System

Abstract

An object of the system according to the embodiment is to make the progress of a conference smooth and automate the creation and sharing of minutes.SOLUTION: In general, according to one embodiment, a system includes a receiver, an analyzer, a generator, a progressor, a text generator, a determiner, a minutes generator, and a sharer. The reception part inputs a goal of the conference. The analysis unit analyzes the information input by the reception unit. The generation section generates an agenda or an idea on the basis of the information analyzed by the analysis section. The progression unit grasps a progression status during the conference in real time. The text generator generates text from the speech of the participant. The decision unit clarifies a decision item and a next action at the end of the conference. The minutes creating section automatically creates minutes. The sharing part automatically shares the minutes with the conference participants.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, conducting meetings, creating minutes, and sharing them was a time-consuming process, making it difficult to do so efficiently.

[0005] The system according to the embodiment aims to facilitate smooth progress of meetings and automate the creation and sharing of minutes. [Means for solving the problem]

[0006] The system according to the embodiment comprises a reception unit, an analysis unit, a generation unit, a progress unit, a text conversion unit, a decision unit, a minutes generation unit, and a sharing unit. The reception unit inputs the goal of the meeting. The analysis unit analyzes the information input by the reception unit. The generation unit generates an agenda or ideas based on the information analyzed by the analysis unit. The progress unit grasps the progress of the meeting in real time. The text conversion unit converts participants' comments into text. The decision unit clarifies decisions and next actions at the end of the meeting. The minutes generation unit automatically creates minutes. The sharing unit automatically shares the minutes with meeting participants. [Effects of the Invention]

[0007] The system according to the embodiment can facilitate smooth progress of meetings and automate the creation and sharing of minutes. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A meeting support system according to an embodiment of the present invention is a system in which a user inputs the goal of a meeting, and a multimodal AI provides an agenda and ideas, supports the progress of the meeting, clarifies decisions and next actions at the end of the meeting, and automatically creates and shares minutes. The meeting support system inputs the goal of a meeting, and a multimodal AI provides an agenda and ideas, supporting the progress of the meeting. At the end of the meeting, the system clarifies decisions and next actions, and automatically creates and shares minutes. For example, the meeting support system inputs the goal of the meeting. For example, the meeting support system requires only that the user input the purpose of the meeting and the goals they wish to achieve. This information is input into the multimodal AI. The multimodal AI then analyzes the input information and provides an agenda and ideas. For example, the meeting support system proposes agendas such as product features, market analysis, and competitive research. It also provides ideas based on past data and trends. Next, the multimodal AI participates in the meeting as an AI assistant and supports the progress of the meeting. For example, the meeting support system monitors the progress of the meeting in real time and suggests when to move on to the next agenda item. The meeting support system also converts participants' comments into text and emphasizes important points. Next, the multimodal AI in the meeting support system clarifies decisions and next actions at the end of the meeting. For example, the meeting support system clarifies product specifications, development schedules, and responsible parties. Next, the meeting support system automatically creates minutes and shares them with meeting participants. For example, the meeting support system generates minutes immediately after the meeting and sends them to all participants by email. This allows the meeting support system to accurately record and share the contents of the meeting. This allows the meeting support system to simultaneously improve the quality of meetings and reduce meeting times. For example, meetings can proceed more smoothly and waste less time can be reduced. Furthermore, the quality of meetings is improved when AI provides agendas and ideas. This improves corporate productivity and enables more efficient meeting management.

[0029] A conference support system according to an embodiment includes a reception unit, an analysis unit, a generation unit, a progress unit, a text conversion unit, a determination unit, a minutes generation unit, and a sharing unit. The reception unit inputs the goal of the conference. The goal of the conference includes, but is not limited to, the purpose of the conference and a target to be achieved. The reception unit also supports multiple input methods, such as voice input, text input, and image input. For example, the reception unit may preferentially provide voice input to a user who prefers voice input, and preferentially provide text input to a user who prefers text input. The analysis unit analyzes the information input by the reception unit. The analysis may be based on, for example, past data and trends, but is not limited to, the analysis unit may analyze, for example, past conference records and industry trends to generate an agenda and ideas. The analysis unit may also estimate a user's emotions and adjust the method of expression of the analysis. For example, the analysis unit provides detailed analysis results when the user is relaxed, and provides concise analysis results when the user is in a hurry. The generation unit generates an agenda and ideas based on the information analyzed by the analysis unit. The generation is performed, for example, based on a list of topics and types of ideas, but is not limited to such examples. For example, the generation unit generates a technical agenda and ideas for a technical meeting, and generates a marketing-specific agenda and ideas for a marketing meeting. The generation unit can also estimate the user's emotions and adjust the generation method. For example, the generation unit generates a detailed agenda and ideas when the user is relaxed, and generates a concise agenda and ideas when the user is in a hurry. The proceeding unit grasps the progress of the meeting in real time. The progress is grasped, for example, based on progress stages and time management, but is not limited to such examples. For example, the proceeding unit monitors the progress of the meeting in real time and suggests when to move on to the next agenda item. The proceeding unit can also estimate the user's emotions and adjust the proceeding method. For example, if the user is nervous, the moderator suggests a method of proceeding that will allow the user to relax, and if the user is in a hurry, suggests a method of proceeding quickly. The text converter converts the remarks of the participants into text.The text conversion is performed based on, for example, voice recognition technology and a text format, but is not limited to these examples. The text conversion unit converts participants' speech into text using, for example, voice recognition technology and emphasizes important points. The text conversion unit can also estimate a user's emotions and adjust the text conversion method accordingly. For example, the text conversion unit may convert detailed speech into text if the user is relaxed, and convert concise speech into text if the user is in a hurry. The decision unit clarifies decisions and next actions at the end of the meeting. The clarification of decisions is performed based on, for example, the type of decision and the next action, but is not limited to these examples. The decision unit clarifies product specifications, development schedules, and responsible parties at the end of the meeting. The decision unit can also estimate a user's emotions and adjust the method of clarification of decisions. For example, the decision unit may clarify detailed decisions if the user is relaxed, and convert concise decisions if the user is in a hurry. The minutes generation unit automatically creates minutes. The automatic creation of minutes is performed based on, for example, an algorithm used and the type of information recorded, but is not limited to these examples. For example, the minutes generation unit generates minutes immediately after the end of the meeting and sends them to all participants by email. The minutes generation unit can also estimate the user's emotions and adjust the method for generating the minutes. For example, the minutes generation unit generates detailed minutes when the user is relaxed, and generates concise minutes when the user is in a hurry. The sharing unit automatically shares the minutes with the meeting participants. Automatic sharing is performed, for example, based on the sharing platform and the timing of sharing, but is not limited to these examples. For example, the sharing unit can send the minutes by email, or can upload them to cloud storage and share them. The sharing unit can also estimate the user's emotions and adjust the sharing method. For example, the sharing unit shares detailed minutes when the user is relaxed, and shares concise minutes when the user is in a hurry. As a result, the meeting support system according to the embodiment consistently supports processes from entering meeting goals to sharing the minutes, thereby improving the quality of meetings and reducing time.

[0030] The reception unit can input the purpose of the meeting and the goals to be achieved. Examples of the purpose of the meeting and the goals to be achieved include, but are not limited to, the focus of the discussion and the expected results. For example, the reception unit receives input from a user of the purpose of the meeting and the goals to be achieved. The reception unit can also support multiple input methods, such as voice input, text input, and image input. For example, the reception unit can provide voice input preferentially to a user who prefers voice input, and provide text input preferentially to a user who prefers text input. This clarifies the purpose and goals of the meeting, allowing the meeting to proceed smoothly. Some or all of the above-described processing in the reception unit can be performed using, for example, AI, or can be performed without using AI. For example, the reception unit can input the purpose of the meeting and the goals to be achieved input by the user into a generation AI, which can then analyze the input.

[0031] The analysis unit can generate an agenda or ideas based on past data or trends. Examples of past data and trends include, but are not limited to, past meeting records and industry trends. For example, the analysis unit can analyze past meeting records to generate an agenda or ideas. The analysis unit can also analyze industry trends to generate an agenda or ideas. For example, the analysis unit can generate a list of topics or types of ideas based on past meeting records. The analysis unit can also generate an agenda or ideas based on industry trends. This makes it possible to provide more effective agendas and ideas by utilizing past data and trends. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input past meeting records and industry trends into a generation AI, which then performs analysis.

[0032] The proceedings unit can grasp the progress of the meeting in real time and propose the timing to move on to the next agenda item. Understanding the progress includes, for example, but is not limited to, the stages of progress and time management. For example, the proceedings unit can monitor the progress of the meeting in real time and propose the timing to move on to the next agenda item. The proceedings unit can also grasp the stages of progress and propose the timing to move on to the next agenda item. For example, the proceedings unit can grasp the progress of the meeting in real time and propose the timing to move on to the next agenda item. The proceedings unit can also manage time and propose the timing to move on to the next agenda item. This can smooth the progress of the meeting and reduce wasted time. Some or all of the above-mentioned processing in the proceedings unit may be performed using, for example, AI, or may be performed without using AI. For example, the proceedings unit can input the progress of the meeting into a generation AI, which can then analyze it.

[0033] The text conversion unit can convert the participants' remarks into text and emphasize key points. Text conversion can include, but is not limited to, speech recognition technology and text formatting. For example, the text conversion unit can convert the participants' remarks into text and emphasize important points using speech recognition technology. The text conversion unit can also analyze the content of the remarks and highlight important keywords. For example, the text conversion unit can convert the remarks into text using speech recognition technology and highlight important keywords. The text conversion unit can also summarize the content of the remarks and provide a summary. This improves the quality of the minutes by accurately recording the content of the remarks and emphasizing important points. Some or all of the above-described processing in the text conversion unit can be performed using, for example, AI, or without AI. For example, the text conversion unit can input the participants' remarks into a generation AI, which then converts the remarks into text.

[0034] The decision unit can clarify decisions and next actions at the end of a meeting. Decisions include, but are not limited to, the type of decision and the next action. For example, the decision unit can clarify product specifications, development schedules, and responsible parties at the end of a meeting. The decision unit can also specify the next action. For example, the decision unit can specify the next action and clarify the responsible parties and deadlines at the end of a meeting. This clarifies the outcome of the meeting and specifies the next action, thereby enhancing the effectiveness of the meeting. Some or all of the above-mentioned processing in the decision unit may be performed using, or without, AI. For example, the decision unit can input decisions and next actions to a generation AI at the end of a meeting, and the generation AI can clarify them.

[0035] The minutes generation unit can automatically create minutes. Examples of automatic minutes generation include, but are not limited to, the algorithm used and the type of information recorded. For example, the minutes generation unit generates minutes immediately after the meeting ends and sends them by email to all participants. The minutes generation unit can also upload the minutes to cloud storage for sharing. For example, the minutes generation unit generates minutes immediately after the meeting ends and uploads them to cloud storage for sharing. This automates the creation of minutes, saving time and effort and ensuring accurate records. Some or all of the above-described processing in the minutes generation unit may be performed using, or without, AI. For example, the minutes generation unit can input the contents of the meeting into a generation AI, which then automatically creates minutes.

[0036] The sharing unit can automatically share the minutes with meeting participants. Automatic sharing includes, for example, the platform for sharing and the timing of sharing, but is not limited to these examples. For example, the sharing unit can send the minutes by email or upload them to cloud storage for sharing. The sharing unit can also share the minutes in real time. For example, the sharing unit generates minutes immediately after the end of the meeting and shares them in real time. In this way, by automatically sharing the minutes, information is transmitted quickly and accurately. Some or all of the above-mentioned processing in the sharing unit may be performed using, for example, AI, or may be performed without using AI. For example, the sharing unit can input the minutes into a generation AI, which then automatically shares them.

[0037] The reception unit can analyze the user's past meeting history and suggest an optimal goal input method. Past meeting history includes, for example, past agendas and participant feedback, but is not limited to these examples. The reception unit, for example, suggests a goal input method that the user used in a successful meeting in the past. The reception unit can also make suggestions to avoid goal input methods that the user used in unsuccessful meetings in the past. For example, the reception unit suggests the most effective goal input method based on the user's past meeting history. This improves the effectiveness of meetings by suggesting an optimal goal input method based on the past meeting history. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's past meeting history into a generation AI, which then performs analysis.

[0038] When inputting the meeting goals, the reception unit can perform filtering based on the user's current projects and areas of interest. Examples of current projects and areas of interest include, but are not limited to, the progress of the project and a method for identifying the area of ​​interest. For example, the reception unit can prioritize and suggest goals related to the user's current project. The reception unit can also suggest related goals based on the user's areas of interest. For example, the reception unit can suggest optimal goals based on the user's past project history. This improves the effectiveness of the meeting by suggesting optimal goals based on the user's current projects and areas of interest. Some or all of the above-described processing in the reception unit can be performed using, for example, AI, or without AI. For example, the reception unit can input data on the user's current projects and areas of interest into a generation AI, which can then perform filtering.

[0039] The reception unit can select the optimal input means depending on the user's input method when entering the meeting goal. Examples of input methods include, but are not limited to, voice input, text input, and image input. For example, if the user prefers voice input, the reception unit can prioritize voice input. Furthermore, if the user prefers text input, the reception unit can also prioritize text input. For example, if the user prefers image input, the reception unit can prioritize image input. This provides the optimal means depending on the user's input method, thereby facilitating the goal entry of the meeting. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input data on the user's input method into a generation AI, which can select the optimal input means.

[0040] When inputting meeting goals, the reception unit can prioritize inputting highly relevant goals taking into account the user's geographical location information. Examples of geographical location information include, but are not limited to, GPS data and location information identification methods. For example, if the user is in a specific area, the reception unit can prioritize inputting goals related to that area. Furthermore, if the user is on a business trip, the reception unit can prioritize inputting goals related to the business trip destination. For example, if the user is at home, the reception unit prioritizes inputting goals related to the user's home. This improves the effectiveness of the meeting by suggesting optimal goals based on the user's geographical location information. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's geographical location information to a generation AI, which can then perform analysis.

[0041] When a meeting goal is input, the reception unit can analyze the user's social media activity and suggest related goals. Social media activity includes, but is not limited to, the content of posts and the frequency of activities. For example, the reception unit can suggest goals related to topics mentioned by the user on social media. The reception unit can also analyze the user's social media activity and suggest related goals. For example, the reception unit can suggest related goals based on the activities of the user's friends on social media. This improves the effectiveness of the meeting by suggesting optimal goals based on the user's social media activity. Some or all of the above-described processing by the reception unit can be performed using, for example, AI, or without AI. For example, the reception unit can input data on the user's social media activity into a generation AI, which can then perform analysis.

[0042] The reception unit can customize the input method by reflecting the user's past feedback when inputting the meeting goal. Past feedback includes, but is not limited to, participant evaluations and areas for improvement. For example, the reception unit can prioritize providing an input method that the user previously preferred. The reception unit can also suggest an optimal input method based on the user's past feedback. For example, the reception unit can suggest an input method that avoids input methods that the user previously dissatisfied with. This improves the effectiveness of the meeting by providing an optimal input method based on the user's past feedback. Some or all of the above-described processing in the reception unit can be performed using, or without, AI. For example, the reception unit can input data of the user's past feedback into a generation AI, which can then analyze the data.

[0043] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the meeting. The importance of the meeting includes, but is not limited to, the purpose of the meeting and the roles of the participants. For example, the analysis unit provides detailed analysis results for a highly important meeting. The analysis unit can also provide concise analysis results for a less important meeting. For example, the analysis unit dynamically adjusts the level of detail of the analysis according to the importance of the meeting. This improves the effectiveness of the meeting by providing optimal analysis results according to the importance of the meeting. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the importance of the meeting into a generation AI, which then performs analysis.

[0044] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the meeting. Examples of meeting categories include, but are not limited to, business meetings and technical meetings. For example, in the case of a technical meeting, the analysis unit can apply a technical analysis algorithm. Furthermore, in the case of a marketing meeting, the analysis unit can also apply an analysis algorithm specialized for marketing. For example, in the case of a financial meeting, the analysis unit can apply an analysis algorithm specialized for financial data. This increases the effectiveness of the meeting by applying the optimal analysis algorithm depending on the category of the meeting. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the category of the meeting into a generation AI, which then performs analysis.

[0045] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. Past analysis results include, but are not limited to, past meeting records and methods for improving analysis accuracy. The analysis unit can improve the accuracy of the analysis, for example, based on analysis results previously performed by the user. The analysis unit can also analyze the user's past analysis results and propose an optimal analysis method. For example, the analysis unit can adjust the analysis algorithm by referring to the user's past analysis results. This improves the accuracy of the analysis by referring to the user's past analysis results. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can input data of the user's past analysis results into a generation AI, and the generation AI can perform the analysis.

[0046] During analysis, the analysis unit can determine the priority of analysis based on the submission time of the meeting. The submission time of the meeting includes, but is not limited to, for example, the submission deadline and the timing of submission. For example, the analysis unit prioritizes analysis for meetings with an upcoming submission deadline. The analysis unit can also postpone analysis for meetings with a distant submission deadline. For example, the analysis unit dynamically adjusts the priority of analysis according to the submission time. This improves the effectiveness of the meeting by determining the priority of analysis based on the submission time of the meeting. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the submission time of the meeting into a generation AI, and the generation AI can perform analysis.

[0047] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the meetings. The relevance of the meetings includes, but is not limited to, for example, the relevance of the agenda and the relevance of the participants. For example, the analysis unit prioritizes analysis for highly relevant meetings. Furthermore, the analysis unit can postpone analysis for less relevant meetings. For example, the analysis unit dynamically adjusts the order of analysis based on the relevance of the meetings. This improves the effectiveness of the meetings by adjusting the order of analysis based on the relevance of the meetings. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the relevance of the meetings into a generation AI, which then performs the analysis.

[0048] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the user's level of expertise. Examples of the level of expertise include, but are not limited to, the participant's work experience and field of expertise. For example, the analysis unit uses a lot of technical terms when the user has specialized knowledge. The analysis unit can also avoid technical terms when the user does not have specialized knowledge. For example, the analysis unit dynamically adjusts the use of technical terms in the analysis according to the user's level of expertise. This improves the effectiveness of the meeting by adjusting the use of technical terms in the analysis according to the user's level of expertise. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input data on the user's level of expertise into a generation AI, which then performs the analysis.

[0049] The generation unit can adjust the level of detail of the generation based on the importance of the meeting during generation. The importance of the meeting includes, but is not limited to, the purpose of the meeting and the positions of the participants. For example, the generation unit generates a detailed agenda and ideas for a highly important meeting. The generation unit can also generate a concise agenda and ideas for a less important meeting. For example, the generation unit dynamically adjusts the level of detail of the generation according to the importance of the meeting. This enhances the effectiveness of the meeting by adjusting the level of detail of the generation according to the importance of the meeting. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input data on the importance of the meeting into a generation AI, and the AI ​​can perform generation.

[0050] During generation, the generation unit can apply different generation algorithms depending on the category of the meeting. Examples of meeting categories include, but are not limited to, business meetings and technical meetings. For example, in the case of a technical meeting, the generation unit applies a technical generation algorithm. Furthermore, in the case of a marketing meeting, the generation unit can also apply a generation algorithm specialized for marketing. For example, in the case of a financial meeting, the generation unit applies a generation algorithm specialized for financial data. This increases the effectiveness of the meeting by applying the optimal generation algorithm depending on the category of the meeting. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input data on the category of the meeting into a generation AI and generate the data using the generation AI.

[0051] During generation, the generation unit can improve the accuracy of generation by referring to the user's past generation results. Past generation results include, but are not limited to, past meeting records and methods for improving generation accuracy. The generation unit improves the accuracy of generation, for example, based on the user's past generation results. The generation unit can also analyze the user's past generation results and propose an optimal generation method. For example, the generation unit adjusts the generation algorithm by referring to the user's past generation results. This improves the accuracy of generation by referring to the user's past generation results. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using AI or without AI. For example, the generation unit can input data of the user's past generation results into a generation AI and perform generation using the generation AI.

[0052] The generation unit can determine the generation priority based on the submission time of the meeting at the time of generation. The submission time of the meeting includes, but is not limited to, for example, a submission deadline and the timing of submission. For example, the generation unit prioritizes generating agendas and ideas for a meeting with an upcoming submission deadline. The generation unit can also postpone generating agendas and ideas for a meeting with a distant submission deadline. For example, the generation unit dynamically adjusts the generation priority according to the submission time. This improves the effectiveness of the meeting by determining the generation priority based on the submission time of the meeting. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input data on the submission time of the meeting into a generation AI, and the generation AI can perform generation.

[0053] The generation unit can adjust the order of generation based on the relevance of the meetings during generation. The relevance of the meetings includes, but is not limited to, the relevance of the agenda and the relevance of the participants. For example, for a highly relevant meeting, the generation unit can prioritize generating agendas and ideas. Furthermore, for a less relevant meeting, the generation unit can postpone generating agendas and ideas. For example, the generation unit dynamically adjusts the order of generation according to the relevance of the meetings. This improves the effectiveness of the meetings by adjusting the order of generation based on the relevance of the meetings. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input data on the relevance of the meetings into a generation AI, and the generation AI can perform generation.

[0054] During generation, the generation unit can adjust the use of technical terminology in the generated video according to the user's level of expertise. Examples of the level of expertise include, but are not limited to, the participant's work experience and field of expertise. For example, the generation unit uses a lot of technical terminology when the user has specialized knowledge. The generation unit can also avoid technical terminology when the user does not have specialized knowledge. For example, the generation unit dynamically adjusts the use of technical terminology in the generated video according to the user's level of expertise. This improves the effectiveness of the meeting by adjusting the use of technical terminology in the generated video according to the user's level of expertise. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without AI. For example, the generation unit can input data on the user's level of expertise into a generation AI, and the generation AI can perform generation.

[0055] The proceeding unit can adjust the level of detail of the proceedings based on the importance of the meeting during the proceedings. Examples of the importance of the meeting include, but are not limited to, the purpose of the meeting and the positions of the participants. For example, the proceeding unit can propose a detailed proceeding method for a highly important meeting. The proceeding unit can also propose a concise proceeding method for a low-importance meeting. For example, the proceeding unit dynamically adjusts the level of detail of the proceedings according to the importance of the meeting. This improves the effectiveness of the meeting by adjusting the level of detail of the proceedings according to the importance of the meeting. Some or all of the above-mentioned processing in the proceeding unit may be performed using, for example, AI, or may be performed without using AI. For example, the proceeding unit can input data on the importance of the meeting into a generation AI, and the generation AI can proceed with the proceedings.

[0056] The proceeding unit can apply different proceeding algorithms depending on the category of the meeting during the proceedings. Examples of meeting categories include, but are not limited to, business meetings and technical meetings. For example, in the case of a technical meeting, the proceeding unit can apply a technical proceeding algorithm. Furthermore, in the case of a marketing meeting, the proceeding unit can apply a proceeding algorithm specialized for marketing. For example, in the case of a financial meeting, the proceeding unit can apply a proceeding algorithm specialized for financial data. In this way, the effectiveness of the meeting is enhanced by applying the optimal proceeding algorithm depending on the category of the meeting. Some or all of the above-mentioned processing in the proceeding unit may be performed using, for example, AI, or may be performed without using AI. For example, the proceeding unit can input data on the category of the meeting into a generation AI and have the generation AI perform the proceedings.

[0057] The progression unit can improve the accuracy of progression by referring to the user's past progression results during progression. Past progression results include, but are not limited to, past meeting records and progression accuracy improvement methods. The progression unit can improve the accuracy of progression, for example, based on the user's past progression results. The progression unit can also analyze the user's past progression results and propose an optimal progression method. For example, the progression unit can adjust the progression algorithm by referring to the user's past progression results. This improves the accuracy of progression by referring to the user's past progression results. Some or all of the above-mentioned processing in the progression unit can be performed, for example, using AI or without AI. For example, the progression unit can input data of the user's past progression results into a generation AI and use the generation AI to perform progression.

[0058] The progress unit can determine the priority of the progress based on the submission time of the meeting during the progress. The submission time of the meeting includes, but is not limited to, for example, the submission deadline and the timing of submission. For example, the progress unit prioritizes the progress of a meeting with an approaching submission deadline. Furthermore, the progress unit can postpone the progress of a meeting with a distant submission deadline. For example, the progress unit dynamically adjusts the priority of the progress according to the submission time. In this way, the effectiveness of the meeting is improved by determining the priority of the progress based on the submission time of the meeting. Some or all of the above-mentioned processing in the progress unit may be performed using, for example, AI, or may be performed without using AI. For example, the progress unit can input data on the submission time of the meeting into a generation AI and have the generation AI proceed the meeting.

[0059] The proceeding unit can adjust the order of proceedings based on the relevance of the meetings during the proceedings. The relevance of the meetings includes, but is not limited to, for example, the relevance of the agenda and the relevance of the participants. For example, the proceeding unit can prioritize proceedings for highly relevant meetings. Furthermore, the proceeding unit can postpone proceedings for less relevant meetings. For example, the proceeding unit dynamically adjusts the order of proceedings according to the relevance of the meetings. In this way, adjusting the order of proceedings based on the relevance of the meetings enhances the effectiveness of the meetings. Some or all of the above-mentioned processing in the proceeding unit may be performed using, for example, AI, or may be performed without using AI. For example, the proceeding unit can input data on the relevance of the meetings into a generation AI and proceed with the generation AI.

[0060] The moderator can adjust the use of technical terms during the meeting according to the user's level of expertise. Examples of the level of expertise include, but are not limited to, the participant's work experience and field of expertise. For example, the moderator uses a lot of technical terms when the user has specialized knowledge. The moderator can also avoid technical terms when the user does not have specialized knowledge. For example, the moderator dynamically adjusts the use of technical terms during the meeting according to the user's level of expertise. This improves the effectiveness of the meeting by adjusting the use of technical terms during the meeting according to the user's level of expertise. Some or all of the above-described processing in the moderator can be performed using, or without, AI. For example, the moderator can input data on the user's level of expertise into a generation AI, and the generation AI can then guide the meeting.

[0061] The text conversion unit can adjust the level of detail of the text based on the importance of the utterance when converting the utterance into text. The importance of the utterance includes, but is not limited to, the content of the utterance and the position of the speaker. For example, the text conversion unit converts a utterance of high importance into text in detail. The text conversion unit can also convert a utterance of low importance into text in a concise manner. For example, the text conversion unit dynamically adjusts the level of detail of the text depending on the importance of the utterance. This improves the effectiveness of the meeting by adjusting the level of detail of the text depending on the importance of the utterance. Some or all of the above-mentioned processing in the text conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the text conversion unit can input data on the importance of the utterance into a generation AI, and the generation AI can convert the utterance into text.

[0062] The text conversion unit can apply different text conversion algorithms depending on the category of the utterance when converting the utterance into text. Examples of utterance categories include, but are not limited to, technical utterances and business utterances. For example, in the case of technical utterances, the text conversion unit can apply a technical text conversion algorithm. Furthermore, in the case of marketing-related utterances, the text conversion unit can also apply a text conversion algorithm specialized for marketing. For example, in the case of finance-related utterances, the text conversion unit can apply a text conversion algorithm specialized for financial data. This increases the effectiveness of the meeting by applying the optimal text conversion algorithm depending on the category of the utterance. Some or all of the above-mentioned processing in the text conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the text conversion unit can input data on the category of the utterance into a generation AI, and have the generation AI perform the text conversion.

[0063] During text conversion, the text conversion unit can improve the accuracy of the text conversion by referring to the user's past text conversion results. Past text conversion results include, but are not limited to, past meeting records and text conversion accuracy improvement methods. The text conversion unit can improve the accuracy of the text conversion based on, for example, the user's past text conversion results. The text conversion unit can also analyze the user's past text conversion results and propose an optimal text conversion method. For example, the text conversion unit can adjust the text conversion algorithm by referring to the user's past text conversion results. This improves the accuracy of the text conversion by referring to the user's past text conversion results. Some or all of the above-mentioned processing in the text conversion unit can be performed using, for example, AI, or without AI. For example, the text conversion unit can input data of the user's past text conversion results into a generation AI, and the generation AI can perform text conversion.

[0064] The text conversion unit can determine the priority of text conversion based on the time of submission of the utterance when converting the utterance into text. The time of submission of the utterance includes, but is not limited to, the submission deadline and the timing of submission. For example, the text conversion unit prioritizes text conversion for utterances with an approaching submission deadline. The text conversion unit can also postpone text conversion for utterances with a distant submission deadline. For example, the text conversion unit dynamically adjusts the priority of text conversion depending on the submission time. This improves the effectiveness of the meeting by determining the priority of text conversion based on the time of submission of the utterance. Some or all of the above-mentioned processing in the text conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the text conversion unit can input data on the time of submission of the utterance into a generation AI, and the generation AI can perform text conversion.

[0065] The text conversion unit can adjust the order of text conversion based on the relevance of the utterances during text conversion. The relevance of the utterances includes, but is not limited to, the relevance of the agenda and the relevance of the speaker. For example, the text conversion unit prioritizes text conversion for highly relevant utterances. The text conversion unit can also postpone text conversion for less relevant utterances. For example, the text conversion unit dynamically adjusts the order of text conversion according to the relevance of the utterances. This improves the effectiveness of the meeting by adjusting the order of text conversion based on the relevance of the utterances. Some or all of the above-described processing in the text conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the text conversion unit can input data on the relevance of the utterances into a generation AI, and the generation AI can perform text conversion.

[0066] The text conversion unit can adjust the use of technical terms in the text conversion according to the user's level of expertise. Examples of the level of expertise include, but are not limited to, the speaker's work experience and field of expertise. For example, the text conversion unit uses a lot of technical terms when the user has specialized knowledge. The text conversion unit can also avoid technical terms when the user does not have specialized knowledge. For example, the text conversion unit dynamically adjusts the use of technical terms in the text conversion according to the user's level of expertise. This improves the effectiveness of the meeting by adjusting the use of technical terms in the text conversion according to the user's level of expertise. Some or all of the above-described processing in the text conversion unit may be performed using, for example, AI, or may be performed without AI. For example, the text conversion unit can input data on the user's level of expertise into a generation AI, and the generation AI can perform the text conversion.

[0067] When making a decision, the decision unit can adjust the level of detail of the decision items based on the importance of the meeting. The importance of the meeting includes, but is not limited to, the purpose of the meeting and the positions of the participants. For example, the decision unit clarifies detailed decision items for a highly important meeting. Furthermore, the decision unit can also clarify concise decision items for a less important meeting. For example, the decision unit dynamically adjusts the level of detail of the decision items according to the importance of the meeting. This enhances the effectiveness of the meeting by adjusting the level of detail of the decision items according to the importance of the meeting. Some or all of the above-described processing in the decision unit may be performed using, for example, AI, or may be performed without using AI. For example, the decision unit can input data on the importance of the meeting into a generation AI, which then makes a decision.

[0068] When making a decision, the decision unit can apply different decision algorithms depending on the category of the meeting. Examples of meeting categories include, but are not limited to, business meetings and technical meetings. For example, in the case of a technical meeting, the decision unit can apply a technical decision algorithm. Furthermore, in the case of a marketing meeting, the decision unit can also apply a decision algorithm specialized for marketing. For example, in the case of a financial meeting, the decision unit can apply a decision algorithm specialized for financial data. This increases the effectiveness of the meeting by applying the optimal decision algorithm depending on the category of the meeting. Some or all of the above-described processing in the decision unit may be performed using, for example, AI, or may be performed without using AI. For example, the decision unit can input data on the category of the meeting into a generation AI, and the generation AI can make a decision.

[0069] When making a decision, the decision unit can improve the accuracy of the decision by referring to the user's past decision results. Past decision results include, but are not limited to, past meeting records and methods for improving decision accuracy. The decision unit can improve the accuracy of the decision, for example, based on the user's past decision results. The decision unit can also analyze the user's past decision results and propose an optimal decision method. For example, the decision unit can adjust the decision algorithm by referring to the user's past decision results. This improves the accuracy of the decision by referring to the user's past decision results. Some or all of the above-mentioned processing in the decision unit can be performed, for example, using AI or without AI. For example, the decision unit can input data on the user's past decision results into a generation AI and have the generation AI make a decision.

[0070] When making a decision, the determination unit can determine the priority of the decision items based on the submission time of the meeting. The submission time of the meeting includes, but is not limited to, for example, a submission deadline or the timing of submission. For example, the determination unit prioritizes clarifying the decision items for a meeting with an upcoming submission deadline. Furthermore, the determination unit can postpone clarifying the decision items for a meeting with a distant submission deadline. For example, the determination unit dynamically adjusts the priority of the decision items according to the submission time. This improves the effectiveness of the meeting by determining the priority of the decision items based on the submission time of the meeting. Some or all of the above-mentioned processing in the determination unit may be performed using, for example, AI, or may be performed without using AI. For example, the determination unit can input data on the submission time of the meeting into a generation AI, and the generation AI can make a decision.

[0071] When making a decision, the decision unit can adjust the order of the decisions based on the relevance of the meeting. The relevance of the meeting includes, but is not limited to, the relevance of the agenda and the relevance of the participants. For example, the decision unit prioritizes clarifying the decisions for a highly relevant meeting. Furthermore, the decision unit can postpone clarifying the decisions for a less relevant meeting. For example, the decision unit dynamically adjusts the order of the decisions according to the relevance of the meeting. This improves the effectiveness of the meeting by adjusting the order of the decisions based on the relevance of the meeting. Some or all of the above-described processing in the decision unit may be performed using, for example, AI, or may be performed without using AI. For example, the decision unit can input data on the relevance of the meeting into a generation AI, and the generation AI can make a decision.

[0072] When making a decision, the decision unit can adjust the use of technical terminology in the decision depending on the user's level of expertise. Examples of the level of expertise include, but are not limited to, the participant's work experience and field of expertise. For example, the decision unit uses a lot of technical terminology when the user has specialized knowledge. The decision unit can also avoid technical terminology when the user does not have specialized knowledge. For example, the decision unit dynamically adjusts the use of technical terminology in the decision depending on the user's level of expertise. This improves the effectiveness of the meeting by adjusting the use of technical terminology in the decision depending on the user's level of expertise. Some or all of the above-described processing in the decision unit may be performed using, for example, AI, or may be performed without using AI. For example, the decision unit can input data on the user's level of expertise into a generation AI, and the generation AI can make a decision.

[0073] When generating minutes, the minutes generation unit can adjust the level of detail in the minutes based on the importance of the meeting. The importance of the meeting includes, but is not limited to, the purpose of the meeting and the titles of the participants. For example, the minutes generation unit generates detailed minutes for a highly important meeting. Furthermore, the minutes generation unit can also generate concise minutes for a less important meeting. For example, the minutes generation unit dynamically adjusts the level of detail in the minutes according to the importance of the meeting. This enhances the effectiveness of the meeting by adjusting the level of detail in the minutes according to the importance of the meeting. Some or all of the above-described processing in the minutes generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the minutes generation unit can input data on the importance of the meeting into a generation AI, which then generates minutes.

[0074] When generating minutes, the minutes generation unit can apply different minutes generation algorithms depending on the category of the meeting. Examples of meeting categories include, but are not limited to, business meetings and technical meetings. For example, in the case of a technical meeting, the minutes generation unit can apply a technical minutes generation algorithm. Furthermore, in the case of a marketing meeting, the minutes generation unit can also apply a minutes generation algorithm specialized for marketing. For example, in the case of a financial meeting, the minutes generation unit can apply a minutes generation algorithm specialized for financial data. This increases the effectiveness of the meeting by applying the optimal minutes generation algorithm depending on the category of the meeting. Some or all of the above-described processing in the minutes generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the minutes generation unit can input data on the category of the meeting into a generation AI, which then generates minutes.

[0075] When generating minutes, the minutes generation unit can improve the accuracy of the minutes generation by referring to the user's past minutes generation results. Past minutes generation results include, but are not limited to, past meeting records and generation accuracy improvement methods. The minutes generation unit can improve the accuracy of the minutes generation, for example, based on the user's past minutes generation results. The minutes generation unit can also analyze the user's past minutes generation results and propose an optimal minutes generation method. For example, the minutes generation unit can adjust the minutes generation algorithm by referring to the user's past minutes generation results. This improves the accuracy of the minutes generation by referring to the user's past minutes generation results. Some or all of the above-mentioned processing in the minutes generation unit can be performed, for example, using AI or without AI. For example, the minutes generation unit can input data of the user's past minutes generation results into a generation AI and generate minutes using the generation AI.

[0076] When generating minutes, the minutes generation unit can determine the priority of minutes based on the submission time of the meeting. The submission time of the meeting includes, but is not limited to, for example, the submission deadline and the timing of submission. For example, the minutes generation unit prioritizes the generation of minutes for a meeting with an upcoming submission deadline. The minutes generation unit can also postpone the generation of minutes for a meeting with a distant submission deadline. For example, the minutes generation unit dynamically adjusts the priority of minutes according to the submission time. This improves the effectiveness of the meeting by determining the priority of minutes based on the submission time of the meeting. Some or all of the above-mentioned processing in the minutes generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the minutes generation unit can input data on the submission time of the meeting into a generation AI, and the generation AI can generate minutes.

[0077] When generating minutes, the minutes generation unit can adjust the order of the minutes based on the relevance of the meeting. The relevance of the meeting includes, but is not limited to, the relevance of the agenda and the relevance of the participants. For example, the minutes generation unit prioritizes generating minutes for a highly relevant meeting. The minutes generation unit can also postpone generating minutes for a less relevant meeting. For example, the minutes generation unit dynamically adjusts the order of the minutes according to the relevance of the meeting. This improves the effectiveness of the meeting by adjusting the order of the minutes based on the relevance of the meeting. Some or all of the above-mentioned processing in the minutes generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the minutes generation unit can input data on the relevance of the meeting into a generation AI, and the generation AI can generate minutes.

[0078] When generating minutes, the minutes generation unit can adjust the use of technical terms in the minutes according to the user's level of expertise. Examples of the level of expertise include, but are not limited to, the participants' work experience and fields of expertise. For example, the minutes generation unit uses a lot of technical terms if the user has technical expertise. Furthermore, the minutes generation unit can avoid technical terms if the user does not have technical expertise. For example, the minutes generation unit dynamically adjusts the use of technical terms in the minutes according to the user's level of expertise. This improves the effectiveness of the meeting by adjusting the use of technical terms in the minutes according to the user's level of expertise. Some or all of the above-described processing in the minutes generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the minutes generation unit can input data on the user's level of expertise into a generation AI, which then generates minutes.

[0079] The sharing unit can adjust the level of detail of the shared information based on the importance of the meeting when sharing. The importance of the meeting includes, but is not limited to, the purpose of the meeting and the roles of the participants, for example. For example, the sharing unit shares detailed minutes for a highly important meeting. Furthermore, the sharing unit can also share concise minutes for a less important meeting. For example, the sharing unit dynamically adjusts the level of detail of the shared information based on the importance of the meeting. This enhances the effectiveness of the meeting by adjusting the level of detail of the shared information based on the importance of the meeting. Some or all of the above-described processing in the sharing unit may be performed using, for example, AI, or may be performed without using AI. For example, the sharing unit can input data on the importance of the meeting into a generating AI, and the generating AI can perform sharing.

[0080] When sharing, the sharing unit can apply different sharing algorithms depending on the category of the meeting. Examples of meeting categories include, but are not limited to, business meetings and technical meetings. For example, in the case of a technical meeting, the sharing unit can apply a technical sharing algorithm. Furthermore, in the case of a marketing meeting, the sharing unit can also apply a sharing algorithm specialized for marketing. For example, in the case of a financial meeting, the sharing unit can apply a sharing algorithm specialized for financial data. This increases the effectiveness of the meeting by applying the optimal sharing algorithm depending on the category of the meeting. Some or all of the above-mentioned processing in the sharing unit may be performed using, for example, AI, or may be performed without using AI. For example, the sharing unit can input data of the category of the meeting into a generating AI, and the generating AI can perform sharing.

[0081] The sharing unit can improve the accuracy of sharing by referring to the user's past sharing results when sharing. Past sharing results include, but are not limited to, past meeting records and methods for improving sharing accuracy. The sharing unit can improve the accuracy of sharing, for example, based on the user's past sharing results. The sharing unit can also analyze the user's past sharing results and propose an optimal sharing method. For example, the sharing unit can adjust the sharing algorithm by referring to the user's past sharing results. This improves the accuracy of sharing by referring to the user's past sharing results. Some or all of the above-mentioned processing in the sharing unit can be performed, for example, using AI or without AI. For example, the sharing unit can input data of the user's past sharing results into a generation AI and perform sharing using the generation AI.

[0082] The sharing unit can determine the priority of sharing based on the submission time of the meeting when sharing. The submission time of the meeting includes, but is not limited to, for example, the submission deadline and the timing of submission. For example, the sharing unit prioritizes sharing of minutes for a meeting with an upcoming submission deadline. The sharing unit can also postpone sharing of minutes for a meeting with a distant submission deadline. For example, the sharing unit dynamically adjusts the priority of sharing according to the submission time. This improves the effectiveness of the meeting by determining the priority of sharing based on the submission time of the meeting. Some or all of the above-mentioned processing in the sharing unit may be performed using, for example, AI, or may be performed without using AI. For example, the sharing unit can input data on the submission time of the meeting into a generation AI, and the generation AI can perform sharing.

[0083] The sharing unit can adjust the sharing order based on the relevance of the meetings when sharing. The relevance of the meetings includes, but is not limited to, for example, the relevance of the agenda and the relevance of the participants. For example, the sharing unit prioritizes sharing of minutes for highly relevant meetings. Furthermore, the sharing unit can also postpone sharing of minutes for less relevant meetings. For example, the sharing unit dynamically adjusts the sharing order according to the relevance of the meetings. In this way, adjusting the sharing order based on the relevance of the meetings enhances the effectiveness of the meetings. Some or all of the above-described processing in the sharing unit may be performed using, for example, AI, or may be performed without using AI. For example, the sharing unit can input data on the relevance of the meetings into a generation AI, and the generation AI can perform sharing.

[0084] During sharing, the sharing unit can adjust the use of shared terminology according to the user's level of expertise. Examples of expertise levels include, but are not limited to, the participant's work experience and field of expertise. For example, the sharing unit uses a lot of terminology if the user has expertise. The sharing unit can also avoid terminology if the user does not have expertise. For example, the sharing unit dynamically adjusts the use of shared terminology according to the user's level of expertise. This enhances the effectiveness of the meeting by adjusting the use of shared terminology according to the user's level of expertise. Some or all of the above-described processing in the sharing unit may be performed using, for example, AI, or may be performed without AI. For example, the sharing unit can input data on the user's level of expertise into a generating AI, and the generating AI can perform sharing.

[0085] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0086] The conference support system can further include a translation unit. The translation unit supports communication between participants who speak different languages. For example, the translation unit translates what one participant says in real time and provides it to other participants. The translation unit can also generate minutes in multiple languages ​​and share them with participants. This allows the conference support system to achieve smooth communication even in international conferences, thereby improving the effectiveness of the conference.

[0087] The conference support system can further include a reminder unit. The reminder unit sends reminders to participants before and after the conference. For example, the reminder unit notifies participants of the conference start time and preparation items. The reminder unit can also remind participants of next actions and deadlines after the conference ends. This allows the conference support system to support participants in reliably preparing for and following up on the conference, thereby improving the effectiveness of the conference.

[0088] The conference support system can further include a networking unit. The networking unit promotes interaction between conference participants. For example, the networking unit matches participants with common interests based on the participant profiles and areas of interest, and provides opportunities for interaction. The networking unit can also provide a function that allows participants to exchange contact information after the conference ends. In this way, the conference support system can promote networking between participants and increase the effectiveness of the conference.

[0089] The conference support system may further include a data visualization unit. The data visualization unit visually displays data and information discussed during the conference. For example, the data visualization unit may generate graphs and charts and provide them to participants. The data visualization unit may also display data fluctuations in real time, allowing participants to intuitively understand them. This allows the conference support system to facilitate understanding of the data and improve the effectiveness of the conference.

[0090] The meeting support system may further include a virtual reality (VR) unit. The VR unit supports participants in holding meetings in a virtual space. For example, the VR unit may provide a virtual conference room, allowing participants to experience a realistic meeting even from a remote location. The VR unit may also provide the ability to use a virtual whiteboard or 3D model during a meeting. This allows the meeting support system to enhance communication with remote participants and improve the effectiveness of the meeting.

[0091] The conference support system can further include an environmental monitoring unit. The environmental monitoring unit monitors the conference room environment in real time and provides the results to the conference moderator. For example, the environmental monitoring unit measures the temperature, humidity, and CO2 concentration in the conference room and provides feedback to the conference moderator. The environmental monitoring unit can also suggest appropriate ventilation and temperature adjustments during the conference. This allows the conference support system to run the conference in a comfortable environment and improve the effectiveness of the conference.

[0092] The processing flow of the first embodiment will be briefly explained below.

[0093] Step 1: The reception unit inputs the goal of the meeting. The goal of the meeting includes, but is not limited to, for example, the purpose of the meeting and a goal to be achieved. For example, the reception unit receives input from a user of the purpose of the meeting and a goal to be achieved. The reception unit can also support multiple input methods, such as voice input, text input, and image input. For example, the reception unit may preferentially provide voice input to a user who prefers voice input, and preferentially provide text input to a user who prefers text input. Step 2: The analysis unit analyzes the information input by the reception unit. The analysis is performed based on, for example, past data and trends, but is not limited to such examples. For example, the analysis unit analyzes past meeting records and industry trends to generate agendas and ideas. The analysis unit can also estimate the user's emotions and adjust the way the analysis is presented. For example, the analysis unit provides detailed analysis results if the user is relaxed, and provides concise analysis results if the user is in a hurry. Step 3: The generation unit generates an agenda and ideas based on the information analyzed by the analysis unit. Generation is performed, for example, based on the list of topics and the type of ideas, but is not limited to such examples. For example, the generation unit generates a technical agenda and ideas for a technical meeting, and generates a marketing-specific agenda and ideas for a marketing meeting. The generation unit can also estimate the user's emotions and adjust the generation method. For example, the generation unit generates a detailed agenda and ideas if the user is relaxed, and generates a concise agenda and ideas if the user is in a hurry. Step 4: The proceedings unit grasps the progress of the meeting in real time. The progress is grasped based on, for example, the progress stages and time management, but is not limited to these examples. For example, the proceedings unit monitors the progress of the meeting in real time and suggests the timing to move on to the next agenda item. The proceedings unit can also estimate the user's emotions and adjust the proceeding method. For example, if the user is nervous, the proceedings unit suggests a relaxing proceeding method, and if the user is in a hurry, the proceedings unit suggests a quick proceeding method. Step 5: The text conversion unit converts the participants' comments into text. The conversion can be performed, for example, based on voice recognition technology or text formatting, but is not limited to these examples. The text conversion unit converts the participants' comments into text using voice recognition technology, for example, and emphasizes important points. The text conversion unit can also estimate the user's emotions and adjust the text conversion method. For example, the text conversion unit can convert the comments into detailed text if the user is relaxed, and convert the comments into concise text if the user is in a hurry. Step 6: The decision unit clarifies the decisions and next actions at the end of the meeting. The clarification of the decisions is performed, for example, based on the type of decision and the next action, but is not limited to such examples. For example, the decision unit clarifies the product specifications, development schedule, and person in charge at the end of the meeting. The decision unit can also estimate the user's emotions and adjust the method of clarifying the decisions. For example, the decision unit clarifies detailed decisions when the user is relaxed, and clarifies simple decisions when the user is in a hurry. Step 7: The minutes generation unit automatically creates minutes. The automatic creation of minutes is performed based on, for example, but not limited to, the algorithm used and the type of information recorded. For example, the minutes generation unit generates minutes immediately after the meeting ends and sends them by email to all participants. The minutes generation unit can also estimate the user's emotions and adjust the method of generating minutes. For example, the minutes generation unit generates detailed minutes if the user is relaxed, and generates concise minutes if the user is in a hurry. Step 8: The sharing unit automatically shares the minutes with the meeting participants. The automatic sharing is performed based on, for example, the platform to be shared and the timing of sharing, but is not limited to these examples. For example, the sharing unit can send the minutes by email or upload them to cloud storage for sharing. The sharing unit can also estimate the user's emotions and adjust the sharing method. For example, the sharing unit can share detailed minutes if the user is relaxed, and share brief minutes if the user is in a hurry.

[0094] (Example 2) A meeting support system according to an embodiment of the present invention is a system in which a user inputs the goal of a meeting, and a multimodal AI provides an agenda and ideas, supports the progress of the meeting, clarifies decisions and next actions at the end of the meeting, and automatically creates and shares minutes. The meeting support system inputs the goal of a meeting, and a multimodal AI provides an agenda and ideas, supporting the progress of the meeting. At the end of the meeting, the system clarifies decisions and next actions, and automatically creates and shares minutes. For example, the meeting support system inputs the goal of the meeting. For example, the meeting support system requires only that the user input the purpose of the meeting and the goals they wish to achieve. This information is input into the multimodal AI. The multimodal AI then analyzes the input information and provides an agenda and ideas. For example, the meeting support system proposes agendas such as product features, market analysis, and competitive research. It also provides ideas based on past data and trends. Next, the multimodal AI participates in the meeting as an AI assistant and supports the progress of the meeting. For example, the meeting support system monitors the progress of the meeting in real time and suggests when to move on to the next agenda item. The meeting support system also converts participants' comments into text and emphasizes important points. Next, the multimodal AI in the meeting support system clarifies decisions and next actions at the end of the meeting. For example, the meeting support system clarifies product specifications, development schedules, and responsible parties. Next, the meeting support system automatically creates minutes and shares them with meeting participants. For example, the meeting support system generates minutes immediately after the meeting and sends them to all participants by email. This allows the meeting support system to accurately record and share the contents of the meeting. This allows the meeting support system to simultaneously improve the quality of meetings and reduce meeting times. For example, meetings can proceed more smoothly and waste less time can be reduced. Furthermore, the quality of meetings is improved when AI provides agendas and ideas. This improves corporate productivity and enables more efficient meeting management.

[0095] A conference support system according to an embodiment includes a reception unit, an analysis unit, a generation unit, a progress unit, a text conversion unit, a determination unit, a minutes generation unit, and a sharing unit. The reception unit inputs the goal of the conference. The goal of the conference includes, but is not limited to, the purpose of the conference and a target to be achieved. The reception unit also supports multiple input methods, such as voice input, text input, and image input. For example, the reception unit may preferentially provide voice input to a user who prefers voice input, and preferentially provide text input to a user who prefers text input. The analysis unit analyzes the information input by the reception unit. The analysis may be based on, for example, past data and trends, but is not limited to, the analysis unit may analyze, for example, past conference records and industry trends to generate an agenda and ideas. The analysis unit may also estimate a user's emotions and adjust the method of expression of the analysis. For example, the analysis unit provides detailed analysis results when the user is relaxed, and provides concise analysis results when the user is in a hurry. The generation unit generates an agenda and ideas based on the information analyzed by the analysis unit. The generation is performed, for example, based on a list of topics and types of ideas, but is not limited to such examples. For example, the generation unit generates a technical agenda and ideas for a technical meeting, and generates a marketing-specific agenda and ideas for a marketing meeting. The generation unit can also estimate the user's emotions and adjust the generation method. For example, the generation unit generates a detailed agenda and ideas when the user is relaxed, and generates a concise agenda and ideas when the user is in a hurry. The proceeding unit grasps the progress of the meeting in real time. The progress is grasped, for example, based on progress stages and time management, but is not limited to such examples. For example, the proceeding unit monitors the progress of the meeting in real time and suggests when to move on to the next agenda item. The proceeding unit can also estimate the user's emotions and adjust the proceeding method. For example, if the user is nervous, the moderator suggests a method of proceeding that will allow the user to relax, and if the user is in a hurry, suggests a method of proceeding quickly. The text converter converts the remarks of the participants into text.The text conversion is performed based on, for example, voice recognition technology and a text format, but is not limited to these examples. The text conversion unit converts participants' speech into text using, for example, voice recognition technology and emphasizes important points. The text conversion unit can also estimate a user's emotions and adjust the text conversion method accordingly. For example, the text conversion unit may convert detailed speech into text if the user is relaxed, and convert concise speech into text if the user is in a hurry. The decision unit clarifies decisions and next actions at the end of the meeting. The clarification of decisions is performed based on, for example, the type of decision and the next action, but is not limited to these examples. The decision unit clarifies product specifications, development schedules, and responsible parties at the end of the meeting. The decision unit can also estimate a user's emotions and adjust the method of clarification of decisions. For example, the decision unit may clarify detailed decisions if the user is relaxed, and convert concise decisions if the user is in a hurry. The minutes generation unit automatically creates minutes. The automatic creation of minutes is performed based on, for example, an algorithm used and the type of information recorded, but is not limited to these examples. For example, the minutes generation unit generates minutes immediately after the end of the meeting and sends them to all participants by email. The minutes generation unit can also estimate the user's emotions and adjust the method for generating the minutes. For example, the minutes generation unit generates detailed minutes when the user is relaxed, and generates concise minutes when the user is in a hurry. The sharing unit automatically shares the minutes with the meeting participants. Automatic sharing is performed, for example, based on the sharing platform and the timing of sharing, but is not limited to these examples. For example, the sharing unit can send the minutes by email, or can upload them to cloud storage and share them. The sharing unit can also estimate the user's emotions and adjust the sharing method. For example, the sharing unit shares detailed minutes when the user is relaxed, and shares concise minutes when the user is in a hurry. As a result, the meeting support system according to the embodiment consistently supports processes from entering meeting goals to sharing the minutes, thereby improving the quality of meetings and reducing time.

[0096] The reception unit can input the purpose of the meeting and the goals to be achieved. Examples of the purpose of the meeting and the goals to be achieved include, but are not limited to, the focus of the discussion and the expected results. For example, the reception unit receives input from a user of the purpose of the meeting and the goals to be achieved. The reception unit can also support multiple input methods, such as voice input, text input, and image input. For example, the reception unit can provide voice input preferentially to a user who prefers voice input, and provide text input preferentially to a user who prefers text input. This clarifies the purpose and goals of the meeting, allowing the meeting to proceed smoothly. Some or all of the above-described processing in the reception unit can be performed using, for example, AI, or can be performed without using AI. For example, the reception unit can input the purpose of the meeting and the goals to be achieved input by the user into a generation AI, which can then analyze the input.

[0097] The analysis unit can generate an agenda or ideas based on past data or trends. Examples of past data and trends include, but are not limited to, past meeting records and industry trends. For example, the analysis unit can analyze past meeting records to generate an agenda or ideas. The analysis unit can also analyze industry trends to generate an agenda or ideas. For example, the analysis unit can generate a list of topics or types of ideas based on past meeting records. The analysis unit can also generate an agenda or ideas based on industry trends. This makes it possible to provide more effective agendas and ideas by utilizing past data and trends. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input past meeting records and industry trends into a generation AI, which then performs analysis.

[0098] The proceedings unit can grasp the progress of the meeting in real time and propose the timing to move on to the next agenda item. Understanding the progress includes, for example, but is not limited to, the stages of progress and time management. For example, the proceedings unit can monitor the progress of the meeting in real time and propose the timing to move on to the next agenda item. The proceedings unit can also grasp the stages of progress and propose the timing to move on to the next agenda item. For example, the proceedings unit can grasp the progress of the meeting in real time and propose the timing to move on to the next agenda item. The proceedings unit can also manage time and propose the timing to move on to the next agenda item. This can smooth the progress of the meeting and reduce wasted time. Some or all of the above-mentioned processing in the proceedings unit may be performed using, for example, AI, or may be performed without using AI. For example, the proceedings unit can input the progress of the meeting into a generation AI, which can then analyze it.

[0099] The text conversion unit can convert the participants' remarks into text and emphasize key points. Text conversion can include, but is not limited to, speech recognition technology and text formatting. For example, the text conversion unit can convert the participants' remarks into text and emphasize important points using speech recognition technology. The text conversion unit can also analyze the content of the remarks and highlight important keywords. For example, the text conversion unit can convert the remarks into text using speech recognition technology and highlight important keywords. The text conversion unit can also summarize the content of the remarks and provide a summary. This improves the quality of the minutes by accurately recording the content of the remarks and emphasizing important points. Some or all of the above-described processing in the text conversion unit can be performed using, for example, AI, or without AI. For example, the text conversion unit can input the participants' remarks into a generation AI, which then converts the remarks into text.

[0100] The decision unit can clarify decisions and next actions at the end of a meeting. Decisions include, but are not limited to, the type of decision and the next action. For example, the decision unit can clarify product specifications, development schedules, and responsible parties at the end of a meeting. The decision unit can also specify the next action. For example, the decision unit can specify the next action and clarify the responsible parties and deadlines at the end of a meeting. This clarifies the outcome of the meeting and specifies the next action, thereby enhancing the effectiveness of the meeting. Some or all of the above-mentioned processing in the decision unit may be performed using, or without, AI. For example, the decision unit can input decisions and next actions to a generation AI at the end of a meeting, and the generation AI can clarify them.

[0101] The minutes generation unit can automatically create minutes. Examples of automatic minutes generation include, but are not limited to, the algorithm used and the type of information recorded. For example, the minutes generation unit generates minutes immediately after the meeting ends and sends them by email to all participants. The minutes generation unit can also upload the minutes to cloud storage for sharing. For example, the minutes generation unit generates minutes immediately after the meeting ends and uploads them to cloud storage for sharing. This automates the creation of minutes, saving time and effort and ensuring accurate records. Some or all of the above-described processing in the minutes generation unit may be performed using, or without, AI. For example, the minutes generation unit can input the contents of the meeting into a generation AI, which then automatically creates minutes.

[0102] The sharing unit can automatically share the minutes with meeting participants. Automatic sharing includes, for example, the platform for sharing and the timing of sharing, but is not limited to these examples. For example, the sharing unit can send the minutes by email or upload them to cloud storage for sharing. The sharing unit can also share the minutes in real time. For example, the sharing unit generates minutes immediately after the end of the meeting and shares them in real time. In this way, by automatically sharing the minutes, information is transmitted quickly and accurately. Some or all of the above-mentioned processing in the sharing unit may be performed using, for example, AI, or may be performed without using AI. For example, the sharing unit can input the minutes into a generation AI, which then automatically shares them.

[0103] The reception unit can analyze the user's emotions and adjust the timing of the meeting goal input based on the analyzed user's emotions. For example, if the user is feeling stressed, the reception unit prompts the user to input the meeting goal at a time when the user can relax. Furthermore, if the user is concentrating, the reception unit can prompt the user to input the meeting goal immediately. For example, if the user is tired, the reception unit prompts the user to input the meeting goal after a break. This allows the meeting goal to be input at the optimal time depending on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the reception unit may be performed using an AI, or may be performed without using an AI. For example, the reception unit can input the user's emotion data into the generation AI, which can then estimate the emotion.

[0104] The reception unit can analyze the user's past meeting history and suggest an optimal goal input method. Past meeting history includes, for example, past agendas and participant feedback, but is not limited to these examples. The reception unit, for example, suggests a goal input method that the user used in a successful meeting in the past. The reception unit can also make suggestions to avoid goal input methods that the user used in unsuccessful meetings in the past. For example, the reception unit suggests the most effective goal input method based on the user's past meeting history. This improves the effectiveness of meetings by suggesting an optimal goal input method based on the past meeting history. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's past meeting history into a generation AI, which then performs analysis.

[0105] When inputting the meeting goals, the reception unit can perform filtering based on the user's current projects and areas of interest. Examples of current projects and areas of interest include, but are not limited to, the progress of the project and a method for identifying the area of ​​interest. For example, the reception unit can prioritize and suggest goals related to the user's current project. The reception unit can also suggest related goals based on the user's areas of interest. For example, the reception unit can suggest optimal goals based on the user's past project history. This improves the effectiveness of the meeting by suggesting optimal goals based on the user's current projects and areas of interest. Some or all of the above-described processing in the reception unit can be performed using, for example, AI, or without AI. For example, the reception unit can input data on the user's current projects and areas of interest into a generation AI, which can then perform filtering.

[0106] The reception unit can select the optimal input means depending on the user's input method when entering the meeting goal. Examples of input methods include, but are not limited to, voice input, text input, and image input. For example, if the user prefers voice input, the reception unit can prioritize voice input. Furthermore, if the user prefers text input, the reception unit can also prioritize text input. For example, if the user prefers image input, the reception unit can prioritize image input. This provides the optimal means depending on the user's input method, thereby facilitating the goal entry of the meeting. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input data on the user's input method into a generation AI, which can select the optimal input means.

[0107] The reception unit can estimate the user's emotions and determine the priority of the meeting goals to be input based on the estimated user emotions. The priority of the meeting goals to be input based on emotions can include, but is not limited to, the results of emotion analysis and priority determination criteria. For example, if the user is nervous, the reception unit can prioritize inputting goals with high importance. Furthermore, if the user is relaxed, the reception unit can also input detailed goals. For example, if the user is in a hurry, the reception unit can prioritize inputting concise goals. This improves the effectiveness of the meeting by determining the priority of the meeting goals based on the user's emotions. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit can be performed using, for example, an AI. For example, the reception unit can input the user's emotion data into a generation AI, which can then estimate the emotion.

[0108] When inputting meeting goals, the reception unit can prioritize inputting highly relevant goals taking into account the user's geographical location information. Examples of geographical location information include, but are not limited to, GPS data and location information identification methods. For example, if the user is in a specific area, the reception unit can prioritize inputting goals related to that area. Furthermore, if the user is on a business trip, the reception unit can prioritize inputting goals related to the business trip destination. For example, if the user is at home, the reception unit prioritizes inputting goals related to the user's home. This improves the effectiveness of the meeting by suggesting optimal goals based on the user's geographical location information. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's geographical location information to a generation AI, which can then perform analysis.

[0109] When a meeting goal is input, the reception unit can analyze the user's social media activity and suggest related goals. Social media activity includes, but is not limited to, the content of posts and the frequency of activities. For example, the reception unit can suggest goals related to topics mentioned by the user on social media. The reception unit can also analyze the user's social media activity and suggest related goals. For example, the reception unit can suggest related goals based on the activities of the user's friends on social media. This improves the effectiveness of the meeting by suggesting optimal goals based on the user's social media activity. Some or all of the above-described processing by the reception unit can be performed using, for example, AI, or without AI. For example, the reception unit can input data on the user's social media activity into a generation AI, which can then perform analysis.

[0110] The reception unit can customize the input method by reflecting the user's past feedback when inputting the meeting goal. Past feedback includes, but is not limited to, participant evaluations and areas for improvement. For example, the reception unit can prioritize providing an input method that the user previously preferred. The reception unit can also suggest an optimal input method based on the user's past feedback. For example, the reception unit can suggest an input method that avoids input methods that the user previously dissatisfied with. This improves the effectiveness of the meeting by providing an optimal input method based on the user's past feedback. Some or all of the above-described processing in the reception unit can be performed using, or without, AI. For example, the reception unit can input data of the user's past feedback into a generation AI, which can then analyze the data.

[0111] The analysis unit can estimate the user's emotions and adjust the analysis presentation method based on the estimated user emotions. Examples of adjusting the analysis presentation method based on emotions include, but are not limited to, the results of emotion analysis and selection criteria for the presentation method. For example, the analysis unit can provide detailed analysis results when the user is relaxed. The analysis unit can also provide concise analysis results when the user is in a hurry. For example, the analysis unit can provide visually stimulating analysis results when the user is excited. This improves the effectiveness of meetings by providing optimal analysis results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit can be performed using AI, or without AI. For example, the analysis unit can input the user's emotion data into a generation AI, which can then estimate the emotion.

[0112] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the meeting. The importance of the meeting includes, but is not limited to, the purpose of the meeting and the roles of the participants. For example, the analysis unit provides detailed analysis results for a highly important meeting. The analysis unit can also provide concise analysis results for a less important meeting. For example, the analysis unit dynamically adjusts the level of detail of the analysis according to the importance of the meeting. This improves the effectiveness of the meeting by providing optimal analysis results according to the importance of the meeting. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the importance of the meeting into a generation AI, which then performs analysis.

[0113] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the meeting. Examples of meeting categories include, but are not limited to, business meetings and technical meetings. For example, in the case of a technical meeting, the analysis unit can apply a technical analysis algorithm. Furthermore, in the case of a marketing meeting, the analysis unit can also apply an analysis algorithm specialized for marketing. For example, in the case of a financial meeting, the analysis unit can apply an analysis algorithm specialized for financial data. This increases the effectiveness of the meeting by applying the optimal analysis algorithm depending on the category of the meeting. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the category of the meeting into a generation AI, which then performs analysis.

[0114] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. Past analysis results include, but are not limited to, past meeting records and methods for improving analysis accuracy. The analysis unit can improve the accuracy of the analysis, for example, based on analysis results previously performed by the user. The analysis unit can also analyze the user's past analysis results and propose an optimal analysis method. For example, the analysis unit can adjust the analysis algorithm by referring to the user's past analysis results. This improves the accuracy of the analysis by referring to the user's past analysis results. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can input data of the user's past analysis results into a generation AI, and the generation AI can perform the analysis.

[0115] The analysis unit can estimate the user's emotions and adjust the length of the analysis based on the estimated user emotions. Examples of methods for adjusting the length of the analysis based on emotions include, but are not limited to, the results of emotion analysis and length adjustment criteria. For example, the analysis unit can provide a short analysis result if the user is in a hurry. The analysis unit can also provide a detailed analysis result if the user is relaxed. For example, the analysis unit can provide a visually stimulating analysis result if the user is excited. This improves the effectiveness of meetings by adjusting the length of the analysis based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit can be performed using AI, or without AI. For example, the analysis unit can input the user's emotion data into a generation AI, which can then estimate the emotion.

[0116] During analysis, the analysis unit can determine the priority of analysis based on the submission time of the meeting. The submission time of the meeting includes, but is not limited to, for example, the submission deadline and the timing of submission. For example, the analysis unit prioritizes analysis for meetings with an upcoming submission deadline. The analysis unit can also postpone analysis for meetings with a distant submission deadline. For example, the analysis unit dynamically adjusts the priority of analysis according to the submission time. This improves the effectiveness of the meeting by determining the priority of analysis based on the submission time of the meeting. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the submission time of the meeting into a generation AI, and the generation AI can perform analysis.

[0117] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the meetings. The relevance of the meetings includes, but is not limited to, for example, the relevance of the agenda and the relevance of the participants. For example, the analysis unit prioritizes analysis for highly relevant meetings. Furthermore, the analysis unit can postpone analysis for less relevant meetings. For example, the analysis unit dynamically adjusts the order of analysis based on the relevance of the meetings. This improves the effectiveness of the meetings by adjusting the order of analysis based on the relevance of the meetings. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the relevance of the meetings into a generation AI, which then performs the analysis.

[0118] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the user's level of expertise. Examples of the level of expertise include, but are not limited to, the participant's work experience and field of expertise. For example, the analysis unit uses a lot of technical terms when the user has specialized knowledge. The analysis unit can also avoid technical terms when the user does not have specialized knowledge. For example, the analysis unit dynamically adjusts the use of technical terms in the analysis according to the user's level of expertise. This improves the effectiveness of the meeting by adjusting the use of technical terms in the analysis according to the user's level of expertise. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input data on the user's level of expertise into a generation AI, which then performs the analysis.

[0119] The generation unit can estimate the user's emotions and adjust the agenda and idea generation method based on the estimated user emotions. Examples of ways to adjust the agenda and idea generation method based on emotions include, but are not limited to, the results of emotion analysis and selection criteria for the generation method. For example, the generation unit can generate a detailed agenda and ideas when the user is relaxed. The generation unit can also generate a concise agenda and ideas when the user is in a hurry. For example, the generation unit can generate a visually stimulating agenda and ideas when the user is excited. This improves the effectiveness of meetings by adjusting the agenda and idea generation method according to the user's emotions. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit can be performed using AI, for example, or without AI. For example, the generation unit can input the user's emotion data into the generation AI, which can then estimate the emotion.

[0120] The generation unit can adjust the level of detail of the generation based on the importance of the meeting during generation. The importance of the meeting includes, but is not limited to, the purpose of the meeting and the positions of the participants. For example, the generation unit generates a detailed agenda and ideas for a highly important meeting. The generation unit can also generate a concise agenda and ideas for a less important meeting. For example, the generation unit dynamically adjusts the level of detail of the generation according to the importance of the meeting. This enhances the effectiveness of the meeting by adjusting the level of detail of the generation according to the importance of the meeting. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input data on the importance of the meeting into a generation AI, and the AI ​​can perform generation.

[0121] During generation, the generation unit can apply different generation algorithms depending on the category of the meeting. Examples of meeting categories include, but are not limited to, business meetings and technical meetings. For example, in the case of a technical meeting, the generation unit applies a technical generation algorithm. Furthermore, in the case of a marketing meeting, the generation unit can also apply a generation algorithm specialized for marketing. For example, in the case of a financial meeting, the generation unit applies a generation algorithm specialized for financial data. This increases the effectiveness of the meeting by applying the optimal generation algorithm depending on the category of the meeting. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input data on the category of the meeting into a generation AI and generate the data using the generation AI.

[0122] During generation, the generation unit can improve the accuracy of generation by referring to the user's past generation results. Past generation results include, but are not limited to, past meeting records and methods for improving generation accuracy. The generation unit improves the accuracy of generation, for example, based on the user's past generation results. The generation unit can also analyze the user's past generation results and propose an optimal generation method. For example, the generation unit adjusts the generation algorithm by referring to the user's past generation results. This improves the accuracy of generation by referring to the user's past generation results. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using AI or without AI. For example, the generation unit can input data of the user's past generation results into a generation AI and perform generation using the generation AI.

[0123] The generation unit can estimate the user's emotions and determine the priority of the agendas and ideas to be generated based on the estimated user emotions. The priority of the agendas and ideas generated based on emotions can include, but is not limited to, the results of emotion analysis and priority criteria. For example, if the user is nervous, the generation unit can prioritize generating agendas and ideas with high importance. The generation unit can also generate detailed agendas and ideas when the user is relaxed. For example, if the user is in a hurry, the generation unit can prioritize generating concise agendas and ideas. This improves the effectiveness of meetings by prioritizing agendas and ideas according to the user's emotions. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit can be performed using, for example, AI, or without AI. For example, the generation unit can input the user's emotion data into the generation AI, which can then estimate the emotion.

[0124] The generation unit can determine the generation priority based on the submission time of the meeting at the time of generation. The submission time of the meeting includes, but is not limited to, for example, a submission deadline and the timing of submission. For example, the generation unit prioritizes generating agendas and ideas for a meeting with an upcoming submission deadline. The generation unit can also postpone generating agendas and ideas for a meeting with a distant submission deadline. For example, the generation unit dynamically adjusts the generation priority according to the submission time. This improves the effectiveness of the meeting by determining the generation priority based on the submission time of the meeting. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input data on the submission time of the meeting into a generation AI, and the generation AI can perform generation.

[0125] The generation unit can adjust the order of generation based on the relevance of the meetings during generation. The relevance of the meetings includes, but is not limited to, the relevance of the agenda and the relevance of the participants. For example, for a highly relevant meeting, the generation unit can prioritize generating agendas and ideas. Furthermore, for a less relevant meeting, the generation unit can postpone generating agendas and ideas. For example, the generation unit dynamically adjusts the order of generation according to the relevance of the meetings. This improves the effectiveness of the meetings by adjusting the order of generation based on the relevance of the meetings. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input data on the relevance of the meetings into a generation AI, and the generation AI can perform generation.

[0126] During generation, the generation unit can adjust the use of technical terminology in the generated video according to the user's level of expertise. Examples of the level of expertise include, but are not limited to, the participant's work experience and field of expertise. For example, the generation unit uses a lot of technical terminology when the user has specialized knowledge. The generation unit can also avoid technical terminology when the user does not have specialized knowledge. For example, the generation unit dynamically adjusts the use of technical terminology in the generated video according to the user's level of expertise. This improves the effectiveness of the meeting by adjusting the use of technical terminology in the generated video according to the user's level of expertise. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without AI. For example, the generation unit can input data on the user's level of expertise into a generation AI, and the generation AI can perform generation.

[0127] The moderator can estimate the user's emotions and adjust the conference proceeding method based on the estimated user emotions. Examples of methods for adjusting the conference proceeding method based on emotions include, but are not limited to, emotion analysis results and conference proceeding method selection criteria. For example, if the user is nervous, the moderator can suggest a relaxed conference proceeding method. Furthermore, if the user is relaxed, the moderator can also suggest a detailed conference proceeding method. For example, if the user is in a hurry, the moderator can suggest a quick conference proceeding method. This improves the effectiveness of the conference by adjusting the conference proceeding method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the moderator can be performed using AI, or without AI. For example, the moderator can input the user's emotion data into the generation AI, which can then estimate the emotion.

[0128] The proceeding unit can adjust the level of detail of the proceedings based on the importance of the meeting during the proceedings. Examples of the importance of the meeting include, but are not limited to, the purpose of the meeting and the positions of the participants. For example, the proceeding unit can propose a detailed proceeding method for a highly important meeting. The proceeding unit can also propose a concise proceeding method for a low-importance meeting. For example, the proceeding unit dynamically adjusts the level of detail of the proceedings according to the importance of the meeting. This improves the effectiveness of the meeting by adjusting the level of detail of the proceedings according to the importance of the meeting. Some or all of the above-mentioned processing in the proceeding unit may be performed using, for example, AI, or may be performed without using AI. For example, the proceeding unit can input data on the importance of the meeting into a generation AI, and the generation AI can proceed with the proceedings.

[0129] The proceeding unit can apply different proceeding algorithms depending on the category of the meeting during the proceedings. Examples of meeting categories include, but are not limited to, business meetings and technical meetings. For example, in the case of a technical meeting, the proceeding unit can apply a technical proceeding algorithm. Furthermore, in the case of a marketing meeting, the proceeding unit can apply a proceeding algorithm specialized for marketing. For example, in the case of a financial meeting, the proceeding unit can apply a proceeding algorithm specialized for financial data. In this way, the effectiveness of the meeting is enhanced by applying the optimal proceeding algorithm depending on the category of the meeting. Some or all of the above-mentioned processing in the proceeding unit may be performed using, for example, AI, or may be performed without using AI. For example, the proceeding unit can input data on the category of the meeting into a generation AI and have the generation AI perform the proceedings.

[0130] The progression unit can improve the accuracy of progression by referring to the user's past progression results during progression. Past progression results include, but are not limited to, past meeting records and progression accuracy improvement methods. The progression unit can improve the accuracy of progression, for example, based on the user's past progression results. The progression unit can also analyze the user's past progression results and propose an optimal progression method. For example, the progression unit can adjust the progression algorithm by referring to the user's past progression results. This improves the accuracy of progression by referring to the user's past progression results. Some or all of the above-mentioned processing in the progression unit can be performed, for example, using AI or without AI. For example, the progression unit can input data of the user's past progression results into a generation AI and use the generation AI to perform progression.

[0131] The facilitating unit can estimate the user's emotions and determine the priority of the meetings based on the estimated user emotions. Examples of methods for determining the priority of the meetings based on emotions include, but are not limited to, emotion analysis results and priority criteria. For example, if the user is nervous, the facilitating unit can prioritize more important meetings. Furthermore, if the user is relaxed, the facilitating unit can also provide detailed meetings. For example, if the user is in a hurry, the facilitating unit can prioritize quick meetings. This improves the effectiveness of the meeting by determining the priority of the meetings based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the facilitating unit can be performed using AI, or without AI. For example, the facilitating unit can input the user's emotion data into a generation AI, which can then estimate the emotion.

[0132] The progress unit can determine the priority of the progress based on the submission time of the meeting during the progress. The submission time of the meeting includes, but is not limited to, for example, the submission deadline and the timing of submission. For example, the progress unit prioritizes the progress of a meeting with an approaching submission deadline. Furthermore, the progress unit can postpone the progress of a meeting with a distant submission deadline. For example, the progress unit dynamically adjusts the priority of the progress according to the submission time. In this way, the effectiveness of the meeting is improved by determining the priority of the progress based on the submission time of the meeting. Some or all of the above-mentioned processing in the progress unit may be performed using, for example, AI, or may be performed without using AI. For example, the progress unit can input data on the submission time of the meeting into a generation AI and have the generation AI proceed the meeting.

[0133] The proceeding unit can adjust the order of proceedings based on the relevance of the meetings during the proceedings. The relevance of the meetings includes, but is not limited to, for example, the relevance of the agenda and the relevance of the participants. For example, the proceeding unit can prioritize proceedings for highly relevant meetings. Furthermore, the proceeding unit can postpone proceedings for less relevant meetings. For example, the proceeding unit dynamically adjusts the order of proceedings according to the relevance of the meetings. In this way, adjusting the order of proceedings based on the relevance of the meetings enhances the effectiveness of the meetings. Some or all of the above-mentioned processing in the proceeding unit may be performed using, for example, AI, or may be performed without using AI. For example, the proceeding unit can input data on the relevance of the meetings into a generation AI and proceed with the generation AI.

[0134] The moderator can adjust the use of technical terms during the meeting according to the user's level of expertise. Examples of the level of expertise include, but are not limited to, the participant's work experience and field of expertise. For example, the moderator uses a lot of technical terms when the user has specialized knowledge. The moderator can also avoid technical terms when the user does not have specialized knowledge. For example, the moderator dynamically adjusts the use of technical terms during the meeting according to the user's level of expertise. This improves the effectiveness of the meeting by adjusting the use of technical terms during the meeting according to the user's level of expertise. Some or all of the above-described processing in the moderator can be performed using, or without, AI. For example, the moderator can input data on the user's level of expertise into a generation AI, and the generation AI can then guide the meeting.

[0135] The text conversion unit can estimate the user's emotions and adjust the text conversion method for the utterances based on the estimated user emotions. Examples of adjusting the text conversion method for the utterances based on emotions include, but are not limited to, the results of emotion analysis and criteria for selecting the text conversion method. For example, the text conversion unit can perform detailed text conversion when the user is relaxed. The text conversion unit can also perform concise text conversion when the user is in a hurry. For example, the text conversion unit can perform visually stimulating text conversion when the user is excited. This improves the effectiveness of the meeting by adjusting the text conversion method for the utterances based on the user's emotions. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the text conversion unit can be performed using AI, for example, or without AI. For example, the text conversion unit can input the user's emotion data into a generation AI, which can then estimate the emotion.

[0136] The text conversion unit can adjust the level of detail of the text based on the importance of the utterance when converting the utterance into text. The importance of the utterance includes, but is not limited to, the content of the utterance and the position of the speaker. For example, the text conversion unit converts a utterance of high importance into text in detail. The text conversion unit can also convert a utterance of low importance into text in a concise manner. For example, the text conversion unit dynamically adjusts the level of detail of the text depending on the importance of the utterance. This improves the effectiveness of the meeting by adjusting the level of detail of the text depending on the importance of the utterance. Some or all of the above-mentioned processing in the text conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the text conversion unit can input data on the importance of the utterance into a generation AI, and the generation AI can convert the utterance into text.

[0137] The text conversion unit can apply different text conversion algorithms depending on the category of the utterance when converting the utterance into text. Examples of utterance categories include, but are not limited to, technical utterances and business utterances. For example, in the case of technical utterances, the text conversion unit can apply a technical text conversion algorithm. Furthermore, in the case of marketing-related utterances, the text conversion unit can also apply a text conversion algorithm specialized for marketing. For example, in the case of finance-related utterances, the text conversion unit can apply a text conversion algorithm specialized for financial data. This increases the effectiveness of the meeting by applying the optimal text conversion algorithm depending on the category of the utterance. Some or all of the above-mentioned processing in the text conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the text conversion unit can input data on the category of the utterance into a generation AI, and have the generation AI perform the text conversion.

[0138] During text conversion, the text conversion unit can improve the accuracy of the text conversion by referring to the user's past text conversion results. Past text conversion results include, but are not limited to, past meeting records and text conversion accuracy improvement methods. The text conversion unit can improve the accuracy of the text conversion based on, for example, the user's past text conversion results. The text conversion unit can also analyze the user's past text conversion results and propose an optimal text conversion method. For example, the text conversion unit can adjust the text conversion algorithm by referring to the user's past text conversion results. This improves the accuracy of the text conversion by referring to the user's past text conversion results. Some or all of the above-mentioned processing in the text conversion unit can be performed using, for example, AI, or without AI. For example, the text conversion unit can input data of the user's past text conversion results into a generation AI, and the generation AI can perform text conversion.

[0139] The text conversion unit can estimate the user's emotions and determine the priority of text conversion based on the estimated user emotions. Determining the priority of text conversion based on emotions can be done, for example, using emotion analysis results and priority determination criteria, but is not limited to these examples. For example, if the user is nervous, the text conversion unit can prioritize important utterances to text. Furthermore, if the user is relaxed, the text conversion unit can also transcribe detailed utterances to text. For example, if the user is in a hurry, the text conversion unit can prioritize concise utterances to text. This improves the effectiveness of meetings by determining the priority of text conversion based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the text conversion unit can be performed using AI, or without AI. For example, the text conversion unit can input the user's emotion data into a generation AI, which can then estimate the emotion.

[0140] The text conversion unit can determine the priority of text conversion based on the time of submission of the utterance when converting the utterance into text. The time of submission of the utterance includes, but is not limited to, the submission deadline and the timing of submission. For example, the text conversion unit prioritizes text conversion for utterances with an approaching submission deadline. The text conversion unit can also postpone text conversion for utterances with a distant submission deadline. For example, the text conversion unit dynamically adjusts the priority of text conversion depending on the submission time. This improves the effectiveness of the meeting by determining the priority of text conversion based on the time of submission of the utterance. Some or all of the above-mentioned processing in the text conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the text conversion unit can input data on the time of submission of the utterance into a generation AI, and the generation AI can perform text conversion.

[0141] The text conversion unit can adjust the order of text conversion based on the relevance of the utterances during text conversion. The relevance of the utterances includes, but is not limited to, the relevance of the agenda and the relevance of the speaker. For example, the text conversion unit prioritizes text conversion for highly relevant utterances. The text conversion unit can also postpone text conversion for less relevant utterances. For example, the text conversion unit dynamically adjusts the order of text conversion according to the relevance of the utterances. This improves the effectiveness of the meeting by adjusting the order of text conversion based on the relevance of the utterances. Some or all of the above-described processing in the text conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the text conversion unit can input data on the relevance of the utterances into a generation AI, and the generation AI can perform text conversion.

[0142] The text conversion unit can adjust the use of technical terms in the text conversion according to the user's level of expertise. Examples of the level of expertise include, but are not limited to, the speaker's work experience and field of expertise. For example, the text conversion unit uses a lot of technical terms when the user has specialized knowledge. The text conversion unit can also avoid technical terms when the user does not have specialized knowledge. For example, the text conversion unit dynamically adjusts the use of technical terms in the text conversion according to the user's level of expertise. This improves the effectiveness of the meeting by adjusting the use of technical terms in the text conversion according to the user's level of expertise. Some or all of the above-described processing in the text conversion unit may be performed using, for example, AI, or may be performed without AI. For example, the text conversion unit can input data on the user's level of expertise into a generation AI, and the generation AI can perform the text conversion.

[0143] The decision unit can estimate the user's emotions and adjust the decision clarification method based on the estimated user emotions. Examples of ways to adjust the decision clarification method based on emotions include, but are not limited to, the results of emotion analysis and selection criteria for the clarification method. For example, if the user is relaxed, the decision unit can clarify detailed decisions. Furthermore, if the user is in a hurry, the decision unit can also clarify concise decisions. For example, if the user is excited, the decision unit can clarify visually stimulating decisions. This improves the effectiveness of meetings by adjusting the decision clarification method according to the user's emotions. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the decision unit can be performed using, for example, an AI, or without an AI. For example, the decision unit can input the user's emotion data into a generation AI, which can then estimate the emotion.

[0144] When making a decision, the decision unit can adjust the level of detail of the decision items based on the importance of the meeting. The importance of the meeting includes, but is not limited to, the purpose of the meeting and the positions of the participants. For example, the decision unit clarifies detailed decision items for a highly important meeting. Furthermore, the decision unit can also clarify concise decision items for a less important meeting. For example, the decision unit dynamically adjusts the level of detail of the decision items according to the importance of the meeting. This enhances the effectiveness of the meeting by adjusting the level of detail of the decision items according to the importance of the meeting. Some or all of the above-described processing in the decision unit may be performed using, for example, AI, or may be performed without using AI. For example, the decision unit can input data on the importance of the meeting into a generation AI, which then makes a decision.

[0145] When making a decision, the decision unit can apply different decision algorithms depending on the category of the meeting. Examples of meeting categories include, but are not limited to, business meetings and technical meetings. For example, in the case of a technical meeting, the decision unit can apply a technical decision algorithm. Furthermore, in the case of a marketing meeting, the decision unit can also apply a decision algorithm specialized for marketing. For example, in the case of a financial meeting, the decision unit can apply a decision algorithm specialized for financial data. This increases the effectiveness of the meeting by applying the optimal decision algorithm depending on the category of the meeting. Some or all of the above-described processing in the decision unit may be performed using, for example, AI, or may be performed without using AI. For example, the decision unit can input data on the category of the meeting into a generation AI, and the generation AI can make a decision.

[0146] When making a decision, the decision unit can improve the accuracy of the decision by referring to the user's past decision results. Past decision results include, but are not limited to, past meeting records and methods for improving decision accuracy. The decision unit can improve the accuracy of the decision, for example, based on the user's past decision results. The decision unit can also analyze the user's past decision results and propose an optimal decision method. For example, the decision unit can adjust the decision algorithm by referring to the user's past decision results. This improves the accuracy of the decision by referring to the user's past decision results. Some or all of the above-mentioned processing in the decision unit can be performed, for example, using AI or without AI. For example, the decision unit can input data on the user's past decision results into a generation AI and have the generation AI make a decision.

[0147] The determination unit can estimate the user's emotions and prioritize decisions based on the estimated user emotions. Determining the priority of decisions based on emotions can be done, for example, using emotion analysis results and priority criteria, but is not limited to these examples. For example, if the user is nervous, the determination unit can prioritize and clarify decisions of high importance. The determination unit can also prioritize and clarify detailed decisions when the user is relaxed. For example, if the user is in a hurry, the determination unit can prioritize and clarify simple decisions. This improves the effectiveness of meetings by prioritizing decisions based on the user's emotions. The emotion estimation can be achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the determination unit can be performed using an AI, for example, or without an AI. For example, the determination unit can input the user's emotion data into a generation AI, which can then estimate the emotion.

[0148] When making a decision, the determination unit can determine the priority of the decision items based on the submission time of the meeting. The submission time of the meeting includes, but is not limited to, for example, a submission deadline or the timing of submission. For example, the determination unit prioritizes clarifying the decision items for a meeting with an upcoming submission deadline. Furthermore, the determination unit can postpone clarifying the decision items for a meeting with a distant submission deadline. For example, the determination unit dynamically adjusts the priority of the decision items according to the submission time. This improves the effectiveness of the meeting by determining the priority of the decision items based on the submission time of the meeting. Some or all of the above-mentioned processing in the determination unit may be performed using, for example, AI, or may be performed without using AI. For example, the determination unit can input data on the submission time of the meeting into a generation AI, and the generation AI can make a decision.

[0149] When making a decision, the decision unit can adjust the order of the decisions based on the relevance of the meeting. The relevance of the meeting includes, but is not limited to, the relevance of the agenda and the relevance of the participants. For example, the decision unit prioritizes clarifying the decisions for a highly relevant meeting. Furthermore, the decision unit can postpone clarifying the decisions for a less relevant meeting. For example, the decision unit dynamically adjusts the order of the decisions according to the relevance of the meeting. This improves the effectiveness of the meeting by adjusting the order of the decisions based on the relevance of the meeting. Some or all of the above-described processing in the decision unit may be performed using, for example, AI, or may be performed without using AI. For example, the decision unit can input data on the relevance of the meeting into a generation AI, and the generation AI can make a decision.

[0150] When making a decision, the decision unit can adjust the use of technical terminology in the decision depending on the user's level of expertise. Examples of the level of expertise include, but are not limited to, the participant's work experience and field of expertise. For example, the decision unit uses a lot of technical terminology when the user has specialized knowledge. The decision unit can also avoid technical terminology when the user does not have specialized knowledge. For example, the decision unit dynamically adjusts the use of technical terminology in the decision depending on the user's level of expertise. This improves the effectiveness of the meeting by adjusting the use of technical terminology in the decision depending on the user's level of expertise. Some or all of the above-described processing in the decision unit may be performed using, for example, AI, or may be performed without using AI. For example, the decision unit can input data on the user's level of expertise into a generation AI, and the generation AI can make a decision.

[0151] The minutes generation unit can estimate the user's emotions and adjust the minutes generation method based on the estimated user emotions. Examples of adjusting the minutes generation method based on emotions include, but are not limited to, the results of emotion analysis and selection criteria for the generation method. For example, the minutes generation unit can generate detailed minutes when the user is relaxed. The minutes generation unit can also generate concise minutes when the user is in a hurry. For example, the minutes generation unit can generate visually stimulating minutes when the user is excited. This improves the effectiveness of the meeting by adjusting the minutes generation method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the minutes generation unit can be performed using AI, or without AI. For example, the minutes generation unit can input the user's emotion data into the generation AI, which can then estimate the emotion.

[0152] When generating minutes, the minutes generation unit can adjust the level of detail in the minutes based on the importance of the meeting. The importance of the meeting includes, but is not limited to, the purpose of the meeting and the titles of the participants. For example, the minutes generation unit generates detailed minutes for a highly important meeting. Furthermore, the minutes generation unit can also generate concise minutes for a less important meeting. For example, the minutes generation unit dynamically adjusts the level of detail in the minutes according to the importance of the meeting. This enhances the effectiveness of the meeting by adjusting the level of detail in the minutes according to the importance of the meeting. Some or all of the above-described processing in the minutes generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the minutes generation unit can input data on the importance of the meeting into a generation AI, which then generates minutes.

[0153] When generating minutes, the minutes generation unit can apply different minutes generation algorithms depending on the category of the meeting. Examples of meeting categories include, but are not limited to, business meetings and technical meetings. For example, in the case of a technical meeting, the minutes generation unit can apply a technical minutes generation algorithm. Furthermore, in the case of a marketing meeting, the minutes generation unit can also apply a minutes generation algorithm specialized for marketing. For example, in the case of a financial meeting, the minutes generation unit can apply a minutes generation algorithm specialized for financial data. This increases the effectiveness of the meeting by applying the optimal minutes generation algorithm depending on the category of the meeting. Some or all of the above-described processing in the minutes generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the minutes generation unit can input data on the category of the meeting into a generation AI, which then generates minutes.

[0154] When generating minutes, the minutes generation unit can improve the accuracy of the minutes generation by referring to the user's past minutes generation results. Past minutes generation results include, but are not limited to, past meeting records and generation accuracy improvement methods. The minutes generation unit can improve the accuracy of the minutes generation, for example, based on the user's past minutes generation results. The minutes generation unit can also analyze the user's past minutes generation results and propose an optimal minutes generation method. For example, the minutes generation unit can adjust the minutes generation algorithm by referring to the user's past minutes generation results. This improves the accuracy of the minutes generation by referring to the user's past minutes generation results. Some or all of the above-mentioned processing in the minutes generation unit can be performed, for example, using AI or without AI. For example, the minutes generation unit can input data of the user's past minutes generation results into a generation AI and generate minutes using the generation AI.

[0155] The minutes generation unit can estimate the user's emotions and prioritize the minutes based on the estimated user emotions. Prioritizing the minutes based on emotions can be achieved, for example, by using emotion analysis results and priority criteria, but is not limited to these examples. For example, if the user is nervous, the minutes generation unit can prioritize generating minutes of high importance. Furthermore, if the user is relaxed, the minutes generation unit can also generate detailed minutes. For example, if the user is in a hurry, the minutes generation unit can prioritize generating concise minutes. This improves the effectiveness of the meeting by prioritizing the minutes based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the minutes generation unit can be performed using, for example, AI, or without AI. For example, the minutes generation unit can input the user's emotion data into the generation AI, which can then estimate the emotion.

[0156] When generating minutes, the minutes generation unit can determine the priority of minutes based on the submission time of the meeting. The submission time of the meeting includes, but is not limited to, for example, the submission deadline and the timing of submission. For example, the minutes generation unit prioritizes the generation of minutes for a meeting with an upcoming submission deadline. The minutes generation unit can also postpone the generation of minutes for a meeting with a distant submission deadline. For example, the minutes generation unit dynamically adjusts the priority of minutes according to the submission time. This improves the effectiveness of the meeting by determining the priority of minutes based on the submission time of the meeting. Some or all of the above-mentioned processing in the minutes generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the minutes generation unit can input data on the submission time of the meeting into a generation AI, and the generation AI can generate minutes.

[0157] When generating minutes, the minutes generation unit can adjust the order of the minutes based on the relevance of the meeting. The relevance of the meeting includes, but is not limited to, the relevance of the agenda and the relevance of the participants. For example, the minutes generation unit prioritizes generating minutes for a highly relevant meeting. The minutes generation unit can also postpone generating minutes for a less relevant meeting. For example, the minutes generation unit dynamically adjusts the order of the minutes according to the relevance of the meeting. This improves the effectiveness of the meeting by adjusting the order of the minutes based on the relevance of the meeting. Some or all of the above-mentioned processing in the minutes generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the minutes generation unit can input data on the relevance of the meeting into a generation AI, and the generation AI can generate minutes.

[0158] When generating minutes, the minutes generation unit can adjust the use of technical terms in the minutes according to the user's level of expertise. Examples of the level of expertise include, but are not limited to, the participants' work experience and fields of expertise. For example, the minutes generation unit uses a lot of technical terms if the user has technical expertise. Furthermore, the minutes generation unit can avoid technical terms if the user does not have technical expertise. For example, the minutes generation unit dynamically adjusts the use of technical terms in the minutes according to the user's level of expertise. This improves the effectiveness of the meeting by adjusting the use of technical terms in the minutes according to the user's level of expertise. Some or all of the above-described processing in the minutes generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the minutes generation unit can input data on the user's level of expertise into a generation AI, which then generates minutes.

[0159] The sharing unit can estimate the user's emotions and adjust the sharing method of the minutes based on the estimated user emotions. Examples of adjusting the sharing method of the minutes based on emotions include, but are not limited to, the results of emotion analysis and criteria for selecting the sharing method. For example, if the user is relaxed, the sharing unit can share detailed minutes. Also, if the user is in a hurry, the sharing unit can share concise minutes. For example, if the user is excited, the sharing unit can share visually stimulating minutes. This improves the effectiveness of the meeting by adjusting the sharing method of the minutes based on the user's emotions. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the sharing unit can be performed using AI, or without AI. For example, the sharing unit can input the user's emotion data into the generation AI, which can then estimate the emotion.

[0160] The sharing unit can adjust the level of detail of the shared information based on the importance of the meeting when sharing. The importance of the meeting includes, but is not limited to, the purpose of the meeting and the roles of the participants, for example. For example, the sharing unit shares detailed minutes for a highly important meeting. Furthermore, the sharing unit can also share concise minutes for a less important meeting. For example, the sharing unit dynamically adjusts the level of detail of the shared information based on the importance of the meeting. This enhances the effectiveness of the meeting by adjusting the level of detail of the shared information based on the importance of the meeting. Some or all of the above-described processing in the sharing unit may be performed using, for example, AI, or may be performed without using AI. For example, the sharing unit can input data on the importance of the meeting into a generating AI, and the generating AI can perform sharing.

[0161] When sharing, the sharing unit can apply different sharing algorithms depending on the category of the meeting. Examples of meeting categories include, but are not limited to, business meetings and technical meetings. For example, in the case of a technical meeting, the sharing unit can apply a technical sharing algorithm. Furthermore, in the case of a marketing meeting, the sharing unit can also apply a sharing algorithm specialized for marketing. For example, in the case of a financial meeting, the sharing unit can apply a sharing algorithm specialized for financial data. This increases the effectiveness of the meeting by applying the optimal sharing algorithm depending on the category of the meeting. Some or all of the above-mentioned processing in the sharing unit may be performed using, for example, AI, or may be performed without using AI. For example, the sharing unit can input data of the category of the meeting into a generating AI, and the generating AI can perform sharing.

[0162] The sharing unit can improve the accuracy of sharing by referring to the user's past sharing results when sharing. Past sharing results include, but are not limited to, past meeting records and methods for improving sharing accuracy. The sharing unit can improve the accuracy of sharing, for example, based on the user's past sharing results. The sharing unit can also analyze the user's past sharing results and propose an optimal sharing method. For example, the sharing unit can adjust the sharing algorithm by referring to the user's past sharing results. This improves the accuracy of sharing by referring to the user's past sharing results. Some or all of the above-mentioned processing in the sharing unit can be performed, for example, using AI or without AI. For example, the sharing unit can input data of the user's past sharing results into a generation AI and perform sharing using the generation AI.

[0163] The sharing unit can estimate the user's emotions and determine sharing priorities based on the estimated user emotions. Determining sharing priorities based on emotions can include, but is not limited to, emotion analysis results and priority determination criteria. For example, if the user is nervous, the sharing unit can prioritize sharing of important minutes. Furthermore, if the user is relaxed, the sharing unit can also share detailed minutes. For example, if the user is in a hurry, the sharing unit can prioritize sharing of concise minutes. This improves the effectiveness of meetings by determining sharing priorities based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the sharing unit can be performed using AI, for example, or without AI. For example, the sharing unit can input the user's emotion data into a generation AI, which can then estimate the emotion.

[0164] The sharing unit can determine the priority of sharing based on the submission time of the meeting when sharing. The submission time of the meeting includes, but is not limited to, for example, the submission deadline and the timing of submission. For example, the sharing unit prioritizes sharing of minutes for a meeting with an upcoming submission deadline. The sharing unit can also postpone sharing of minutes for a meeting with a distant submission deadline. For example, the sharing unit dynamically adjusts the priority of sharing according to the submission time. This improves the effectiveness of the meeting by determining the priority of sharing based on the submission time of the meeting. Some or all of the above-mentioned processing in the sharing unit may be performed using, for example, AI, or may be performed without using AI. For example, the sharing unit can input data on the submission time of the meeting into a generation AI, and the generation AI can perform sharing.

[0165] The sharing unit can adjust the sharing order based on the relevance of the meetings when sharing. The relevance of the meetings includes, but is not limited to, for example, the relevance of the agenda and the relevance of the participants. For example, the sharing unit prioritizes sharing of minutes for highly relevant meetings. Furthermore, the sharing unit can also postpone sharing of minutes for less relevant meetings. For example, the sharing unit dynamically adjusts the sharing order according to the relevance of the meetings. In this way, adjusting the sharing order based on the relevance of the meetings enhances the effectiveness of the meetings. Some or all of the above-described processing in the sharing unit may be performed using, for example, AI, or may be performed without using AI. For example, the sharing unit can input data on the relevance of the meetings into a generation AI, and the generation AI can perform sharing.

[0166] During sharing, the sharing unit can adjust the use of shared terminology according to the user's level of expertise. Examples of expertise levels include, but are not limited to, the participant's work experience and field of expertise. For example, the sharing unit uses a lot of terminology if the user has expertise. The sharing unit can also avoid terminology if the user does not have expertise. For example, the sharing unit dynamically adjusts the use of shared terminology according to the user's level of expertise. This enhances the effectiveness of the meeting by adjusting the use of shared terminology according to the user's level of expertise. Some or all of the above-described processing in the sharing unit may be performed using, for example, AI, or may be performed without AI. For example, the sharing unit can input data on the user's level of expertise into a generating AI, and the generating AI can perform sharing. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation unit, progress unit, text conversion unit, determination unit, minutes generation unit, and sharing unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12. For example, the generation unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the progress unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the text conversion unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the determination unit is realized by the specific processing unit 290 of the data processing device 12. For example, the minutes generation unit is realized by the specific processing unit 290 of the data processing device 12. For example, the sharing unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation unit, progress unit, text conversion unit, determination unit, minutes generation unit, and sharing unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12. For example, the generation unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the progress unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the text conversion unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the determination unit is realized by the specific processing unit 290 of the data processing device 12. For example, the minutes generation unit is realized by the specific processing unit 290 of the data processing device 12. For example, the sharing unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation unit, progress unit, text conversion unit, determination unit, minutes generation unit, and sharing unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12. For example, the generation unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the progress unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the text conversion unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the determination unit is realized by the specific processing unit 290 of the data processing device 12. For example, the minutes generating unit is realized by the specific processing unit 290 of the data processing device 12. For example, the sharing unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation unit, progress unit, text conversion unit, determination unit, minutes generation unit, and sharing unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12. For example, the generation unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the progress unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the text conversion unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the determination unit is realized by the specific processing unit 290 of the data processing device 12. For example, the minutes generation unit is realized by the specific processing unit 290 of the data processing device 12. For example, the shared unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12.

[0167] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0168] The conference support system can further include a feedback collection unit. The feedback collection unit collects feedback from participants after the conference ends and provides it to the analysis unit. For example, the feedback collection unit sends a questionnaire to participants regarding the progress and content of the conference and sends the results to the analysis unit. The feedback collection unit can also estimate emotions from participants' facial expressions and voices and evaluate their satisfaction with the conference. This allows the conference support system to identify areas for improvement for the next conference based on participants' feedback and achieve more effective conference management.

[0169] The conference support system can further include a translation unit. The translation unit supports communication between participants who speak different languages. For example, the translation unit translates what one participant says in real time and provides it to other participants. The translation unit can also generate minutes in multiple languages ​​and share them with participants. This allows the conference support system to achieve smooth communication even in international conferences, thereby improving the effectiveness of the conference.

[0170] The conference support system can further include a reminder unit. The reminder unit sends reminders to participants before and after the conference. For example, the reminder unit notifies participants of the conference start time and preparation items. The reminder unit can also remind participants of next actions and deadlines after the conference ends. This allows the conference support system to support participants in reliably preparing for and following up on the conference, thereby improving the effectiveness of the conference.

[0171] The conference support system can further include a networking unit. The networking unit promotes interaction between conference participants. For example, the networking unit matches participants with common interests based on the participant profiles and areas of interest, and provides opportunities for interaction. The networking unit can also provide a function that allows participants to exchange contact information after the conference ends. In this way, the conference support system can promote networking between participants and increase the effectiveness of the conference.

[0172] The conference support system may further include a data visualization unit. The data visualization unit visually displays data and information discussed during the conference. For example, the data visualization unit may generate graphs and charts and provide them to participants. The data visualization unit may also display data fluctuations in real time, allowing participants to intuitively understand them. This allows the conference support system to facilitate understanding of the data and improve the effectiveness of the conference.

[0173] The conference support system can further include an emotion analysis unit. The emotion analysis unit analyzes the emotions of the participants during the conference in real time and provides the result to the conference moderator. For example, the emotion analysis unit estimates the emotions of the participants from their facial expressions and voices and provides feedback to the conference moderator. The emotion analysis unit can also generate a report of changes in the emotions of the participants after the conference ends. This allows the conference support system to adjust the progress of the conference based on the emotions of the participants and improve the effectiveness of the conference.

[0174] The meeting support system may further include a virtual reality (VR) unit. The VR unit supports participants in holding meetings in a virtual space. For example, the VR unit may provide a virtual conference room, allowing participants to experience a realistic meeting even from a remote location. The VR unit may also provide the ability to use a virtual whiteboard or 3D model during a meeting. This allows the meeting support system to enhance communication with remote participants and improve the effectiveness of the meeting.

[0175] The conference support system can further include a health management unit. The health management unit monitors the health status of participants during the conference and provides the information to the conference moderator. For example, the health management unit measures the heart rate and stress level of participants and provides feedback to the conference moderator. The health management unit can also suggest appropriate times to take breaks during the conference. This allows the conference support system to manage the conference while taking into consideration the health of the participants, thereby improving the effectiveness of the conference.

[0176] The conference support system may further include an entertainment unit. The entertainment unit provides entertainment to help participants relax and increase their concentration during the conference. For example, the entertainment unit may provide short videos or music between conferences to help participants refresh themselves. The entertainment unit may also provide games or quizzes to encourage interaction between participants after the conference has ended. This allows the conference support system to help participants relax and increase their concentration, improving the effectiveness of the conference.

[0177] The conference support system can further include an environmental monitoring unit. The environmental monitoring unit monitors the conference room environment in real time and provides the results to the conference moderator. For example, the environmental monitoring unit measures the temperature, humidity, and CO2 concentration in the conference room and provides feedback to the conference moderator. The environmental monitoring unit can also suggest appropriate ventilation and temperature adjustments during the conference. This allows the conference support system to run the conference in a comfortable environment and improve the effectiveness of the conference.

[0178] The processing flow of the second embodiment will be briefly explained below.

[0179] Step 1: The reception unit inputs the goal of the meeting. The goal of the meeting includes, but is not limited to, for example, the purpose of the meeting and a goal to be achieved. For example, the reception unit receives input from a user of the purpose of the meeting and a goal to be achieved. The reception unit can also support multiple input methods, such as voice input, text input, and image input. For example, the reception unit may preferentially provide voice input to a user who prefers voice input, and preferentially provide text input to a user who prefers text input. Step 2: The analysis unit analyzes the information input by the reception unit. The analysis is performed based on, for example, past data and trends, but is not limited to such examples. For example, the analysis unit analyzes past meeting records and industry trends to generate agendas and ideas. The analysis unit can also estimate the user's emotions and adjust the way the analysis is presented. For example, the analysis unit provides detailed analysis results if the user is relaxed, and provides concise analysis results if the user is in a hurry. Step 3: The generation unit generates an agenda and ideas based on the information analyzed by the analysis unit. Generation is performed, for example, based on the list of topics and the type of ideas, but is not limited to such examples. For example, the generation unit generates a technical agenda and ideas for a technical meeting, and generates a marketing-specific agenda and ideas for a marketing meeting. The generation unit can also estimate the user's emotions and adjust the generation method. For example, the generation unit generates a detailed agenda and ideas if the user is relaxed, and generates a concise agenda and ideas if the user is in a hurry. Step 4: The proceedings unit grasps the progress of the meeting in real time. The progress is grasped based on, for example, the progress stages and time management, but is not limited to these examples. For example, the proceedings unit monitors the progress of the meeting in real time and suggests the timing to move on to the next agenda item. The proceedings unit can also estimate the user's emotions and adjust the proceeding method. For example, if the user is nervous, the proceedings unit suggests a relaxing proceeding method, and if the user is in a hurry, the proceedings unit suggests a quick proceeding method. Step 5: The text conversion unit converts the participants' comments into text. The conversion can be performed, for example, based on voice recognition technology or text formatting, but is not limited to these examples. The text conversion unit converts the participants' comments into text using voice recognition technology, for example, and emphasizes important points. The text conversion unit can also estimate the user's emotions and adjust the text conversion method. For example, the text conversion unit can convert the comments into detailed text if the user is relaxed, and convert the comments into concise text if the user is in a hurry. Step 6: The decision unit clarifies the decisions and next actions at the end of the meeting. The clarification of the decisions is performed, for example, based on the type of decision and the next action, but is not limited to such examples. For example, the decision unit clarifies the product specifications, development schedule, and person in charge at the end of the meeting. The decision unit can also estimate the user's emotions and adjust the method of clarifying the decisions. For example, the decision unit clarifies detailed decisions when the user is relaxed, and clarifies simple decisions when the user is in a hurry. Step 7: The minutes generation unit automatically creates minutes. The automatic creation of minutes is performed based on, for example, but not limited to, the algorithm used and the type of information recorded. For example, the minutes generation unit generates minutes immediately after the meeting ends and sends them by email to all participants. The minutes generation unit can also estimate the user's emotions and adjust the method of generating minutes. For example, the minutes generation unit generates detailed minutes if the user is relaxed, and generates concise minutes if the user is in a hurry. Step 8: The sharing unit automatically shares the minutes with the meeting participants. The automatic sharing is performed based on, for example, the platform to be shared and the timing of sharing, but is not limited to these examples. For example, the sharing unit can send the minutes by email or upload them to cloud storage for sharing. The sharing unit can also estimate the user's emotions and adjust the sharing method. For example, the sharing unit can share detailed minutes if the user is relaxed, and share brief minutes if the user is in a hurry.

[0180] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0181] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0182] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0183] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0184] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0185] 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.

[0186] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0187] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0188] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0189] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0190] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0191] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0192] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0193] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0194] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0195] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0196] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0197] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0198] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0199] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0200] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0201] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0202] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0203] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0204] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0205] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0206] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0207] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0208] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0209] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0210] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0211] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0212] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0213] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0214] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0215] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0216] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0217] 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.

[0218] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0219] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0220] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0221] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0222] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0223] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0224] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0225] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0226] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0227] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0228] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0229] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0230] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0231] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0232] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0233] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0234] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0235] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0236] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0237] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0238] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0239] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0240] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0241] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0242] 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.

[0243] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0244] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0245] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0246] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0247] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0248] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0249] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0250] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0251] [Explanation of symbols]

[0252] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A reception desk where the goals of the meeting are entered; an analysis unit that analyzes the information input by the reception unit; a generation unit that generates an agenda or ideas based on the information analyzed by the analysis unit; A progress team that keeps track of the progress of the meeting in real time, a text converter that converts participants' comments into text; A decision-making section that clarifies decisions and next actions at the end of the meeting; a minutes generation unit that automatically creates minutes; A sharing unit that automatically shares the minutes with meeting participants. A system characterized by:

2. The reception unit Enter the purpose of the meeting and the goals you want to achieve 2. The system of claim 1.

3. The analysis unit Generate an agenda or ideas based on historical data or trends 2. The system of claim 1.

4. The progression section Get real-time insight into meeting progress and suggest when to move on to the next topic 2. The system of claim 1.

5. The text conversion unit Transcribe what participants say and highlight key points 2. The system of claim 1.

6. The determination unit Clarify decisions and next steps at the end of the meeting 2. The system of claim 1.

7. The minutes generation unit Automatically create meeting minutes 2. The system of claim 1.

8. The common part is Automatically share meeting minutes with meeting participants 2. The system of claim 1.

Images