System

Abstract

An object of the system according to the embodiment is to automate progress management of a meeting, creation of minutes, and notification of a next action.SOLUTION: A system according to an embodiment includes a reception unit, a setting unit, a return unit, a generation unit, and a transmission unit. The reception unit initializes the purpose and time of the meeting. The setting unit sets a setup of the conference based on the information initially set by the receiving unit. The returning unit returns the topic to the main subject when the topic deviates from the main subject during the conference. The generation unit automatically generates a minutes after the end of the conference. The transmission part transmits the next action by mail for each participant.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies require manual management of meeting progress, creation of minutes, and notification of next actions, which is inefficient and time-consuming.

[0005] The system according to the embodiment aims to automate the management of the progress of a meeting, the creation of minutes, and the notification of the next action. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, a setting unit, a return unit, a generation unit, and a transmission unit. The reception unit initially sets the purpose and time of the meeting. The setting unit sets the schedule for the meeting based on the information initially set by the reception unit. The return unit returns the topic to the main topic if it strays from the main topic during the meeting. The generation unit automatically generates minutes after the meeting ends. The transmission unit sends the next action by email to each participant. [Effects of the Invention]

[0007] The system according to the embodiment can automate the management of the progress of a meeting, the creation of minutes, and the notification of the next action. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A meeting support system according to an embodiment of the present invention is a system that initially sets the purpose and time of a meeting, sets the meeting schedule, returns the topic to the main topic if the topic strays from the main topic, automatically generates minutes, and sends a Next Action to each participant by email. The meeting support system initially sets the purpose and time of a meeting in natural language, and AI automatically sets the meeting schedule. If the topic strays from the main topic during the meeting, the AI ​​subtly returns the topic to the main topic at an appropriate time. After the meeting ends, the AI ​​automatically generates minutes and automatically sends a Next Action to each participant by email. For example, the meeting support system initially sets the purpose and time of the meeting in natural language. For example, the system may set the schedule as follows: "The purpose of today's meeting is to discuss the development plan for a new product. The meeting will last one hour." This information is input into the AI. The AI ​​then automatically sets the meeting schedule. For example, the system creates a meeting agenda and determines the time allocation for each topic. This ensures the meeting proceeds smoothly. Next, if the topic strays from the main topic during the meeting, the AI ​​subtly returns the topic to the main topic at an appropriate time. For example, the system supports the progress of the meeting by saying, "Let's move on to the next agenda item." Next, after the meeting ends, the AI ​​in the meeting support system automatically generates minutes. The minutes include the content discussed and decisions made in the meeting. Furthermore, the meeting support system automatically sends a Next Action to each participant by email. For example, it includes specific instructions such as, "Please prepare the materials by the next meeting." This allows the meeting support system to improve the efficiency of meetings, allowing all participants to clearly understand the next action. This allows the meeting support system to improve the efficiency of meetings, allowing all participants to clearly understand the next action.

[0029] A meeting support system according to an embodiment includes a reception unit, a setting unit, a return unit, a generation unit, and a transmission unit. The reception unit initially sets the purpose and time of the meeting. The reception unit sets the purpose and time of the meeting in natural language, for example, as follows: "The purpose of today's meeting is to discuss a new product development plan. The meeting will last one hour." This information is input to an AI. The setting unit sets the meeting schedule based on the information initially set by the reception unit. The setting unit, for example, creates a meeting agenda and determines the time allocation for each topic. For example, the setting unit can set the meeting schedule taking into account past meeting data, the positions and areas of expertise of participants. The return unit returns the topic to the main topic if the topic strays from the main topic during the meeting. The return unit supports the progress of the meeting by, for example, saying, "Let's move on to the next topic." The return unit can also return the topic to the main topic if, for example, a certain amount of time has passed or a specific keyword appears. The generation unit automatically generates minutes after the meeting ends. The generation unit, for example, automatically generates minutes including the contents discussed and decisions made in the meeting. The generation unit can also, for example, estimate the user's emotions and adjust the method for generating the minutes based on the estimated emotions. The transmission unit sends the Next Action by email to each participant. The transmission unit sends the Next Action including specific instructions, such as, for example, "Please prepare materials by the next meeting." The transmission unit can also, for example, estimate the user's emotions and adjust the method for sending the Next Action based on the estimated emotions. This enables the meeting support system according to the embodiment to initially set the purpose and time of the meeting, set up a schedule, bring the topic back to the main topic, automatically generate minutes, and transmit the Next Action.

[0030] The reception unit can initially set the purpose and time of the meeting in natural language. The reception unit, for example, sets the purpose and time of the meeting in natural language. For example, it sets it as follows: "The purpose of today's meeting is to discuss the development plan for a new product. The meeting will last one hour." This information is input to the AI. By thus initially setting the purpose and time of the meeting in natural language, convenience for users is improved. Some or all of the above-described processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the purpose and time of the meeting input in natural language to the generation AI, which can then analyze it.

[0031] The setting unit can set the schedule for a meeting based on past meeting data or the positions and areas of expertise of participants. The setting unit can set optimal schedules for meetings with similar purposes based on, for example, past meeting data. The setting unit can also analyze the progress of past meetings to set efficient schedules. Furthermore, the setting unit can select the optimal schedule setting method by referring to feedback from participants in past meetings. This allows for more appropriate schedules to be set by taking into account past meeting data and the positions and areas of expertise of participants. Some or all of the above-mentioned processing in the setting unit can be performed using, for example, AI, or can be performed without using AI. For example, the setting unit can input past meeting data into a generation AI and have the generation AI analyze it.

[0032] The return unit can return the topic to the main topic when a certain amount of time has passed or when a specific keyword appears. For example, the return unit can return the topic to the main topic when a certain amount of time has passed, taking into account the progress of the meeting. The return unit can also return the topic to the main topic by analyzing the content of comments made by the meeting participants when a specific keyword appears. Furthermore, the return unit can also quickly return the topic to the main topic when the progress of the meeting is delayed. This makes it possible to return the topic to the main topic at an appropriate time when the topic has strayed from the main topic. Some or all of the above-mentioned processing in the return unit may be performed, for example, using AI, or may be performed without using AI. For example, the return unit can have a generation AI analyze the appearance of a specific keyword and adjust the timing to return the topic to the main topic.

[0033] The generation unit can automatically generate minutes including the contents discussed and decisions made in the meeting. For example, if many contents were discussed in the meeting, the generation unit can generate detailed minutes. Furthermore, if many decisions were made in the meeting, the generation unit can also generate minutes that cover the main points. Furthermore, if few contents were discussed in the meeting, the generation unit can also generate concise minutes. In this way, by automatically generating minutes after the meeting, the contents of the meeting can be accurately recorded. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the contents discussed and decisions made in the meeting into a generation AI, which can then automatically generate minutes.

[0034] The sending unit can send the Next Action to each participant by email. The sending unit sends the Next Action including specific instructions, such as "Please prepare materials by the next meeting." The sending unit can also estimate the user's emotions and adjust the method for sending the Next Action based on the estimated emotions. The sending unit can also customize the content to be sent based on the participant's job title or field of expertise. This makes it possible to clearly communicate the next action by sending the Next Action to each participant by email. Some or all of the above-mentioned processing in the sending unit may be performed using, for example, AI, or may be performed without using AI. For example, the sending unit can input the Next Action to a generating AI and have the generating AI customize the content to be sent.

[0035] The reception unit can analyze data on the purpose and duration of past meetings and select an appropriate initial setup method. The reception unit, for example, sets the optimal time for meetings with similar purposes based on past meeting data. The reception unit can also analyze the progress of past meetings and set efficient time allocation. Furthermore, the reception unit can select the optimal initial setup method by referring to feedback from participants in past meetings. In this way, the optimal initial setup method can be selected by analyzing past meeting data. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input past meeting data into a generation AI and have the generation AI analyze it.

[0036] When initially setting the purpose and time of a meeting, the reception unit can filter based on the user's current project or area of ​​interest. For example, the reception unit can prioritize setting the purpose and time of a meeting related to a project currently being carried out by the user. The reception unit can also set the purpose and time of a related meeting based on the user's area of ​​interest. Furthermore, the reception unit can also set the optimal purpose and time of a meeting by referring to the user's past project history. This allows the purpose and time of a related meeting to be set based on the user's current project or area of ​​interest. Some or all of the above-described processing in the reception unit can be performed using, for example, AI, or can be performed without using AI. For example, the reception unit can input the user's project data into a generation AI and have the generation AI analyze it.

[0037] The reception unit can select an appropriate setting means depending on the user's input method when initially setting the purpose and time of the meeting. For example, if the user uses voice input, the reception unit can set the purpose and time of the meeting using voice recognition technology. Furthermore, if the user uses text input, the reception unit can also set the purpose and time of the meeting using text analysis technology. Furthermore, if the user uses image input, the reception unit can also set the purpose and time of the meeting using image recognition technology. This improves convenience by selecting the optimal setting means depending on the user's input method. Some or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input voice data to a generation AI and have the generation AI analyze it.

[0038] The setting unit can analyze past conference data and select an appropriate setup method. The setting unit, for example, sets optimal setup for conferences with similar purposes based on past conference data. The setting unit can also analyze the progress of past conferences and set efficient setup. Furthermore, the setting unit can select an optimal setup method by referring to feedback from participants in past conferences. In this way, the optimal setup method can be selected by analyzing past conference data. Some or all of the above-mentioned processing in the setting unit may be performed using, for example, AI, or may be performed without using AI. For example, the setting unit can input past conference data into a generation AI and have the generation AI analyze it.

[0039] The setting unit can filter based on the participants' job titles and areas of expertise when setting up the meeting schedule. The setting unit, for example, prioritizes important agenda items based on the participants' job titles. The setting unit can also set relevant agenda items based on the participants' areas of expertise. Furthermore, the setting unit can set optimal schedules by referring to the participants' past meeting history. This makes it possible to set relevant agenda items based on the participants' job titles and areas of expertise. Some or all of the above-mentioned processing in the setting unit may be performed using AI, for example, or may be performed without using AI. For example, the setting unit can input data on the participants' job titles and areas of expertise into a generation AI and have the generation AI analyze the data.

[0040] When setting up a meeting schedule, the setting unit can improve the accuracy of the settings by referring to the user's past meeting history. The setting unit sets an optimal schedule based on, for example, the user's past meeting history. The setting unit can also analyze the user's past meeting history and set an efficient schedule. Furthermore, the setting unit can improve the accuracy of the settings by referring to the user's past meeting history. In this way, the accuracy of the settings can be improved by referring to the user's past meeting history. Some or all of the above-described processing in the setting unit may be performed using, for example, AI, or may be performed without using AI. For example, the setting unit can input the user's past meeting history into a generation AI and have the generation AI analyze it.

[0041] The return unit can select a method for returning the topic to the main topic depending on the progress of the meeting, as well as when a certain amount of time has passed. For example, when a certain amount of time has passed, the return unit returns the topic to the main topic taking into account the progress of the meeting. The return unit can also quickly return the topic to the main topic if the meeting is running behind schedule. Furthermore, when the meeting is progressing smoothly, the return unit can also return the topic to the main topic at an appropriate timing. In this way, by selecting a method for returning the topic to the main topic depending on the progress of the meeting, the topic can be returned to the main topic more effectively. Some or all of the above-described processing in the return unit may be performed using, for example, AI, or may be performed without using AI. For example, the return unit can input data on the progress of the meeting into a generation AI and have the generation AI analyze it.

[0042] The return unit can return the topic to the main topic by analyzing the content of the statements made by the meeting participants, in addition to when a specific keyword appears. For example, when a specific keyword appears, the return unit can analyze the content of the statements made by the meeting participants and return the topic to the main topic. The return unit can also return the topic to the main topic at an appropriate time if the content of the statements made by the meeting participants strays from the main topic. Furthermore, the return unit can analyze the content of the statements made by the meeting participants in real time and return the topic to the main topic at an optimal time. In this way, by analyzing the content of the statements made by the meeting participants, the topic can be returned to the main topic at a more appropriate time. Some or all of the above-described processing in the return unit may be performed using, for example, AI, or may be performed without using AI. For example, the return unit can input the content data of the statements made by the meeting participants into a generation AI and have the generation AI analyze it.

[0043] The return unit can select an appropriate return method by referring to past meeting data when returning the topic to the main topic. For example, the return unit selects a return method that was effective in a similar situation based on past meeting data. The return unit can also analyze the progress of past meetings and select the optimal return method. Furthermore, the return unit can also select the optimal return method by referring to feedback from participants in past meetings. In this way, the optimal return method can be selected by referring to past meeting data. Some or all of the above-mentioned processing in the return unit may be performed using, for example, AI, or may be performed without using AI. For example, the return unit can input past meeting data into a generation AI and have the generation AI analyze it.

[0044] The generation unit can adjust the level of detail in the minutes based on the content discussed and decisions made in the meeting. For example, if many content items were discussed in the meeting, the generation unit can generate detailed minutes. Furthermore, if many decisions were made in the meeting, the generation unit can also generate minutes that focus on the main points. Furthermore, if few content items were discussed in the meeting, the generation unit can also generate concise minutes. In this way, by adjusting the level of detail in the minutes based on the content discussed and decisions made in the meeting, minutes with an appropriate level of detail can be generated. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the content discussed and decisions made in the meeting into a generation AI, and have the generation AI adjust the level of detail in the minutes.

[0045] When generating minutes, the generation unit can apply different generation algorithms depending on the category of the meeting. For example, in the case of a technical meeting, the generation unit generates minutes including technical details. In addition, in the case of a marketing meeting, the generation unit can also generate minutes related to marketing strategies. Furthermore, in the case of a management meeting, the generation unit can also generate minutes related to management policies. In this way, by applying an appropriate generation algorithm depending on the category of the meeting, more appropriate minutes can be generated. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input meeting category data into a generation AI and have the generation AI analyze the data.

[0046] When generating minutes, the generation unit can improve the accuracy of generation by referring to the user's past minutes results. The generation unit generates optimal minutes, for example, based on the user's past minutes results. The generation unit can also analyze the user's past minutes results to improve the accuracy of generation. Furthermore, the generation unit can also improve the generation algorithm by referring to the user's past minutes results. In this way, the accuracy of generation can be improved by referring to the user's past minutes results. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can input the user's past minutes results into the generation AI and have it analyzed by the generation AI.

[0047] When generating minutes, the generation unit can determine the priority of the minutes based on the time the meeting was held. For example, the generation unit prioritizes generating minutes of the most recent meeting. The generation unit can also prioritize generating minutes of important meetings. Furthermore, the generation unit can also prioritize generating minutes of regular meetings. In this way, by determining the priority of minutes based on the time the meeting was held, important minutes can be generated preferentially. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input data on the time the meeting was held into the generation AI and have it analyzed by the generation AI.

[0048] When generating minutes, the generation unit can adjust the order of the minutes based on the relevance of the meeting. For example, the generation unit prioritizes recording highly relevant topics in the minutes. The generation unit can also postpone recording less relevant topics in the minutes. Furthermore, the generation unit can adjust the order of the minutes based on the order in which the meeting proceeds. In this way, by adjusting the order of the minutes based on the relevance of the meeting, minutes can be generated in a more appropriate order. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input meeting relevance data into the generation AI and have it analyzed by the generation AI.

[0049] When generating minutes, the generation unit can adjust the frequency of use of technical terms in the minutes according to the user's level of expertise. For example, if the user has technical expertise, the generation unit can generate minutes that use a lot of technical terms. Also, if the user does not have technical expertise, the generation unit can generate minutes that avoid technical terms. Furthermore, the generation unit can generate minutes that use appropriate technical terms according to the user's level of expertise. In this way, by adjusting the use of technical terms according to the user's level of expertise, minutes that are easier to understand can be generated. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the user's level of expertise data into the generation AI and have it analyzed by the generation AI.

[0050] When transmitting a Next Action, the transmission unit can customize the transmission content based on the participant's job title and field of expertise. The transmission unit transmits an appropriate Next Action, for example, according to the participant's job title. The transmission unit can also transmit a related Next Action based on the participant's field of expertise. Furthermore, the transmission unit can transmit the optimal Next Action by referring to the participant's past behavioral history. In this way, by customizing the transmission content based on the participant's job title and field of expertise, a more appropriate Next Action can be transmitted. Some or all of the above-described processing in the transmission unit may be performed using, for example, AI, or may be performed without using AI. For example, the transmission unit can input data on the participant's job title and field of expertise into a generation AI and have the generation AI analyze the data.

[0051] When transmitting a Next Action, the transmission unit can improve the accuracy of the transmission by referring to the participant's past behavioral history. The transmission unit transmits the optimal Next Action based on, for example, the participant's past behavioral history. The transmission unit can also analyze the participant's past behavioral history to improve the accuracy of the transmission. Furthermore, the transmission unit can also customize the content of the transmission by referring to the participant's past behavioral history. In this way, the accuracy of the transmission can be improved by referring to the participant's past behavioral history. Some or all of the above-mentioned processing in the transmission unit may be performed using, for example, AI, or may be performed without using AI. For example, the transmission unit can input the participant's past behavioral history data into a generation AI and have the generation AI analyze it.

[0052] When transmitting a Next Action, the transmitting unit can determine the transmission priority based on the content of the conference. For example, the transmitting unit prioritizes the transmission of a Next Action for an important conference. The transmitting unit can also prioritize the transmission of a Next Action with a high urgency. Furthermore, the transmitting unit can determine the transmission priority of the Next Action based on the progress of the conference. In this way, by determining the transmission priority based on the content of the conference, important Next Actions can be transmitted with priority. Some or all of the above-described processing in the transmitting unit may be performed using, or without, AI, for example. For example, the transmitting unit can input content data of the conference into a generating AI and have the generating AI analyze it.

[0053] When transmitting the Next Action, the transmission unit can select an appropriate transmission method by taking into account the geographical location information of the participants. For example, if the participant is in the office, the transmission unit selects a transmission method that is effective in the office. Furthermore, if the participant is on a business trip, the transmission unit can select a transmission method that is effective at the business trip destination. Furthermore, if the participant is at home, the transmission unit can select a transmission method that is effective remotely. In this way, a more appropriate transmission method can be selected by taking into account the geographical location information of the participants. Some or all of the above-described processing in the transmission unit may be performed using, for example, AI, or may be performed without using AI. For example, the transmission unit can input the geographical location information data of the participants into the generation AI and have it analyzed by the generation AI.

[0054] When sending a Next Action, the sending unit can analyze the participant's social media activity and customize the relevant sending content. For example, the sending unit sends a Next Action related to a topic mentioned by the participant on social media. The sending unit can also select the optimal sending timing by referring to the participant's social media activity time. Furthermore, the sending unit can also send a related Next Action by referring to the activity of the participant's friends on social media. In this way, by analyzing the participant's social media activity, a more appropriate Next Action can be sent. Some or all of the above-mentioned processing in the sending unit may be performed using, for example, AI, or may be performed without using AI. For example, the sending unit can input the participant's social media activity data into a generation AI and have the generation AI analyze it.

[0055] When transmitting a Next Action, the transmission unit can customize the transmission method by reflecting the participants' past feedback. The transmission unit, for example, selects the optimal transmission method based on feedback provided by the participants in the past. The transmission unit can also analyze the participants' past feedback and improve the transmission method. Furthermore, the transmission unit can provide a customized transmission method by referring to the participants' past feedback. In this way, a more appropriate transmission method can be selected by reflecting the participants' past feedback. Some or all of the above-described processing in the transmission unit may be performed using, for example, AI, or may be performed without using AI. For example, the transmission unit can input the participants' past feedback data into a generation AI and have the generation AI analyze it.

[0056] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0057] The conference support system can further include a document management unit. The document management unit can centrally manage materials used during the conference and minutes, allowing participants to easily access them. For example, materials can be uploaded before the conference so that participants can review them in advance. Minutes can also be saved after the conference so that participants can refer to them later. This allows for smooth preparation and follow-up of the conference. Furthermore, the document management unit can manage the versions of materials and provide the latest information. For example, if materials are updated, participants can be notified and the latest materials can be provided, allowing for smooth information sharing.

[0058] The conference support system can further include a network monitoring unit. The network monitoring unit can monitor the network status during a conference in real time to ensure communication stability. For example, it can detect network delays and connection problems and respond quickly. The network monitoring unit can also monitor the connection status of participants and notify them if a problem occurs. This can minimize communication problems during a conference. Furthermore, the network monitoring unit can also save recorded conference data so that it can be viewed later. For example, by saving recorded conference data in the cloud and allowing participants to view it later, the content of the conference can be accurately understood.

[0059] The conference support system can further include a security management unit. The security management unit can ensure the security of data and communications during a conference and prevent information leaks. For example, it can authenticate conference participants and ensure that only authorized users can participate. The security management unit can also encrypt data during a conference to ensure the security of communications. This minimizes the risk of confidential information leaks. Furthermore, the security management unit can record conference logs and detect unauthorized access. For example, security can be strengthened by regularly auditing conference logs and notifying if unauthorized access occurs.

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

[0061] Step 1: The receptionist initially sets the purpose and time of the meeting. For example, they set it in natural language, such as, "The purpose of today's meeting is to discuss the development plan for a new product. The meeting will last one hour." This information is input into the AI. Step 2: The setting unit sets up the meeting arrangements based on the information initially set by the reception unit. For example, it creates a meeting agenda and determines the time allocation for each topic. It can also set up the meeting arrangements by taking into account past meeting data and the positions and areas of expertise of the participants. Step 3: The return section brings the topic back to the main topic if it strays from the main topic during the meeting. For example, it supports the progress of the meeting by saying, "Let's move on to the next topic." It can also bring the topic back to the main topic if a certain amount of time has passed or if a specific keyword appears. Step 4: The generation unit automatically generates minutes after the meeting. For example, minutes including the contents discussed and decisions made during the meeting are automatically generated. The system can also estimate the user's emotions and adjust the method for generating minutes based on the estimated emotions. Step 5: The sender sends the Next Action to each participant by email. For example, the sender sends a Next Action containing specific instructions, such as "Please prepare the materials by the next meeting." The sender can also estimate the user's emotions and adjust the method for sending the Next Action based on the estimated emotions.

[0062] (Example 2) A meeting support system according to an embodiment of the present invention is a system that initially sets the purpose and time of a meeting, sets the meeting schedule, returns the topic to the main topic if the topic strays from the main topic, automatically generates minutes, and sends a Next Action to each participant by email. The meeting support system initially sets the purpose and time of a meeting in natural language, and AI automatically sets the meeting schedule. If the topic strays from the main topic during the meeting, the AI ​​subtly returns the topic to the main topic at an appropriate time. After the meeting ends, the AI ​​automatically generates minutes and automatically sends a Next Action to each participant by email. For example, the meeting support system initially sets the purpose and time of the meeting in natural language. For example, the system may set the schedule as follows: "The purpose of today's meeting is to discuss the development plan for a new product. The meeting will last one hour." This information is input into the AI. The AI ​​then automatically sets the meeting schedule. For example, the system creates a meeting agenda and determines the time allocation for each topic. This ensures the meeting proceeds smoothly. Next, if the topic strays from the main topic during the meeting, the AI ​​subtly returns the topic to the main topic at an appropriate time. For example, the system supports the progress of the meeting by saying, "Let's move on to the next agenda item." Next, after the meeting ends, the AI ​​in the meeting support system automatically generates minutes. The minutes include the content discussed and decisions made in the meeting. Furthermore, the meeting support system automatically sends a Next Action to each participant by email. For example, it includes specific instructions such as, "Please prepare the materials by the next meeting." This allows the meeting support system to improve the efficiency of meetings, allowing all participants to clearly understand the next action. This allows the meeting support system to improve the efficiency of meetings, allowing all participants to clearly understand the next action.

[0063] A meeting support system according to an embodiment includes a reception unit, a setting unit, a return unit, a generation unit, and a transmission unit. The reception unit initially sets the purpose and time of the meeting. The reception unit sets the purpose and time of the meeting in natural language, for example, as follows: "The purpose of today's meeting is to discuss a new product development plan. The meeting will last one hour." This information is input to an AI. The setting unit sets the meeting schedule based on the information initially set by the reception unit. The setting unit, for example, creates a meeting agenda and determines the time allocation for each topic. For example, the setting unit can set the meeting schedule taking into account past meeting data, the positions and areas of expertise of participants. The return unit returns the topic to the main topic if the topic strays from the main topic during the meeting. The return unit supports the progress of the meeting by, for example, saying, "Let's move on to the next topic." The return unit can also return the topic to the main topic if, for example, a certain amount of time has passed or a specific keyword appears. The generation unit automatically generates minutes after the meeting ends. The generation unit, for example, automatically generates minutes including the contents discussed and decisions made in the meeting. The generation unit can also, for example, estimate the user's emotions and adjust the method for generating the minutes based on the estimated emotions. The transmission unit sends the Next Action by email to each participant. The transmission unit sends the Next Action including specific instructions, such as, for example, "Please prepare materials by the next meeting." The transmission unit can also, for example, estimate the user's emotions and adjust the method for sending the Next Action based on the estimated emotions. This enables the meeting support system according to the embodiment to initially set the purpose and time of the meeting, set up a schedule, bring the topic back to the main topic, automatically generate minutes, and transmit the Next Action.

[0064] The reception unit can initially set the purpose and time of the meeting in natural language. The reception unit, for example, sets the purpose and time of the meeting in natural language. For example, it sets it as follows: "The purpose of today's meeting is to discuss the development plan for a new product. The meeting will last one hour." This information is input to the AI. By thus initially setting the purpose and time of the meeting in natural language, convenience for users is improved. Some or all of the above-described processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the purpose and time of the meeting input in natural language to the generation AI, which can then analyze it.

[0065] The setting unit can set the schedule for a meeting based on past meeting data or the positions and areas of expertise of participants. The setting unit can set optimal schedules for meetings with similar purposes based on, for example, past meeting data. The setting unit can also analyze the progress of past meetings to set efficient schedules. Furthermore, the setting unit can select the optimal schedule setting method by referring to feedback from participants in past meetings. This allows for more appropriate schedules to be set by taking into account past meeting data and the positions and areas of expertise of participants. Some or all of the above-mentioned processing in the setting unit can be performed using, for example, AI, or can be performed without using AI. For example, the setting unit can input past meeting data into a generation AI and have the generation AI analyze it.

[0066] The return unit can return the topic to the main topic when a certain amount of time has passed or when a specific keyword appears. For example, the return unit can return the topic to the main topic when a certain amount of time has passed, taking into account the progress of the meeting. The return unit can also return the topic to the main topic by analyzing the content of comments made by the meeting participants when a specific keyword appears. Furthermore, the return unit can also quickly return the topic to the main topic when the progress of the meeting is delayed. This makes it possible to return the topic to the main topic at an appropriate time when the topic has strayed from the main topic. Some or all of the above-mentioned processing in the return unit may be performed, for example, using AI, or may be performed without using AI. For example, the return unit can have a generation AI analyze the appearance of a specific keyword and adjust the timing to return the topic to the main topic.

[0067] The generation unit can automatically generate minutes including the contents discussed and decisions made in the meeting. For example, if many contents were discussed in the meeting, the generation unit can generate detailed minutes. Furthermore, if many decisions were made in the meeting, the generation unit can also generate minutes that cover the main points. Furthermore, if few contents were discussed in the meeting, the generation unit can also generate concise minutes. In this way, by automatically generating minutes after the meeting, the contents of the meeting can be accurately recorded. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the contents discussed and decisions made in the meeting into a generation AI, which can then automatically generate minutes.

[0068] The sending unit can send the Next Action to each participant by email. The sending unit sends the Next Action including specific instructions, such as "Please prepare materials by the next meeting." The sending unit can also estimate the user's emotions and adjust the method for sending the Next Action based on the estimated emotions. The sending unit can also customize the content to be sent based on the participant's job title or field of expertise. This makes it possible to clearly communicate the next action by sending the Next Action to each participant by email. Some or all of the above-mentioned processing in the sending unit may be performed using, for example, AI, or may be performed without using AI. For example, the sending unit can input the Next Action to a generating AI and have the generating AI customize the content to be sent.

[0069] The reception unit can estimate the user's emotions and adjust the initial settings of the purpose and time of the meeting based on the estimated emotions. For example, if the user is nervous, the reception unit can briefly set the purpose and time of the meeting to allow the user to relax. Furthermore, if the user is relaxed, the reception unit can also set a detailed purpose and time to ensure the smooth progress of the meeting. Furthermore, if the user is in a hurry, the reception unit can also set the purpose and time of the meeting to allow the meeting to proceed efficiently in a short amount of time. This allows for more appropriate settings by adjusting the initial settings of the purpose and time of the meeting according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's emotion data into the generation AI, causing the generation AI to adjust the initial settings of the purpose and time of the meeting.

[0070] The reception unit can analyze data on the purpose and duration of past meetings and select an appropriate initial setup method. The reception unit, for example, sets the optimal time for meetings with similar purposes based on past meeting data. The reception unit can also analyze the progress of past meetings and set efficient time allocation. Furthermore, the reception unit can select the optimal initial setup method by referring to feedback from participants in past meetings. In this way, the optimal initial setup method can be selected by analyzing past meeting data. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input past meeting data into a generation AI and have the generation AI analyze it.

[0071] When initially setting the purpose and time of a meeting, the reception unit can filter based on the user's current project or area of ​​interest. For example, the reception unit can prioritize setting the purpose and time of a meeting related to a project currently being carried out by the user. The reception unit can also set the purpose and time of a related meeting based on the user's area of ​​interest. Furthermore, the reception unit can also set the optimal purpose and time of a meeting by referring to the user's past project history. This allows the purpose and time of a related meeting to be set based on the user's current project or area of ​​interest. Some or all of the above-described processing in the reception unit can be performed using, for example, AI, or can be performed without using AI. For example, the reception unit can input the user's project data into a generation AI and have the generation AI analyze it.

[0072] The reception unit can select an appropriate setting means depending on the user's input method when initially setting the purpose and time of the meeting. For example, if the user uses voice input, the reception unit can set the purpose and time of the meeting using voice recognition technology. Furthermore, if the user uses text input, the reception unit can also set the purpose and time of the meeting using text analysis technology. Furthermore, if the user uses image input, the reception unit can also set the purpose and time of the meeting using image recognition technology. This improves convenience by selecting the optimal setting means depending on the user's input method. Some or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input voice data to a generation AI and have the generation AI analyze it.

[0073] The setting unit can estimate the user's emotions and adjust the method for setting up the meeting arrangements based on the estimated emotions. For example, if the user is nervous, the setting unit can set up a simple arrangement to allow the user to relax. Furthermore, if the user is relaxed, the setting unit can set up detailed arrangements to ensure smooth progress of the meeting. Furthermore, if the user is in a hurry, the setting unit can set up arrangements to allow the meeting to proceed efficiently in a short amount of time. This allows for more appropriate arrangements to be set by adjusting the method for setting up the meeting arrangements based on the user's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the setting unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the setting unit can input the user's emotion data into the generation AI, causing the generation AI to adjust the method for setting up the meeting arrangements.

[0074] The setting unit can analyze past conference data and select an appropriate setup method. The setting unit, for example, sets optimal setup for conferences with similar purposes based on past conference data. The setting unit can also analyze the progress of past conferences and set efficient setup. Furthermore, the setting unit can select an optimal setup method by referring to feedback from participants in past conferences. In this way, the optimal setup method can be selected by analyzing past conference data. Some or all of the above-mentioned processing in the setting unit may be performed using, for example, AI, or may be performed without using AI. For example, the setting unit can input past conference data into a generation AI and have the generation AI analyze it.

[0075] The setting unit can filter based on the participants' job titles and areas of expertise when setting up the meeting schedule. The setting unit, for example, prioritizes important agenda items based on the participants' job titles. The setting unit can also set relevant agenda items based on the participants' areas of expertise. Furthermore, the setting unit can set optimal schedules by referring to the participants' past meeting history. This makes it possible to set relevant agenda items based on the participants' job titles and areas of expertise. Some or all of the above-mentioned processing in the setting unit may be performed using AI, for example, or may be performed without using AI. For example, the setting unit can input data on the participants' job titles and areas of expertise into a generation AI and have the generation AI analyze the data.

[0076] When setting up a meeting schedule, the setting unit can improve the accuracy of the settings by referring to the user's past meeting history. The setting unit sets an optimal schedule based on, for example, the user's past meeting history. The setting unit can also analyze the user's past meeting history and set an efficient schedule. Furthermore, the setting unit can improve the accuracy of the settings by referring to the user's past meeting history. In this way, the accuracy of the settings can be improved by referring to the user's past meeting history. Some or all of the above-described processing in the setting unit may be performed using, for example, AI, or may be performed without using AI. For example, the setting unit can input the user's past meeting history into a generation AI and have the generation AI analyze it.

[0077] The return unit can estimate the user's emotions and adjust the timing to return the topic to the main topic based on the estimated emotions. For example, if the user is nervous, the return unit can return the topic to the main topic at a timing when the user can relax. Furthermore, if the user is relaxed, the return unit can also return the topic to the main topic at an appropriate timing. Furthermore, if the user is in a hurry, the return unit can quickly return the topic to the main topic. In this way, by adjusting the timing to return the topic to the main topic according to the user's emotions, the topic can be returned to the main topic at a more appropriate timing. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the return unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the return unit can input the user's emotion data into the generation AI and have the generation AI adjust the timing to return the topic to the main topic.

[0078] The return unit can select a method for returning the topic to the main topic depending on the progress of the meeting, as well as when a certain amount of time has passed. For example, when a certain amount of time has passed, the return unit returns the topic to the main topic taking into account the progress of the meeting. The return unit can also quickly return the topic to the main topic if the meeting is running behind schedule. Furthermore, when the meeting is progressing smoothly, the return unit can also return the topic to the main topic at an appropriate timing. In this way, by selecting a method for returning the topic to the main topic depending on the progress of the meeting, the topic can be returned to the main topic more effectively. Some or all of the above-described processing in the return unit may be performed using, for example, AI, or may be performed without using AI. For example, the return unit can input data on the progress of the meeting into a generation AI and have the generation AI analyze it.

[0079] The return unit can return the topic to the main topic by analyzing the content of the statements made by the meeting participants, in addition to when a specific keyword appears. For example, when a specific keyword appears, the return unit can analyze the content of the statements made by the meeting participants and return the topic to the main topic. The return unit can also return the topic to the main topic at an appropriate time if the content of the statements made by the meeting participants strays from the main topic. Furthermore, the return unit can analyze the content of the statements made by the meeting participants in real time and return the topic to the main topic at an optimal time. In this way, by analyzing the content of the statements made by the meeting participants, the topic can be returned to the main topic at a more appropriate time. Some or all of the above-described processing in the return unit may be performed using, for example, AI, or may be performed without using AI. For example, the return unit can input the content data of the statements made by the meeting participants into a generation AI and have the generation AI analyze it.

[0080] The return unit can select an appropriate return method by referring to past meeting data when returning the topic to the main topic. For example, the return unit selects a return method that was effective in a similar situation based on past meeting data. The return unit can also analyze the progress of past meetings and select the optimal return method. Furthermore, the return unit can also select the optimal return method by referring to feedback from participants in past meetings. In this way, the optimal return method can be selected by referring to past meeting data. Some or all of the above-mentioned processing in the return unit may be performed using, for example, AI, or may be performed without using AI. For example, the return unit can input past meeting data into a generation AI and have the generation AI analyze it.

[0081] The generation unit can estimate the user's emotions and adjust the generation method of the minutes based on the estimated emotions. For example, if the user is relaxed, the generation unit can generate detailed minutes. If the user is in a hurry, the generation unit can also generate concise minutes that focus on the main points. Furthermore, if the user is excited, the generation unit can generate minutes with visually stimulating effects. This allows for more appropriate minutes to be generated by adjusting the generation method of the minutes according to the user's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the generation unit can be performed using, for example, AI, or without AI. For example, the generation unit can input the user's emotion data into the generation AI, causing the generation AI to adjust the generation method of the minutes.

[0082] The generation unit can adjust the level of detail in the minutes based on the content discussed and decisions made in the meeting. For example, if many content items were discussed in the meeting, the generation unit can generate detailed minutes. Furthermore, if many decisions were made in the meeting, the generation unit can also generate minutes that focus on the main points. Furthermore, if few content items were discussed in the meeting, the generation unit can also generate concise minutes. In this way, by adjusting the level of detail in the minutes based on the content discussed and decisions made in the meeting, minutes with an appropriate level of detail can be generated. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the content discussed and decisions made in the meeting into a generation AI, and have the generation AI adjust the level of detail in the minutes.

[0083] When generating minutes, the generation unit can apply different generation algorithms depending on the category of the meeting. For example, in the case of a technical meeting, the generation unit generates minutes including technical details. In addition, in the case of a marketing meeting, the generation unit can also generate minutes related to marketing strategies. Furthermore, in the case of a management meeting, the generation unit can also generate minutes related to management policies. In this way, by applying an appropriate generation algorithm depending on the category of the meeting, more appropriate minutes can be generated. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input meeting category data into a generation AI and have the generation AI analyze the data.

[0084] When generating minutes, the generation unit can improve the accuracy of generation by referring to the user's past minutes results. The generation unit generates optimal minutes, for example, based on the user's past minutes results. The generation unit can also analyze the user's past minutes results to improve the accuracy of generation. Furthermore, the generation unit can also improve the generation algorithm by referring to the user's past minutes results. In this way, the accuracy of generation can be improved by referring to the user's past minutes results. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can input the user's past minutes results into the generation AI and have it analyzed by the generation AI.

[0085] The generation unit can estimate the user's emotions and adjust the length of the minutes based on the estimated emotions. For example, if the user is in a hurry, the generation unit can generate short, to-the-point minutes. Furthermore, if the user is relaxed, the generation unit can generate longer minutes with detailed explanations. Furthermore, if the user is excited, the generation unit can generate minutes with visually stimulating effects. By adjusting the length of the minutes according to the user's emotions, minutes of a more appropriate length can be generated. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit can be performed using, for example, AI, or without AI. For example, the generation unit can input the user's emotion data into the generation AI and have the generation AI adjust the length of the minutes.

[0086] When generating minutes, the generation unit can determine the priority of the minutes based on the time the meeting was held. For example, the generation unit prioritizes generating minutes of the most recent meeting. The generation unit can also prioritize generating minutes of important meetings. Furthermore, the generation unit can also prioritize generating minutes of regular meetings. In this way, by determining the priority of minutes based on the time the meeting was held, important minutes can be generated preferentially. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input data on the time the meeting was held into the generation AI and have it analyzed by the generation AI.

[0087] When generating minutes, the generation unit can adjust the order of the minutes based on the relevance of the meeting. For example, the generation unit prioritizes recording highly relevant topics in the minutes. The generation unit can also postpone recording less relevant topics in the minutes. Furthermore, the generation unit can adjust the order of the minutes based on the order in which the meeting proceeds. In this way, by adjusting the order of the minutes based on the relevance of the meeting, minutes can be generated in a more appropriate order. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input meeting relevance data into the generation AI and have it analyzed by the generation AI.

[0088] When generating minutes, the generation unit can adjust the frequency of use of technical terms in the minutes according to the user's level of expertise. For example, if the user has technical expertise, the generation unit can generate minutes that use a lot of technical terms. Also, if the user does not have technical expertise, the generation unit can generate minutes that avoid technical terms. Furthermore, the generation unit can generate minutes that use appropriate technical terms according to the user's level of expertise. In this way, by adjusting the use of technical terms according to the user's level of expertise, minutes that are easier to understand can be generated. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the user's level of expertise data into the generation AI and have it analyzed by the generation AI.

[0089] The transmission unit can estimate the user's emotions and adjust the method for transmitting the next action based on the estimated emotions. For example, if the user is relaxed, the transmission unit can transmit a detailed Next Action. Furthermore, if the user is in a hurry, the transmission unit can also transmit a concise Next Action that focuses on the main points. Furthermore, if the user is excited, the transmission unit can also transmit a Next Action with a visually stimulating effect. By adjusting the method for transmitting the Next Action according to the user's emotions, the Next Action can be transmitted in a more appropriate manner. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the transmission unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the transmission unit can input the user's emotion data into the generation AI, and have the generation AI adjust the method for transmitting the Next Action.

[0090] When transmitting a Next Action, the transmission unit can customize the transmission content based on the participant's job title and field of expertise. The transmission unit transmits an appropriate Next Action, for example, according to the participant's job title. The transmission unit can also transmit a related Next Action based on the participant's field of expertise. Furthermore, the transmission unit can transmit the optimal Next Action by referring to the participant's past behavioral history. In this way, by customizing the transmission content based on the participant's job title and field of expertise, a more appropriate Next Action can be transmitted. Some or all of the above-described processing in the transmission unit may be performed using, for example, AI, or may be performed without using AI. For example, the transmission unit can input data on the participant's job title and field of expertise into a generation AI and have the generation AI analyze the data.

[0091] When transmitting a Next Action, the transmission unit can improve the accuracy of the transmission by referring to the participant's past behavioral history. The transmission unit transmits the optimal Next Action based on, for example, the participant's past behavioral history. The transmission unit can also analyze the participant's past behavioral history to improve the accuracy of the transmission. Furthermore, the transmission unit can also customize the content of the transmission by referring to the participant's past behavioral history. In this way, the accuracy of the transmission can be improved by referring to the participant's past behavioral history. Some or all of the above-mentioned processing in the transmission unit may be performed using, for example, AI, or may be performed without using AI. For example, the transmission unit can input the participant's past behavioral history data into a generation AI and have the generation AI analyze it.

[0092] When transmitting a Next Action, the transmitting unit can determine the transmission priority based on the content of the conference. For example, the transmitting unit prioritizes the transmission of a Next Action for an important conference. The transmitting unit can also prioritize the transmission of a Next Action with a high urgency. Furthermore, the transmitting unit can determine the transmission priority of the Next Action based on the progress of the conference. In this way, by determining the transmission priority based on the content of the conference, important Next Actions can be transmitted with priority. Some or all of the above-described processing in the transmitting unit may be performed using, or without, AI, for example. For example, the transmitting unit can input content data of the conference into a generating AI and have the generating AI analyze it.

[0093] The transmission unit can estimate the user's emotion and adjust the timing of transmitting the next action based on the estimated emotion. For example, if the user is relaxed, the transmission unit can transmit the next action at an appropriate timing. Furthermore, if the user is in a hurry, the transmission unit can also transmit the next action quickly. Furthermore, if the user is excited, the transmission unit can transmit the next action at an appropriate timing. In this way, by adjusting the transmission timing of the next action according to the user's emotion, the next action can be transmitted at a more appropriate timing. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the transmission unit may be performed using an AI, for example, or without using an AI. For example, the transmission unit can input the user's emotion data into the generation AI and have the generation AI adjust the transmission timing of the next action.

[0094] When transmitting the Next Action, the transmission unit can select an appropriate transmission method by taking into account the geographical location information of the participants. For example, if the participant is in the office, the transmission unit selects a transmission method that is effective in the office. Furthermore, if the participant is on a business trip, the transmission unit can select a transmission method that is effective at the business trip destination. Furthermore, if the participant is at home, the transmission unit can select a transmission method that is effective remotely. In this way, a more appropriate transmission method can be selected by taking into account the geographical location information of the participants. Some or all of the above-described processing in the transmission unit may be performed using, for example, AI, or may be performed without using AI. For example, the transmission unit can input the geographical location information data of the participants into the generation AI and have it analyzed by the generation AI.

[0095] When sending a Next Action, the sending unit can analyze the participant's social media activity and customize the relevant sending content. For example, the sending unit sends a Next Action related to a topic mentioned by the participant on social media. The sending unit can also select the optimal sending timing by referring to the participant's social media activity time. Furthermore, the sending unit can also send a related Next Action by referring to the activity of the participant's friends on social media. In this way, by analyzing the participant's social media activity, a more appropriate Next Action can be sent. Some or all of the above-mentioned processing in the sending unit may be performed using, for example, AI, or may be performed without using AI. For example, the sending unit can input the participant's social media activity data into a generation AI and have the generation AI analyze it.

[0096] When transmitting a Next Action, the transmission unit can customize the transmission method by reflecting the participants' past feedback. The transmission unit, for example, selects the optimal transmission method based on feedback provided by the participants in the past. The transmission unit can also analyze the participants' past feedback and improve the transmission method. Furthermore, the transmission unit can provide a customized transmission method by referring to the participants' past feedback. In this way, a more appropriate transmission method can be selected by reflecting the participants' past feedback. Some or all of the above-described processing in the transmission unit may be performed using, for example, AI, or may be performed without using AI. For example, the transmission unit can input the participants' past feedback data into a generation AI and have the generation AI analyze it. === Hard Collateral 1-1 === Each of the multiple elements, including the above-mentioned reception unit, setting unit, return unit, generation unit, and transmission unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart device 14 and initializes the purpose and time of the meeting in natural language. The setting unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and sets up the meeting schedule based on the initialized information. The return unit is realized, for example, by the control unit 46A of the smart device 14 and returns the topic to the main topic if it strays from the main topic during the meeting. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and automatically generates minutes after the meeting ends. The transmission unit is realized, for example, by the control unit 46A of the smart device 14 and sends a Next Action to each participant by email. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned reception unit, setting unit, return unit, generation unit, and transmission unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart glasses 214 and initializes the purpose and time of the meeting in natural language. The setting unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and sets the meeting schedule based on the initialized information. The return unit is realized, for example, by the control unit 46A of the smart glasses 214 and returns the topic to the main topic if it strays from the main topic during the meeting. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and automatically generates minutes after the meeting ends. The transmission unit is realized, for example, by the control unit 46A of the smart glasses 214 and sends a Next Action to each participant by email. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned reception unit, setting unit, return unit, generation unit, and transmission unit is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the headset-type terminal 314 and initializes the purpose and time of the conference in natural language. The setting unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and sets up the conference schedule based on the initialized information. The return unit is realized, for example, by the control unit 46A of the headset-type terminal 314 and returns the topic to the main topic if it strays from the main topic during the conference. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and automatically generates minutes after the conference ends. The transmission unit is realized, for example, by the control unit 46A of the headset-type terminal 314 and sends a Next Action to each participant by email. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, setting unit, return unit, generation unit, and transmission unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the robot 414 and initializes the purpose and time of the meeting in natural language. The setting unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and sets up the meeting schedule based on the initialized information. The return unit is realized, for example, by the control unit 46A of the robot 414 and returns the topic to the main topic if it strays from the main topic during the meeting. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and automatically generates minutes after the meeting ends. The transmission unit is realized, for example, by the control unit 46A of the robot 414 and sends a Next Action to each participant by email.

[0097] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0098] The conference support system can further include a real-time translation unit. The real-time translation unit can translate speech content in real time to facilitate communication between participants who speak different languages ​​during a conference. For example, speech from an English-speaking participant can be translated into Japanese and provided to participants who speak Japanese. The real-time translation unit can also generate conference minutes in multiple languages. This enables smooth communication even in international conferences. Furthermore, the real-time translation unit can estimate the emotions of participants and adjust the tone of the translation according to their emotions. For example, the speech of a nervous participant can be translated in a relaxed tone to lighten the atmosphere of the conference.

[0099] The meeting support system can further include a visual support unit. The visual support unit can provide visual materials during a meeting to deepen participants' understanding. For example, it can generate graphs and charts related to the content of comments in real time and display them on the screen. The visual support unit can also provide a timeline that visually shows the progress of the meeting. This allows participants to understand the progress of the meeting at a glance. Furthermore, the visual support unit can estimate the emotions of participants and provide visual feedback according to their emotions. For example, if participants are excited, it can add visually stimulating effects to increase the liveliness of the meeting.

[0100] The conference support system can further include a speech recognition unit. The speech recognition unit can convert statements made during a conference into text in real time and support the generation of meeting minutes. For example, speech content can be automatically converted into text so that participants can review it later. The speech recognition unit can also detect specific keywords and highlight important statements. This allows participants to efficiently grasp the main points of the conference. Furthermore, the speech recognition unit can estimate the emotions of participants and provide feedback according to their emotions. For example, if a participant is nervous, it can lighten the atmosphere of the conference by providing feedback to help them relax.

[0101] The conference support system can further include a data analysis unit. The data analysis unit can analyze data collected during the conference in real time and provide feedback to participants. For example, the data analysis unit can analyze the frequency and duration of speech and adjust the balance of speech among participants. The data analysis unit can also analyze the progress of the conference and suggest efficient ways to proceed, thereby improving the efficiency of the conference. Furthermore, the data analysis unit can estimate the emotions of participants and provide feedback according to their emotions. For example, if a participant is relaxed, detailed feedback can be provided to deepen understanding of the conference.

[0102] The meeting support system can further include a reminder unit. The reminder unit can send reminders to participants before and after the meeting to support meeting preparation and follow-up. For example, a reminder can be sent the day before the meeting to encourage participants to prepare for the meeting. A reminder can also be sent after the meeting to confirm the next action. This allows for smooth meeting preparation and follow-up. Furthermore, the reminder unit can estimate the emotions of participants and provide reminders according to their emotions. For example, if a participant is nervous, a reminder to help them relax can be sent to support meeting preparation.

[0103] The conference support system can further include a schedule adjustment unit. The schedule adjustment unit can automatically adjust participants' schedules and suggest optimal conference times. For example, it can analyze participants' calendars to find a time when everyone can attend. The schedule adjustment unit can also prioritize the schedule according to the importance of the conference. This enables efficient schedule adjustment. Furthermore, the schedule adjustment unit can estimate participants' emotions and adjust the schedule according to their emotions. For example, if participants are busy, it can reduce the burden of the conference by suggesting a schedule that allows the conference to proceed efficiently in a short amount of time.

[0104] The meeting support system can further include a feedback collection unit. The feedback collection unit collects feedback from participants after the meeting and can use the collected feedback to improve the next meeting. For example, it collects and analyzes evaluations of the progress and content of the meeting. The feedback collection unit can also collect feedback while maintaining the anonymity of participants. This makes it possible to collect frank opinions. Furthermore, the feedback collection unit can estimate the emotions of participants and adjust the feedback collection method according to their emotions. For example, if a participant is relaxed, asking for detailed feedback can be used to improve the meeting.

[0105] The conference support system can further include a document management unit. The document management unit can centrally manage materials used during the conference and minutes, allowing participants to easily access them. For example, materials can be uploaded before the conference so that participants can review them in advance. Minutes can also be saved after the conference so that participants can refer to them later. This allows for smooth preparation and follow-up of the conference. Furthermore, the document management unit can manage the versions of materials and provide the latest information. For example, if materials are updated, participants can be notified and the latest materials can be provided, allowing for smooth information sharing.

[0106] The conference support system can further include a network monitoring unit. The network monitoring unit can monitor the network status during a conference in real time to ensure communication stability. For example, it can detect network delays and connection problems and respond quickly. The network monitoring unit can also monitor the connection status of participants and notify them if a problem occurs. This can minimize communication problems during a conference. Furthermore, the network monitoring unit can also save recorded conference data so that it can be viewed later. For example, by saving recorded conference data in the cloud and allowing participants to view it later, the content of the conference can be accurately understood.

[0107] The conference support system can further include a security management unit. The security management unit can ensure the security of data and communications during a conference and prevent information leaks. For example, it can authenticate conference participants and ensure that only authorized users can participate. The security management unit can also encrypt data during a conference to ensure the security of communications. This minimizes the risk of confidential information leaks. Furthermore, the security management unit can record conference logs and detect unauthorized access. For example, security can be strengthened by regularly auditing conference logs and notifying if unauthorized access occurs.

[0108] The processing flow of the second embodiment will be briefly explained below.

[0109] Step 1: The receptionist initially sets the purpose and time of the meeting. For example, they set it in natural language, such as, "The purpose of today's meeting is to discuss the development plan for a new product. The meeting will last one hour." This information is input into the AI. Step 2: The setting unit sets up the meeting arrangements based on the information initially set by the reception unit. For example, it creates a meeting agenda and determines the time allocation for each topic. It can also set up the meeting arrangements by taking into account past meeting data and the positions and areas of expertise of the participants. Step 3: The return section brings the topic back to the main topic if it strays from the main topic during the meeting. For example, it supports the progress of the meeting by saying, "Let's move on to the next topic." It can also bring the topic back to the main topic if a certain amount of time has passed or if a specific keyword appears. Step 4: The generation unit automatically generates minutes after the meeting. For example, minutes including the contents discussed and decisions made during the meeting are automatically generated. The system can also estimate the user's emotions and adjust the method for generating minutes based on the estimated emotions. Step 5: The sender sends the Next Action to each participant by email. For example, the sender sends a Next Action containing specific instructions, such as "Please prepare the materials by the next meeting." The sender can also estimate the user's emotions and adjust the method for sending the Next Action based on the estimated emotions.

[0110] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0111] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0112] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0113] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0114] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0115] 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.

[0116] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0117] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0118] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0119] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0120] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0121] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0122] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0123] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0124] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0125] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0126] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0127] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0128] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0129] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0130] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0131] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0132] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0133] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0134] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0135] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0136] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0137] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0138] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0139] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0140] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0141] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0142] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0143] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0144] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0145] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0146] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0147] 7, a 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.

[0148] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0149] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0150] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0151] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0152] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0153] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0154] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0155] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0156] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0157] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0158] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0159] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0160] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0161] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0162] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0163] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0164] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0165] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0166] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0167] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0168] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0169] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0170] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0171] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0172] 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.

[0173] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0174] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0175] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0176] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0177] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0178] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0179] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0180] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0181] [Explanation of symbols]

[0182] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A reception section that initially sets the purpose and time of the meeting; a setting unit that sets arrangements for the conference based on the information initially set by the reception unit; A back-to-topic section that brings the topic back to the topic if the topic strays from the topic during the meeting; A generation unit that automatically generates minutes after the meeting ends; A sending unit that sends the next action to each participant by email. A system characterized by:

2. The reception unit Set meeting purpose and time in natural language 2. The system of claim 1.

3. The setting unit Schedule meetings based on past meeting data or participants' roles and areas of expertise 2. The system of claim 1.

4. The return portion is Bring the topic back to the main topic after a certain amount of time has passed or when certain keywords appear 2. The system of claim 1.

5. The generation unit Automatically generate meeting minutes that include what was discussed and what decisions were made 2. The system of claim 1.

6. The transmission unit Send Next Action to each participant by email 2. The system of claim 1.

7. The reception unit Inferring user emotions and adjusting initial meeting purpose and time settings based on the estimated emotions 2. The system of claim 1.

8. The reception unit Analyze data on the purpose and duration of past meetings to select the appropriate initial setup method 2. The system of claim 1.

9. The reception unit Initial meeting purpose and time filtering based on the user's current projects and interests 2. The system of claim 1.

10. The reception unit When initially setting the purpose and time of a meeting, select an appropriate setting method according to the user's input method.

2. The system of claim 1.

Images