system

Abstract

The system according to this embodiment aims to streamline the process of organizing the contents of a meeting, summarizing the points to be discussed and resolutions to be made for the next meeting, and sending invitations to the necessary participants. [Solution] The system according to the embodiment comprises a sorting unit, an extraction unit, and a transmission unit. The sorting unit sorts the contents of the meeting. The extraction unit extracts the discussion points and resolutions for the next meeting based on the contents sorted by the sorting unit. The transmission unit sends invitations to the necessary participants based on the discussion points and resolutions extracted by the extraction unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that the work of organizing the content of the MTG, summarizing the next points of argument and matters for decision, and sending invitations to necessary participants is laborious and difficult to perform efficiently.

[0005] The system according to the embodiment aims to streamline the work of organizing the content of the MTG, summarizing the next points of argument and matters for decision, and sending invitations to necessary participants.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a compiling unit, an extraction unit, and a transmission unit. The compiling unit compiling the contents of the meeting. The extraction unit extracts the discussion points and resolutions for the next meeting based on the contents compiled by the compiling unit. The transmission unit sends invitations to the necessary participants based on the discussion points and resolutions extracted by the extraction unit. [Effects of the Invention]

[0007] The system according to this embodiment can streamline the process of organizing the contents of a meeting, summarizing the points to be discussed and resolutions for the next meeting, and sending invitations to the necessary participants. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The MTG management system according to an embodiment of the present invention is a system that organizes the content of a meeting after it has been held, summarizes the discussion points and resolutions for the next meeting, and sends invitations to the necessary participants. This system utilizes AI to automate tasks related to meetings, allowing employees without secretaries to focus on their core responsibilities. First, after the meeting ends, the AI ​​uses speech recognition technology to create meeting minutes and performs text analysis to extract the discussion points and resolutions for the next meeting. Next, the AI ​​checks the participants' calendars and uses an algorithm to find a date and time when everyone can attend to send invitations. This system automates the following tasks: 1. Coordinating participants' schedules, 2. Preparing the content of the meeting, and 3. Creating meeting minutes. As a result, employees without secretaries can work as if they had one. Thus, the MTG management system can organize the content of a meeting, extract the discussion points and resolutions for the next meeting, and send invitations to the necessary participants.

[0029] The MTG management system according to this embodiment comprises a sorting unit, an extraction unit, and a transmission unit. The sorting unit sorts the contents of the MTG. For example, the sorting unit creates minutes of the MTG and classifies the information by agenda item. The sorting unit can also determine the importance of the information and sort important information with priority. The sorting unit can use AI and speech recognition technology to create minutes. For example, the sorting unit takes audio data of the MTG as input and converts it into text data using speech recognition technology. The sorting unit can use speech recognition technology to automatically transcribe the spoken content into text and create minutes. The extraction unit extracts the issues and resolutions for the next MTG based on the contents sorted by the sorting unit. For example, the extraction unit performs text analysis and extracts important issues and resolutions. The extraction unit can use AI and natural language processing technology to perform text analysis. For example, the extraction unit takes text data as input and extracts important information using natural language processing technology. The extraction unit performs text analysis and can automatically extract the issues and resolutions for the next MTG. The sending unit sends invitations to the necessary participants based on the issues and resolutions extracted by the extraction unit. The sending unit sends invitations using an algorithm to check participants' calendars and find a date and time when everyone can attend. The sending unit can use AI to check participants' calendars and select the optimal date and time. For example, the sending unit takes participants' calendar data as input and sends invitations using an algorithm to select the optimal date and time. The sending unit can check participants' calendars and send invitations for a date and time when everyone can attend. As a result, the MTG management system according to this embodiment can organize the contents of the MTG, extract the issues and resolutions for the next meeting, and send invitations to the necessary participants.

[0030] The editing department organizes the content of meetings. For example, the editing department creates meeting minutes and categorizes information by topic. Specifically, it collects meeting audio data and converts it into text data using speech recognition technology. Speech recognition technology can identify the speaker's voice and accurately transcribe the content of the speech into text. The editing department analyzes the transcribed data and categorizes the information by topic. For example, it analyzes the content of the speech, extracts relevant information for each topic, and creates meeting minutes. The editing department can also determine the importance of the information and prioritize organizing important information. Factors considered in determining importance include the frequency of the speech, the speaker's position, and keywords in the speech. The editing department can use AI to create meeting minutes using speech recognition technology. The AI ​​analyzes the audio data and automatically transcribes the content of the speech into text. For example, the editing department takes meeting audio data as input and converts it into text data using speech recognition technology. Speech recognition technology can identify the speaker's voice and accurately transcribe the content of the speech into text. The editing department can use speech recognition technology to automatically transcribe spoken content into text and create meeting minutes. This allows the editing department to efficiently organize meeting content and create minutes. Furthermore, the editing department can save the created minutes in a database, making them searchable and referable as needed. This allows for easy reference to past meeting content, which is useful for preparing for future meetings and facilitating discussions.

[0031] The extraction unit extracts the discussion points and resolutions for the next meeting based on the content organized by the organization unit. Specifically, it takes the meeting minutes created by the organization unit as input and performs text analysis. Natural language processing (NLP) technology is used for the text analysis to analyze the content of the meeting minutes. Natural language processing technology is a technology for extracting important information from text data, and can extract keywords and understand context. The extraction unit analyzes the content of the meeting minutes and extracts the discussion points and resolutions for the next meeting. For example, it extracts important keywords from the meeting minutes and sets the agenda for the next meeting based on them. It also analyzes the content of the meeting minutes and extracts resolutions and action items. The extraction unit can use AI to perform text analysis using natural language processing technology. The AI ​​analyzes the content of the meeting minutes and automatically extracts important information. For example, the extraction unit takes text data as input and extracts important information using natural language processing technology. Natural language processing technology extracts important keywords and phrases from the text data and sets the agenda and resolutions for the next meeting based on them. This allows the extraction unit to efficiently extract the discussion points and resolutions for the next meeting based on the content organized by the organization unit. Furthermore, the extraction unit can store the extracted information in a database, which can be used to prepare for the next meeting and facilitate the discussion. As a result, the extraction unit can efficiently extract the discussion points and resolutions for the next meeting, enabling smooth preparation and progress of the meeting.

[0032] The sending unit sends invitations to the necessary participants based on the discussion points and resolutions extracted by the extraction unit. Specifically, it takes the discussion points and resolutions for the next meeting extracted by the extraction unit as input and checks the participants' calendars. The sending unit obtains the participants' calendar data and uses an algorithm to find a date and time when everyone can attend. For example, the sending unit takes the participants' calendar data as input and sends invitations using an algorithm that selects the optimal date and time. The algorithm analyzes the participants' schedules and identifies a date and time when everyone can attend. The sending unit creates an invitation based on the identified date and time and sends it to the participants. The invitation includes information such as the date, time, location, agenda, and resolutions for the next meeting. The sending unit can use AI to check participants' calendars and select the optimal date and time. The AI ​​analyzes the participants' schedules and identifies a date and time when everyone can attend. For example, the sending unit takes the participants' calendar data as input and sends invitations using an algorithm that selects the optimal date and time. This allows the sending unit to check participants' calendars and send invitations at a date and time when everyone can attend. Furthermore, the sending unit can manage the status of invitation delivery and confirm responses from participants. This allows the sending unit to efficiently schedule the next meeting and hold the meeting at a time that is convenient for all participants.

[0033] The editing unit can create meeting minutes using speech recognition technology. For example, the editing unit can take audio data from a meeting as input and convert it into text data using speech recognition technology. The editing unit can automatically transcribe spoken content into text and create meeting minutes using speech recognition technology. For example, the editing unit can transcribe spoken content into text in real time using a speech recognition algorithm. The editing unit can transcribe spoken content with high accuracy using speech recognition technology. This automates the creation of meeting minutes by using speech recognition technology. Speech recognition technology includes, for example, deep learning-based speech recognition algorithms and specific speech recognition software. Some or all of the above processes in the editing unit may be performed using, for example, generative AI, or without generative AI. For example, the editing unit can input audio data into a generative AI and have the generative AI generate text data from the audio data.

[0034] The extraction unit can perform text analysis and extract the issues and resolutions for the next meeting. For example, the extraction unit takes text data as input and uses natural language processing techniques to extract important information. The extraction unit can perform text analysis and automatically extract the issues and resolutions for the next meeting. For example, the extraction unit uses natural language processing algorithms to extract important information from text data. The extraction unit can analyze text data using natural language processing techniques and extract important issues and resolutions. This allows for the automatic extraction of issues and resolutions for the next meeting through text analysis. Natural language processing techniques include, for example, topic modeling, keyword extraction, and document classification. Some or all of the above-described processes in the extraction unit may be performed using, for example, generative AI, or without generative AI. For example, the extraction unit can input text data into a generative AI and have the generative AI perform the extraction of important information.

[0035] The sending unit can check participants' calendars and send invitations using an algorithm to find a date and time when everyone can attend. For example, the sending unit can take participants' calendar data as input and send invitations using an algorithm to select the optimal date and time. The sending unit can check participants' calendars and send invitations at a date and time when everyone can attend. For example, the sending unit can use a calendar checking algorithm to analyze participants' calendars and select the optimal date and time. The sending unit can use an optimization algorithm to find a date and time when everyone can attend. This allows the sending unit to send invitations at a date and time when everyone can attend by checking participants' calendars. Some or all of the above processing in the sending unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the sending unit can input participants' calendar data into a generative AI and have the generative AI select the optimal date and time.

[0036] The editing department can adjust the level of detail in meeting minutes based on the speaker's position and area of ​​expertise when organizing the content of a meeting. For example, if the speaker is a senior manager, the editing department can create minutes that concisely summarize the key points. If the speaker is an expert, the editing department can create minutes that include technical details. If the speaker is a new employee, the editing department can create minutes that include basic explanations. By adjusting the level of detail in the minutes according to the speaker's position and area of ​​expertise, more appropriate minutes can be created. Identifying positions and areas of expertise includes, for example, hierarchical positions and classifications of areas of expertise. Some or all of the above processing in the editing department may be performed using, for example, a generating AI, or not using a generating AI. For example, the editing department can input data on the speaker's position and area of ​​expertise into a generating AI and have the generating AI perform the adjustment of the level of detail in the meeting minutes.

[0037] The organization unit can apply different organization algorithms to each agenda item when organizing the contents of a meeting. For example, for a technical agenda item, the organization unit can apply an organization algorithm that includes detailed technical information. For a business strategy agenda item, the organization unit can apply an organization algorithm that concisely summarizes the key points. For a project progress agenda item, the organization unit can apply an algorithm that organizes the progress status chronologically. By applying different organization algorithms to each agenda item, more appropriate meeting minutes can be created. Organization algorithms include, for example, the classification method and the algorithm to be used for each agenda item. Some or all of the above processing in the organization unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the organization unit can input data for each agenda item into a generative AI and have the generative AI execute the application of the organization algorithm.

[0038] The editing department can prioritize organizing the content of a meeting by considering the geographical location of the speakers. For example, if a speaker is participating from a remote location, the editing department will prioritize organizing their comments. If a speaker is participating from headquarters, the editing department can prioritize organizing topics related to headquarters. If a speaker is participating from a field, the editing department can prioritize organizing topics related to the field situation. This allows for the prioritization of highly relevant content by considering the speakers' geographical location. Identifying geographical location information includes, for example, GPS data and location services. Some or all of the above processing in the editing department may be performed using, for example, a generative AI, or not using a generative AI. For example, the editing department can input the speakers' geographical location data into a generative AI and have the generative AI organize the highly relevant content.

[0039] The content editing unit can analyze the speakers' social media activity and organize relevant content when organizing MTG (Meeting) content. For example, the editing unit can prioritize topics that speakers frequently mention on social media. The editing unit can also consider industry trends that speakers follow on social media when organizing content. The editing unit can organize relevant topics based on information shared by speakers on social media. This allows for the prioritization of relevant content by analyzing speakers' social media activity. Analysis of social media activity includes, for example, analyzing the content of posts and evaluating activity frequency. Some or all of the above processing in the editing unit may be performed using, for example, generative AI, or not using generative AI. For example, the editing unit can input speakers' social media data into a generative AI and have the generative AI organize relevant content.

[0040] The extraction unit can improve the accuracy of its extraction by referring to past meeting data when extracting issues and resolutions. For example, the extraction unit can extract relevant issues based on issues that were frequently discussed in past meetings. The extraction unit can extract relevant resolutions by referring to resolutions made in past meetings. The extraction unit can analyze past meeting data, find patterns, and improve the accuracy of its extraction. Thus, the accuracy of the extraction is improved by referring to past meeting data. Referring to past meeting data includes, for example, building a database and methods for searching the data. Some or all of the above processing in the extraction unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the extraction unit can input past meeting data into a generation AI and have the generation AI perform the task of improving the accuracy of the extraction.

[0041] The extraction unit can apply different extraction algorithms to each agenda item when extracting issues and resolutions. For example, for technical agenda items, the extraction unit can apply an extraction algorithm that includes technical details. For business strategy agenda items, the extraction unit can apply an extraction algorithm that concisely summarizes the key points. For project progress agenda items, the extraction unit can apply an algorithm that extracts progress in chronological order. By applying different extraction algorithms to each agenda item, more appropriate content can be extracted. The extraction algorithms include, for example, the classification method and the algorithm to be used for each agenda item. Some or all of the above processing in the extraction unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the extraction unit can input data for each agenda item into a generative AI and have the generative AI execute the application of the extraction algorithm.

[0042] The extraction unit can prioritize extracting highly relevant content by considering the speaker's geographical location when extracting discussion points and resolutions. For example, if a speaker is participating from a remote location, the extraction unit will prioritize extracting their statements. If a speaker is participating from headquarters, the extraction unit can prioritize extracting discussion points and resolutions related to headquarters. If a speaker is participating from a field, the extraction unit can prioritize extracting discussion points and resolutions related to the field situation. This allows for the priority extraction of highly relevant content by considering the speaker's geographical location. Identifying geographical location information includes, for example, GPS data and location information services. Some or all of the above processing in the extraction unit may be performed using, for example, a generation AI, or without a generation AI. For example, the extraction unit can input the speaker's geographical location data into a generation AI and have the generation AI perform the extraction of highly relevant content.

[0043] The extraction unit can analyze the speaker's social media activity and extract relevant content when extracting issues and resolutions. For example, the extraction unit can prioritize extracting topics that the speaker frequently mentions on social media. The extraction unit can also consider industry trends that the speaker follows on social media when extracting content. The extraction unit can extract relevant issues and resolutions based on information shared by the speaker on social media. This allows for the priority extraction of relevant content by analyzing the speaker's social media activity. Analysis of social media activity includes, for example, analyzing the content of posts and evaluating the frequency of activity. Some or all of the above processing in the extraction unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the extraction unit can input the speaker's social media data into a generative AI and have the generative AI perform the extraction of relevant content.

[0044] The sending unit can select the optimal sending timing when sending invitations by referring to the attendance history of past participants. For example, the sending unit can send invitations based on the time slot in the past when participants had the highest attendance rate. The sending unit can analyze past attendance history and select the timing when participants are most likely to attend. The sending unit can refer to past attendance history to select the day of the week and time slot when participants are most likely to attend. In this way, the optimal sending timing can be selected by referring to past attendance history. Referring to attendance history includes, for example, building a database and methods for searching the history. Some or all of the above processing in the sending unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the sending unit can input past attendance history data into a generation AI and have the generation AI perform the selection of the optimal sending timing.

[0045] The sending unit can customize the content of invitations based on the participant's job title and area of ​​expertise. For example, if the participant is a senior manager, the sending unit can send a concise invitation summarizing the key points. If the participant is a specialist, the sending unit can send an invitation that includes technical details. If the participant is a new employee, the sending unit can send an invitation that includes basic explanations. This allows for the sending of more appropriate invitations by customizing the content according to the participant's job title and area of ​​expertise. Identifying job titles and areas of expertise includes, for example, job hierarchy and area of ​​expertise classification. Some or all of the above processing in the sending unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the sending unit can input data on the participant's job title and area of ​​expertise into a generative AI and have the generative AI perform the customization of the invitation content.

[0046] The sending unit can select the optimal sending method when sending invitations, taking into account the participant's geographical location information. For example, if the participant is in a remote location, the sending unit can send an invitation to an online meeting. If the participant is at the head office, the sending unit can send an invitation to an in-person meeting. If the participant is on-site, the sending unit can send an invitation to an on-site meeting. This allows the sending unit to select the optimal sending method by considering the participant's geographical location information. Identifying geographical location information includes, for example, GPS data or location services. Some or all of the above processing in the sending unit may be performed using, for example, a generative AI, or without a generative AI. For example, the sending unit can input the participant's geographical location data into a generative AI and have the generative AI select the optimal sending method.

[0047] The sending unit can analyze participants' social media activity and send relevant content when sending invitations. For example, the sending unit can send invitations that include topics frequently mentioned by participants on social media. The sending unit can send invitations that take into account industry trends that participants follow on social media. The sending unit can send invitations that include relevant content based on information shared by participants on social media. This allows the sending unit to send invitations that include relevant content by analyzing participants' social media activity. Analysis of social media activity includes, for example, analyzing the content of posts and evaluating activity frequency. Some or all of the above processing in the sending unit may be performed, for example, using generative AI, or not using generative AI. For example, the sending unit can input participants' social media data into a generative AI and have the generative AI perform the sending of relevant content.

[0048] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0049] The extraction unit can extract important information by referring to the speaker's past speaking history when extracting MTG content. For example, it can extract relevant points of discussion based on topics the speaker has frequently mentioned in the past. It can also extract relevant resolutions by referring to matters the speaker has previously resolved. Furthermore, it can improve the accuracy of extraction by analyzing the speaker's past speaking patterns. In this way, the accuracy of extraction is improved by referring to the speaker's past speaking history.

[0050] The sending unit can select the optimal sending timing for invitations by referring to participants' past attendance history. For example, invitations can be sent based on the time slot in the past when participants had the highest attendance rate. Furthermore, past attendance history can be analyzed to select the time when participants are most likely to attend. Additionally, past attendance history can be used to select the day of the week and time slot when participants are most likely to attend. This allows for the selection of the optimal sending timing by referring to past attendance history.

[0051] The editing department can adjust the level of detail in meeting minutes based on the speaker's position and area of ​​expertise when organizing meeting content. For example, if the speaker is a senior manager, minutes can be created that concisely summarize the key points. If the speaker is an expert, minutes can be created that include technical details. Furthermore, if the speaker is a new employee, minutes can be created that include basic explanations. By adjusting the level of detail in the minutes according to the speaker's position and area of ​​expertise, more appropriate minutes can be created.

[0052] The sending unit can customize the content of invitations based on the participant's position and area of ​​expertise. For example, if the participant is a senior manager, a concise invitation summarizing the key points can be sent. If the participant is a specialist, an invitation including technical details can be sent. Furthermore, if the participant is a new employee, an invitation including basic explanations can be sent. This allows for the sending of more appropriate invitations by customizing the content according to the participant's position and area of ​​expertise.

[0053] The organization department can apply different organization algorithms to each agenda item when organizing the contents of meetings. For example, for technical agenda items, an organization algorithm that includes detailed technical information can be applied. For business strategy agenda items, an organization algorithm that concisely summarizes the key points can be applied. Furthermore, for project progress agenda items, an algorithm that organizes the progress status chronologically can be applied. By applying different organization algorithms to each agenda item, more appropriate meeting minutes can be created.

[0054] The extraction unit can improve the accuracy of its extraction of issues and resolutions by referring to past meeting data. For example, it can extract related issues based on issues that were frequently discussed in past meetings. It can also extract related resolutions by referring to resolutions made in past meetings. Furthermore, it can analyze past meeting data to find patterns and improve the accuracy of its extraction. In this way, the accuracy of extraction is improved by referring to past meeting data.

[0055] The sending unit can select the optimal sending method when sending invitations, taking into account the participant's geographical location. For example, if a participant is in a remote location, an invitation to an online meeting can be sent. If the participant is at the head office, an invitation to an in-person meeting can be sent. Furthermore, if the participant is on-site, an invitation to an on-site meeting can be sent. This allows the system to select the optimal sending method by considering the participant's geographical location.

[0056] The following briefly describes the processing flow for example form 1.

[0057] Step 1: The organization department organizes the contents of the meeting. For example, the organization department creates meeting minutes and categorizes information by agenda item. The organization department can also determine the importance of the information and prioritize its organization. Furthermore, the organization department can use AI and speech recognition technology to convert the meeting audio data into text data, automatically transcribing the spoken content into text and creating meeting minutes. Step 2: The extraction unit extracts the discussion points and resolutions for the next meeting based on the content organized by the organization unit. For example, the extraction unit performs text analysis to extract important discussion points and resolutions. The extraction unit can use AI and natural language processing technology to analyze text data and extract important information. Step 3: The sending unit sends invitations to the necessary participants based on the issues and resolutions extracted by the extraction unit. For example, the sending unit checks participants' calendars and sends invitations using an algorithm to find a date and time when everyone can attend. The sending unit can use AI to check participants' calendars and select the optimal date and time.

[0058] (Example of form 2) The MTG management system according to an embodiment of the present invention is a system that organizes the content of a meeting after it has been held, summarizes the discussion points and resolutions for the next meeting, and sends invitations to the necessary participants. This system utilizes AI to automate tasks related to meetings, allowing employees without secretaries to focus on their core responsibilities. First, after the meeting ends, the AI ​​uses speech recognition technology to create meeting minutes and performs text analysis to extract the discussion points and resolutions for the next meeting. Next, the AI ​​checks the participants' calendars and uses an algorithm to find a date and time when everyone can attend to send invitations. This system automates the following tasks: 1. Coordinating participants' schedules, 2. Preparing the content of the meeting, and 3. Creating meeting minutes. As a result, employees without secretaries can work as if they had one. Thus, the MTG management system can organize the content of a meeting, extract the discussion points and resolutions for the next meeting, and send invitations to the necessary participants.

[0059] The MTG management system according to this embodiment comprises a sorting unit, an extraction unit, and a transmission unit. The sorting unit sorts the contents of the MTG. For example, the sorting unit creates minutes of the MTG and classifies the information by agenda item. The sorting unit can also determine the importance of the information and sort important information with priority. The sorting unit can use AI and speech recognition technology to create minutes. For example, the sorting unit takes audio data of the MTG as input and converts it into text data using speech recognition technology. The sorting unit can use speech recognition technology to automatically transcribe the spoken content into text and create minutes. The extraction unit extracts the issues and resolutions for the next MTG based on the contents sorted by the sorting unit. For example, the extraction unit performs text analysis and extracts important issues and resolutions. The extraction unit can use AI and natural language processing technology to perform text analysis. For example, the extraction unit takes text data as input and extracts important information using natural language processing technology. The extraction unit performs text analysis and can automatically extract the issues and resolutions for the next MTG. The sending unit sends invitations to the necessary participants based on the issues and resolutions extracted by the extraction unit. The sending unit sends invitations using an algorithm to check participants' calendars and find a date and time when everyone can attend. The sending unit can use AI to check participants' calendars and select the optimal date and time. For example, the sending unit takes participants' calendar data as input and sends invitations using an algorithm to select the optimal date and time. The sending unit can check participants' calendars and send invitations for a date and time when everyone can attend. As a result, the MTG management system according to this embodiment can organize the contents of the MTG, extract the issues and resolutions for the next meeting, and send invitations to the necessary participants.

[0060] The editing department organizes the content of meetings. For example, the editing department creates meeting minutes and categorizes information by topic. Specifically, it collects meeting audio data and converts it into text data using speech recognition technology. Speech recognition technology can identify the speaker's voice and accurately transcribe the content of the speech into text. The editing department analyzes the transcribed data and categorizes the information by topic. For example, it analyzes the content of the speech, extracts relevant information for each topic, and creates meeting minutes. The editing department can also determine the importance of the information and prioritize organizing important information. Factors considered in determining importance include the frequency of the speech, the speaker's position, and keywords in the speech. The editing department can use AI to create meeting minutes using speech recognition technology. The AI ​​analyzes the audio data and automatically transcribes the content of the speech into text. For example, the editing department takes meeting audio data as input and converts it into text data using speech recognition technology. Speech recognition technology can identify the speaker's voice and accurately transcribe the content of the speech into text. The editing department can use speech recognition technology to automatically transcribe spoken content into text and create meeting minutes. This allows the editing department to efficiently organize meeting content and create minutes. Furthermore, the editing department can save the created minutes in a database, making them searchable and referable as needed. This allows for easy reference to past meeting content, which is useful for preparing for future meetings and facilitating discussions.

[0061] The extraction unit extracts the discussion points and resolutions for the next meeting based on the content organized by the organization unit. Specifically, it takes the meeting minutes created by the organization unit as input and performs text analysis. Natural language processing (NLP) technology is used for the text analysis to analyze the content of the meeting minutes. Natural language processing technology is a technology for extracting important information from text data, and can extract keywords and understand context. The extraction unit analyzes the content of the meeting minutes and extracts the discussion points and resolutions for the next meeting. For example, it extracts important keywords from the meeting minutes and sets the agenda for the next meeting based on them. It also analyzes the content of the meeting minutes and extracts resolutions and action items. The extraction unit can use AI to perform text analysis using natural language processing technology. The AI ​​analyzes the content of the meeting minutes and automatically extracts important information. For example, the extraction unit takes text data as input and extracts important information using natural language processing technology. Natural language processing technology extracts important keywords and phrases from the text data and sets the agenda and resolutions for the next meeting based on them. This allows the extraction unit to efficiently extract the discussion points and resolutions for the next meeting based on the content organized by the organization unit. Furthermore, the extraction unit can store the extracted information in a database, which can be used to prepare for the next meeting and facilitate the discussion. As a result, the extraction unit can efficiently extract the discussion points and resolutions for the next meeting, enabling smooth preparation and progress of the meeting.

[0062] The sending unit sends invitations to the necessary participants based on the discussion points and resolutions extracted by the extraction unit. Specifically, it takes the discussion points and resolutions for the next meeting extracted by the extraction unit as input and checks the participants' calendars. The sending unit obtains the participants' calendar data and uses an algorithm to find a date and time when everyone can attend. For example, the sending unit takes the participants' calendar data as input and sends invitations using an algorithm that selects the optimal date and time. The algorithm analyzes the participants' schedules and identifies a date and time when everyone can attend. The sending unit creates an invitation based on the identified date and time and sends it to the participants. The invitation includes information such as the date, time, location, agenda, and resolutions for the next meeting. The sending unit can use AI to check participants' calendars and select the optimal date and time. The AI ​​analyzes the participants' schedules and identifies a date and time when everyone can attend. For example, the sending unit takes the participants' calendar data as input and sends invitations using an algorithm that selects the optimal date and time. This allows the sending unit to check participants' calendars and send invitations at a date and time when everyone can attend. Furthermore, the sending unit can manage the status of invitation delivery and confirm responses from participants. This allows the sending unit to efficiently schedule the next meeting and hold the meeting at a time that is convenient for all participants.

[0063] The editing unit can create meeting minutes using speech recognition technology. For example, the editing unit can take audio data from a meeting as input and convert it into text data using speech recognition technology. The editing unit can automatically transcribe spoken content into text and create meeting minutes using speech recognition technology. For example, the editing unit can transcribe spoken content into text in real time using a speech recognition algorithm. The editing unit can transcribe spoken content with high accuracy using speech recognition technology. This automates the creation of meeting minutes by using speech recognition technology. Speech recognition technology includes, for example, deep learning-based speech recognition algorithms and specific speech recognition software. Some or all of the above processes in the editing unit may be performed using, for example, generative AI, or without generative AI. For example, the editing unit can input audio data into a generative AI and have the generative AI generate text data from the audio data.

[0064] The extraction unit can perform text analysis and extract the issues and resolutions for the next meeting. For example, the extraction unit takes text data as input and uses natural language processing techniques to extract important information. The extraction unit can perform text analysis and automatically extract the issues and resolutions for the next meeting. For example, the extraction unit uses natural language processing algorithms to extract important information from text data. The extraction unit can analyze text data using natural language processing techniques and extract important issues and resolutions. This allows for the automatic extraction of issues and resolutions for the next meeting through text analysis. Natural language processing techniques include, for example, topic modeling, keyword extraction, and document classification. Some or all of the above-described processes in the extraction unit may be performed using, for example, generative AI, or without generative AI. For example, the extraction unit can input text data into a generative AI and have the generative AI perform the extraction of important information.

[0065] The sending unit can check participants' calendars and send invitations using an algorithm to find a date and time when everyone can attend. For example, the sending unit can take participants' calendar data as input and send invitations using an algorithm to select the optimal date and time. The sending unit can check participants' calendars and send invitations at a date and time when everyone can attend. For example, the sending unit can use a calendar checking algorithm to analyze participants' calendars and select the optimal date and time. The sending unit can use an optimization algorithm to find a date and time when everyone can attend. This allows the sending unit to send invitations at a date and time when everyone can attend by checking participants' calendars. Some or all of the above processing in the sending unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the sending unit can input participants' calendar data into a generative AI and have the generative AI select the optimal date and time.

[0066] The editing unit can estimate the user's emotions and adjust the way the meeting minutes are presented based on the estimated emotions. For example, if the user is stressed, the editing unit can create concise and to-the-point minutes. If the user is relaxed, the editing unit can create minutes that include detailed explanations. If the user is in a hurry, the editing unit can create minutes in a bulleted list format that can be quickly understood. This allows for the creation of more appropriate minutes by adjusting the presentation of the minutes according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the editing unit may be performed using or without a generative AI. For example, the editing unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0067] The editing department can adjust the level of detail in meeting minutes based on the speaker's position and area of ​​expertise when organizing the content of a meeting. For example, if the speaker is a senior manager, the editing department can create minutes that concisely summarize the key points. If the speaker is an expert, the editing department can create minutes that include technical details. If the speaker is a new employee, the editing department can create minutes that include basic explanations. By adjusting the level of detail in the minutes according to the speaker's position and area of ​​expertise, more appropriate minutes can be created. Identifying positions and areas of expertise includes, for example, hierarchical positions and classifications of areas of expertise. Some or all of the above processing in the editing department may be performed using, for example, a generating AI, or not using a generating AI. For example, the editing department can input data on the speaker's position and area of ​​expertise into a generating AI and have the generating AI perform the adjustment of the level of detail in the meeting minutes.

[0068] The organization unit can apply different organization algorithms to each agenda item when organizing the contents of a meeting. For example, for a technical agenda item, the organization unit can apply an organization algorithm that includes detailed technical information. For a business strategy agenda item, the organization unit can apply an organization algorithm that concisely summarizes the key points. For a project progress agenda item, the organization unit can apply an algorithm that organizes the progress status chronologically. By applying different organization algorithms to each agenda item, more appropriate meeting minutes can be created. Organization algorithms include, for example, the classification method and the algorithm to be used for each agenda item. Some or all of the above processing in the organization unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the organization unit can input data for each agenda item into a generative AI and have the generative AI execute the application of the organization algorithm.

[0069] The organization unit can estimate the user's emotions and prioritize meeting minutes based on those emotions. For example, if the user is stressed, the organization unit will prioritize important agenda items. If the user is relaxed, the organization unit can prioritize all agenda items equally. If the user is in a hurry, the organization unit can prioritize agenda items that are directly relevant to the next meeting. This allows for prioritizing important agenda items by determining the priority of meeting minutes according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the organization unit may be performed using or without a generative AI. For example, the organization unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0070] The editing department can prioritize organizing the content of a meeting by considering the geographical location of the speakers. For example, if a speaker is participating from a remote location, the editing department will prioritize organizing their comments. If a speaker is participating from headquarters, the editing department can prioritize organizing topics related to headquarters. If a speaker is participating from a field, the editing department can prioritize organizing topics related to the field situation. This allows for the prioritization of highly relevant content by considering the speakers' geographical location. Identifying geographical location information includes, for example, GPS data and location services. Some or all of the above processing in the editing department may be performed using, for example, a generative AI, or not using a generative AI. For example, the editing department can input the speakers' geographical location data into a generative AI and have the generative AI organize the highly relevant content.

[0071] The content editing unit can analyze the speakers' social media activity and organize relevant content when organizing MTG (Meeting) content. For example, the editing unit can prioritize topics that speakers frequently mention on social media. The editing unit can also consider industry trends that speakers follow on social media when organizing content. The editing unit can organize relevant topics based on information shared by speakers on social media. This allows for the prioritization of relevant content by analyzing speakers' social media activity. Analysis of social media activity includes, for example, analyzing the content of posts and evaluating activity frequency. Some or all of the above processing in the editing unit may be performed using, for example, generative AI, or not using generative AI. For example, the editing unit can input speakers' social media data into a generative AI and have the generative AI organize relevant content.

[0072] The extraction unit can estimate the user's emotions and adjust the way the extracted points and resolutions are presented based on the estimated user emotions. For example, if the user is stressed, the extraction unit can use a concise and to-the-point presentation. If the user is relaxed, the extraction unit can use a presentation that includes detailed explanations. If the user is in a hurry, the extraction unit can use a bulleted list format that can be quickly understood. This allows for the extraction of more appropriate content by adjusting the presentation of points and resolutions according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the extraction unit may be performed using a generative AI, or not. For example, the extraction unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0073] The extraction unit can improve the accuracy of its extraction by referring to past meeting data when extracting issues and resolutions. For example, the extraction unit can extract relevant issues based on issues that were frequently discussed in past meetings. The extraction unit can extract relevant resolutions by referring to resolutions made in past meetings. The extraction unit can analyze past meeting data, find patterns, and improve the accuracy of its extraction. Thus, the accuracy of the extraction is improved by referring to past meeting data. Referring to past meeting data includes, for example, building a database and methods for searching the data. Some or all of the above processing in the extraction unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the extraction unit can input past meeting data into a generation AI and have the generation AI perform the task of improving the accuracy of the extraction.

[0074] The extraction unit can apply different extraction algorithms to each agenda item when extracting issues and resolutions. For example, for technical agenda items, the extraction unit can apply an extraction algorithm that includes technical details. For business strategy agenda items, the extraction unit can apply an extraction algorithm that concisely summarizes the key points. For project progress agenda items, the extraction unit can apply an algorithm that extracts progress in chronological order. By applying different extraction algorithms to each agenda item, more appropriate content can be extracted. The extraction algorithms include, for example, the classification method and the algorithm to be used for each agenda item. Some or all of the above processing in the extraction unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the extraction unit can input data for each agenda item into a generative AI and have the generative AI execute the application of the extraction algorithm.

[0075] The extraction unit can estimate the user's emotions and determine the priority of the issues and resolutions to be extracted based on the estimated emotions. For example, if the user is stressed, the extraction unit will prioritize extracting important issues and resolutions. If the user is relaxed, the extraction unit can extract all issues and resolutions equally. If the user is in a hurry, the extraction unit can prioritize extracting issues and resolutions that are directly relevant to the next meeting. In this way, by determining the priority of issues and resolutions according to the user's emotions, important content can be extracted preferentially. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the extraction unit may be performed using a generative AI, or not using a generative AI. For example, the extraction unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0076] The extraction unit can prioritize extracting highly relevant content by considering the speaker's geographical location when extracting discussion points and resolutions. For example, if a speaker is participating from a remote location, the extraction unit will prioritize extracting their statements. If a speaker is participating from headquarters, the extraction unit can prioritize extracting discussion points and resolutions related to headquarters. If a speaker is participating from a field, the extraction unit can prioritize extracting discussion points and resolutions related to the field situation. This allows for the priority extraction of highly relevant content by considering the speaker's geographical location. Identifying geographical location information includes, for example, GPS data and location information services. Some or all of the above processing in the extraction unit may be performed using, for example, a generation AI, or without a generation AI. For example, the extraction unit can input the speaker's geographical location data into a generation AI and have the generation AI perform the extraction of highly relevant content.

[0077] The extraction unit can analyze the speaker's social media activity and extract relevant content when extracting issues and resolutions. For example, the extraction unit can prioritize extracting topics that the speaker frequently mentions on social media. The extraction unit can also consider industry trends that the speaker follows on social media when extracting content. The extraction unit can extract relevant issues and resolutions based on information shared by the speaker on social media. This allows for the priority extraction of relevant content by analyzing the speaker's social media activity. Analysis of social media activity includes, for example, analyzing the content of posts and evaluating the frequency of activity. Some or all of the above processing in the extraction unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the extraction unit can input the speaker's social media data into a generative AI and have the generative AI perform the extraction of relevant content.

[0078] The sending unit can estimate the user's emotions and adjust the way the invitation is presented based on the estimated emotions. For example, if the user is stressed, the sending unit can send a concise and to-the-point invitation. If the user is relaxed, the sending unit can send an invitation with detailed explanations. If the user is in a hurry, the sending unit can send an invitation in bullet points that can be quickly understood. This allows for the sending of more appropriate invitations by adjusting the way the invitation is presented according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the sending unit may be performed using a generative AI, or not. For example, the sending unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0079] The sending unit can select the optimal sending timing when sending invitations by referring to the attendance history of past participants. For example, the sending unit can send invitations based on the time slot in the past when participants had the highest attendance rate. The sending unit can analyze past attendance history and select the timing when participants are most likely to attend. The sending unit can refer to past attendance history to select the day of the week and time slot when participants are most likely to attend. In this way, the optimal sending timing can be selected by referring to past attendance history. Referring to attendance history includes, for example, building a database and methods for searching the history. Some or all of the above processing in the sending unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the sending unit can input past attendance history data into a generation AI and have the generation AI perform the selection of the optimal sending timing.

[0080] The sending unit can customize the content of invitations based on the participant's job title and area of ​​expertise. For example, if the participant is a senior manager, the sending unit can send a concise invitation summarizing the key points. If the participant is a specialist, the sending unit can send an invitation that includes technical details. If the participant is a new employee, the sending unit can send an invitation that includes basic explanations. This allows for the sending of more appropriate invitations by customizing the content according to the participant's job title and area of ​​expertise. Identifying job titles and areas of expertise includes, for example, job hierarchy and area of ​​expertise classification. Some or all of the above processing in the sending unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the sending unit can input data on the participant's job title and area of ​​expertise into a generative AI and have the generative AI perform the customization of the invitation content.

[0081] The sending unit can estimate the user's emotions and determine the priority of invitations based on the estimated emotions. For example, if the user is stressed, the sending unit can prioritize sending important invitations. If the user is relaxed, the sending unit can send all invitations equally. If the user is in a hurry, the sending unit can prioritize sending invitations that directly relate to the next meeting. This allows important invitations to be sent preferentially by determining the priority of invitations according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the sending unit may be performed using a generative AI, or not using a generative AI. For example, the sending unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0082] The sending unit can select the optimal sending method when sending invitations, taking into account the participant's geographical location information. For example, if the participant is in a remote location, the sending unit can send an invitation to an online meeting. If the participant is at the head office, the sending unit can send an invitation to an in-person meeting. If the participant is on-site, the sending unit can send an invitation to an on-site meeting. This allows the sending unit to select the optimal sending method by considering the participant's geographical location information. Identifying geographical location information includes, for example, GPS data or location services. Some or all of the above processing in the sending unit may be performed using, for example, a generative AI, or without a generative AI. For example, the sending unit can input the participant's geographical location data into a generative AI and have the generative AI select the optimal sending method.

[0083] The sending unit can analyze participants' social media activity and send relevant content when sending invitations. For example, the sending unit can send invitations that include topics frequently mentioned by participants on social media. The sending unit can send invitations that take into account industry trends that participants follow on social media. The sending unit can send invitations that include relevant content based on information shared by participants on social media. This allows the sending unit to send invitations that include relevant content by analyzing participants' social media activity. Analysis of social media activity includes, for example, analyzing the content of posts and evaluating activity frequency. Some or all of the above processing in the sending unit may be performed, for example, using generative AI, or not using generative AI. For example, the sending unit can input participants' social media data into a generative AI and have the generative AI perform the sending of relevant content.

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

[0085] The editing department can analyze the speakers' speaking style and tone when organizing meeting content, and adjust the way the minutes are written accordingly. For example, they can highlight points emphasized by speakers as important information. They can also carefully organize emotionally spoken content. Furthermore, they can concisely summarize lengthy statements made by speakers. By adjusting the way minutes are written according to the speakers' speaking style and tone, they can create more appropriate meeting minutes.

[0086] The extraction unit can extract important information by referring to the speaker's past speaking history when extracting MTG content. For example, it can extract relevant points of discussion based on topics the speaker has frequently mentioned in the past. It can also extract relevant resolutions by referring to matters the speaker has previously resolved. Furthermore, it can improve the accuracy of extraction by analyzing the speaker's past speaking patterns. In this way, the accuracy of extraction is improved by referring to the speaker's past speaking history.

[0087] The sending unit can select the optimal sending timing for invitations by referring to participants' past attendance history. For example, invitations can be sent based on the time slot in the past when participants had the highest attendance rate. Furthermore, past attendance history can be analyzed to select the time when participants are most likely to attend. Additionally, past attendance history can be used to select the day of the week and time slot when participants are most likely to attend. This allows for the selection of the optimal sending timing by referring to past attendance history.

[0088] The editing department can adjust the level of detail in meeting minutes based on the speaker's position and area of ​​expertise when organizing meeting content. For example, if the speaker is a senior manager, minutes can be created that concisely summarize the key points. If the speaker is an expert, minutes can be created that include technical details. Furthermore, if the speaker is a new employee, minutes can be created that include basic explanations. By adjusting the level of detail in the minutes according to the speaker's position and area of ​​expertise, more appropriate minutes can be created.

[0089] The extraction unit can estimate the user's emotions and adjust the way the extracted points and resolutions are presented based on those emotions. For example, if the user is stressed, a concise and to-the-point expression can be used. If the user is relaxed, an expression that includes detailed explanations can be used. Furthermore, if the user is in a hurry, a bulleted list format that can be quickly understood can be used. By adjusting the way the points and resolutions are presented according to the user's emotions, more appropriate content can be extracted.

[0090] The sending unit can customize the content of invitations based on the participant's position and area of ​​expertise. For example, if the participant is a senior manager, a concise invitation summarizing the key points can be sent. If the participant is a specialist, an invitation including technical details can be sent. Furthermore, if the participant is a new employee, an invitation including basic explanations can be sent. This allows for the sending of more appropriate invitations by customizing the content according to the participant's position and area of ​​expertise.

[0091] The organization department can apply different organization algorithms to each agenda item when organizing the contents of meetings. For example, for technical agenda items, an organization algorithm that includes detailed technical information can be applied. For business strategy agenda items, an organization algorithm that concisely summarizes the key points can be applied. Furthermore, for project progress agenda items, an algorithm that organizes the progress status chronologically can be applied. By applying different organization algorithms to each agenda item, more appropriate meeting minutes can be created.

[0092] The extraction unit can improve the accuracy of its extraction of issues and resolutions by referring to past meeting data. For example, it can extract related issues based on issues that were frequently discussed in past meetings. It can also extract related resolutions by referring to resolutions made in past meetings. Furthermore, it can analyze past meeting data to find patterns and improve the accuracy of its extraction. In this way, the accuracy of extraction is improved by referring to past meeting data.

[0093] The sending unit can estimate the user's emotions and adjust the way the invitation is presented based on those emotions. For example, if the user is stressed, a concise and to-the-point invitation can be sent. If the user is relaxed, an invitation with detailed explanations can be sent. Furthermore, if the user is in a hurry, an invitation in bullet points that can be quickly understood can be sent. In this way, by adjusting the way the invitation is presented according to the user's emotions, a more appropriate invitation can be sent.

[0094] The sending unit can select the optimal sending method when sending invitations, taking into account the participant's geographical location. For example, if a participant is in a remote location, an invitation to an online meeting can be sent. If the participant is at the head office, an invitation to an in-person meeting can be sent. Furthermore, if the participant is on-site, an invitation to an on-site meeting can be sent. This allows the system to select the optimal sending method by considering the participant's geographical location.

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

[0096] Step 1: The organization department organizes the contents of the meeting. For example, the organization department creates meeting minutes and categorizes information by agenda item. The organization department can also determine the importance of the information and prioritize its organization. Furthermore, the organization department can use AI and speech recognition technology to convert the meeting audio data into text data, automatically transcribing the spoken content into text and creating meeting minutes. Step 2: The extraction unit extracts the discussion points and resolutions for the next meeting based on the content organized by the organization unit. For example, the extraction unit performs text analysis to extract important discussion points and resolutions. The extraction unit can use AI and natural language processing technology to analyze text data and extract important information. Step 3: The sending unit sends invitations to the necessary participants based on the issues and resolutions extracted by the extraction unit. For example, the sending unit checks participants' calendars and sends invitations using an algorithm to find a date and time when everyone can attend. The sending unit can use AI to check participants' calendars and select the optimal date and time.

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

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

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

[0100] Each of the multiple elements described above, including the organizing unit, extraction unit, and transmission unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the organizing unit is implemented by the control unit 46A of the smart device 14 and creates meeting minutes using speech recognition technology. The extraction unit is implemented by the identification processing unit 290 of the data processing device 12 and extracts the discussion points and resolutions for the next meeting using natural language processing technology. The transmission unit is implemented by the identification processing unit 290 of the data processing device 12 and sends invitations after checking the participants' calendars. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0116] Each of the multiple elements described above, including the organizing unit, extraction unit, and transmission unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing device 12. For example, the organizing unit is implemented by the control unit 46A of the smart glasses 214 and uses speech recognition technology to create meeting minutes. The extraction unit is implemented, for example, by the identification processing unit 290 of the data processing device 12 and uses natural language processing technology to extract the discussion points and resolutions for the next meeting. The transmission unit is implemented, for example, by the identification processing unit 290 of the data processing device 12 and checks the participants' calendars to send invitations. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0132] Each of the multiple elements described above, including the organizing unit, extraction unit, and transmission unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the organizing unit is implemented by the control unit 46A of the headset terminal 314 and creates meeting minutes using speech recognition technology. The extraction unit is implemented by the identification processing unit 290 of the data processing unit 12 and extracts the discussion points and resolutions for the next meeting using natural language processing technology. The transmission unit is implemented by the identification processing unit 290 of the data processing unit 12 and sends invitations after checking the participants' calendars. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0149] Each of the multiple elements described above, including the organizing unit, extraction unit, and transmission unit, is implemented, for example, by at least one of the robot 414 and the data processing unit 12. For example, the organizing unit is implemented by the control unit 46A of the robot 414 and creates meeting minutes using speech recognition technology. The extraction unit is implemented by the identification processing unit 290 of the data processing unit 12 and extracts the discussion points and resolutions for the next meeting using natural language processing technology. The transmission unit is implemented by the identification processing unit 290 of the data processing unit 12 and sends invitations after checking the participants' calendars. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

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

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

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

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

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

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

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

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

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

[0159] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

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

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

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

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

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

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

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

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

[0168] (Note 1) A section for organizing the contents of MTG, Based on the content organized by the aforementioned organizing unit, an extraction unit extracts the discussion points and resolutions for the next meeting. A transmission unit sends invitations to the necessary participants based on the issues and resolutions extracted by the extraction unit, Equipped with A system characterized by the following features. (Note 2) The aforementioned editing unit, Create meeting minutes using speech recognition technology The system described in Appendix 1, characterized by the features described herein. (Note 3) The extraction unit is Perform text analysis to extract the next discussion points and resolutions. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned transmitting unit We check participants' calendars and use an algorithm to find a time and date when everyone is available to send out invitations. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned editing unit, The system estimates the user's emotions and adjusts the way the meeting minutes are written based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned editing unit, When organizing the contents of a meeting, adjust the level of detail in the minutes based on the speaker's role and area of ​​expertise. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned editing unit, When organizing the contents of a meeting, a different organizational algorithm is applied to each topic. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned editing unit, It estimates user sentiment and determines the priority of meeting minutes based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned editing unit, When organizing the contents of a meeting, prioritize and organize the most relevant information by considering the geographical location of the speakers. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned editing unit, When organizing the content of a meeting, analyze the social media activity of the speakers and organize the relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 11) The extraction unit is We estimate the user's emotions and adjust the way the issues and resolutions are expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The extraction unit is When extracting issues and resolutions, we refer to past meeting data to improve the accuracy of the extraction. The system described in Appendix 1, characterized by the features described herein. (Note 13) The extraction unit is When extracting issues and resolutions, a different extraction algorithm is applied to each agenda item. The system described in Appendix 1, characterized by the features described herein. (Note 14) The extraction unit is We estimate user sentiment and determine the priority of issues and resolutions to be extracted based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 15) The extraction unit is When extracting discussion points and resolutions, the geographical location of the speakers is taken into consideration to prioritize the extraction of highly relevant content. The system described in Appendix 1, characterized by the features described herein. (Note 16) The extraction unit is When extracting points of discussion or resolutions, we analyze the social media activity of the speakers and extract relevant content. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned transmitting unit It estimates the user's emotions and adjusts the way the invitation is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned transmitting unit When sending invitations, the system selects the optimal sending timing by referring to the attendance history of past participants. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned transmitting unit When sending out invitations, customize the content based on the participant's role and area of ​​expertise. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned transmitting unit The system estimates the user's emotions and prioritizes invitations based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned transmitting unit When sending out invitations, the optimal sending method is selected considering the geographical location of the participants. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned transmitting unit When sending out invitations, we analyze participants' social media activity and send them relevant content. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

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

Claims

1. A section for organizing the contents of MTG, Based on the content organized by the aforementioned organizing unit, an extraction unit extracts the discussion points and resolutions for the next meeting. A transmission unit sends invitations to the necessary participants based on the issues and resolutions extracted by the extraction unit, Equipped with A system characterized by the following features.

2. The aforementioned editing unit, Create meeting minutes using speech recognition technology The system according to feature 1.

3. The extraction unit is Perform text analysis to extract the next discussion points and resolutions. The system according to feature 1.

4. The aforementioned transmitting unit We check participants' calendars and use an algorithm to find a time and date when everyone is available to send out invitations. The system according to feature 1.

5. The aforementioned editing unit, The system estimates the user's emotions and adjusts the way the meeting minutes are written based on those estimated emotions. The system according to feature 1.

6. The aforementioned editing unit, When organizing the contents of a meeting, adjust the level of detail in the minutes based on the speaker's role and area of ​​expertise. The system according to feature 1.

7. The aforementioned editing unit, When organizing the contents of a meeting, a different organizational algorithm is applied to each topic. The system according to feature 1.

8. The aforementioned editing unit, It estimates user sentiment and determines the priority of meeting minutes based on the estimated user sentiment. The system according to feature 1.

Images