all of the above processing in the follow-up unit may be performed using, for example, a generative AI, or without a generative AI. For example, the follow-up unit can input meeting content data into a generative AI and have the generative AI determine the priority of follow-ups.

[0046] The follow-up unit can automatically generate templates for follow-up emails and notifications based on the content of the meeting. For example, the follow-up unit can automatically generate follow-up email templates based on the meeting agenda. For example, the follow-up unit can automatically generate follow-up notification templates based on the progress of the meeting. For example, the follow-up unit can customize the templates for follow-up emails and notifications based on the content of the meeting. This improves the efficiency of follow-up by automatically generating templates for follow-up emails and notifications. The specific methods and criteria for automatically generating templates need to be clearly defined, for example, in terms of the format and type of content of the templates. Some or all of the above processes in the follow-up unit may be performed using a generation AI, for example, or without a generation AI. For example, the follow-up unit can input meeting content data into a generation AI and have the generation AI automatically generate templates for follow-up emails and notifications.

[0047] The follow-up unit can add a function to automatically set follow-up reminders based on the meeting content. For example, the follow-up unit can automatically set important follow-up reminders based on the meeting agenda. For example, the follow-up unit can automatically set follow-up reminders based on the progress of the meeting. For example, the follow-up unit can customize follow-up reminders based on the meeting content. This ensures that important follow-ups are not forgotten by automatically setting follow-up reminders. The specific methods and criteria for automatically setting reminders need to be clearly defined, for example, in terms of notification timing and notification method. Some or all of the above processing in the follow-up unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the follow-up unit can input meeting content data into a generative AI and have the generative AI set follow-up reminders.

[0048] The follow-up unit can add a function to track the progress of follow-ups in real time based on the content of the meeting. For example, the follow-up unit can track the progress of follow-ups in real time based on the agenda of the meeting. For example, the follow-up unit can track the progress of follow-ups in real time based on the progress of the meeting. For example, the follow-up unit can customize and track the progress of follow-ups based on the content of the meeting. This makes it easier to understand the progress of tasks by tracking the progress of follow-ups in real time. The specific methods and criteria for tracking progress in real time need to be clearly defined, for example, in the progress evaluation criteria and tracking methods. Some or all of the above processing in the follow-up unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the follow-up unit can input meeting content data into a generative AI and have the generative AI perform the tracking of the progress of follow-ups.

[0049] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0050] The document provisioning department can add a function that automatically highlights relevant documents according to the progress of the meeting. For example, if the meeting is progressing quickly, important documents will be highlighted and displayed. If the meeting is progressing slowly, detailed documents will be displayed to facilitate deeper discussion. If the meeting is interrupted, important documents will be reminded when it resumes. This ensures that important documents are not missed by highlighting relevant documents according to the progress of the meeting.

[0051] The meeting minutes creation department can analyze meeting audio data and generate minutes with color coding for each speaker. For example, it can display the minutes in different colors for each speaker, making them easier to distinguish visually. It can also color-code speakers according to their position or role to indicate importance. The intensity of the color can be changed according to the frequency of each speaker's contributions to visualize the level of discussion activity. In this way, by color-coding each speaker, it is possible to provide meeting minutes that are easy to distinguish visually.

[0052] The follow-up department can be enhanced with a function to automatically determine the priority of follow-ups based on the meeting content. For example, it can prioritize important follow-ups based on the meeting agenda, automatically determine the priority of follow-ups based on the meeting's progress, or evaluate the importance of follow-ups and determine their priority based on the meeting content. This allows important follow-ups to be prioritized by automatically determining their priority.

[0053] The meeting minutes creation function can be enhanced to highlight important statements and discussions according to the progress of the meeting. For example, if the meeting is moving quickly, important statements can be highlighted in bold or a different color. If the meeting is moving slowly, important discussions can be summarized and displayed. If the meeting is interrupted, key points can be reminded when it resumes. This ensures that important points are not missed by highlighting important statements and discussions according to the progress of the meeting.

[0054] The materials provision department can automatically search for and provide past meeting materials and related literature based on the content of the meeting. For example, it can automatically search for and provide past meeting materials related to the meeting agenda. It can also automatically search for and provide related literature and research materials based on the content of the meeting. It can provide necessary materials in real time as the meeting progresses, supporting the discussion. In this way, it can support the discussion by automatically providing past meeting materials and related literature.

[0055] The following briefly describes the processing flow for example form 1.

[0056] Step 1: The minutes creation department analyzes the meeting audio and generates the minutes. Specifically, it uses speech recognition technology to convert the meeting audio into text data and natural language processing technology to summarize the meeting content and generate the minutes. Step 2: The document provision department provides the necessary documents based on the meeting minutes generated by the meeting minutes preparation department. Specifically, it understands the content of the meeting and automatically searches for and generates the necessary documents. Step 3: The follow-up team sends follow-up emails and notifications and creates to-do lists based on the meeting minutes generated by the minutes creation team. Specifically, they send follow-up emails and notifications to people who need to be contacted and create to-do lists for each meeting participant.

[0057] (Example of form 2) The meeting support system according to an embodiment of the present invention is a system in which AI automatically creates meeting minutes during a meeting and understands their contents. This meeting support system analyzes the meeting audio in real time and generates meeting minutes. The generated meeting minutes are updated sequentially in accordance with the progress of the meeting and can be viewed in real time by all participants. The meeting support system has a function to immediately provide necessary materials during the meeting. The AI ​​understands the content of the meeting and automatically searches for and generates the necessary materials. This makes the meeting proceed smoothly and efficiently. Furthermore, the meeting support system also has a follow-up function. After the meeting ends, the AI ​​automatically sends follow-up emails and notifications to people who need to be contacted. It also creates a to-do list for each meeting participant, clarifying the tasks decided in the meeting. With this system, the preparation, progress, and follow-up of meetings are automated, maximizing work efficiency. The quality of meetings is also improved, and their role as a place for decision-making is strengthened. In today's world, where efficient meeting management is required due to the spread of remote work, this system is extremely useful. For example, the meeting support system analyzes the meeting audio in real time and generates meeting minutes. The generated meeting minutes are updated sequentially in line with the progress of the meeting, and all participants can view them in real time. The meeting support system has the function of instantly providing necessary materials during the meeting. AI understands the content of the meeting and automatically searches for and generates the necessary materials. This makes the meeting proceed smoothly and efficiently. Furthermore, the meeting support system also has a follow-up function. After the meeting ends, the AI ​​automatically sends follow-up emails and notifications to people who need to be contacted. It also creates a to-do list for each meeting participant, clarifying the tasks decided at the meeting. This system automates meeting preparation, progress, and follow-up, maximizing work efficiency. The quality of meetings is also improved, and their role as a forum for decision-making is strengthened. In today's world, where efficient meeting management is required due to the spread of remote work, this system is extremely useful. As a result, the meeting support system can automate meeting preparation, progress, and follow-up, maximizing work efficiency.

[0058] The meeting support system according to this embodiment comprises a minutes creation unit, a materials provision unit, and a follow-up unit. The minutes creation unit analyzes the audio of the meeting and generates minutes. The minutes creation unit converts the audio of the meeting into text data using, for example, speech recognition technology. The minutes creation unit can also summarize the content of the meeting and generate minutes using natural language processing technology. The minutes creation unit converts the audio of the meeting into text data in real time using, for example, speech recognition technology. The minutes creation unit can also summarize the content of the meeting and generate minutes using natural language processing technology. The minutes creation unit converts the audio of the meeting into text data in real time using, for example, speech recognition technology. The minutes creation unit can also summarize the content of the meeting and generate minutes using natural language processing technology. The materials provision unit provides necessary materials based on the minutes generated by the minutes creation unit. The materials provision unit understands the content of the meeting and automatically searches for and generates necessary materials. The document provision unit, for example, understands the content of the meeting and automatically searches for and generates the necessary documents. The document provision unit, for example, understands the content of the meeting and automatically searches for and generates the necessary documents. The follow-up unit, based on the minutes generated by the minutes creation unit, sends follow-up emails and notifications and creates to-do lists. The follow-up unit, for example, sends follow-up emails and notifications to people who need to be contacted. The follow-up unit, for example, creates to-do lists for each meeting participant. The follow-up unit, for example, sends follow-up emails and notifications to people who need to be contacted. The follow-up unit, for example, creates to-do lists for each meeting participant. As a result, the meeting support system according to the embodiment can improve the efficiency of meetings by analyzing meeting audio, generating minutes, providing necessary documents, and performing follow-up.

[0059] The minutes creation department analyzes the audio of meetings and generates meeting minutes. Specifically, the minutes creation department uses speech recognition technology to convert the meeting audio into text data. This speech recognition technology can capture speech during the meeting in real time and transcribe it into text for each speaker. For example, what is said during the meeting is immediately displayed as text, allowing participants to review it on the spot. Furthermore, the minutes creation department uses natural language processing technology to summarize the meeting content and extract key points. This natural language processing technology understands the context and meaning of speech, and can summarize the main points while eliminating redundant parts. For example, even in long meetings, it can generate minutes that concisely summarize the important points of discussion and decisions. By combining these technologies, the minutes creation department converts the meeting audio into text data in real time and then summarizes its content to generate meeting minutes. This allows for the rapid and accurate creation of meeting records, and participants can review the minutes after the meeting to grasp important information without missing anything.

[0060] The document provision department provides necessary materials based on the meeting minutes generated by the meeting minutes creation department. Specifically, the document provision department has the function to understand the content of the meeting and automatically search for and generate relevant materials. For example, it can automatically search for past meeting materials and references related to topics discussed during the meeting and provide them to participants. The document provision department can also generate new materials based on the content of the meeting. For example, it can automatically document action plans and schedules decided at the meeting and distribute them to participants. Through these functions, the document provision department improves the efficiency of meetings by gaining a deeper understanding of the content and quickly providing necessary information. Furthermore, the document provision department can store the generated materials in the cloud, making them accessible to participants at any time. This allows for easy reference of necessary materials after the meeting, promoting information sharing and utilization. By understanding the content of the meeting and automatically searching for and generating necessary materials, the document provision department supports participants in efficiently obtaining information.

[0061] The Follow-up Department sends follow-up emails and notifications and creates to-do lists based on the meeting minutes generated by the Minutes Creation Department. Specifically, the Follow-up Department identifies action items and assignees decided at the meeting and automatically sends follow-up emails and notifications based on that. For example, it can send follow-up emails containing deadlines and detailed instructions to those responsible for tasks decided at the meeting. The Follow-up Department also has the function of creating to-do lists for each meeting participant and managing their progress. For example, it can list the tasks decided at the meeting and update the progress for each person in charge. This streamlines task management after the meeting, and allows those in charge to clearly understand their role and progress. Furthermore, the Follow-up Department has a reminder function and can send notifications to those in charge of tasks as the deadline approaches. This prevents task delays and supports smooth progress. By automating post-meeting follow-up and streamlining task management, the Follow-up Department can maximize the results of the meeting.

[0062] The meeting minutes creation unit can analyze meeting audio in real time and generate meeting minutes. For example, the meeting minutes creation unit can use speech recognition technology to convert meeting audio into text data in real time. The meeting minutes creation unit can also use natural language processing technology to summarize the meeting content and generate meeting minutes. This allows for the immediate generation of meeting minutes by analyzing meeting audio in real time. The specific definition and criteria of "real time" need to be clarified, for example, by considering latency and processing speed. Some or all of the above-described processes in the meeting minutes creation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the meeting minutes creation unit can input meeting audio data into a generation AI and generate meeting minutes in real time.

[0063] The document provision department can understand the content of a meeting and automatically search for and generate the necessary documents. For example, the document provision department can analyze the content of a meeting using natural language processing technology and automatically search for and generate the necessary documents. For example, the document provision department can understand the content of a meeting using machine learning technology and automatically search for and generate the necessary documents. For example, the document provision department can analyze the content of a meeting using natural language processing technology and automatically search for and generate the necessary documents. For example, the document provision department can understand the content of a meeting using machine learning technology and automatically search for and generate the necessary documents. This allows the meeting to proceed smoothly by understanding the content and automatically providing the necessary documents. The specific methods and criteria for understanding need to be clearly defined, for example, using natural language processing technology or machine learning technology. The specific methods and criteria for automatic searching and generation need to be clearly defined, for example, using search algorithms or generation algorithms. Some or all of the above-described processes in the document provision department may be performed using, for example, a generation AI, or not using a generation AI. For example, the document provision department can input meeting content data into a generation AI and have the generation AI search for and generate the necessary documents.

[0064] The follow-up department can send follow-up emails or notifications to individuals who need to be contacted. For example, the follow-up department can analyze meeting minutes to identify individuals who need to be contacted. The follow-up department can identify meeting speakers and task assignees and send follow-up emails or notifications. This streamlines post-meeting follow-up by sending follow-up emails or notifications to those who need to be contacted. The specific method for identifying individuals who need to be contacted should be clearly defined, for example, by identifying meeting speakers or task assignees. Some or all of the above-described processes in the follow-up department may be performed using, for example, a generative AI, or not. For example, the follow-up department can input meeting minutes data into a generative AI and have the AI ​​identify individuals who need to be contacted and send follow-up emails or notifications.

[0065] The follow-up unit can create a to-do list for each meeting participant. The follow-up unit can, for example, analyze the meeting minutes and identify the tasks of each meeting participant. The follow-up unit can, for example, analyze the meeting's speaking history and create a to-do list for each meeting participant. The follow-up unit can, for example, analyze the meeting minutes and identify the tasks of each meeting participant. The follow-up unit can, for example, analyze the meeting's speaking history and create a to-do list for each meeting participant. By creating a to-do list for each meeting participant, the tasks decided at the meeting can be clearly identified. The specific method for identifying each meeting participant needs to be clearly defined, for example, by using a participant list or speaking history. Some or all of the above processing in the follow-up unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the follow-up unit can input meeting minutes data into a generation AI and have the generation AI create a to-do list for each meeting participant.

[0066] The minutes-taking department can estimate the emotions of meeting participants and adjust the way the minutes are written based on those estimated emotions. For example, if participants are tense, the minutes-taking department will make the minutes concise and easy to understand. If participants are relaxed, the minutes-taking department will provide detailed minutes, including background information on the discussion. If participants are excited, the minutes-taking department will highlight key points and increase the visual elements of the minutes. By adjusting the way the minutes are written according to the emotions of the participants, it is possible to provide easy-to-understand minutes. The specific methods and criteria for estimating emotions need to be clarified, for example, through voice analysis or facial expression analysis. The specific methods and criteria for adjusting the way the minutes are written need to be clarified, for example, through word choice and sentence structure. Some or all of the above processing in the minutes-taking department may be performed using, for example, generative AI, or without generative AI. For example, the meeting minutes creation department can input emotional data of meeting participants into a generating AI and have the AI ​​adjust the way the minutes are presented.

[0067] The minutes creation unit can add a function to highlight important statements and discussions according to the progress of the meeting. For example, if the meeting is progressing quickly, the minutes creation unit can highlight important statements in bold or color. If the meeting is progressing slowly, the minutes creation unit can summarize and display important discussions. If the meeting is interrupted, the minutes creation unit can remind participants of important points when the meeting resumes. This ensures that important points are not missed by highlighting important statements and discussions according to the progress of the meeting. Specific criteria and methods according to the progress should be clearly defined, for example, by the phase of the meeting or the importance of the statements. Specific methods and criteria for highlighting should be clearly defined, for example, by the color of the text or the size of the font. Some or all of the above processing in the minutes creation unit may be performed using, for example, a generation AI, or not. For example, the minutes creation unit can input meeting progress data into a generation AI and have the generation AI perform the highlighting of important statements and discussions.

[0068] The minutes creation unit can analyze the audio data of a meeting and generate minutes by color-coding each speaker. For example, the minutes creation unit can display the minutes in different colors for each speaker to make them easier to distinguish visually. For example, the minutes creation unit can color-code according to the speaker's position or role to indicate importance. For example, the minutes creation unit can change the intensity of the color according to the frequency of a speaker's contributions to visualize the activity level of the discussion. In this way, by color-coding each speaker, it is possible to provide minutes that are easy to distinguish visually. The specific method and criteria for color-coding need to be clearly defined, for example, by the criteria for selecting colors for each speaker and the types of colors used. Some or all of the above processing in the minutes creation unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the minutes creation unit can input the audio data of the meeting into a generation AI and have the generation AI perform the color-coding for each speaker.

[0069] The minutes creation unit can estimate the emotions of meeting participants and emphasize the summary portion of the minutes based on the estimated emotions. For example, if meeting participants are tired, the minutes creation unit will make the summary portion concise and emphasize only the important points. For example, if meeting participants are focused, the minutes creation unit will include detailed information in the summary portion. For example, if meeting participants are excited, the minutes creation unit will add visual elements to the summary portion to facilitate understanding. This makes it easier to understand important points by emphasizing the summary portion of the minutes according to the emotions of the meeting participants. The specific methods and criteria for emphasizing the summary portion should be made clear, for example, by changing the color of the text or the size of the font. Some or all of the above processing in the minutes creation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the minutes creation unit can input the emotion data of the meeting participants into a generative AI and have the generative AI perform the emphasis of the summary portion.

[0070] The meeting minutes creation unit can be equipped with a function to analyze meeting audio data and statistically display the frequency and duration of speeches. For example, the meeting minutes creation unit can display the frequency of speech for each speaker in a graph to visualize biases in the discussion. For example, the meeting minutes creation unit can display the duration of speeches in a timeline to make it easier to understand the progress of the meeting. For example, the meeting minutes creation unit can extract keywords from the content of speeches and statistically display frequently occurring keywords. This allows for the visualization of biases in the discussion by statistically displaying the frequency and duration of speeches. The specific methods and criteria for statistical display need to be clearly defined, for example, by the type of graph and the items to be displayed. Some or all of the above processing in the meeting minutes creation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the meeting minutes creation unit can input meeting audio data into a generative AI and have the generative AI perform the statistical display of the frequency and duration of speeches.

[0071] The minutes creation unit can analyze meeting audio data and automatically classify the minutes based on specific keywords. For example, the minutes creation unit can classify the minutes by meeting agenda items to make them easier to search. For example, the minutes creation unit can link related minutes based on keywords in the content of the speeches. For example, the minutes creation unit can automatically classify minutes related to specific projects or tasks to make them easier to manage. This makes it easier to search by classifying the minutes based on specific keywords. The specific selection method and criteria for these keywords need to be clearly defined, for example, by frequency or importance. Some or all of the above processing in the minutes creation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the minutes creation unit can input meeting audio data into a generative AI and have the generative AI classify the minutes based on specific keywords.

[0072] The document provisioning unit can estimate the emotions of meeting participants and adjust how the materials are displayed based on those estimates. For example, if a participant is nervous, the unit might display simple materials that are easy to understand. If a participant is relaxed, the unit might display detailed materials that include background information for the discussion. If a participant is excited, the unit might display visually stimulating materials to stimulate the discussion. By adjusting how the materials are displayed according to the emotions of the meeting participants, the unit can provide materials that are easy to understand. The specific methods and criteria for estimating emotions need to be clarified, for example, through voice analysis or facial expression analysis. The specific methods and criteria for adjusting the display method need to be clarified, for example, through layout changes or color changes. Some or all of the above processing in the document provisioning unit may be performed using, for example, generative AI, or without generative AI. For example, the document provisioning unit can input the emotional data of the meeting participants into a generative AI and have the generative AI adjust how the materials are displayed.

[0073] The document provisioning unit can add a function to automatically highlight relevant documents according to the progress of the meeting. For example, the document provisioning unit can automatically display relevant documents in accordance with the progress of the meeting to facilitate discussion. For example, if the meeting is progressing quickly, the document provisioning unit can highlight and display important documents. For example, if the meeting is progressing slowly, the document provisioning unit can display detailed documents to facilitate deeper discussion. This ensures that important documents are not missed by highlighting relevant documents according to the progress of the meeting. Specific criteria and methods for highlighting according to the progress should be clearly defined, for example, by the phase of the meeting or the importance of the statements. Specific methods and criteria for highlighting should be clearly defined, for example, by the color of the text or the size of the font. Some or all of the above processing in the document provisioning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the document provisioning unit can input meeting progress data into a generative AI and have the generative AI perform the highlighting of relevant documents.

[0074] The document provision department can automatically search for and provide past meeting materials and related literature based on the content of the meeting. For example, the document provision department can automatically search for and provide past meeting materials related to the agenda of the meeting. For example, the document provision department can automatically search for and provide related literature and research materials based on the content of the meeting. For example, the document provision department can support discussions by providing necessary materials in real time in accordance with the progress of the meeting. In this way, discussions can be supported by automatically providing past meeting materials and related literature. The specific types and search methods for past meeting materials need to be clarified, for example, in meeting minutes or presentation materials. The specific types and search methods for related literature need to be clarified, for example, in academic papers or technical documents. Some or all of the above processing in the document provision department may be performed using, for example, a generative AI, or not using a generative AI. For example, the document provision department can input meeting content data into a generative AI and have the generative AI perform the search and provision of past meeting materials and related literature.

[0075] The information provision department can estimate the emotions of meeting participants and prioritize materials based on those emotions. For example, if a participant is nervous, the information provision department will prioritize displaying important materials to facilitate understanding. For example, if a participant is relaxed, the information provision department will prioritize displaying detailed materials to deepen the discussion. For example, if a participant is excited, the information provision department will prioritize displaying visually stimulating materials to stimulate the discussion. In this way, by prioritizing materials according to the emotions of meeting participants, important materials can be provided preferentially. The specific methods and criteria for estimating emotions need to be clarified, for example, by voice analysis or facial expression analysis. The specific methods and criteria for determining priorities need to be clarified, for example, by importance or urgency. Some or all of the above processing in the information provision department may be performed using, for example, generative AI, or without generative AI. For example, the information provision department can input the emotional data of meeting participants into generative AI and have the generative AI determine the priority of materials.

[0076] The materials provision department can add a function to automatically provide relevant video and audio materials based on the meeting content. For example, the materials provision department can automatically search for and provide videos related to the meeting agenda. For example, the materials provision department can automatically search for and provide relevant audio materials based on the meeting content. For example, the materials provision department can support discussions by providing necessary video and audio materials in real time in accordance with the progress of the meeting. This allows for support of discussions by automatically providing relevant video and audio materials. The specific types and methods of providing relevant video and audio materials need to be clearly defined, for example, presentation videos or interview audio. Some or all of the above processing in the materials provision department may be performed using, for example, a generative AI, or without a generative AI. For example, the materials provision department can input meeting content data into a generative AI and have the generative AI provide relevant video and audio materials.

[0077] The document provision department can add multilingual support by translating documents in real time based on the meeting content. For example, the document provision department can translate and provide documents related to the meeting agenda in real time. For example, the document provision department can provide relevant documents in multiple languages ​​based on the meeting content to support international discussions. For example, the document provision department can translate necessary documents in real time in accordance with the progress of the meeting to facilitate discussions. In this way, international discussions can be supported by translating documents in real time. The specific methods and criteria for real-time translation need to be clearly defined, for example, in the translation algorithm and supported languages. Some or all of the above processing in the document provision department may be performed using, for example, generative AI, or not using generative AI. For example, the document provision department can input meeting content data into generative AI and have the generative AI perform real-time document translation.

[0078] The follow-up unit can estimate the emotions of meeting participants and adjust the content of the follow-up based on the estimated emotions. For example, if a meeting participant is nervous, the follow-up unit will make the content of the follow-up concise and easy to understand. For example, if a meeting participant is relaxed, the follow-up unit will provide a detailed follow-up, including background information on the discussion. For example, if a meeting participant is excited, the follow-up unit will highlight key points and increase the visual elements of the follow-up. In this way, by adjusting the content of the follow-up according to the emotions of the meeting participants, an easy-to-understand follow-up can be provided. The specific methods and criteria for estimating emotions need to be clarified, for example, by voice analysis or facial expression analysis. The specific methods and criteria for adjusting the content need to be clarified, for example, by word choice or sentence structure. Some or all of the above processing in the follow-up unit may be performed using, for example, generative AI, or not using generative AI. For example, the follow-up unit can input the emotional data of meeting participants into a generative AI and have the generative AI perform the adjustment of the follow-up content.

[0079] The follow-up unit can be equipped with a function to automatically determine the priority of follow-ups based on the content of the meeting. For example, the follow-up unit can prioritize important follow-ups based on the meeting agenda. For example, the follow-up unit can automatically determine the priority of follow-ups based on the progress of the meeting. For example, the follow-up unit can evaluate the importance of follow-ups and determine their priority based on the content of the meeting. This allows important follow-ups to be prioritized by automatically determining the priority of follow-ups. The specific methods and criteria for automatically determining priorities need to be clearly defined, for example, by importance or urgency. Some or all of the above processing in the follow-up unit may be performed using, for example, a generative AI, or without a generative AI. For example, the follow-up unit can input meeting content data into a generative AI and have the generative AI determine the priority of follow-ups.

[0080] The follow-up unit can automatically generate templates for follow-up emails and notifications based on the content of the meeting. For example, the follow-up unit can automatically generate follow-up email templates based on the meeting agenda. For example, the follow-up unit can automatically generate follow-up notification templates based on the progress of the meeting. For example, the follow-up unit can customize the templates for follow-up emails and notifications based on the content of the meeting. This improves the efficiency of follow-up by automatically generating templates for follow-up emails and notifications. The specific methods and criteria for automatically generating templates need to be clearly defined, for example, in terms of the format and type of content of the templates. Some or all of the above processes in the follow-up unit may be performed using a generation AI, for example, or without a generation AI. For example, the follow-up unit can input meeting content data into a generation AI and have the generation AI automatically generate templates for follow-up emails and notifications.

[0081] The follow-up unit can estimate the emotions of meeting participants and determine the priority of the to-do list based on those estimated emotions. For example, if a meeting participant is tense, the follow-up unit will prioritize displaying important tasks to facilitate understanding. For example, if a meeting participant is relaxed, the follow-up unit will prioritize displaying detailed tasks to deepen the discussion. For example, if a meeting participant is excited, the follow-up unit will prioritize displaying visually stimulating tasks to stimulate the discussion. This allows important tasks to be processed preferentially by determining the priority of the to-do list according to the emotions of the meeting participants. The specific methods and criteria for estimating emotions need to be clarified, for example, by using voice analysis or facial expression analysis. The specific methods and criteria for determining priorities need to be clarified, for example, by using importance or urgency. Some or all of the above processing in the follow-up unit may be performed using, for example, generative AI, or without using generative AI. For example, the follow-up unit can input the emotional data of meeting participants into a generative AI and have the generative AI determine the priority of the to-do list.

[0082] The follow-up unit can add a function to automatically set follow-up reminders based on the meeting content. For example, the follow-up unit can automatically set important follow-up reminders based on the meeting agenda. For example, the follow-up unit can automatically set follow-up reminders based on the progress of the meeting. For example, the follow-up unit can customize follow-up reminders based on the meeting content. This ensures that important follow-ups are not forgotten by automatically setting follow-up reminders. The specific methods and criteria for automatically setting reminders need to be clearly defined, for example, in terms of notification timing and notification method. Some or all of the above processing in the follow-up unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the follow-up unit can input meeting content data into a generative AI and have the generative AI set follow-up reminders.

[0083] The follow-up unit can add a function to track the progress of follow-ups in real time based on the content of the meeting. For example, the follow-up unit can track the progress of follow-ups in real time based on the agenda of the meeting. For example, the follow-up unit can track the progress of follow-ups in real time based on the progress of the meeting. For example, the follow-up unit can customize and track the progress of follow-ups based on the content of the meeting. This makes it easier to understand the progress of tasks by tracking the progress of follow-ups in real time. The specific methods and criteria for tracking progress in real time need to be clearly defined, for example, in the progress evaluation criteria and tracking methods. Some or all of the above processing in the follow-up unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the follow-up unit can input meeting content data into a generative AI and have the generative AI perform the tracking of the progress of follow-ups.

[0084] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0085] The meeting minutes creation department can analyze the audio data of meetings, estimate the emotions of the speakers, and reflect this in the minutes. For example, if a speaker is angry, their statement will be highlighted to convey the tension of the meeting. If a speaker is happy, their statement will be displayed in a bright color to reflect the atmosphere of the meeting. If a speaker is sad, their statement will be displayed in a light color to convey the tone of their emotion. In this way, the emotional aspects of the meeting can be reflected in the minutes.

[0086] The document provisioning department can add a function that automatically highlights relevant documents according to the progress of the meeting. For example, if the meeting is progressing quickly, important documents will be highlighted and displayed. If the meeting is progressing slowly, detailed documents will be displayed to facilitate deeper discussion. If the meeting is interrupted, important documents will be reminded when it resumes. This ensures that important documents are not missed by highlighting relevant documents according to the progress of the meeting.

[0087] The follow-up team can estimate the emotions of meeting participants and adjust the content of the follow-up based on those estimates. For example, if participants are nervous, the follow-up content can be made concise and easy to understand. If participants are relaxed, a detailed follow-up can be provided, including background information on the discussion. If participants are excited, key points can be highlighted, and the visual elements of the follow-up can be increased. In this way, by adjusting the content of the follow-up according to the emotions of the meeting participants, it is possible to provide a follow-up that is easy to understand.

[0088] The meeting minutes creation department can analyze meeting audio data and generate minutes with color coding for each speaker. For example, it can display the minutes in different colors for each speaker, making them easier to distinguish visually. It can also color-code speakers according to their position or role to indicate importance. The intensity of the color can be changed according to the frequency of each speaker's contributions to visualize the level of discussion activity. In this way, by color-coding each speaker, it is possible to provide meeting minutes that are easy to distinguish visually.

[0089] The materials provision department can estimate the emotions of meeting participants and adjust how materials are displayed based on those estimates. For example, if participants are nervous, simple materials are displayed to make them easier to understand. If participants are relaxed, detailed materials are displayed, including background information for the discussion. If participants are excited, visually stimulating materials are displayed to stimulate the discussion. In this way, by adjusting how materials are displayed according to the emotions of the meeting participants, easy-to-understand materials can be provided.

[0090] The follow-up department can be enhanced with a function to automatically determine the priority of follow-ups based on the meeting content. For example, it can prioritize important follow-ups based on the meeting agenda, automatically determine the priority of follow-ups based on the meeting's progress, or evaluate the importance of follow-ups and determine their priority based on the meeting content. This allows important follow-ups to be prioritized by automatically determining their priority.

[0091] The meeting minutes creation function can be enhanced to highlight important statements and discussions according to the progress of the meeting. For example, if the meeting is moving quickly, important statements can be highlighted in bold or a different color. If the meeting is moving slowly, important discussions can be summarized and displayed. If the meeting is interrupted, key points can be reminded when it resumes. This ensures that important points are not missed by highlighting important statements and discussions according to the progress of the meeting.

[0092] The follow-up function can estimate the emotions of meeting participants and prioritize tasks on the to-do list based on those estimates. For example, if participants are tense, important tasks will be displayed first to facilitate understanding. If participants are relaxed, detailed tasks will be displayed first to deepen the discussion. If participants are excited, visually stimulating tasks will be displayed first to stimulate the discussion. This allows important tasks to be prioritized by determining the priority of the to-do list according to the emotions of the meeting participants.

[0093] The materials provision department can automatically search for and provide past meeting materials and related literature based on the content of the meeting. For example, it can automatically search for and provide past meeting materials related to the meeting agenda. It can also automatically search for and provide related literature and research materials based on the content of the meeting. It can provide necessary materials in real time as the meeting progresses, supporting the discussion. In this way, it can support the discussion by automatically providing past meeting materials and related literature.

[0094] The follow-up function can estimate the emotions of meeting participants and automatically generate templates for follow-up emails and notifications based on those estimated emotions. For example, if participants are nervous, it generates a concise template that is easy to understand. If participants are relaxed, it generates a detailed template that includes background information on the discussion. If participants are excited, it generates a visually stimulating template to stimulate the discussion. This allows for efficient follow-up by automatically generating follow-up templates according to the emotions of the meeting participants.

[0095] The following briefly describes the processing flow for example form 2.

[0096] Step 1: The minutes creation department analyzes the meeting audio and generates the minutes. Specifically, it uses speech recognition technology to convert the meeting audio into text data and natural language processing technology to summarize the meeting content and generate the minutes. Step 2: The document provision department provides the necessary documents based on the meeting minutes generated by the meeting minutes preparation department. Specifically, it understands the content of the meeting and automatically searches for and generates the necessary documents. Step 3: The follow-up team sends follow-up emails and notifications and creates to-do lists based on the meeting minutes generated by the minutes creation team. Specifically, they send follow-up emails and notifications to people who need to be contacted and create to-do lists for each meeting participant.

[0097] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0098] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0099] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0100] Each of the multiple elements described above, including the minutes creation unit, the document provision unit, and the follow-up unit, is implemented by, for example, at least one of the smart device 14 and the data processing unit 12. For example, the minutes creation unit collects meeting audio using the microphone 38B of the smart device 14, analyzes the audio using the specific processing unit 290 of the data processing unit 12, and generates meeting minutes. The document provision unit understands the content of the meeting using the specific processing unit 290 of the data processing unit 12 and automatically searches for and generates necessary documents. The follow-up unit sends follow-up emails and notifications and creates to-do lists for each meeting participant based on the minutes generated by the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0101] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0102] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0103] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0104] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0105] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0106] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0107] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0108] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0109] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0110] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0111] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0112] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0113] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0114] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0115] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0116] Each of the multiple elements described above, including the minutes creation unit, the document provision unit, and the follow-up unit, is implemented, for example, by at least one of the smart glasses 214 and the data processing unit 12. For example, the minutes creation unit collects meeting audio using the microphone 238 of the smart glasses 214, analyzes the audio using the specific processing unit 290 of the data processing unit 12, and generates meeting minutes. The document provision unit understands the content of the meeting using the specific processing unit 290 of the data processing unit 12 and automatically searches for and generates necessary documents. The follow-up unit sends follow-up emails and notifications and creates to-do lists for each meeting participant based on the minutes generated by the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the devices and control units is not limited to the example described above and can be changed in various ways.

[0117] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0118] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0119] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0120] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0121] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0122] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0123] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0124] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0125] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0126] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0127] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0128] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0129] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0130] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0131] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0132] Each of the multiple elements described above, including the minutes creation unit, the document provision unit, and the follow-up unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the minutes creation unit collects meeting audio using the microphone 238 of the headset terminal 314, analyzes the audio using the specific processing unit 290 of the data processing unit 12, and generates meeting minutes. The document provision unit understands the content of the meeting using the specific processing unit 290 of the data processing unit 12 and automatically searches for and generates necessary documents. The follow-up unit sends follow-up emails and notifications and creates to-do lists for each meeting participant based on the minutes generated by the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the devices and control units is not limited to the example described above and can be modified in various ways.

[0133] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0134] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0135] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0136] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0137] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0138] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0139] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0140] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0141] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0142] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0143] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0144] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0145] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0146] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0147] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0148] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0149] Each of the multiple elements described above, including the minutes creation unit, the document provision unit, and the follow-up unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the minutes creation unit collects meeting audio using the microphone 238 of the robot 414, analyzes the audio using the specific processing unit 290 of the data processing unit 12, and generates meeting minutes. The document provision unit understands the content of the meeting using the specific processing unit 290 of the data processing unit 12 and automatically searches for and generates necessary documents. The follow-up unit sends follow-up emails and notifications and creates to-do lists for each meeting participant based on the minutes generated by the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the devices and control units is not limited to the example described above and can be modified in various ways.

[0150] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0151] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0152] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0153] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0154] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0155] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0156] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0157] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0158] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0159] 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.

[0160] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0161] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0162] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0163] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0164] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0165] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0166] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0167] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0168] (Note 1) The meeting minutes creation department analyzes the audio of the meeting and generates meeting minutes, Based on the minutes generated by the minutes preparation unit, the document provision unit provides the necessary materials, The following unit includes a follow-up unit that sends follow-up emails and notifications and creates a to-do list based on the minutes generated by the minutes creation unit. A system characterized by the following features. (Note 2) The aforementioned minutes preparation department, Analyze meeting audio in real time and generate meeting minutes. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned document provision department, Understand the content of the meeting and automatically search for and generate the necessary materials. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned follow-up unit is, Send follow-up emails or notifications to people who need to be contacted. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned follow-up unit is, Create a to-do list for each meeting participant. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned minutes preparation department, The system estimates the emotions of meeting participants and adjusts the wording of the meeting minutes based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned minutes preparation department, Add a feature to highlight important statements and discussions as the meeting progresses. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned minutes preparation department, The system analyzes the audio data from the meeting, color-codes each speaker, and generates meeting minutes. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned minutes preparation department, Estimate the emotions of meeting participants and highlight the summary portion of the meeting minutes based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned minutes preparation department, Add a feature to analyze meeting audio data and statistically display the frequency and duration of speech. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned minutes preparation department, The system analyzes meeting audio data and automatically categorizes meeting minutes based on specific keywords. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned document provision department, The system estimates the emotions of meeting participants and adjusts how materials are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned document provision department, Add a feature that automatically highlights relevant documents based on the progress of the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned document provision department, Based on the content of the meeting, past meeting materials and related literature are automatically searched and provided. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned document provision department, The system estimates the emotions of meeting participants and prioritizes materials based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned document provision department, Add a feature that automatically provides relevant video and audio materials based on the meeting content. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned document provision department, We will add a feature that translates documents in real time based on the meeting content and supports multiple languages. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned follow-up unit is, The system estimates the emotions of meeting participants and adjusts follow-up activities based on those estimates. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned follow-up unit is, Add a feature that automatically determines the priority of follow-up based on the meeting content. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned follow-up unit is, Based on the meeting content, automatically generate templates for follow-up emails and notifications. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned follow-up unit is, Estimate the emotions of meeting participants and prioritize the to-do list based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned follow-up unit is, Add a feature that automatically sets follow-up reminders based on the meeting content. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned follow-up unit is, We will add a feature that tracks the progress of follow-ups in real time based on the content of the meeting. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0169] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The meeting minutes creation department analyzes the audio of the meeting and generates meeting minutes, Based on the minutes generated by the minutes preparation unit, the document provision unit provides the necessary materials, The following unit includes a follow-up unit that sends follow-up emails and notifications and creates a to-do list based on the minutes generated by the minutes creation unit. A system characterized by the following features.

2. The aforementioned minutes preparation department, Analyze meeting audio in real time and generate meeting minutes. The system according to feature 1.

3. The aforementioned document provision department, Understand the content of the meeting and automatically search for and generate necessary documents. The system according to feature 1.

4. The aforementioned follow-up unit is, Send follow-up emails or notifications to people who need to be contacted. The system according to feature 1.

5. The aforementioned follow-up unit is, Create a to-do list for each meeting participant. The system according to feature 1.

6. The aforementioned minutes preparation department, The system estimates the emotions of meeting participants and adjusts the wording of the meeting minutes based on those estimated emotions. The system according to feature 1.

7. The aforementioned minutes preparation department, Add a feature to highlight important statements and discussions as the meeting progresses. The system according to feature 1.

8. The aforementioned minutes preparation department, The system analyzes the audio data from the meeting, color-codes each speaker, and generates meeting minutes. The system according to feature 1.

Images