System

Abstract

To provide a system that causes generative AIs to discuss with each other and dig deep into a theme to create something.SOLUTION: A system according to the embodiment comprises a reception unit, a discussion unit, a suggestion unit, and a management unit. The reception unit receives input of a theme. The discussion unit causes a plurality of generation AIs to hold a discussion based on the theme received by the reception unit. The suggestion unit aggregates opinions obtained by the discussion unit, and suggests a solution. The management unit manages the progress of the discussion.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 a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology does not efficiently advance discussions or consolidate opinions using generative AI, and there is room for improvement.

[0005] The system of the embodiment aims to have generative AIs discuss with each other and delve deeper into themes to create something. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, a discussion unit, a proposal unit, and a management unit. The reception unit accepts input of a theme. The discussion unit has multiple generation AIs hold discussions based on the theme accepted by the reception unit. The proposal unit consolidates opinions obtained by the discussion unit and proposes solutions. The management unit manages the progress of the discussion. Effect of the Invention

[0007] The system of the embodiment allows generative AIs to hold discussions with each other and delve deeper into themes to create more. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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 PREFERRED EMBODIMENTS

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

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

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs and 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 code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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, the RAM 30, and the 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 (e.g., 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., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to 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 Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[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 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. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The creation support system according to the embodiment of the present invention uses multiple generation AIs simultaneously, and allows the generation AIs to discuss with each other and create by digging deeper into a theme. This creation support system allows the user to select how many AIs to discuss with by operating a button, and also allows the user to check the log during the process. Specifically, first, the user inputs the theme that the user wants to discuss. Next, the user selects the number of generation AIs to participate in the discussion by operating a button. The selected generation AIs start a discussion based on the theme, and each generation AI states its opinion. The generation AIs deepen the discussion based on each other's opinions, and finally propose a creative solution to the theme. The user can check the log during the discussion, and can also correct the direction of the discussion as necessary. For example, the user can adjust the content of the discussion by providing feedback on the opinion of a specific generation AI. This system makes it possible for multiple generation AIs to cooperate to dig deeper into a theme and propose creative solutions. The user can manage discussions between the generation AIs with simple operations and efficiently obtain creative ideas. This allows the creation support system to allow multiple generation AIs to cooperate to dig deeper into a theme and propose creative solutions.

[0029] The creation support system according to the embodiment includes a reception unit, a discussion unit, a proposal unit, and a management unit. The reception unit inputs a theme that the user wants to have discussed. For example, themes include, but are not limited to, technical problems, business strategies, and social problems. The reception unit selects the number of generation AIs to participate in the discussion by the user by operating a button. For example, if the user selects three generation AIs, the three generation AIs will participate in the discussion. In the discussion unit, the generation AIs hold a discussion. The generation AIs express their opinions using, for example, a text generation AI (for example, LLM). The generation AIs deepen the discussion based on each other's opinions. For example, the generation AI receives a prompt saying "Please express your opinion on this topic," and each generation AI expresses its opinion. The proposal unit aggregates the opinions of the generation AIs and proposes a final solution. For example, the proposal unit proposes the most appropriate solution based on the opinions expressed by the generation AIs. The management unit manages the progress of the discussion. For example, it monitors the progress of the discussion and makes adjustments as necessary. The management unit records the progress of the discussion as a log. For example, it records the content and progress of the discussion so that it can be checked later. As a result, in the creativity support system according to the embodiment, multiple generation AIs cooperate to delve into a theme and propose creative solutions. Some or all of the above-mentioned processing in the management unit may be performed, for example, using AI, or may be performed without using AI. For example, the management unit may manage the progress of the discussion using an AI model that monitors the progress of the discussion and adjusts the direction of the discussion as necessary.

[0030] The reception unit inputs the theme that the user wants to discuss. Examples of themes include, but are not limited to, technical issues, business strategies, and social issues. The reception unit selects the number of generation AIs to participate in the discussion by the user by operating a button. For example, if the user selects three generation AIs, the three generation AIs will participate in the discussion. The reception unit is designed to be intuitively operated through a user interface, and is provided with a theme input field and a generation AI selection button. The theme input field is in a free-form format, allowing the user to describe specific problems and issues in detail. In addition, the reception unit also has a function to refer to previously entered themes and discussion history, allowing the user to set a new theme based on the content of past discussions. When selecting a generation AI, the characteristics and areas of expertise of each generation AI are displayed, allowing the user to select the optimal generation AI depending on the purpose of the discussion. For example, a technology-specialized generation AI can be selected for technical issues, and a business-specialized generation AI can be selected for business strategies. In this way, the reception unit supports the user to start a discussion efficiently and effectively.

[0031] In the discussion section, the generation AIs hold discussions. The generation AIs express their opinions using, for example, text generation AIs (e.g., LLM). The generation AIs deepen the discussion based on each other's opinions. For example, the generation AIs receive a prompt saying, "Please express your opinion on this topic," and each generation AI expresses its opinion. The discussion section sets up a protocol for the generation AIs to efficiently advance the discussion, and supports multiple discussion formats, such as a format in which each generation AI expresses its opinion in turn and a format in which discussions are focused on a specific topic. The generation AIs use natural language processing technology to express opinions from multiple perspectives on the topic entered by the user. For example, for technical problems, they can express opinions that take into account not only technical solutions but also costs, feasibility, and risks. In addition, the generation AIs deepen the discussion by analyzing the opinions of other generation AIs in real time and expressing counterarguments and supplementary opinions. The discussion section converts the opinions expressed by the generation AIs into text in real time, allowing users to visually check the progress of the discussion. This allows the generation AI to hold discussions efficiently and effectively, enabling the discussion section to provide useful information to users.

[0032] The proposal unit aggregates the opinions of the generation AI and proposes a final solution. For example, it proposes the most appropriate solution based on the opinions stated by the generation AI. The proposal unit has the function of classifying the opinions stated by the generation AI and organizing them based on importance and relevance. Specifically, it analyzes the opinions stated by the generation AI using text mining technology and extracts common themes and keywords. This allows the proposal unit to efficiently aggregate the opinions of the generation AI and eliminate duplication and contradiction. Furthermore, the proposal unit simulates multiple solutions based on the opinions of the generation AI and selects the most effective solution from among them. For example, for technical problems, it compares multiple technical solutions and comprehensively evaluates costs, feasibility, risks, etc. to propose the optimal solution. The proposal unit provides the user with a detailed explanation of the solution and implementation steps, and presents a specific action plan. This allows the proposal unit to support the user in taking concrete action based on the opinions of the generation AI.

[0033] The management unit manages the progress of the discussion. For example, it monitors the progress of the discussion and makes adjustments as necessary. The management unit has the function of monitoring the progress of the discussion in real time and adjusting so that the generation AI expresses its opinion at the appropriate time. Specifically, it manages the order and time in which the generation AI expresses its opinion, and balances the discussion so that it is not biased. In addition, the management unit records the progress of the discussion as a log so that it can be checked later. For example, it records the content and progress of the discussion in text format so that the user can check the progress of the discussion later. In addition, the management unit provides an interface to smooth the progress of the discussion and has a dashboard that allows users to visually check the progress of the discussion. The dashboard displays the opinions of the generation AI and the progress of the discussion in real time, allowing users to intuitively grasp the progress of the discussion. The management unit not only monitors the progress of the discussion, but can also adjust the direction of the discussion as necessary. For example, if the discussion is too biased toward a specific topic or if misunderstandings or confusion occur when the generation AI expresses its opinion, the management unit intervenes at the appropriate time and corrects the direction of the discussion. This allows the management department to support discussions so that they proceed efficiently and effectively, and provide users with a useful forum for discussion.

[0034] The management unit can monitor the progress of the discussion and make adjustments as necessary. The management unit, for example, monitors the progress of the discussion. For example, it monitors the stage of the discussion and the speed of progress. The management unit can also adjust the direction of the discussion as necessary. For example, if the discussion is stagnating, the management unit proposes a new direction of the discussion. This improves the quality of the discussion by appropriately managing the progress of the discussion and making adjustments as necessary. Some or all of the above-mentioned processing in the management unit may be performed, for example, using AI or may be performed without using AI. For example, the management unit can manage the progress of the discussion using an AI model that monitors the progress of the discussion and adjusts the direction of the discussion as necessary.

[0035] The reception unit allows the user to select the number of generation AIs to participate in the discussion by button operation. The reception unit, for example, allows the user to select the number of generation AIs to participate in the discussion by button operation. For example, if the user selects three generation AIs, the three generation AIs participate in the discussion. The reception unit can also adjust the scale of the discussion based on the number of generation AIs selected by the user. For example, if the number of generation AIs is large, the method of proceeding with the discussion is adjusted to make the progress of the discussion smoother. In this way, the scale of the discussion can be adjusted by the user selecting the number of generation AIs. Part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can manage the progress of the discussion using an AI model that adjusts the scale of the discussion based on the number of generation AIs selected by the user.

[0036] In the discussion section, the generation AIs can deepen their discussion based on their opinions. In the discussion section, for example, the generation AIs can deepen their discussion based on their opinions. For example, the generation AIs receive a prompt saying "Please state your opinion on this topic," and each generation AI states its opinion. In addition, in the discussion section, the generation AIs can evaluate each other's opinions and deepen the discussion. For example, the generation AIs provide feedback on the opinions of other generation AIs to advance the discussion. In this way, the generation AIs can exchange opinions and deepen the discussion, thereby proposing more creative solutions. Some or all of the above-mentioned processing in the discussion section may be performed, for example, using AI, or may be performed without using AI. For example, the discussion section can proceed with the discussion using an AI model in which the generation AIs exchange opinions and deepen the discussion.

[0037] The suggestion unit can aggregate the opinions of the generation AI to propose a final solution. The suggestion unit, for example, aggregates the opinions of the generation AI to propose a final solution. For example, the suggestion unit proposes the most appropriate solution based on the opinions stated by the generation AI. The suggestion unit can also classify and aggregate the opinions of the generation AI. For example, the suggestions are classified by theme and a solution is proposed for each theme. In this way, the opinions of the generation AI can be aggregated to propose a final solution. Some or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI or may be performed without using AI. For example, the suggestion unit can propose a solution using an AI model that aggregates the opinions of the generation AI and proposes a final solution.

[0038] The management unit can record the progress of the discussion. The management unit, for example, records the progress of the discussion as a log. For example, the content and progress of the discussion are recorded so that they can be checked later. The management unit can also record the progress of the discussion in real time. For example, as the discussion progresses, the log is recorded in real time so that the user can check it at any time. By recording the progress of the discussion as a log, the content of the discussion can be checked later. Some or all of the above-mentioned processing in the management unit may be performed, for example, using AI, or may be performed without using AI. For example, the management unit can manage the progress of the discussion using an AI model that records the progress of the discussion and analyzes the log as necessary.

[0039] The reception unit can analyze the past theme input history and suggest an input method. The reception unit, for example, analyzes the past theme input history. For example, it analyzes the past input contents and the frequency of input. The reception unit can also suggest the optimal input method based on the analysis result. For example, themes that the user frequently inputs in the past can be automatically displayed as candidates. It can also preferentially suggest input methods (voice, text, etc.) that the user used in the past. Furthermore, it can predict and suggest a theme to be used in a specific time period from the user's past input history. In this way, it is possible to suggest the optimal input method to the user by analyzing the past theme input history. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can manage the input of the theme using an AI model that analyzes the past theme input history and suggests the optimal input method.

[0040] The reception unit can present input candidates based on the user's field of interest when inputting a theme. The reception unit, for example, identifies the user's field of interest. For example, the reception unit identifies the field of interest based on past activity history or survey results. The reception unit can also present input candidates based on the identified field of interest. For example, based on keywords recently searched by the user, related themes are presented as candidates. Also, based on the contents of articles or books recently read by the user, related themes can be suggested. Furthermore, based on the contents of events or seminars recently attended by the user, related themes can be presented. As a result, by presenting input candidates based on the user's field of interest, the theme input is made more efficient. Part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can manage the input of the theme using an AI model that identifies the user's field of interest and presents input candidates.

[0041] The reception unit can preferentially present a highly relevant theme based on the geographical location information of the user when inputting a theme. The reception unit, for example, acquires the geographical location information of the user. For example, the reception unit acquires the geographical location information of the user using GPS data or an IP address. The reception unit can also present a highly relevant theme based on the acquired geographical location information. For example, when the user is in a specific area, the reception unit preferentially presents a theme related to the area. In addition, when the user is traveling, the reception unit can also suggest a theme related to the travel destination. Furthermore, when the user is participating in a specific event, the reception unit can also preferentially present a theme related to the event. In this way, the reception unit can preferentially present a highly relevant theme by taking into account the geographical location information of the user. Part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can acquire the geographical location information of the user and manage the input of the theme using an AI model that presents a highly relevant theme.

[0042] The reception unit can analyze the social media activity of the user when inputting a theme and suggest related themes. The reception unit, for example, analyzes the social media activity of the user. For example, it analyzes the content recently posted by the user and the content posted by the account followed by the user. The reception unit can also suggest related themes based on the analysis results. For example, it proposes related themes based on the content recently posted by the user. It can also present related themes based on the content posted by the account followed by the user. It can also suggest related themes based on the activity content of the group or community in which the user participates. In this way, it is possible to suggest related themes by analyzing the social media activity of the user. Part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can manage the input of themes using an AI model that analyzes the social media activity of the user and suggests related themes.

[0043] The discussion section can select a discussion method by referring to the past discussion history of the generation AI during the discussion. The discussion section, for example, refers to the past discussion history of the generation AI. For example, it refers to the past discussion contents and the results of the discussion. The discussion section can also select the optimal discussion method based on the referred discussion history. For example, the generation AI selects the optimal discussion method based on the discussion method that was successful in the past. In addition, the generation AI can select another discussion method to avoid the discussion method that failed in the past. Furthermore, it is also possible to select the most suitable method for the topic from the discussion methods that the generation AI used in the past. In this way, the optimal discussion method can be selected by referring to the past discussion history of the generation AI. Part or all of the above-mentioned processing in the discussion section may be performed, for example, using AI, or may be performed without using AI. For example, the discussion section can manage the progress of the discussion by using an AI model that refers to the past discussion history of the generation AI and selects the optimal discussion method.

[0044] The discussion unit can apply different discussion algorithms depending on the category of the theme during the discussion. The discussion unit, for example, identifies the category of the theme. For example, the category of the theme is identified using a classification method such as a technical category, a business category, or a social category. The discussion unit can also apply different discussion algorithms depending on the category of the identified theme. For example, in the case of a technical theme, a discussion algorithm specialized in technology is applied. In addition, in the case of a social theme, a discussion algorithm specialized in social issues can be applied. Furthermore, in the case of an economic theme, a discussion algorithm based on economic analysis can be applied. As a result, the accuracy of the discussion is improved by applying different discussion algorithms depending on the category of the theme. Part or all of the above-mentioned processing in the discussion unit may be performed, for example, using AI, or may be performed without using AI. For example, the discussion unit can identify the category of the theme and manage the progress of the discussion using an AI model that applies different discussion algorithms.

[0045] The discussion section can hold a discussion based on the geographical distribution of the generation AI during the discussion. The discussion section, for example, takes into account the geographical distribution of the generation AI. For example, when the generation AIs are distributed in different regions, the discussion can take into account the perspective of each region. In addition, when the generation AIs are concentrated in a specific region, the discussion can take into account the characteristics of that region. Furthermore, when the generation AIs are distributed internationally, the discussion can take into account an international perspective. As a result, by taking into account the geographical distribution of the generation AI, a discussion that takes into account the perspective of each region is possible. Part or all of the above-mentioned processing in the discussion section may be performed, for example, using an AI, or may be performed without using an AI. For example, the discussion section can manage the progress of the discussion by taking into account the geographical distribution of the generation AI and using an AI model that conducts the discussion.

[0046] The discussion section can improve the accuracy of the discussion by referring to related literature and data during the discussion. The discussion section, for example, refers to related literature and data. For example, the generation AI refers to related academic papers to improve the accuracy of the discussion. The generation AI can also refer to related statistical data to improve the accuracy of the discussion. Furthermore, the generation AI can also refer to related news articles to improve the accuracy of the discussion. As a result, the accuracy of the discussion is improved by referring to related literature and data. Some or all of the above-mentioned processing in the discussion section may be performed, for example, using AI, or may be performed without using AI. For example, the discussion section can manage the progress of the discussion using an AI model that refers to related literature and data and improves the accuracy of the discussion.

[0047] The suggestion unit can adjust the level of detail of the proposal based on the importance of the opinion of the generation AI at the time of proposal. The suggestion unit, for example, evaluates the importance of the opinion of the generation AI. For example, the importance of the opinion is evaluated based on the influence and reliability of the opinion. The suggestion unit can also adjust the level of detail of the proposal based on the evaluated importance of the opinion. For example, if the opinion of the generation AI is important, a detailed proposal is made. Also, if the opinion of the generation AI is general, a concise proposal can be made. Furthermore, if the opinion of the generation AI is specialized, a proposal including specialized information can be made. As a result, by adjusting the level of detail of the proposal based on the importance of the opinion of the generation AI, more appropriate proposals can be made. Part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can manage the proposal using an AI model that evaluates the importance of the opinion of the generation AI and adjusts the level of detail of the proposal.

[0048] The suggestion unit can apply different proposal algorithms depending on the category of the theme when making a proposal. The suggestion unit, for example, identifies the category of the theme. For example, the category of the theme is identified using a classification method such as a technical category, a business category, or a social category. The suggestion unit can also apply different proposal algorithms depending on the category of the identified theme. For example, in the case of a technical theme, a proposal algorithm specialized in technology is applied. In addition, in the case of a social theme, a proposal algorithm specialized in social issues can be applied. Furthermore, in the case of an economic theme, a proposal algorithm based on economic analysis can be applied. As a result, the accuracy of the proposal is improved by applying different proposal algorithms depending on the category of the theme. Part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can manage the proposal using an AI model that identifies the category of the theme and applies different proposal algorithms.

[0049] The suggestion unit can determine the priority of the proposal based on the time of submission of the opinion of the generation AI at the time of proposal. The suggestion unit, for example, evaluates the time of submission of the opinion of the generation AI. For example, the suggestion unit evaluates the time of submission of the opinion based on the timing of the submission of the opinion and the influence of the opinion. The suggestion unit can also determine the priority of the proposal based on the time of submission of the evaluated opinion. For example, if the opinion of the generation AI is submitted early, the opinion is preferentially proposed. Also, if the opinion of the generation AI is submitted late, the opinion can be postponed. Furthermore, if the opinions of the generation AI are submitted at the same time, the priority can be determined based on the importance. As a result, by determining the priority of the proposal based on the time of submission of the opinion of the generation AI, more appropriate proposals can be made. Part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can manage the proposals using an AI model that evaluates the time of submission of the opinion of the generation AI and determines the priority of the proposal.

[0050] The suggestion unit can adjust the order of the suggestions based on the relevance of the opinions of the generation AI at the time of suggestion. The suggestion unit, for example, evaluates the relevance of the opinions of the generation AI. For example, the suggestion unit evaluates the relevance of the opinions based on the content of the opinions and the influence of the opinions. The suggestion unit can also adjust the order of the suggestions based on the evaluated relevance of the opinions. For example, if the opinions of the generation AI are directly related to the theme, the opinions are preferentially proposed. Also, if the opinions of the generation AI are indirectly related to the theme, the opinions can be postponed. Furthermore, if the opinions of the generation AI are not related to the theme, the opinions can be excluded from the suggestions. This enables more appropriate suggestions by adjusting the order of the suggestions based on the relevance of the opinions of the generation AI. Part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can manage the suggestions using an AI model that evaluates the relevance of the opinions of the generation AI and adjusts the order of the suggestions.

[0051] The management unit can monitor the progress of the discussion and select a progress method by referring to the past progress history. The management unit, for example, monitors the progress of the discussion. For example, it monitors the stage of the discussion and the speed of progress. The management unit can also refer to the past progress history. For example, it refers to the past discussion content and the progress result. Furthermore, the management unit can select the optimal progress method based on the referred progress history. For example, it selects the optimal progress method based on the progress method that was successful in the past. In addition, it can select a different progress method to avoid the progress method that failed in the past. In this way, the optimal progress method can be selected by referring to the past progress history. Part or all of the above-mentioned processing in the management unit may be performed, for example, using AI, or may be performed without using AI. For example, the management unit can manage the progress of the discussion using an AI model that monitors the progress of the discussion and selects a progress method by referring to the past progress history.

[0052] The management unit can monitor the progress of the discussion and apply different progress algorithms depending on the category of the theme. The management unit, for example, monitors the progress of the discussion. For example, it monitors the stage of the discussion and the speed of progress. The management unit can also identify the category of the theme. For example, it identifies the category of the theme using a classification method such as a technical category, a business category, or a social category. Furthermore, the management unit can apply different progress algorithms depending on the category of the identified theme. For example, in the case of a technical theme, a progress algorithm specialized in technology is applied. In addition, in the case of a social theme, a progress algorithm specialized in social issues can be applied. As a result, the accuracy of the discussion is improved by applying different progress algorithms depending on the category of the theme. Part or all of the above-mentioned processing in the management unit may be performed, for example, using AI, or may be performed without using AI. For example, the management unit can manage the progress of the discussion using an AI model that monitors the progress of the discussion, identifies the category of the theme, and applies different progress algorithms.

[0053] The management unit monitors the progress of the discussion and can proceed based on the geographical distribution of the generation AI. The management unit, for example, monitors the progress of the discussion. For example, it monitors the stage of the discussion and the speed of progress. The management unit can also take into account the geographical distribution of the generation AI. For example, if the generation AIs are distributed in different regions, the discussion can proceed while incorporating the perspective of each region. In addition, if the generation AIs are concentrated in a specific region, the discussion can proceed while taking into account the characteristics of that region. Furthermore, if the generation AIs are distributed internationally, the discussion can proceed while incorporating an international perspective. As a result, by taking into account the geographical distribution of the generation AIs, it is possible to proceed while taking into account the perspective of each region. Part or all of the above-mentioned processing in the management unit may be performed, for example, using AI, or may be performed without using AI. For example, the management unit can monitor the progress of the discussion and manage the progress of the discussion using an AI model that takes into account the geographical distribution of the generation AIs.

[0054] The management unit can monitor the progress of the discussion and improve the accuracy of the progress by referring to literature and data. The management unit, for example, monitors the progress of the discussion. For example, it monitors the stage of the discussion and the speed of progress. The management unit can also refer to related literature and data. For example, the generation AI can refer to related academic papers to improve the accuracy of the progress. The generation AI can also refer to related statistical data to improve the accuracy of the progress. Furthermore, the generation AI can also refer to related news articles to improve the accuracy of the progress. As a result, the accuracy of the progress is improved by referring to related literature and data. Part or all of the above-mentioned processing in the management unit may be performed, for example, using AI, or may be performed without using AI. For example, the management unit can manage the progress of the discussion using an AI model that monitors the progress of the discussion and improves the accuracy of the progress by referring to related literature and data.

[0055] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0056] The reception unit can analyze the user's past discussion history and suggest the optimal number of generation AIs. For example, if there have been many successful discussions in the past using three generation AIs, three generation AIs will be suggested. Also, if a specific generation AI has been found to be effective based on the past discussion history, that generation AI can be suggested preferentially. Furthermore, the reception unit can suggest the optimal combination of generation AIs based on the themes and results of past discussions. This makes it possible to hold more effective discussions by utilizing the user's past discussion history.

[0057] The management department can monitor the progress of the discussion and adjust the direction of the discussion by evaluating the performance of the generation AI. For example, if a specific generation AI is providing better opinions than other generation AIs, the opinions of that generation AI will be given more weight. Also, if the performance of a generation AI is declining, it can shift the lead of the discussion to another generation AI. In addition, it can evaluate the performance of the generation AI in real time and add new generation AIs as necessary. This can improve the quality of the discussion.

[0058] The discussion section can evaluate the opinions of the generation AI in real time and optimize the progress of the discussion. For example, if the opinions of the generation AI are contradictory, it can point out the inconsistencies and have the discussion resume. Also, if the opinions of the generation AI are consistent, it can advance the discussion based on those opinions. Furthermore, if the opinion of the generation AI offers a new perspective, it can deepen the discussion by placing emphasis on that perspective. This makes it possible to effectively utilize the opinions of the generation AI to advance the discussion.

[0059] The suggestion unit can propose multiple solutions based on the opinions of the generation AI and allow the user to select one. For example, the suggestion unit can display a list of multiple solutions proposed by the generation AI, and the user can select the most appropriate solution. It can also clearly indicate the advantages and disadvantages of each solution, making it easier for the user to compare them. Furthermore, it can also propose a specific implementation plan based on the solution selected by the user. This allows the user to select the optimal solution from multiple options.

[0060] The reception unit can propose an optimal combination of generation AIs based on the user's past topic input history. For example, it can propose a combination of generation AIs that have been successful in the past on a specific topic. Also, if a specific generation AI has been found to be effective based on the past topic input history, it can also preferentially propose that generation AI. Furthermore, it can analyze the past topic input history and propose the optimal number of generation AIs. This makes it possible to hold more effective discussions by utilizing the user's past topic input history.

[0061] The suggestion unit can propose multiple solutions based on the opinions of the generation AI and allow the user to select one. For example, the suggestion unit can display a list of multiple solutions proposed by the generation AI, and the user can select the most appropriate solution. It can also clearly indicate the advantages and disadvantages of each solution, making it easier for the user to compare them. Furthermore, it can also propose a specific implementation plan based on the solution selected by the user. This allows the user to select the optimal solution from multiple options.

[0062] The process flow of the first embodiment will be briefly described below.

[0063] Step 1: The reception unit inputs the topic that the user wants to discuss. Examples of topics include, but are not limited to, technical issues, business strategies, and social issues. The reception unit also allows the user to select the number of generation AIs to participate in the discussion by operating a button. For example, if the user selects three generation AIs, the three generation AIs will participate in the discussion. Step 2: In the discussion section, the generation AIs hold a discussion. The generation AIs express their opinions, for example, using a text generation AI (e.g., LLM). The generation AIs deepen the discussion based on each other's opinions. For example, the generation AIs receive a prompt saying, "Please state your opinion on this topic," and each generation AI expresses its opinion. Step 3: The proposal unit collects the opinions of the generation AI and proposes a final solution. For example, the proposal unit proposes the most appropriate solution based on the opinions expressed by the generation AI. Step 4: The management unit manages the progress of the discussion. For example, it monitors the progress of the discussion and makes adjustments as necessary. The management unit records the progress of the discussion as a log. For example, it records the content and progress of the discussion so that it can be checked later. Some or all of the above-mentioned processing in the management unit may be performed, for example, using AI, or may be performed without using AI. For example, the management unit can manage the progress of the discussion using an AI model that monitors the progress of the discussion and adjusts the direction of the discussion as necessary.

[0064] (Example 2) The creation support system according to the embodiment of the present invention uses multiple generation AIs simultaneously, and allows the generation AIs to discuss with each other and create by digging deeper into a theme. This creation support system allows the user to select how many AIs to discuss with by operating a button, and also allows the user to check the log during the process. Specifically, first, the user inputs the theme that the user wants to discuss. Next, the user selects the number of generation AIs to participate in the discussion by operating a button. The selected generation AIs start a discussion based on the theme, and each generation AI states its opinion. The generation AIs deepen the discussion based on each other's opinions, and finally propose a creative solution to the theme. The user can check the log during the discussion, and can also correct the direction of the discussion as necessary. For example, the user can adjust the content of the discussion by providing feedback on the opinion of a specific generation AI. This system makes it possible for multiple generation AIs to cooperate to dig deeper into a theme and propose creative solutions. The user can manage discussions between the generation AIs with simple operations and efficiently obtain creative ideas. This allows the creation support system to allow multiple generation AIs to cooperate to dig deeper into a theme and propose creative solutions.

[0065] The creation support system according to the embodiment includes a reception unit, a discussion unit, a proposal unit, and a management unit. The reception unit inputs a theme that the user wants to have discussed. For example, themes include, but are not limited to, technical problems, business strategies, and social problems. The reception unit selects the number of generation AIs to participate in the discussion by the user by operating a button. For example, if the user selects three generation AIs, the three generation AIs will participate in the discussion. In the discussion unit, the generation AIs hold a discussion. The generation AIs express their opinions using, for example, a text generation AI (for example, LLM). The generation AIs deepen the discussion based on each other's opinions. For example, the generation AI receives a prompt saying "Please express your opinion on this topic," and each generation AI expresses its opinion. The proposal unit aggregates the opinions of the generation AIs and proposes a final solution. For example, the proposal unit proposes the most appropriate solution based on the opinions expressed by the generation AIs. The management unit manages the progress of the discussion. For example, it monitors the progress of the discussion and makes adjustments as necessary. The management unit records the progress of the discussion as a log. For example, it records the content and progress of the discussion so that it can be checked later. As a result, in the creativity support system according to the embodiment, multiple generation AIs cooperate to delve into a theme and propose creative solutions. Some or all of the above-mentioned processing in the management unit may be performed, for example, using AI, or may be performed without using AI. For example, the management unit may manage the progress of the discussion using an AI model that monitors the progress of the discussion and adjusts the direction of the discussion as necessary.

[0066] The reception unit inputs the theme that the user wants to discuss. Examples of themes include, but are not limited to, technical issues, business strategies, and social issues. The reception unit selects the number of generation AIs to participate in the discussion by the user by operating a button. For example, if the user selects three generation AIs, the three generation AIs will participate in the discussion. The reception unit is designed to be intuitively operated through a user interface, and is provided with a theme input field and a generation AI selection button. The theme input field is in a free-form format, allowing the user to describe specific problems and issues in detail. In addition, the reception unit also has a function to refer to previously entered themes and discussion history, allowing the user to set a new theme based on the content of past discussions. When selecting a generation AI, the characteristics and areas of expertise of each generation AI are displayed, allowing the user to select the optimal generation AI depending on the purpose of the discussion. For example, a technology-specialized generation AI can be selected for technical issues, and a business-specialized generation AI can be selected for business strategies. In this way, the reception unit supports the user to start a discussion efficiently and effectively.

[0067] In the discussion section, the generation AIs hold discussions. The generation AIs express their opinions using, for example, text generation AIs (e.g., LLM). The generation AIs deepen the discussion based on each other's opinions. For example, the generation AIs receive a prompt saying, "Please express your opinion on this topic," and each generation AI expresses its opinion. The discussion section sets up a protocol for the generation AIs to efficiently advance the discussion, and supports multiple discussion formats, such as a format in which each generation AI expresses its opinion in turn and a format in which discussions are focused on a specific topic. The generation AIs use natural language processing technology to express opinions from multiple perspectives on the topic entered by the user. For example, for technical problems, they can express opinions that take into account not only technical solutions but also costs, feasibility, and risks. In addition, the generation AIs deepen the discussion by analyzing the opinions of other generation AIs in real time and expressing counterarguments and supplementary opinions. The discussion section converts the opinions expressed by the generation AIs into text in real time, allowing users to visually check the progress of the discussion. This allows the generation AI to hold discussions efficiently and effectively, enabling the discussion section to provide useful information to users.

[0068] The proposal unit aggregates the opinions of the generation AI and proposes a final solution. For example, it proposes the most appropriate solution based on the opinions stated by the generation AI. The proposal unit has the function of classifying the opinions stated by the generation AI and organizing them based on importance and relevance. Specifically, it analyzes the opinions stated by the generation AI using text mining technology and extracts common themes and keywords. This allows the proposal unit to efficiently aggregate the opinions of the generation AI and eliminate duplication and contradiction. Furthermore, the proposal unit simulates multiple solutions based on the opinions of the generation AI and selects the most effective solution from among them. For example, for technical problems, it compares multiple technical solutions and comprehensively evaluates costs, feasibility, risks, etc. to propose the optimal solution. The proposal unit provides the user with a detailed explanation of the solution and implementation steps, and presents a specific action plan. This allows the proposal unit to support the user in taking concrete action based on the opinions of the generation AI.

[0069] The management unit manages the progress of the discussion. For example, it monitors the progress of the discussion and makes adjustments as necessary. The management unit has the function of monitoring the progress of the discussion in real time and adjusting so that the generation AI expresses its opinion at the appropriate time. Specifically, it manages the order and time in which the generation AI expresses its opinion, and balances the discussion so that it is not biased. In addition, the management unit records the progress of the discussion as a log so that it can be checked later. For example, it records the content and progress of the discussion in text format so that the user can check the progress of the discussion later. In addition, the management unit provides an interface to smooth the progress of the discussion and has a dashboard that allows users to visually check the progress of the discussion. The dashboard displays the opinions of the generation AI and the progress of the discussion in real time, allowing users to intuitively grasp the progress of the discussion. The management unit not only monitors the progress of the discussion, but can also adjust the direction of the discussion as necessary. For example, if the discussion is too biased toward a specific topic or if misunderstandings or confusion occur when the generation AI expresses its opinion, the management unit intervenes at the appropriate time and corrects the direction of the discussion. This allows the management department to support discussions so that they proceed efficiently and effectively, and provide users with a useful forum for discussion.

[0070] The management unit can monitor the progress of the discussion and make adjustments as necessary. The management unit, for example, monitors the progress of the discussion. For example, it monitors the stage of the discussion and the speed of progress. The management unit can also adjust the direction of the discussion as necessary. For example, if the discussion is stagnating, the management unit proposes a new direction of the discussion. This improves the quality of the discussion by appropriately managing the progress of the discussion and making adjustments as necessary. Some or all of the above-mentioned processing in the management unit may be performed, for example, using AI or may be performed without using AI. For example, the management unit can manage the progress of the discussion using an AI model that monitors the progress of the discussion and adjusts the direction of the discussion as necessary.

[0071] The reception unit allows the user to select the number of generation AIs to participate in the discussion by button operation. The reception unit, for example, allows the user to select the number of generation AIs to participate in the discussion by button operation. For example, if the user selects three generation AIs, the three generation AIs participate in the discussion. The reception unit can also adjust the scale of the discussion based on the number of generation AIs selected by the user. For example, if the number of generation AIs is large, the method of proceeding with the discussion is adjusted to make the progress of the discussion smoother. In this way, the scale of the discussion can be adjusted by the user selecting the number of generation AIs. Part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can manage the progress of the discussion using an AI model that adjusts the scale of the discussion based on the number of generation AIs selected by the user.

[0072] In the discussion section, the generation AIs can deepen their discussion based on their opinions. In the discussion section, for example, the generation AIs can deepen their discussion based on their opinions. For example, the generation AIs receive a prompt saying "Please state your opinion on this topic," and each generation AI states its opinion. In addition, in the discussion section, the generation AIs can evaluate each other's opinions and deepen the discussion. For example, the generation AIs provide feedback on the opinions of other generation AIs to advance the discussion. In this way, the generation AIs can exchange opinions and deepen the discussion, thereby proposing more creative solutions. Some or all of the above-mentioned processing in the discussion section may be performed, for example, using AI, or may be performed without using AI. For example, the discussion section can proceed with the discussion using an AI model in which the generation AIs exchange opinions and deepen the discussion.

[0073] The suggestion unit can aggregate the opinions of the generation AI to propose a final solution. The suggestion unit, for example, aggregates the opinions of the generation AI to propose a final solution. For example, the suggestion unit proposes the most appropriate solution based on the opinions stated by the generation AI. The suggestion unit can also classify and aggregate the opinions of the generation AI. For example, the suggestions are classified by theme and a solution is proposed for each theme. In this way, the opinions of the generation AI can be aggregated to propose a final solution. Some or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI or may be performed without using AI. For example, the suggestion unit can propose a solution using an AI model that aggregates the opinions of the generation AI and proposes a final solution.

[0074] The management unit can record the progress of the discussion. The management unit, for example, records the progress of the discussion as a log. For example, the content and progress of the discussion are recorded so that they can be checked later. The management unit can also record the progress of the discussion in real time. For example, as the discussion progresses, the log is recorded in real time so that the user can check it at any time. By recording the progress of the discussion as a log, the content of the discussion can be checked later. Some or all of the above-mentioned processing in the management unit may be performed, for example, using AI, or may be performed without using AI. For example, the management unit can manage the progress of the discussion using an AI model that records the progress of the discussion and analyzes the log as necessary.

[0075] The reception unit can estimate the user's emotion and adjust the theme input method based on the user's emotion. The reception unit, for example, estimates the user's emotion. For example, the user's emotion is estimated using facial expression recognition technology or voice analysis technology. The reception unit can also adjust the theme input method based on the estimated user's emotion. For example, when the user is stressed, a simple interface is provided to minimize the input procedure. In addition, when the user is relaxed, detailed input options can be provided and a customizable input method can be suggested. Furthermore, when the user is in a hurry, voice input is prioritized to allow the theme to be input quickly. This allows more appropriate theme input by adjusting the theme input method according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can manage the input of the theme using an AI model that estimates the user's emotions and adjusts the way the theme is input based on the estimated emotions.

[0076] The reception unit can analyze the past theme input history and suggest an input method. The reception unit, for example, analyzes the past theme input history. For example, it analyzes the past input contents and the frequency of input. The reception unit can also suggest the optimal input method based on the analysis result. For example, themes that the user frequently inputs in the past can be automatically displayed as candidates. It can also preferentially suggest input methods (voice, text, etc.) that the user used in the past. Furthermore, it can predict and suggest a theme to be used in a specific time period from the user's past input history. In this way, it is possible to suggest the optimal input method to the user by analyzing the past theme input history. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can manage the input of the theme using an AI model that analyzes the past theme input history and suggests the optimal input method.

[0077] The reception unit can present input candidates based on the user's field of interest when inputting a theme. The reception unit, for example, identifies the user's field of interest. For example, the reception unit identifies the field of interest based on past activity history or survey results. The reception unit can also present input candidates based on the identified field of interest. For example, based on keywords recently searched by the user, related themes are presented as candidates. Also, based on the contents of articles or books recently read by the user, related themes can be suggested. Furthermore, based on the contents of events or seminars recently attended by the user, related themes can be presented. As a result, by presenting input candidates based on the user's field of interest, the theme input is made more efficient. Part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can manage the input of the theme using an AI model that identifies the user's field of interest and presents input candidates.

[0078] The reception unit can estimate the user's emotion and determine the priority of the input themes based on the user's emotion. The reception unit, for example, estimates the user's emotion. For example, the user's emotion is estimated using facial expression recognition technology or voice analysis technology. The reception unit can also determine the priority of the input themes based on the estimated user's emotion. For example, if the user is excited, the theme is discussed preferentially. Also, if the user is feeling anxious, the theme can be postponed. Furthermore, if the user is relaxed, the priority of the themes can be flexibly adjusted. As a result, the progress of the discussion is optimized by determining the priority of the themes according to the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can manage the input of themes using an AI model that estimates a user's emotions and prioritizes themes based on the estimated emotions.

[0079] The reception unit can preferentially present a highly relevant theme based on the geographical location information of the user when inputting a theme. The reception unit, for example, acquires the geographical location information of the user. For example, the reception unit acquires the geographical location information of the user using GPS data or an IP address. The reception unit can also present a highly relevant theme based on the acquired geographical location information. For example, when the user is in a specific area, the reception unit preferentially presents a theme related to the area. In addition, when the user is traveling, the reception unit can also suggest a theme related to the travel destination. Furthermore, when the user is participating in a specific event, the reception unit can also preferentially present a theme related to the event. In this way, the reception unit can preferentially present a highly relevant theme by taking into account the geographical location information of the user. Part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can acquire the geographical location information of the user and manage the input of the theme using an AI model that presents a highly relevant theme.

[0080] The reception unit can analyze the social media activity of the user when inputting a theme and suggest related themes. The reception unit, for example, analyzes the social media activity of the user. For example, it analyzes the content recently posted by the user and the content posted by the account followed by the user. The reception unit can also suggest related themes based on the analysis results. For example, it proposes related themes based on the content recently posted by the user. It can also present related themes based on the content posted by the account followed by the user. It can also suggest related themes based on the activity content of the group or community in which the user participates. In this way, it is possible to suggest related themes by analyzing the social media activity of the user. Part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can manage the input of themes using an AI model that analyzes the social media activity of the user and suggests related themes.

[0081] The discussion unit can estimate the user's emotions and adjust the way the discussion proceeds based on the user's emotions. The discussion unit, for example, estimates the user's emotions. For example, the user's emotions are estimated using facial expression recognition technology or voice analysis technology. The discussion unit can also adjust the way the discussion proceeds based on the estimated user's emotions. For example, if the user is nervous, a gentle way of proceeding is adopted. Also, if the user is relaxed, a way of proceeding that promotes lively discussion can be adopted. Furthermore, if the user is in a hurry, a way of proceeding that quickly reaches a conclusion can be adopted. This improves the quality of the discussion by adjusting the way the discussion proceeds according to the user's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the discussion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the discussion unit can manage the progress of the discussion using an AI model that estimates the user's emotions and adjusts the way the discussion proceeds based on the estimated emotions.

[0082] The discussion section can select a discussion method by referring to the past discussion history of the generation AI during the discussion. The discussion section, for example, refers to the past discussion history of the generation AI. For example, it refers to the past discussion contents and the results of the discussion. The discussion section can also select the optimal discussion method based on the referred discussion history. For example, the generation AI selects the optimal discussion method based on the discussion method that was successful in the past. In addition, the generation AI can select another discussion method to avoid the discussion method that failed in the past. Furthermore, it is also possible to select the most suitable method for the topic from the discussion methods that the generation AI used in the past. In this way, the optimal discussion method can be selected by referring to the past discussion history of the generation AI. Part or all of the above-mentioned processing in the discussion section may be performed, for example, using AI, or may be performed without using AI. For example, the discussion section can manage the progress of the discussion by using an AI model that refers to the past discussion history of the generation AI and selects the optimal discussion method.

[0083] The discussion unit can apply different discussion algorithms depending on the category of the theme during the discussion. The discussion unit, for example, identifies the category of the theme. For example, the category of the theme is identified using a classification method such as a technical category, a business category, or a social category. The discussion unit can also apply different discussion algorithms depending on the category of the identified theme. For example, in the case of a technical theme, a discussion algorithm specialized in technology is applied. In addition, in the case of a social theme, a discussion algorithm specialized in social issues can be applied. Furthermore, in the case of an economic theme, a discussion algorithm based on economic analysis can be applied. As a result, the accuracy of the discussion is improved by applying different discussion algorithms depending on the category of the theme. Part or all of the above-mentioned processing in the discussion unit may be performed, for example, using AI, or may be performed without using AI. For example, the discussion unit can identify the category of the theme and manage the progress of the discussion using an AI model that applies different discussion algorithms.

[0084] The discussion unit can estimate the user's emotions and determine the priority of the discussion based on the user's emotions. The discussion unit, for example, estimates the user's emotions. For example, the user's emotions are estimated using facial expression recognition technology or voice analysis technology. The discussion unit can also determine the priority of the discussion based on the estimated user's emotions. For example, if the user is excited, the topic is discussed with priority. Also, if the user is feeling anxious, the topic can be postponed. Furthermore, if the user is relaxed, the priority of the topic can be flexibly adjusted. As a result, the progress of the discussion is optimized by determining the priority of the discussion according to the user's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the discussion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the discussion unit can manage the progress of the discussion using an AI model that estimates the user's emotions and determines the priority of the discussion based on the estimated emotions.

[0085] The discussion section can hold a discussion based on the geographical distribution of the generation AI during the discussion. The discussion section, for example, takes into account the geographical distribution of the generation AI. For example, when the generation AIs are distributed in different regions, the discussion can take into account the perspective of each region. In addition, when the generation AIs are concentrated in a specific region, the discussion can take into account the characteristics of that region. Furthermore, when the generation AIs are distributed internationally, the discussion can take into account an international perspective. As a result, by taking into account the geographical distribution of the generation AI, a discussion that takes into account the perspective of each region is possible. Part or all of the above-mentioned processing in the discussion section may be performed, for example, using an AI, or may be performed without using an AI. For example, the discussion section can manage the progress of the discussion by taking into account the geographical distribution of the generation AI and using an AI model that conducts the discussion.

[0086] The discussion section can improve the accuracy of the discussion by referring to related literature and data during the discussion. The discussion section, for example, refers to related literature and data. For example, the generation AI refers to related academic papers to improve the accuracy of the discussion. The generation AI can also refer to related statistical data to improve the accuracy of the discussion. Furthermore, the generation AI can also refer to related news articles to improve the accuracy of the discussion. As a result, the accuracy of the discussion is improved by referring to related literature and data. Some or all of the above-mentioned processing in the discussion section may be performed, for example, using AI, or may be performed without using AI. For example, the discussion section can manage the progress of the discussion using an AI model that refers to related literature and data and improves the accuracy of the discussion.

[0087] The suggestion unit can estimate the user's emotion and adjust the way of expressing the proposal based on the user's emotion. The suggestion unit, for example, estimates the user's emotion. For example, the user's emotion is estimated using facial expression recognition technology or voice analysis technology. The suggestion unit can also adjust the way of expressing the proposal based on the estimated emotion of the user. For example, if the user is nervous, a simple and highly visible proposal is made. Also, if the user is relaxed, a proposal including detailed information can be made. Furthermore, if the user is in a hurry, a proposal that focuses on the main points can be made. This allows for more appropriate proposals by adjusting the way of expressing the proposal according to the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the suggestion unit can manage the proposal using an AI model that estimates the user's emotion and adjusts the way of expressing the proposal based on the estimated emotion.

[0088] The suggestion unit can adjust the level of detail of the proposal based on the importance of the opinion of the generation AI at the time of proposal. The suggestion unit, for example, evaluates the importance of the opinion of the generation AI. For example, the importance of the opinion is evaluated based on the influence and reliability of the opinion. The suggestion unit can also adjust the level of detail of the proposal based on the evaluated importance of the opinion. For example, if the opinion of the generation AI is important, a detailed proposal is made. Also, if the opinion of the generation AI is general, a concise proposal can be made. Furthermore, if the opinion of the generation AI is specialized, a proposal including specialized information can be made. As a result, by adjusting the level of detail of the proposal based on the importance of the opinion of the generation AI, more appropriate proposals can be made. Part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can manage the proposal using an AI model that evaluates the importance of the opinion of the generation AI and adjusts the level of detail of the proposal.

[0089] The suggestion unit can apply different proposal algorithms depending on the category of the theme when making a proposal. The suggestion unit, for example, identifies the category of the theme. For example, the category of the theme is identified using a classification method such as a technical category, a business category, or a social category. The suggestion unit can also apply different proposal algorithms depending on the category of the identified theme. For example, in the case of a technical theme, a proposal algorithm specialized in technology is applied. In addition, in the case of a social theme, a proposal algorithm specialized in social issues can be applied. Furthermore, in the case of an economic theme, a proposal algorithm based on economic analysis can be applied. As a result, the accuracy of the proposal is improved by applying different proposal algorithms depending on the category of the theme. Part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can manage the proposal using an AI model that identifies the category of the theme and applies different proposal algorithms.

[0090] The suggestion unit can estimate the user's emotion and adjust the length of the proposal based on the user's emotion. The suggestion unit, for example, estimates the user's emotion. For example, the suggestion unit estimates the user's emotion using facial expression recognition technology or voice analysis technology. The suggestion unit can also adjust the length of the proposal based on the estimated user's emotion. For example, if the user is in a hurry, a short and to the point proposal can be made. If the user is relaxed, a longer proposal including detailed explanations can be made. Furthermore, if the user is excited, a proposal with a visually stimulating effect can be made. This allows for more appropriate proposals by adjusting the length of the proposal according to the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the suggestion unit can manage the proposal using an AI model that estimates the user's emotion and adjusts the length of the proposal based on the estimated emotion.

[0091] The suggestion unit can determine the priority of the proposal based on the time of submission of the opinion of the generation AI at the time of proposal. The suggestion unit, for example, evaluates the time of submission of the opinion of the generation AI. For example, the suggestion unit evaluates the time of submission of the opinion based on the timing of the submission of the opinion and the influence of the opinion. The suggestion unit can also determine the priority of the proposal based on the time of submission of the evaluated opinion. For example, if the opinion of the generation AI is submitted early, the opinion is preferentially proposed. Also, if the opinion of the generation AI is submitted late, the opinion can be postponed. Furthermore, if the opinions of the generation AI are submitted at the same time, the priority can be determined based on the importance. As a result, by determining the priority of the proposal based on the time of submission of the opinion of the generation AI, more appropriate proposals can be made. Part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can manage the proposals using an AI model that evaluates the time of submission of the opinion of the generation AI and determines the priority of the proposal.

[0092] The suggestion unit can adjust the order of the suggestions based on the relevance of the opinions of the generation AI at the time of suggestion. The suggestion unit, for example, evaluates the relevance of the opinions of the generation AI. For example, the suggestion unit evaluates the relevance of the opinions based on the content of the opinions and the influence of the opinions. The suggestion unit can also adjust the order of the suggestions based on the evaluated relevance of the opinions. For example, if the opinions of the generation AI are directly related to the theme, the opinions are preferentially proposed. Also, if the opinions of the generation AI are indirectly related to the theme, the opinions can be postponed. Furthermore, if the opinions of the generation AI are not related to the theme, the opinions can be excluded from the suggestions. This enables more appropriate suggestions by adjusting the order of the suggestions based on the relevance of the opinions of the generation AI. Part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can manage the suggestions using an AI model that evaluates the relevance of the opinions of the generation AI and adjusts the order of the suggestions.

[0093] The management unit can estimate the user's emotions and adjust the progress of the discussion based on the user's emotions. The management unit, for example, estimates the user's emotions. For example, the user's emotions are estimated using facial expression recognition technology or voice analysis technology. The management unit can also adjust the progress of the discussion based on the estimated user's emotions. For example, if the user is nervous, a gentle progress method is adopted. Also, if the user is relaxed, a progress method that promotes lively discussion can be adopted. Furthermore, if the user is in a hurry, a progress method that quickly reaches a conclusion can be adopted. This improves the quality of the discussion by adjusting the progress of the discussion according to the user's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the management unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the management unit can manage the progress of the discussion using an AI model that estimates the user's emotions and adjusts the progress of the discussion based on the estimated emotions.

[0094] The management unit can monitor the progress of the discussion and select a progress method by referring to the past progress history. The management unit, for example, monitors the progress of the discussion. For example, it monitors the stage of the discussion and the speed of progress. The management unit can also refer to the past progress history. For example, it refers to the past discussion content and the progress result. Furthermore, the management unit can select the optimal progress method based on the referred progress history. For example, it selects the optimal progress method based on the progress method that was successful in the past. In addition, it can select a different progress method to avoid the progress method that failed in the past. In this way, the optimal progress method can be selected by referring to the past progress history. Part or all of the above-mentioned processing in the management unit may be performed, for example, using AI, or may be performed without using AI. For example, the management unit can manage the progress of the discussion using an AI model that monitors the progress of the discussion and selects a progress method by referring to the past progress history.

[0095] The management unit can monitor the progress of the discussion and apply different progress algorithms depending on the category of the theme. The management unit, for example, monitors the progress of the discussion. For example, it monitors the stage of the discussion and the speed of progress. The management unit can also identify the category of the theme. For example, it identifies the category of the theme using a classification method such as a technical category, a business category, or a social category. Furthermore, the management unit can apply different progress algorithms depending on the category of the identified theme. For example, in the case of a technical theme, a progress algorithm specialized in technology is applied. In addition, in the case of a social theme, a progress algorithm specialized in social issues can be applied. As a result, the accuracy of the discussion is improved by applying different progress algorithms depending on the category of the theme. Part or all of the above-mentioned processing in the management unit may be performed, for example, using AI, or may be performed without using AI. For example, the management unit can manage the progress of the discussion using an AI model that monitors the progress of the discussion, identifies the category of the theme, and applies different progress algorithms.

[0096] The management unit can estimate the user's emotions and determine the priority of the discussion based on the user's emotions. The management unit, for example, estimates the user's emotions. For example, the user's emotions are estimated using facial expression recognition technology or voice analysis technology. The management unit can also determine the priority of the discussion based on the estimated user's emotions. For example, if the user is excited, the topic is discussed with priority. Also, if the user is feeling anxious, the topic can be postponed. Furthermore, if the user is relaxed, the priority of the topic can be flexibly adjusted. In this way, the discussion progress is optimized by determining the priority of the discussion progress according to the user's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the management unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the management department can manage the progress of a discussion using an AI model that estimates the user's emotions and determines the priority of the discussion progress based on the estimated emotions.

[0097] The management unit monitors the progress of the discussion and can proceed based on the geographical distribution of the generation AI. The management unit, for example, monitors the progress of the discussion. For example, it monitors the stage of the discussion and the speed of progress. The management unit can also take into account the geographical distribution of the generation AI. For example, if the generation AIs are distributed in different regions, the discussion can proceed while incorporating the perspective of each region. In addition, if the generation AIs are concentrated in a specific region, the discussion can proceed while taking into account the characteristics of that region. Furthermore, if the generation AIs are distributed internationally, the discussion can proceed while incorporating an international perspective. As a result, by taking into account the geographical distribution of the generation AIs, it is possible to proceed while taking into account the perspective of each region. Part or all of the above-mentioned processing in the management unit may be performed, for example, using AI, or may be performed without using AI. For example, the management unit can monitor the progress of the discussion and manage the progress of the discussion using an AI model that takes into account the geographical distribution of the generation AIs.

[0098] The management unit can monitor the progress of the discussion and improve the accuracy of the progress by referring to literature and data. The management unit, for example, monitors the progress of the discussion. For example, it monitors the stage of the discussion and the speed of progress. The management unit can also refer to related literature and data. For example, the generation AI can refer to related academic papers to improve the accuracy of the progress. The generation AI can also refer to related statistical data to improve the accuracy of the progress. Furthermore, the generation AI can also refer to related news articles to improve the accuracy of the progress. As a result, the accuracy of the progress is improved by referring to related literature and data. Part or all of the above-mentioned processing in the management unit may be performed, for example, using AI, or may be performed without using AI. For example, the management unit can manage the progress of the discussion using an AI model that monitors the progress of the discussion and improves the accuracy of the progress by referring to related literature and data.

[0099] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0100] The reception unit can analyze the user's past discussion history and suggest the optimal number of generation AIs. For example, if there have been many successful discussions in the past using three generation AIs, three generation AIs will be suggested. Also, if a specific generation AI has been found to be effective based on the past discussion history, that generation AI can be suggested preferentially. Furthermore, the reception unit can suggest the optimal combination of generation AIs based on the themes and results of past discussions. This makes it possible to hold more effective discussions by utilizing the user's past discussion history.

[0101] The management department can monitor the progress of the discussion and adjust the direction of the discussion by evaluating the performance of the generation AI. For example, if a specific generation AI is providing better opinions than other generation AIs, the opinions of that generation AI will be given more weight. Also, if the performance of a generation AI is declining, it can shift the lead of the discussion to another generation AI. In addition, it can evaluate the performance of the generation AI in real time and add new generation AIs as necessary. This can improve the quality of the discussion.

[0102] The reception unit can estimate the user's emotions and automatically adjust the number of generation AIs based on the user's emotions. For example, if the user is stressed, a discussion can be conducted with fewer generation AIs to provide a simple discussion. Also, if the user is relaxed, a detailed discussion can be conducted using many generation AIs. Furthermore, if the user is in a hurry, the reception unit can suggest the optimal number of generation AIs to quickly reach a conclusion. This makes it possible to adjust the scale of the discussion according to the user's emotions.

[0103] The discussion section can evaluate the opinions of the generation AI in real time and optimize the progress of the discussion. For example, if the opinions of the generation AI are contradictory, it can point out the inconsistencies and have the discussion resume. Also, if the opinions of the generation AI are consistent, it can advance the discussion based on those opinions. Furthermore, if the opinion of the generation AI offers a new perspective, it can deepen the discussion by placing emphasis on that perspective. This makes it possible to effectively utilize the opinions of the generation AI to advance the discussion.

[0104] The suggestion unit can propose multiple solutions based on the opinions of the generation AI and allow the user to select one. For example, the suggestion unit can display a list of multiple solutions proposed by the generation AI, and the user can select the most appropriate solution. It can also clearly indicate the advantages and disadvantages of each solution, making it easier for the user to compare them. Furthermore, it can also propose a specific implementation plan based on the solution selected by the user. This allows the user to select the optimal solution from multiple options.

[0105] The management unit can monitor the progress of the discussion and adjust the tempo of the discussion based on the user's emotions. For example, if the user is impatient, the tempo of the discussion can be sped up. Also, if the user is relaxed, the tempo of the discussion can be slowed down. Furthermore, if the user is excited, the tempo of the discussion can be adjusted to encourage a calm discussion. In this way, the quality of the discussion can be improved by adjusting the tempo of the discussion according to the user's emotions.

[0106] The reception unit can propose an optimal combination of generation AIs based on the user's past topic input history. For example, it can propose a combination of generation AIs that have been successful in the past on a specific topic. Also, if a specific generation AI has been found to be effective based on the past topic input history, it can also preferentially propose that generation AI. Furthermore, it can analyze the past topic input history and propose the optimal number of generation AIs. This makes it possible to hold more effective discussions by utilizing the user's past topic input history.

[0107] The discussion unit can estimate the user's emotions and adjust the way the discussion proceeds based on the user's emotions. For example, if the user is nervous, a gentle discussion method can be adopted. Also, if the user is relaxed, a discussion method that promotes lively discussion can be adopted. Furthermore, if the user is in a hurry, a discussion method that quickly reaches a conclusion can be adopted. In this way, the quality of the discussion can be improved by adjusting the discussion proceeding method according to the user's emotions.

[0108] The suggestion unit can propose multiple solutions based on the opinions of the generation AI and allow the user to select one. For example, the suggestion unit can display a list of multiple solutions proposed by the generation AI, and the user can select the most appropriate solution. It can also clearly indicate the advantages and disadvantages of each solution, making it easier for the user to compare them. Furthermore, it can also propose a specific implementation plan based on the solution selected by the user. This allows the user to select the optimal solution from multiple options.

[0109] The suggestion unit can estimate the user's emotions and adjust the way in which suggestions are expressed based on the user's emotions. For example, if the user is nervous, a simple and highly visible suggestion can be made. If the user is relaxed, a suggestion including detailed information can be made. Furthermore, if the user is in a hurry, a suggestion that focuses on the main points can be made. In this way, by adjusting the way in which suggestions are expressed according to the user's emotions, more appropriate suggestions can be made.

[0110] The process flow of the second embodiment will be briefly described below.

[0111] Step 1: The reception unit inputs the topic that the user wants to discuss. Examples of topics include, but are not limited to, technical issues, business strategies, and social issues. The reception unit also allows the user to select the number of generation AIs to participate in the discussion by operating a button. For example, if the user selects three generation AIs, the three generation AIs will participate in the discussion. Step 2: In the discussion section, the generation AIs hold a discussion. The generation AIs express their opinions, for example, using a text generation AI (e.g., LLM). The generation AIs deepen the discussion based on each other's opinions. For example, the generation AIs receive a prompt saying, "Please state your opinion on this topic," and each generation AI expresses its opinion. Step 3: The proposal unit collects the opinions of the generation AI and proposes a final solution. For example, the proposal unit proposes the most appropriate solution based on the opinions expressed by the generation AI. Step 4: The management unit manages the progress of the discussion. For example, it monitors the progress of the discussion and makes adjustments as necessary. The management unit records the progress of the discussion as a log. For example, it records the content and progress of the discussion so that it can be checked later. Some or all of the above-mentioned processing in the management unit may be performed, for example, using AI, or may be performed without using AI. For example, the management unit can manage the progress of the discussion using an AI model that monitors the progress of the discussion and adjusts the direction of the discussion as necessary.

[0112] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0113] 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<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. 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 a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0114] Furthermore, the above-described processing by the data processing system 10 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 required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0115] Each of the multiple elements including the above-mentioned reception unit, discussion unit, proposal unit, and management unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart device 14, and the user inputs a topic that he or she wants to discuss. The discussion unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and the generation AI holds a discussion. The proposal unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and collects the opinions of the generation AI to propose a final solution. The management unit is realized, for example, by the control unit 46A of the smart device 14, and manages the progress of the discussion. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0116] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0117] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0118] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0119] 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.

[0120] 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 the voice according to instructions from the processor 46.

[0121] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0122] 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 performed in a secure state.

[0123] Fig. 4 shows an example of 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.

[0124] 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.

[0125] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0126] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 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 also perform processing similar to that of the specific processing unit 290 using these models.

[0127] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0128] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[0129] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0130] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0131] Each of the multiple elements including the above-mentioned reception unit, discussion unit, proposal unit, and management unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart glasses 214, and the user inputs a topic that he or she wants to discuss. The discussion unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and the generation AI holds a discussion. The proposal unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and collects the opinions of the generation AI to propose a final solution. The management unit is realized, for example, by the control unit 46A of the smart glasses 214, and manages the progress of the discussion. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0132] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0133] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0134] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0135] 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.

[0136] 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 the voice according to instructions from the processor 46.

[0137] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0138] 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 performed in a secure state.

[0139] 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.

[0140] 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.

[0141] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0142] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific 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.

[0143] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0144] 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 voice indicating a user input for 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.

[0145] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0146] 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 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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0147] Each of the multiple elements including the above-mentioned reception unit, discussion unit, proposal unit, and management unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the headset type terminal 314, and the user inputs a topic that he or she wants to discuss. The discussion unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and the generation AI holds a discussion. The proposal unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and collects the opinions of the generation AI to propose a final solution. The management unit is realized, for example, by the control unit 46A of the headset type terminal 314, and manages the progress of the discussion. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0148] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0149] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0150] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0151] 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. In addition, the microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0152] 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 the voice according to instructions from the processor 46.

[0153] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0154] 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 performed in a secure state.

[0155] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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.

[0156] 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.

[0157] 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.

[0158] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0159] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific 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 program 60 executed on the RAM 48. The robot 414 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.

[0160] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0161] 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 a voice indicating a user input for 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.

[0162] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0163] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information 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.

[0164] Each of the multiple elements including the reception unit, discussion unit, proposal unit, and management unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the robot 414, and the user inputs a topic that he or she wants to discuss. The discussion unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and the generation AI holds a discussion. The proposal unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and collects the opinions of the generation AI to propose a final solution. The management unit is realized, for example, by the control unit 46A of the robot 414, and manages the progress of the discussion. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0165] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0166] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0167] These emotions are distributed in the three o'clock direction of emotion map 400 and usually 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.

[0168] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out on emotion map 400 you go, the more visible the emotions become (the more they are expressed in behavior).

[0169] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0170] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0171] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," have similar emotion values.

[0172] 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.

[0173] 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 Universal Serial Bus (USB) 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.

[0174] In addition, 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 upon request from the data processing device 12.

[0175] 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.

[0176] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0177] The hardware resource that executes the specific process may be one of these various processors, or may be 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.

[0178] As an example of a configuration using one 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 configuration using a processor that realizes the functions of the 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.

[0179] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0180] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0181] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0182] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0183] (Appendix 1) A reception unit that receives input of a theme; a discussion unit in which a plurality of generation AIs hold a discussion based on a theme accepted by the accepting unit; a proposal section that consolidates the opinions obtained by the discussion section and proposes a solution; A management unit that manages the progress of the discussion is provided. A system characterized by: (Appendix 2) The management unit Monitor progress of discussions and make adjustments as necessary 2. The system of claim 1, (Appendix 3) The reception unit is The user selects the number of AIs to participate in the discussion by pressing a button. 2. The system of claim 1, (Appendix 4) The discussion section includes: Generative AIs deepen discussions based on opinions 2. The system of claim 1, (Appendix 5) The suggestion unit, Aggregate the opinions of generative AI to propose a final solution 2. The system of claim 1, (Appendix 6) The management unit Record the progress of the discussion 2. The system of claim 1, (Appendix 7) The reception unit is Infer the user's emotions and adjust the theme input method based on the user's emotions 2. The system of claim 1, (Appendix 8) The reception unit is Analyze past theme input history and suggest input methods 2. The system of claim 1, (Appendix 9) The reception unit is As you type in a topic, suggestions are provided based on your interests. 2. The system of claim 1, (Appendix 10) The reception unit is Estimate the user's emotions and prioritize the input topics based on the user's emotions 2. The system of claim 1, (Appendix 11) The reception unit is When entering a topic, the app will prioritize relevant topics based on the user's geographic location. 2. The system of claim 1, (Appendix 12) The reception unit is When you enter a topic, we analyze your social media activity to suggest topics. 2. The system of claim 1, (Appendix 13) The discussion section includes: Infer the user's emotions and adjust the way the discussion proceeds based on the user's emotions 2. The system of claim 1, (Appendix 14) The discussion section includes: During discussions, the generation AI refers to past discussion history to select the discussion method. 2. The system of claim 1, (Appendix 15) The discussion section includes: During discussion, apply different discussion algorithms depending on the topic category 2. The system of claim 1, (Appendix 16) The discussion section includes: Estimate user sentiment and prioritize discussions based on user sentiment 2. The system of claim 1, (Appendix 17) The discussion section includes: During discussion, the discussion will be based on the geographical distribution of the generating AI. 2. The system of claim 1, (Appendix 18) The discussion section includes: During discussions, refer to literature and data to improve the accuracy of the discussion. 2. The system of claim 1, (Appendix 19) The suggestion unit, Infer the user's emotions and adjust the way suggestions are presented based on the user's emotions 2. The system of claim 1, (Appendix 20) The suggestion unit, When making suggestions, adjust the detail of the suggestions based on the importance of the generative AI's opinions 2. The system of claim 1, (Appendix 21) The suggestion unit, When making suggestions, apply different suggestion algorithms depending on the topic category 2. The system of claim 1, (Appendix 22) The suggestion unit, Estimate user sentiment and adjust the length of suggestions based on user sentiment 2. The system of claim 1, (Appendix 23) The suggestion unit, When making suggestions, we prioritize them based on when the generative AI submitted its opinions. 2. The system of claim 1, (Appendix 24) The suggestion unit, When making suggestions, adjust the order of suggestions based on the relevance of the generative AI’s opinion 2. The system of claim 1, (Appendix 25) The management unit Estimate the user's emotions and adjust the progress of the discussion based on the user's emotions 2. The system of claim 1, (Appendix 26) The management unit Monitor the progress of the discussion and decide how to proceed by referring to past progress history 2. The system of claim 1, (Appendix 27) The management unit Monitor discussion progress and apply different progression algorithms depending on topic categories 2. The system of claim 1, (Appendix 28) The management unit Estimate the user's emotions and determine the priority of the discussion based on the user's emotions 2. The system of claim 1, (Appendix 29) The management unit Monitor the progress of the debate and make progress based on the geographical distribution of the generating AI 2. The system of claim 1, (Appendix 30) The management unit Monitor the progress of discussions and improve their accuracy by referring to literature and data 2. The system of claim 1, [Explanation of symbols]

[0184] 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 unit that receives input of a theme; A discussion unit in which a plurality of generation AIs hold discussions based on the theme accepted by the accepting unit; a proposal section that consolidates the opinions obtained by the discussion section and proposes a solution; A management unit that manages the progress of the discussion is provided. A system characterized by:

2. The management unit Monitor the progress of these discussions and make adjustments as necessary.

2. The system of claim 1 .

3. The reception unit is The user selects the number of generated AIs to participate in the discussion by operating a button.

2. The system of claim 1 .

4. The discussion section includes: The generative AIs deepen the discussion based on their opinions.

2. The system of claim 1 .

5. The suggestion unit, Aggregate the opinions of multiple generative AIs to propose a final solution 2. The system of claim 1 .

6. The management unit Record the progress of the above discussion 2. The system of claim 1 .

7. The reception unit is Infer the user's emotions and adjust the theme input method based on the user's emotions 2. The system of claim 1 .

8. The reception unit is Analyze past theme input history and suggest input methods 2. The system of claim 1 .

Images