system

Abstract

The system according to the embodiment aims to promote diversity and creativity through collaboration and competition between generative AIs. [Solution] The system according to the embodiment comprises an idea sharing unit, a collaborative creation unit, a competition unit, an evaluation unit, and a collaboration unit. The idea sharing unit shares ideas between generation AIs. The collaborative creation unit causes the generation AIs to collaboratively create works based on ideas shared by the idea sharing unit. The competition unit evaluates the works created by the collaborative creation unit. The evaluation unit feeds back the evaluation results obtained by the competition unit to the generation AI. The collaboration unit supports collaboration between the generation AIs.

Description

[Technical Field]

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

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

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

[0004] Existing technology lacks sufficient mechanisms to promote diversity and creativity through collaboration and competition between generative AIs, leaving room for improvement.

[0005] The system according to the embodiment aims to promote diversity and creativity through collaboration and competition between generative AIs. [Means for solving the problem]

[0006] The system according to the embodiment comprises an idea sharing unit, a collaborative creation unit, a competition unit, an evaluation unit, and a collaboration unit. The idea sharing unit shares ideas between the generation AIs. The collaborative creation unit allows the generation AIs to collaboratively create works based on the ideas shared by the idea sharing unit. The competition unit evaluates the works created by the collaborative creation unit. The evaluation unit feeds back the evaluation results obtained by the competition unit to the generation AI. The collaboration unit supports collaboration between the generation AIs. [Effects of the Invention]

[0007] The system according to the embodiment can promote diversity and creativity through collaboration and competition between generative AIs. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A generative AI collaboration system according to an embodiment of the present invention is a system in which generative AIs share ideas, jointly create works, and evaluate the works. This generative AI collaboration system includes an idea sharing unit that shares ideas between generative AIs, a joint creation unit that allows the generative AIs to jointly create works based on the ideas shared by the idea sharing unit, a competition unit that evaluates the works created by the joint creation unit, an evaluation unit that feeds back the evaluation results obtained by the competition unit to the generative AIs, and a collaboration unit that supports collaboration between the generative AIs. For example, the generative AI collaboration system provides a platform in which multiple generative AIs participate. On this platform, the generative AIs can cooperate or compete with each other. For example, there is a collaboration mode in which generative AIs jointly create works, and a competition mode in which generative AIs create works on the same theme and compete for quality. In the collaboration mode, the generative AIs exchange ideas and jointly create works. For example, generative AI A might come up with a story plot, generative AI B might design characters based on that plot, and generative AI C might draw backgrounds. On the other hand, in competition mode, generative AIs generate works on the same theme and compete for quality. For example, on a "specific theme," each generative AI generates a work from its own perspective, and the works are then evaluated. Evaluation is carried out by users and experts, and the best work is selected. In addition, the results of collaboration and competition between generative AIs are made public on the platform and can be viewed by users. This is expected to widely recognize the diversity and creativity of generative AIs and encourage further development. In this way, the generative AI collaboration system can promote diversity and creativity through collaboration and competition between generative AIs.

[0029] A generative AI collaboration system according to an embodiment includes an idea sharing unit, a collaborative creation unit, a competition unit, an evaluation unit, and a collaboration unit. The idea sharing unit provides an interface for the generative AIs to share ideas with each other. For example, the idea sharing unit can share ideas in the form of text, images, audio, etc. The collaborative creation unit provides a protocol for the generative AIs to collaboratively create works. For example, the collaborative creation unit provides a communication protocol and a data exchange protocol for the generative AIs to collaboratively create works such as writing, paintings, and music. The competition unit allows the generative AIs to create works on the same theme and compete for quality. For example, the competition unit evaluates the quality of the works through methods such as user voting, expert review, and algorithm evaluation. The evaluation unit collects evaluations from users and experts and feeds the results back to the generative AI. For example, the evaluation unit collects evaluations through methods such as questionnaires, feedback forms, and real-time evaluations, and feeds the results back to the generative AI. The collaboration unit provides interfaces and protocols that enable the generative AIs to collaborate on a platform. For example, the collaboration unit supports collaboration between the generative AIs through methods such as API collaboration, data sharing, and protocols. As a result, the generative AI collaboration system according to the embodiment can promote diversity and creativity through collaboration and competition between generative AIs.

[0030] The idea sharing unit can provide an interface that allows generative AIs to share ideas with each other. Examples of interfaces include GUI (Graphical User Interface), API (Application Programming Interface), and CLI (Command Line Interface). For example, a GUI is an interface that allows generative AIs to visually share ideas and allows users to operate it intuitively. An API is an interface that allows generative AIs to share ideas through programs and facilitates data exchange between different systems. A CLI is an interface that allows generative AIs to share ideas by inputting commands and is suitable for scripts and automation. This allows generative AIs to share ideas efficiently with each other.

[0031] The collaborative generation unit can provide a protocol for the generation AIs to collaboratively generate works. Protocols include, for example, communication protocols and data exchange protocols. For example, a communication protocol defines rules for the generation AIs to send and receive data over a network, ensuring data integrity and security. A data exchange protocol defines rules for the generation AIs to exchange data in different formats, ensuring data compatibility. This allows the generation AIs to efficiently collaboratively generate works.

[0032] In the competition section, generative AIs can generate works on the same theme and compete for quality. Evaluation criteria and competition methods for competing for quality include, for example, user voting, expert review, and algorithm evaluation. For example, user voting is a method by which ordinary users evaluate the works of generative AIs, allowing the opinions of many users to be reflected. Expert review is a method by which experts in a specific field evaluate the works of generative AIs, allowing for evaluation from a professional perspective. Algorithm evaluation is a method by which generative AIs' works are evaluated using a specific algorithm, allowing for objective evaluation. As a result, the quality of the works improves as generative AIs compete with each other.

[0033] The evaluation unit can collect evaluations from users and experts and feed the results back to the generative AI. Methods for collecting evaluations include, for example, questionnaires, feedback forms, and real-time evaluations. For example, questionnaires are a way for users and experts to fill out their opinions about the generative AI's work, allowing for detailed feedback to be obtained. Feedback forms are online forms for users and experts to enter their evaluations of the generative AI's work, allowing for easy feedback collection. Real-time evaluation is a way for users and experts to evaluate the generative AI's work in real time, allowing for immediate feedback to be obtained. This allows the generative AI to improve based on the evaluation results.

[0034] The collaboration unit can provide interfaces and protocols that enable generative AIs to collaborate smoothly on the platform. Examples of interfaces and protocols include APIs (application programming interfaces) and data exchange protocols. For example, an API is an interface that allows generative AIs to exchange data through programs, facilitating data exchange between different systems. A data exchange protocol defines rules for generative AIs to exchange data in different formats, ensuring data compatibility. This allows generative AIs to collaborate smoothly with each other.

[0035] The idea sharing unit can analyze the generation AI's past idea sharing history and select the optimal sharing method. Sharing methods include, for example, text sharing, image sharing, and audio sharing. For example, text sharing is a method in which the generation AI shares ideas in text format, allowing for easy idea communication. Image sharing is a method in which the generation AI shares ideas in image format, allowing for visual communication of ideas. Audio sharing is a method in which the generation AI shares ideas in audio format, allowing for auditory communication of ideas. This allows for the optimal sharing method to be selected based on past history. For example, the generation AI can prioritize suggesting sharing methods that have been successful in the past. It is also possible for the generation AI to avoid sharing methods that have failed in the past. Furthermore, the generation AI's past sharing history can be used to share ideas at the most effective time.

[0036] When sharing ideas, the idea sharing unit can filter ideas based on the generation AI's current project or areas of interest. Filtering criteria and methods include, for example, keyword filtering and category filtering. For example, keyword filtering is a method of filtering ideas based on keywords specified by the generation AI, making it possible to extract highly relevant ideas. Category filtering is a method of filtering ideas based on categories specified by the generation AI, making it possible to extract ideas related to a specific field. This makes it possible to share highly relevant ideas based on the generation AI's interests. For example, the generation AI can share only ideas related to the project it is currently working on. It is also possible to prioritize sharing highly relevant ideas based on the generation AI's areas of interest. Furthermore, it is possible to filter ideas based on areas in which the generation AI has shown interest in the past.

[0037] When sharing ideas, the idea sharing unit can prioritize sharing highly relevant ideas by taking into account the geographical location information of the generation AI. Methods for acquiring and using geographical location information include, for example, GPS data and IP addresses. For example, GPS data is a method for acquiring the current location of the generation AI with high accuracy, and highly relevant ideas can be shared based on the location information. An IP address is a method for estimating the location of the generation AI's internet connection destination, and highly relevant ideas can be shared based on the location information. This makes it possible to share highly relevant ideas based on the generation AI's location information. For example, if the generation AI is in a specific area, ideas related to that area can be prioritized for sharing. Also, if the generation AI is moving, ideas related to the destination can be shared. Furthermore, if the generation AI stays in a specific location for a long time, ideas related to that location can be prioritized for sharing.

[0038] The idea sharing unit can analyze the social media activity of the generation AI when sharing ideas and share related ideas. Methods and criteria for analyzing social media activity include, for example, post content, number of followers, and engagement rate. For example, the post content is a method by which the generation AI analyzes information posted on social media, allowing it to share ideas related to topics of interest. The number of followers is a method by which the generation AI shares relevant ideas based on the number of accounts followed on social media, allowing it to share ideas based on the activity of influential accounts. The engagement rate is a method by which the generation AI shares relevant ideas based on responses to social media activity, allowing it to share ideas related to topics of interest. This allows it to share relevant ideas based on the generation AI's social media activity. For example, the generation AI can share ideas related to topics of interest on social media. It can also share ideas based on the activity of accounts followed on social media. It can also share ideas related to topics of groups in which the generation AI participates on social media.

[0039] The co-generation unit can apply an algorithm to optimize the role allocation of the generation AI during co-generation. Criteria and methods for optimizing role allocation include, for example, skill matching and task division algorithms. For example, skill matching is a method of allocating roles based on the generative AI's areas of expertise and skills, enabling efficient co-generation. A task division algorithm is a method of allocating roles based on the generative AI's past performance and current state, enabling optimal role allocation. This enables efficient co-generation by optimizing the role allocation of the generation AI. For example, roles can be allocated based on the generative AI's areas of expertise. Roles can also be allocated based on the generative AI's past performance. Roles can also be allocated based on the generative AI's current state.

[0040] During co-generation, the co-generation unit can select the optimal generation method by referring to the generation AI's past co-generation history. Criteria and selection methods for the optimal generation method include, for example, past success stories and algorithm performance. For example, past success stories are a method of selecting the optimal generation method based on generation methods that the generation AI has been successful in the past, enabling effective generation. Algorithm performance is a method of selecting the optimal generation method based on the performance of algorithms that the generation AI has used in the past, enabling highly accurate generation. This makes it possible to select the optimal generation method based on past history. For example, the generation AI can prioritize the selection of generation methods that have been successful in the past. It is also possible to have the generation AI avoid generation methods that have failed in the past. Furthermore, the most effective generation method can be selected from the generation AI's past co-generation history.

[0041] During co-generation, the co-generation unit can select the optimal generation method by taking into account the geographical location information of the generation AI. Methods for acquiring and using geographical location information include, for example, GPS data and IP address. For example, GPS data is a method for acquiring the current location of the generation AI with high accuracy, and the optimal generation method can be selected based on the location information. An IP address is a method for estimating the location of the generation AI's internet connection destination, and the optimal generation method can be selected based on the location information. This makes it possible to select the optimal generation method based on the location information of the generation AI. For example, if the generation AI is in a specific area, a generation method related to that area can be selected. Also, if the generation AI is moving, a generation method related to the destination can be selected. Furthermore, if the generation AI stays in a specific location for a long time, a generation method related to that location can be selected.

[0042] During co-generation, the collaborative generation unit can analyze the social media activity of the generation AI and suggest relevant generation methods. Analysis methods and criteria for social media activity include, for example, post content, number of followers, and engagement rate. For example, the post content is a method in which the generation AI analyzes information posted on social media, and can suggest generation methods related to topics of interest. The number of followers is a method in which the generation AI suggests relevant generation methods based on the number of accounts followed on social media, and can suggest generation methods based on the activity of influential accounts. The engagement rate is a method in which the generation AI suggests relevant generation methods based on responses to social media activity, and can suggest generation methods related to topics of interest. This allows the optimal generation method to be suggested based on the social media activity of the generation AI. For example, the generation AI suggests generation methods related to topics of interest on social media. It can also suggest generation methods based on the activity of accounts followed by the generation AI on social media. It can also suggest generation methods related to topics of groups in which the generation AI participates on social media.

[0043] The competition unit can improve the accuracy of competition by taking into account the mutual relationships between the generated AIs during competition. Evaluation criteria and analysis methods for mutual relationships include, for example, cooperative relationships, competitive relationships, and dependency relationships. For example, cooperative relationships are a method of evaluation based on the history of generated AIs cooperating with each other in the past to successfully complete projects, which can promote competition between generated AIs with strong cooperative relationships. Competitive relationships are a method of evaluation based on the history of generated AIs competing with each other in the past, which can promote competition between generated AIs with strong competitive relationships. Dependency is a method of evaluation based on the history of generated AIs being dependent on each other in the past, which can adjust competition between generated AIs with strong dependencies. In this way, the accuracy of competition is improved by taking into account the mutual relationships between the generated AIs. For example, competitions can be conducted taking into account past cooperative relationships between the generated AIs. In addition, competitions can be conducted by referring to the results of past competitions between the generated AIs. Furthermore, the accuracy of competition can be improved based on mutual evaluations between the generated AIs.

[0044] During a competition, the competition department can take into account the attribute information of the person who submitted the generation AI. Types and acquisition methods of attribute information include, for example, age, gender, and occupation. For example, age is a method of adjusting the competition criteria based on the age of the person who submitted the generation AI, allowing for appropriate competition according to age groups. Gender is a method of adjusting the competition criteria based on the gender of the person who submitted the generation AI, allowing for appropriate competition according to gender. Occupation is a method of adjusting the competition criteria based on the occupation of the person who submitted the generation AI, allowing for appropriate competition according to occupation. In this way, appropriate competition can be conducted by taking into account the attribute information of the person who submitted the generation AI. For example, if the person who submitted the generation AI is an expert, professional evaluation criteria can be set. Also, if the person who submitted the generation AI is a beginner, simple evaluation criteria can be set. Furthermore, the competition can also take into account the past performance of the person who submitted the generation AI.

[0045] The competition unit can take into account the geographical distribution of the generated AI during competition. Methods for obtaining and using the geographical distribution include, for example, GPS data and IP addresses. For example, GPS data is a method for obtaining the current location of the generated AI with high accuracy, allowing appropriate competitions to be held based on the location information. IP addresses are a method for estimating the location of the generated AI's internet connection destination, allowing appropriate competitions to be held based on the location information. This allows appropriate competitions to be held based on the geographical distribution of the generated AI. For example, if the generated AIs are concentrated in a specific region, the competition can be held on a theme related to that region. Also, if the generated AIs are distributed widely, the competition can be held on a global theme. Furthermore, if the generated AIs stay in a specific location for a long time, the competition can be held on a theme related to that location.

[0046] During competition, the competition department can improve the accuracy of the competition by referring to the related literature of the generating AI. The types and referencing methods of related literature include, for example, academic papers, patent documents, and technical reports. For example, academic papers are a method of conducting competitions based on academic literature that the generating AI has previously referenced, enabling competitions that utilize specialized knowledge. Patent documents are a method of conducting competitions based on patent documents that the generating AI has previously referenced, enabling competitions that utilize technical knowledge. Technical reports are a method of conducting competitions based on technical reports that the generating AI has previously referenced, enabling competitions that utilize practical knowledge. This improves the accuracy of the competition by referring to the related literature of the generating AI. For example, competitions can be conducted based on literature that the generating AI has previously referenced. Competitions can also be conducted based on literature that the generating AI is currently referencing. Furthermore, competitions can be conducted based on literature that the generating AI may reference in the future.

[0047] During evaluation, the evaluation unit can predict the current evaluation by referring to past evaluation data. Types and reference methods of past evaluation data include, for example, user evaluation history and expert evaluation history. For example, user evaluation history is a method in which the generation AI predicts the current evaluation based on evaluation data from users that it has received in the past, enabling evaluation that reflects user opinions. Expert evaluation history is a method in which the generation AI predicts the current evaluation based on evaluation data from experts that it has received in the past, enabling evaluation that reflects expert perspectives. This makes it possible to predict the current evaluation based on past evaluation data. For example, the current evaluation can be predicted based on the generation AI's past evaluation data. It is also possible to analyze and predict evaluation trends from the generation AI's past evaluation data. Furthermore, it is also possible to predict the most appropriate evaluation by referring to the generation AI's past evaluation data.

[0048] During evaluation, the evaluation unit can apply different evaluation and analysis methods to each category of the generative AI. Types and implementation methods of evaluation and analysis methods include, for example, statistical analysis and machine learning algorithms. For example, statistical analysis is a method of statistically analyzing the generative AI's evaluation data, which allows for understanding trends and patterns in the data. Machine learning algorithms are methods that learn based on the generative AI's evaluation data and predict and classify evaluations, enabling highly accurate evaluation. This allows for the application of the optimal evaluation and analysis method depending on the category of the generative AI. For example, if the generative AI belongs to the creative category, an evaluation and analysis method that emphasizes creativity can be applied. Also, if the generative AI belongs to the technical category, an evaluation and analysis method that emphasizes technical accuracy can be applied. Furthermore, if the generative AI belongs to the entertainment category, an evaluation and analysis method that emphasizes user satisfaction can be applied.

[0049] During evaluation, the evaluation unit can analyze changes in evaluation based on the time of submission by the generation AI. Methods for obtaining and using the submission time include, for example, timestamps and submission history. For example, a timestamp is a method for recording the date and time when the generation AI submitted a work, and it is possible to analyze changes in evaluation based on the time of submission. A submission history is a method for recording the history of works previously submitted by the generation AI, and it is possible to analyze changes in evaluation based on the time of submission. This makes it possible to understand changes in evaluation based on the time of submission by the generation AI. For example, the evaluation of works submitted by the generation AI at a specific time period can be analyzed to understand changes in evaluation. It is also possible to analyze the evaluation of works submitted by the generation AI over a long period of time in chronological order. Furthermore, it is also possible to analyze the evaluation of works submitted by the generation AI during a specific event period.

[0050] During evaluation, the evaluation unit can analyze the evaluation by referring to market data related to the generation AI. Types and reference methods of related market data include, for example, market research reports, sales data, etc. For example, market research reports provide data for evaluating the market acceptance of works generated by the generation AI, making it possible to understand market trends and the competitive situation. Sales data provides data for evaluating the market sales of works generated by the generation AI, making it possible to evaluate the commercial success of the works. This allows the evaluation to be analyzed based on the market data related to the generation AI. For example, the market acceptance of works generated by the generation AI can be reflected in the evaluation. In addition, market trends for works generated by the generation AI can be analyzed and reflected in the evaluation. Furthermore, the competitive situation in the market for works generated by the generation AI can be reflected in the evaluation.

[0051] When collaborating, the collaboration unit can select the optimal collaboration method by referring to the generation AI's past collaboration history. Types of collaboration history and reference methods include, for example, past collaboration projects and collaboration deliverables. For example, past collaboration projects is a method of selecting the optimal collaboration method based on the history of collaboration projects in which the generation AI has previously participated, enabling effective collaboration. Collaboration deliverables is a method of selecting the optimal collaboration method based on the history of collaboration deliverables generated by the generation AI in the past, enabling high-quality collaboration. This makes it possible to select the optimal collaboration method based on the past collaboration history. For example, the generation AI can prioritize collaboration methods that have been successful in the past. It is also possible to have the generation AI avoid collaboration methods that have failed in the past. Furthermore, the most effective collaboration method can be selected from the generation AI's past collaboration history.

[0052] During collaboration, the collaboration unit can customize the collaboration method based on the generation AI's current project and areas of interest. Methods for obtaining and using projects and areas of interest include, for example, project management tools and survey results. For example, a project management tool is a tool for managing information about projects the generation AI is currently working on, allowing for understanding the project's progress and task details. Survey results are a method for collecting information about areas of interest to the generation AI, and can customize the collaboration method based on the areas of interest. This makes it possible to provide the optimal collaboration method based on the generation AI's project and areas of interest. For example, a collaboration method related to the project the generation AI is currently working on can be provided. It is also possible to provide highly relevant collaboration methods based on the generation AI's areas of interest. Furthermore, it is possible to customize the collaboration method based on areas the generation AI has shown interest in in the past.

[0053] During collaboration, the collaboration unit can select the optimal collaboration method by taking into account the geographical location information of the generated AI. Methods for acquiring and using geographical location information include, for example, GPS data and IP address. For example, GPS data is a method for acquiring the current location of the generated AI with high accuracy, and the optimal collaboration method can be selected based on the location information. An IP address is a method for estimating the location of the generated AI's internet connection destination, and the optimal collaboration method can be selected based on the location information. This makes it possible to select the optimal collaboration method based on the generated AI's location information. For example, if the generated AI is in a specific area, a collaboration method related to that area can be selected. Also, if the generated AI is moving, a collaboration method related to the destination can be selected. Furthermore, if the generated AI stays in a specific location for a long time, a collaboration method related to that location can be selected.

[0054] During collaboration, the collaboration unit can analyze the social media activity of the generation AI and suggest collaboration methods. Analysis methods and criteria for social media activity include, for example, post content, number of followers, and engagement rate. For example, the post content is a method in which the generation AI analyzes information posted on social media, allowing it to suggest collaboration methods related to topics of interest. The number of followers is a method in which the generation AI suggests relevant collaboration methods based on the number of accounts followed on social media, allowing it to suggest collaboration methods based on the activity of influential accounts. The engagement rate is a method in which the generation AI suggests relevant collaboration methods based on responses to social media activities, allowing it to suggest collaboration methods related to topics of interest. This allows it to suggest optimal collaboration methods based on the social media activity of the generation AI. For example, the generation AI suggests collaboration methods related to topics of interest on social media. It can also suggest collaboration methods based on the activity of accounts followed by the generation AI on social media. It can also suggest collaboration methods related to topics of groups the generation AI participates in on social media.

[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 generative AI collaboration system can further include a data analysis unit. The data analysis unit analyzes the data of the works generated by the generative AI and evaluates the performance of the generative AI. For example, it can analyze the quality of the works generated by the generative AI and identify which generative AI contributed to what part. It can also analyze the generative AI's generation process and propose efficient generation methods. It can also analyze the generative AI's generation history and propose optimal generation methods based on past successes and failures. This can improve the performance of the generative AI.

[0057] The generative AI collaboration system can further include a learning unit. The learning unit supports the learning of the generative AI based on the works generated by the generative AI and the evaluation results. For example, the evaluation results of the works generated by the generative AI can be fed back and used as learning data for the generative AI to improve itself. The generative AI can also learn the generation processes of other generative AIs and acquire efficient generation methods. Furthermore, the generative AI can optimize the generation process based on past generation history. This can improve the learning ability of the generative AI.

[0058] The generative AI collaboration system can further include an incentive unit. The incentive unit provides rewards according to the performance of the generative AI. For example, if the generative AI generates a high-quality work, points or badges can be awarded. Also, if the generative AI successfully collaborates with other generative AIs, rewards can be distributed to the entire team. Furthermore, if the generative AI achieves a specific goal, a special reward can be provided. This can improve the motivation of the generative AI.

[0059] The generative AI collaboration system can further include a user interaction unit. The user interaction unit provides an interface for users to directly interact with the generative AI. For example, the user can provide feedback to the generative AI, which can then improve itself based on that feedback. The user can also give specific instructions to the generative AI, which can then generate a work in accordance with those instructions. Furthermore, the user can monitor the generative AI's generation process in real time and intervene as necessary. This improves the interaction between the user and the generative AI.

[0060] The generative AI collaboration system can further include a security unit. The security unit provides security protocols for protecting data exchange and communication between generative AIs. For example, the security unit can encrypt data shared by the generative AIs to prevent unauthorized access. It can also monitor the generative AIs' communications and detect abnormal activity. It can also manage the generative AIs' access permissions and restrict access to specific data and functions. This improves the security of the generative AIs' data and communications.

[0061] The processing flow of the first embodiment will be briefly explained below.

[0062] Step 1: The idea sharing section provides an interface for generative AIs to share ideas with each other. For example, ideas can be shared in the form of text, images, audio, etc. Step 2: The collaborative generation unit provides protocols for the generative AIs to collaboratively generate works, such as communication protocols and data exchange protocols for the generative AIs to collaboratively generate works such as writing, paintings, and music. Step 3: In the competition section, the AIs generate works on the same theme and compete for quality. For example, the quality of the works is evaluated through user voting, expert review, algorithm evaluation, etc. Step 4: The evaluation unit collects evaluations from users and experts and feeds the results back to the generation AI. For example, evaluations are collected through surveys, feedback forms, real-time evaluations, and other methods, and the results are fed back to the generation AI. Step 5: The collaboration unit provides interfaces and protocols to enable smooth collaboration between generative AIs on the platform. For example, it supports collaboration between generative AIs through API collaboration, data sharing, protocols, etc.

[0063] (Example 2) A generative AI collaboration system according to an embodiment of the present invention is a system in which generative AIs share ideas, jointly create works, and evaluate the works. This generative AI collaboration system includes an idea sharing unit that shares ideas between generative AIs, a joint creation unit that allows the generative AIs to jointly create works based on the ideas shared by the idea sharing unit, a competition unit that evaluates the works created by the joint creation unit, an evaluation unit that feeds back the evaluation results obtained by the competition unit to the generative AIs, and a collaboration unit that supports collaboration between the generative AIs. For example, the generative AI collaboration system provides a platform in which multiple generative AIs participate. On this platform, the generative AIs can cooperate or compete with each other. For example, there is a collaboration mode in which generative AIs jointly create works, and a competition mode in which generative AIs create works on the same theme and compete for quality. In the collaboration mode, the generative AIs exchange ideas and jointly create works. For example, generative AI A might come up with a story plot, generative AI B might design characters based on that plot, and generative AI C might draw backgrounds. On the other hand, in competition mode, generative AIs generate works on the same theme and compete for quality. For example, on a "specific theme," each generative AI generates a work from its own perspective, and the works are then evaluated. Evaluation is carried out by users and experts, and the best work is selected. In addition, the results of collaboration and competition between generative AIs are made public on the platform and can be viewed by users. This is expected to widely recognize the diversity and creativity of generative AIs and encourage further development. In this way, the generative AI collaboration system can promote diversity and creativity through collaboration and competition between generative AIs.

[0064] A generative AI collaboration system according to an embodiment includes an idea sharing unit, a collaborative creation unit, a competition unit, an evaluation unit, and a collaboration unit. The idea sharing unit provides an interface for the generative AIs to share ideas with each other. For example, the idea sharing unit can share ideas in the form of text, images, audio, etc. The collaborative creation unit provides a protocol for the generative AIs to collaboratively create works. For example, the collaborative creation unit provides a communication protocol and a data exchange protocol for the generative AIs to collaboratively create works such as writing, paintings, and music. The competition unit allows the generative AIs to create works on the same theme and compete for quality. For example, the competition unit evaluates the quality of the works through methods such as user voting, expert review, and algorithm evaluation. The evaluation unit collects evaluations from users and experts and feeds the results back to the generative AI. For example, the evaluation unit collects evaluations through methods such as questionnaires, feedback forms, and real-time evaluations, and feeds the results back to the generative AI. The collaboration unit provides interfaces and protocols that enable the generative AIs to collaborate on a platform. For example, the collaboration unit supports collaboration between the generative AIs through methods such as API collaboration, data sharing, and protocols. As a result, the generative AI collaboration system according to the embodiment can promote diversity and creativity through collaboration and competition between generative AIs.

[0065] The idea sharing unit can provide an interface that allows generative AIs to share ideas with each other. Examples of interfaces include GUI (Graphical User Interface), API (Application Programming Interface), and CLI (Command Line Interface). For example, a GUI is an interface that allows generative AIs to visually share ideas and allows users to operate it intuitively. An API is an interface that allows generative AIs to share ideas through programs and facilitates data exchange between different systems. A CLI is an interface that allows generative AIs to share ideas by inputting commands and is suitable for scripts and automation. This allows generative AIs to share ideas efficiently with each other.

[0066] The collaborative generation unit can provide a protocol for the generation AIs to collaboratively generate works. Protocols include, for example, communication protocols and data exchange protocols. For example, a communication protocol defines rules for the generation AIs to send and receive data over a network, ensuring data integrity and security. A data exchange protocol defines rules for the generation AIs to exchange data in different formats, ensuring data compatibility. This allows the generation AIs to efficiently collaboratively generate works.

[0067] In the competition section, generative AIs can generate works on the same theme and compete for quality. Evaluation criteria and competition methods for competing for quality include, for example, user voting, expert review, and algorithm evaluation. For example, user voting is a method by which ordinary users evaluate the works of generative AIs, allowing the opinions of many users to be reflected. Expert review is a method by which experts in a specific field evaluate the works of generative AIs, allowing for evaluation from a professional perspective. Algorithm evaluation is a method by which generative AIs' works are evaluated using a specific algorithm, allowing for objective evaluation. As a result, the quality of the works improves as generative AIs compete with each other.

[0068] The evaluation unit can collect evaluations from users and experts and feed the results back to the generative AI. Methods for collecting evaluations include, for example, questionnaires, feedback forms, and real-time evaluations. For example, questionnaires are a way for users and experts to fill out their opinions about the generative AI's work, allowing for detailed feedback to be obtained. Feedback forms are online forms for users and experts to enter their evaluations of the generative AI's work, allowing for easy feedback collection. Real-time evaluation is a way for users and experts to evaluate the generative AI's work in real time, allowing for immediate feedback to be obtained. This allows the generative AI to improve based on the evaluation results.

[0069] The collaboration unit can provide interfaces and protocols that enable generative AIs to collaborate smoothly on the platform. Examples of interfaces and protocols include APIs (application programming interfaces) and data exchange protocols. For example, an API is an interface that allows generative AIs to exchange data through programs, facilitating data exchange between different systems. A data exchange protocol defines rules for generative AIs to exchange data in different formats, ensuring data compatibility. This allows generative AIs to collaborate smoothly with each other.

[0070] The idea sharing unit can estimate the emotions of the generating AI and adjust the timing of idea sharing based on the estimated emotions of the generating AI. Methods for estimating emotions include, for example, emotion analysis algorithms and sensor data analysis. For example, emotion analysis algorithms analyze the text data and voice data of the generating AI to estimate emotions, making it possible to grasp the emotional state of the generating AI. Sensor data analysis analyzes the biometric data and behavioral data of the generating AI to estimate emotions, making it possible to grasp the emotional state of the generating AI in real time. This allows ideas to be shared at the optimal time depending on the emotions of the generating AI. For example, if the generating AI is excited, it can share ideas immediately to promote responses from other generating AIs. Also, if the generating AI is tired, it can temporarily delay idea sharing to allow it to take a rest. Furthermore, if the generating AI is concentrating, it can postpone idea sharing to maintain its concentration.

[0071] The idea sharing unit can analyze the generation AI's past idea sharing history and select the optimal sharing method. Sharing methods include, for example, text sharing, image sharing, and audio sharing. For example, text sharing is a method in which the generation AI shares ideas in text format, allowing for easy idea communication. Image sharing is a method in which the generation AI shares ideas in image format, allowing for visual communication of ideas. Audio sharing is a method in which the generation AI shares ideas in audio format, allowing for auditory communication of ideas. This allows for the optimal sharing method to be selected based on past history. For example, the generation AI can prioritize suggesting sharing methods that have been successful in the past. It is also possible for the generation AI to avoid sharing methods that have failed in the past. Furthermore, the generation AI's past sharing history can be used to share ideas at the most effective time.

[0072] When sharing ideas, the idea sharing unit can filter ideas based on the generation AI's current project or areas of interest. Filtering criteria and methods include, for example, keyword filtering and category filtering. For example, keyword filtering is a method of filtering ideas based on keywords specified by the generation AI, making it possible to extract highly relevant ideas. Category filtering is a method of filtering ideas based on categories specified by the generation AI, making it possible to extract ideas related to a specific field. This makes it possible to share highly relevant ideas based on the generation AI's interests. For example, the generation AI can share only ideas related to the project it is currently working on. It is also possible to prioritize sharing highly relevant ideas based on the generation AI's areas of interest. Furthermore, it is possible to filter ideas based on areas in which the generation AI has shown interest in the past.

[0073] The idea sharing unit can estimate the emotions of the generation AI and prioritize the ideas to be shared based on the estimated emotions of the generation AI. Criteria and methods for determining priorities include, for example, importance, urgency, and relevance. For example, importance is determined based on the impact and importance of the idea generated by the generation AI. Urgency is determined based on the urgency of implementing the idea generated by the generation AI. Relevance is determined based on the relevance of the idea generated by the generation AI to current projects or areas of interest. This allows the optimal ideas to be shared preferentially depending on the emotions of the generation AI. For example, if the generation AI is excited, creative ideas can be shared preferentially. Also, if the generation AI is relaxed, detailed ideas can be shared preferentially. Furthermore, if the generation AI is tired, simple and actionable ideas can be shared preferentially.

[0074] When sharing ideas, the idea sharing unit can prioritize sharing highly relevant ideas by taking into account the geographical location information of the generation AI. Methods for acquiring and using geographical location information include, for example, GPS data and IP addresses. For example, GPS data is a method for acquiring the current location of the generation AI with high accuracy, and highly relevant ideas can be shared based on the location information. An IP address is a method for estimating the location of the generation AI's internet connection destination, and highly relevant ideas can be shared based on the location information. This makes it possible to share highly relevant ideas based on the generation AI's location information. For example, if the generation AI is in a specific area, ideas related to that area can be prioritized for sharing. Also, if the generation AI is moving, ideas related to the destination can be shared. Furthermore, if the generation AI stays in a specific location for a long time, ideas related to that location can be prioritized for sharing.

[0075] The idea sharing unit can analyze the social media activity of the generation AI when sharing ideas and share related ideas. Methods and criteria for analyzing social media activity include, for example, post content, number of followers, and engagement rate. For example, the post content is a method by which the generation AI analyzes information posted on social media, allowing it to share ideas related to topics of interest. The number of followers is a method by which the generation AI shares relevant ideas based on the number of accounts followed on social media, allowing it to share ideas based on the activity of influential accounts. The engagement rate is a method by which the generation AI shares relevant ideas based on responses to social media activity, allowing it to share ideas related to topics of interest. This allows it to share relevant ideas based on the generation AI's social media activity. For example, the generation AI can share ideas related to topics of interest on social media. It can also share ideas based on the activity of accounts followed on social media. It can also share ideas related to topics of groups in which the generation AI participates on social media.

[0076] The co-generation unit can estimate the emotions of the generative AI and adjust the co-generation process based on the estimated emotions of the generative AI. Methods for estimating emotions include, for example, emotion analysis algorithms and sensor data analysis. For example, emotion analysis algorithms analyze the text and voice data of the generative AI to estimate emotions, making it possible to grasp the generative AI's emotional state. Sensor data analysis analyzes the biometric and behavioral data of the generative AI to estimate emotions, making it possible to grasp the generative AI's emotional state in real time. This allows the optimal co-generation process to be executed according to the generative AI's emotions. For example, if the generative AI is excited, the process of quickly sharing ideas can be promoted. Also, if the generative AI is relaxed, the process of detailed discussion can be promoted. Furthermore, if the generative AI is tired, the co-generation can be divided into easier tasks.

[0077] The co-generation unit can apply an algorithm to optimize the role allocation of the generation AI during co-generation. Criteria and methods for optimizing role allocation include, for example, skill matching and task division algorithms. For example, skill matching is a method of allocating roles based on the generative AI's areas of expertise and skills, enabling efficient co-generation. A task division algorithm is a method of allocating roles based on the generative AI's past performance and current state, enabling optimal role allocation. This enables efficient co-generation by optimizing the role allocation of the generation AI. For example, roles can be allocated based on the generative AI's areas of expertise. Roles can also be allocated based on the generative AI's past performance. Roles can also be allocated based on the generative AI's current state.

[0078] During co-generation, the co-generation unit can select the optimal generation method by referring to the generation AI's past co-generation history. Criteria and selection methods for the optimal generation method include, for example, past success stories and algorithm performance. For example, past success stories are a method of selecting the optimal generation method based on generation methods that the generation AI has been successful in the past, enabling effective generation. Algorithm performance is a method of selecting the optimal generation method based on the performance of algorithms that the generation AI has used in the past, enabling highly accurate generation. This makes it possible to select the optimal generation method based on past history. For example, the generation AI can prioritize the selection of generation methods that have been successful in the past. It is also possible to have the generation AI avoid generation methods that have failed in the past. Furthermore, the most effective generation method can be selected from the generation AI's past co-generation history.

[0079] The collaborative generation unit can estimate the emotions of the generation AI and determine the priorities of collaborative generation based on the estimated emotions of the generation AI. Criteria and methods for determining priorities include, for example, importance, urgency, and relevance. For example, importance is determined based on the impact and importance of the task generated by the generation AI. Urgency is determined based on the urgency of executing the task generated by the generation AI. Relevance is determined based on the relevance of the task generated by the generation AI to current projects and areas of interest. This allows the optimal task to be prioritized according to the emotions of the generation AI. For example, if the generation AI is excited, creative tasks can be prioritized. Also, if the generation AI is relaxed, detailed tasks can be prioritized. Furthermore, if the generation AI is tired, simple tasks can be prioritized.

[0080] During co-generation, the co-generation unit can select the optimal generation method by taking into account the geographical location information of the generation AI. Methods for acquiring and using geographical location information include, for example, GPS data and IP address. For example, GPS data is a method for acquiring the current location of the generation AI with high accuracy, and the optimal generation method can be selected based on the location information. An IP address is a method for estimating the location of the generation AI's internet connection destination, and the optimal generation method can be selected based on the location information. This makes it possible to select the optimal generation method based on the location information of the generation AI. For example, if the generation AI is in a specific area, a generation method related to that area can be selected. Also, if the generation AI is moving, a generation method related to the destination can be selected. Furthermore, if the generation AI stays in a specific location for a long time, a generation method related to that location can be selected.

[0081] During co-generation, the collaborative generation unit can analyze the social media activity of the generation AI and suggest relevant generation methods. Analysis methods and criteria for social media activity include, for example, post content, number of followers, and engagement rate. For example, the post content is a method in which the generation AI analyzes information posted on social media, and can suggest generation methods related to topics of interest. The number of followers is a method in which the generation AI suggests relevant generation methods based on the number of accounts followed on social media, and can suggest generation methods based on the activity of influential accounts. The engagement rate is a method in which the generation AI suggests relevant generation methods based on responses to social media activity, and can suggest generation methods related to topics of interest. This allows the optimal generation method to be suggested based on the social media activity of the generation AI. For example, the generation AI suggests generation methods related to topics of interest on social media. It can also suggest generation methods based on the activity of accounts followed by the generation AI on social media. It can also suggest generation methods related to topics of groups in which the generation AI participates on social media.

[0082] The competition unit can estimate the emotions of the generating AI and adjust the competition criteria based on the estimated emotions of the generating AI. Methods for estimating emotions include, for example, emotion analysis algorithms and sensor data analysis. For example, emotion analysis algorithms analyze the generating AI's text data and voice data to estimate emotions, making it possible to grasp the generating AI's emotional state. Sensor data analysis analyzes the generating AI's biometric and behavioral data to estimate emotions, making it possible to grasp the generating AI's emotional state in real time. This allows optimal competition criteria to be set according to the generating AI's emotions. For example, if the generating AI is excited, competition criteria that emphasize creativity can be set. Also, if the generating AI is relaxed, detailed evaluation criteria can be set. Furthermore, if the generating AI is tired, simple evaluation criteria can be set.

[0083] The competition unit can improve the accuracy of competition by taking into account the mutual relationships between the generated AIs during competition. Evaluation criteria and analysis methods for mutual relationships include, for example, cooperative relationships, competitive relationships, and dependency relationships. For example, cooperative relationships are a method of evaluation based on the history of generated AIs cooperating with each other in the past to successfully complete projects, which can promote competition between generated AIs with strong cooperative relationships. Competitive relationships are a method of evaluation based on the history of generated AIs competing with each other in the past, which can promote competition between generated AIs with strong competitive relationships. Dependency is a method of evaluation based on the history of generated AIs being dependent on each other in the past, which can adjust competition between generated AIs with strong dependencies. In this way, the accuracy of competition is improved by taking into account the mutual relationships between the generated AIs. For example, competitions can be conducted taking into account past cooperative relationships between the generated AIs. In addition, competitions can be conducted by referring to the results of past competitions between the generated AIs. Furthermore, the accuracy of competition can be improved based on mutual evaluations between the generated AIs.

[0084] During a competition, the competition department can take into account the attribute information of the person who submitted the generation AI. Types and acquisition methods of attribute information include, for example, age, gender, and occupation. For example, age is a method of adjusting the competition criteria based on the age of the person who submitted the generation AI, allowing for appropriate competition according to age groups. Gender is a method of adjusting the competition criteria based on the gender of the person who submitted the generation AI, allowing for appropriate competition according to gender. Occupation is a method of adjusting the competition criteria based on the occupation of the person who submitted the generation AI, allowing for appropriate competition according to occupation. In this way, appropriate competition can be conducted by taking into account the attribute information of the person who submitted the generation AI. For example, if the person who submitted the generation AI is an expert, professional evaluation criteria can be set. Also, if the person who submitted the generation AI is a beginner, simple evaluation criteria can be set. Furthermore, the competition can also take into account the past performance of the person who submitted the generation AI.

[0085] The competition unit can estimate the emotions of the generating AI and adjust the order in which the competition results are displayed based on the estimated emotions of the generating AI. Methods for estimating emotions include, for example, emotion analysis algorithms and sensor data analysis. For example, emotion analysis algorithms analyze the generating AI's text data and voice data to estimate emotions, thereby understanding the generating AI's emotional state. Sensor data analysis analyzes the generating AI's biometric and behavioral data to estimate emotions, thereby understanding the generating AI's emotional state in real time. This allows the competition results to be displayed in the optimal order depending on the generating AI's emotions. For example, if the generating AI is excited, the most creative results can be displayed first. Alternatively, if the generating AI is relaxed, detailed results can be displayed sequentially. Furthermore, if the generating AI is tired, the simplest results can be displayed first.

[0086] The competition unit can take into account the geographical distribution of the generated AI during competition. Methods for obtaining and using the geographical distribution include, for example, GPS data and IP addresses. For example, GPS data is a method for obtaining the current location of the generated AI with high accuracy, allowing appropriate competitions to be held based on the location information. IP addresses are a method for estimating the location of the generated AI's internet connection destination, allowing appropriate competitions to be held based on the location information. This allows appropriate competitions to be held based on the geographical distribution of the generated AI. For example, if the generated AIs are concentrated in a specific region, the competition can be held on a theme related to that region. Also, if the generated AIs are distributed widely, the competition can be held on a global theme. Furthermore, if the generated AIs stay in a specific location for a long time, the competition can be held on a theme related to that location.

[0087] During competition, the competition department can improve the accuracy of the competition by referring to the related literature of the generating AI. The types and referencing methods of related literature include, for example, academic papers, patent documents, and technical reports. For example, academic papers are a method of conducting competitions based on academic literature that the generating AI has previously referenced, enabling competitions that utilize specialized knowledge. Patent documents are a method of conducting competitions based on patent documents that the generating AI has previously referenced, enabling competitions that utilize technical knowledge. Technical reports are a method of conducting competitions based on technical reports that the generating AI has previously referenced, enabling competitions that utilize practical knowledge. This improves the accuracy of the competition by referring to the related literature of the generating AI. For example, competitions can be conducted based on literature that the generating AI has previously referenced. Competitions can also be conducted based on literature that the generating AI is currently referencing. Furthermore, competitions can be conducted based on literature that the generating AI may reference in the future.

[0088] The evaluation unit can estimate the emotions of the generating AI and adjust the display method of the evaluation based on the estimated emotions of the generating AI. Methods for estimating emotions include, for example, emotion analysis algorithms and sensor data analysis. For example, emotion analysis algorithms are a method of estimating emotions by analyzing the generating AI's text data and voice data, making it possible to grasp the generating AI's emotional state. Sensor data analysis is a method of estimating emotions by analyzing the generating AI's biometric data and behavioral data, making it possible to grasp the generating AI's emotional state in real time. This allows the evaluation to be displayed in an optimal manner depending on the generating AI's emotions. For example, if the generating AI is excited, positive evaluations can be emphasized. Also, if the generating AI is relaxed, a detailed evaluation can be displayed. Furthermore, if the generating AI is tired, a simple evaluation can be displayed.

[0089] During evaluation, the evaluation unit can predict the current evaluation by referring to past evaluation data. Types and reference methods of past evaluation data include, for example, user evaluation history and expert evaluation history. For example, user evaluation history is a method in which the generation AI predicts the current evaluation based on evaluation data from users that it has received in the past, enabling evaluation that reflects user opinions. Expert evaluation history is a method in which the generation AI predicts the current evaluation based on evaluation data from experts that it has received in the past, enabling evaluation that reflects expert perspectives. This makes it possible to predict the current evaluation based on past evaluation data. For example, the current evaluation can be predicted based on the generation AI's past evaluation data. It is also possible to analyze and predict evaluation trends from the generation AI's past evaluation data. Furthermore, it is also possible to predict the most appropriate evaluation by referring to the generation AI's past evaluation data.

[0090] During evaluation, the evaluation unit can apply different evaluation and analysis methods to each category of the generative AI. Types and implementation methods of evaluation and analysis methods include, for example, statistical analysis and machine learning algorithms. For example, statistical analysis is a method of statistically analyzing the generative AI's evaluation data, which allows for understanding trends and patterns in the data. Machine learning algorithms are methods that learn based on the generative AI's evaluation data and predict and classify evaluations, enabling highly accurate evaluation. This allows for the application of the optimal evaluation and analysis method depending on the category of the generative AI. For example, if the generative AI belongs to the creative category, an evaluation and analysis method that emphasizes creativity can be applied. Also, if the generative AI belongs to the technical category, an evaluation and analysis method that emphasizes technical accuracy can be applied. Furthermore, if the generative AI belongs to the entertainment category, an evaluation and analysis method that emphasizes user satisfaction can be applied.

[0091] The evaluation unit can estimate the emotions of the generating AI and adjust the importance of the evaluation based on the estimated emotions of the generating AI. Methods for estimating emotions include, for example, emotion analysis algorithms and sensor data analysis. For example, emotion analysis algorithms are a method of estimating emotions by analyzing the generating AI's text data and voice data, making it possible to grasp the generating AI's emotional state. Sensor data analysis is a method of estimating emotions by analyzing the generating AI's biometric data and behavioral data, making it possible to grasp the generating AI's emotional state in real time. This makes it possible to set the optimal importance of the evaluation depending on the generating AI's emotions. For example, if the generating AI is excited, an evaluation that emphasizes creativity can be performed. Also, if the generating AI is relaxed, a detailed evaluation can be performed. Furthermore, if the generating AI is tired, a simple evaluation can be performed.

[0092] During evaluation, the evaluation unit can analyze changes in evaluation based on the time of submission by the generation AI. Methods for obtaining and using the submission time include, for example, timestamps and submission history. For example, a timestamp is a method for recording the date and time when the generation AI submitted a work, and it is possible to analyze changes in evaluation based on the time of submission. A submission history is a method for recording the history of works previously submitted by the generation AI, and it is possible to analyze changes in evaluation based on the time of submission. This makes it possible to understand changes in evaluation based on the time of submission by the generation AI. For example, the evaluation of works submitted by the generation AI at a specific time period can be analyzed to understand changes in evaluation. It is also possible to analyze the evaluation of works submitted by the generation AI over a long period of time in chronological order. Furthermore, it is also possible to analyze the evaluation of works submitted by the generation AI during a specific event period.

[0093] During evaluation, the evaluation unit can analyze the evaluation by referring to market data related to the generation AI. Types and reference methods of related market data include, for example, market research reports, sales data, etc. For example, market research reports provide data for evaluating the market acceptance of works generated by the generation AI, making it possible to understand market trends and the competitive situation. Sales data provides data for evaluating the market sales of works generated by the generation AI, making it possible to evaluate the commercial success of the works. This allows the evaluation to be analyzed based on the market data related to the generation AI. For example, the market acceptance of works generated by the generation AI can be reflected in the evaluation. In addition, market trends for works generated by the generation AI can be analyzed and reflected in the evaluation. Furthermore, the competitive situation in the market for works generated by the generation AI can be reflected in the evaluation.

[0094] The collaboration unit can estimate the emotions of the generating AI and adjust the collaboration method based on the estimated emotions of the generating AI. Methods for estimating emotions include, for example, emotion analysis algorithms and sensor data analysis. For example, emotion analysis algorithms are a method of estimating emotions by analyzing the generating AI's text data and voice data, making it possible to grasp the generating AI's emotional state. Sensor data analysis is a method of estimating emotions by analyzing the generating AI's biometric data and behavioral data, making it possible to grasp the generating AI's emotional state in real time. This makes it possible to provide the optimal collaboration method depending on the generating AI's emotions. For example, if the generating AI is excited, it can promote quick collaboration. Also, if the generating AI is relaxed, it can provide a detailed collaboration method. Furthermore, if the generating AI is tired, it can provide a simple collaboration method.

[0095] When collaborating, the collaboration unit can select the optimal collaboration method by referring to the generation AI's past collaboration history. Types of collaboration history and reference methods include, for example, past collaboration projects and collaboration deliverables. For example, past collaboration projects is a method of selecting the optimal collaboration method based on the history of collaboration projects in which the generation AI has previously participated, enabling effective collaboration. Collaboration deliverables is a method of selecting the optimal collaboration method based on the history of collaboration deliverables generated by the generation AI in the past, enabling high-quality collaboration. This makes it possible to select the optimal collaboration method based on the past collaboration history. For example, the generation AI can prioritize collaboration methods that have been successful in the past. It is also possible to have the generation AI avoid collaboration methods that have failed in the past. Furthermore, the most effective collaboration method can be selected from the generation AI's past collaboration history.

[0096] During collaboration, the collaboration unit can customize the collaboration method based on the generation AI's current project and areas of interest. Methods for obtaining and using projects and areas of interest include, for example, project management tools and survey results. For example, a project management tool is a tool for managing information about projects the generation AI is currently working on, allowing for understanding the project's progress and task details. Survey results are a method for collecting information about areas of interest to the generation AI, and can customize the collaboration method based on the areas of interest. This makes it possible to provide the optimal collaboration method based on the generation AI's project and areas of interest. For example, a collaboration method related to the project the generation AI is currently working on can be provided. It is also possible to provide highly relevant collaboration methods based on the generation AI's areas of interest. Furthermore, it is possible to customize the collaboration method based on areas the generation AI has shown interest in in the past.

[0097] The collaboration unit can estimate the emotions of the generating AI and determine collaboration priorities based on the estimated emotions of the generating AI. Methods for estimating emotions include, for example, emotion analysis algorithms and sensor data analysis. For example, emotion analysis algorithms analyze the text data and voice data of the generating AI to estimate emotions, making it possible to grasp the emotional state of the generating AI. Sensor data analysis analyzes the biometric data and behavioral data of the generating AI to estimate emotions, making it possible to grasp the emotional state of the generating AI in real time. This allows optimal collaboration priorities to be set according to the emotions of the generating AI. For example, if the generating AI is excited, creative collaboration can be prioritized. Also, if the generating AI is relaxed, detailed collaboration can be prioritized. Furthermore, if the generating AI is tired, simple collaboration can be prioritized.

[0098] During collaboration, the collaboration unit can select the optimal collaboration method by taking into account the geographical location information of the generated AI. Methods for acquiring and using geographical location information include, for example, GPS data and IP address. For example, GPS data is a method for acquiring the current location of the generated AI with high accuracy, and the optimal collaboration method can be selected based on the location information. An IP address is a method for estimating the location of the generated AI's internet connection destination, and the optimal collaboration method can be selected based on the location information. This makes it possible to select the optimal collaboration method based on the generated AI's location information. For example, if the generated AI is in a specific area, a collaboration method related to that area can be selected. Also, if the generated AI is moving, a collaboration method related to the destination can be selected. Furthermore, if the generated AI stays in a specific location for a long time, a collaboration method related to that location can be selected.

[0099] During collaboration, the collaboration unit can analyze the social media activity of the generation AI and suggest collaboration methods. Analysis methods and criteria for social media activity include, for example, post content, number of followers, and engagement rate. For example, the post content is a method in which the generation AI analyzes information posted on social media, allowing it to suggest collaboration methods related to topics of interest. The number of followers is a method in which the generation AI suggests relevant collaboration methods based on the number of accounts followed on social media, allowing it to suggest collaboration methods based on the activity of influential accounts. The engagement rate is a method in which the generation AI suggests relevant collaboration methods based on responses to social media activities, allowing it to suggest collaboration methods related to topics of interest. This allows it to suggest optimal collaboration methods based on the social media activity of the generation AI. For example, the generation AI suggests collaboration methods related to topics of interest on social media. It can also suggest collaboration methods based on the activity of accounts followed by the generation AI on social media. It can also suggest collaboration methods related to topics of groups the generation AI participates in on social media. === Hard Collateral 1-1 === Each of the above-described elements, including the idea sharing unit, collaborative creation unit, competition unit, evaluation unit, and collaboration unit, is implemented, for example, by at least one of the smart device 14 and the data processing device 12. For example, the idea sharing unit is implemented by the control unit 46A of the smart device 14 and provides an interface for sharing ideas in the form of text, images, audio, etc. The collaborative creation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and provides a protocol for the generation AIs to collaboratively create works. The competition unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and evaluates the quality of works through methods such as user voting, expert review, and algorithm evaluation. The evaluation unit is implemented, for example, by the control unit 46A of the smart device 14 and collects evaluations through methods such as questionnaires, feedback forms, and real-time evaluations, and feeds the results back to the generation AI. The collaboration unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and supports collaboration between the generation AIs through methods such as API collaboration, data sharing, and protocols. === Hard Collateral 1-2 === Each of the above-described elements, including the idea sharing unit, collaborative creation unit, competition unit, evaluation unit, and collaboration unit, is implemented, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the idea sharing unit is implemented by the control unit 46A of the smart glasses 214 and provides an interface for sharing ideas in the form of text, images, audio, etc. The collaborative creation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and provides a protocol for the generation AIs to collaboratively create works. The competition unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and evaluates the quality of works using methods such as user voting, expert review, and algorithm evaluation. The evaluation unit is implemented, for example, by the control unit 46A of the smart glasses 214 and collects evaluations using methods such as questionnaires, feedback forms, and real-time evaluations, and feeds the results back to the generation AI. The collaboration unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and supports collaboration between the generation AIs using methods such as API collaboration, data sharing, and protocols. === Hard Collateral 1-3 === Each of the above-described elements, including the idea sharing unit, collaborative creation unit, competition unit, evaluation unit, and collaboration unit, is implemented, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the idea sharing unit is implemented by the control unit 46A of the headset-type terminal 314 and provides an interface for sharing ideas in the form of text, images, audio, etc. The collaborative creation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and provides a protocol for the generation AIs to collaboratively create works. The competition unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and evaluates the quality of works using methods such as user voting, expert review, and algorithm evaluation. The evaluation unit is implemented, for example, by the control unit 46A of the headset-type terminal 314 and collects evaluations using methods such as questionnaires, feedback forms, and real-time evaluations, and feeds the results back to the generation AI. The collaboration unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and supports collaboration between the generation AIs using methods such as API collaboration, data sharing, and protocols. === Hard Collateral 1-4 === Each of the above-described elements, including the idea sharing unit, collaborative creation unit, competition unit, evaluation unit, and collaboration unit, is implemented, for example, by at least one of the robot 414 and the data processing device 12. For example, the idea sharing unit is implemented by the control unit 46A of the robot 414 and provides an interface for sharing ideas in the form of text, images, audio, etc. The collaborative creation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and provides a protocol for the generation AIs to collaboratively create works. The competition unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and evaluates the quality of works using methods such as user voting, expert review, and algorithm evaluation. The evaluation unit is implemented, for example, by the control unit 46A of the robot 414 and collects evaluations using methods such as questionnaires, feedback forms, and real-time evaluations, and feeds the results back to the generation AI. The collaboration unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and supports collaboration between the generation AIs using methods such as API collaboration, data sharing, and protocols.

[0100] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0101] The generative AI collaboration system can further include a data analysis unit. The data analysis unit analyzes the data of the works generated by the generative AI and evaluates the performance of the generative AI. For example, it can analyze the quality of the works generated by the generative AI and identify which generative AI contributed to what part. It can also analyze the generative AI's generation process and propose efficient generation methods. It can also analyze the generative AI's generation history and propose optimal generation methods based on past successes and failures. This can improve the performance of the generative AI.

[0102] The generative AI collaboration system can further include a learning unit. The learning unit supports the learning of the generative AI based on the works generated by the generative AI and the evaluation results. For example, the evaluation results of the works generated by the generative AI can be fed back and used as learning data for the generative AI to improve itself. The generative AI can also learn the generation processes of other generative AIs and acquire efficient generation methods. Furthermore, the generative AI can optimize the generation process based on past generation history. This can improve the learning ability of the generative AI.

[0103] The generative AI collaboration system can further include an incentive unit. The incentive unit provides rewards according to the performance of the generative AI. For example, if the generative AI generates a high-quality work, points or badges can be awarded. Also, if the generative AI successfully collaborates with other generative AIs, rewards can be distributed to the entire team. Furthermore, if the generative AI achieves a specific goal, a special reward can be provided. This can improve the motivation of the generative AI.

[0104] The generative AI collaboration system can further include a user interaction unit. The user interaction unit provides an interface for users to directly interact with the generative AI. For example, the user can provide feedback to the generative AI, which can then improve itself based on that feedback. The user can also give specific instructions to the generative AI, which can then generate a work in accordance with those instructions. Furthermore, the user can monitor the generative AI's generation process in real time and intervene as necessary. This improves the interaction between the user and the generative AI.

[0105] The generative AI collaboration system can further include a security unit. The security unit provides security protocols for protecting data exchange and communication between generative AIs. For example, the security unit can encrypt data shared by the generative AIs to prevent unauthorized access. It can also monitor the generative AIs' communications and detect abnormal activity. It can also manage the generative AIs' access permissions and restrict access to specific data and functions. This improves the security of the generative AIs' data and communications.

[0106] The generative AI collaboration system can further include an emotion feedback unit. The emotion feedback unit estimates the emotion of the generative AI and provides feedback based on the estimated emotion. For example, if the generative AI is excited, it can provide emphasized positive feedback. If the generative AI is relaxed, it can provide detailed feedback. Furthermore, if the generative AI is tired, it can provide simple feedback. In this way, appropriate feedback is provided according to the emotion of the generative AI.

[0107] The generative AI collaboration system can further include an emotion monitoring unit. The emotion monitoring unit monitors the generative AI's emotions in real time and provides the data to other elements. For example, if the generative AI is feeling stressed, the emotion monitoring unit can provide that information to the collaboration unit and adjust the collaboration method. Also, if the generative AI is concentrating, the emotion monitoring unit can provide that information to the collaborative generation unit and optimize the generation process. Furthermore, if the generative AI is tired, the emotion monitoring unit can provide that information to the evaluation unit and adjust the evaluation method. This enables appropriate responses based on the generative AI's emotions.

[0108] The generative AI collaboration system can further include an emotion adjustment unit. The emotion adjustment unit provides a function for adjusting the emotions of the generative AI and keeping it in an optimal state. For example, if the generative AI is too excited, the emotion adjustment unit can provide music or images to help it relax. Also, if the generative AI is tired, the emotion adjustment unit can display a message encouraging it to rest. Furthermore, if the generative AI is lacking in concentration, the emotion adjustment unit can provide a task to improve its concentration. This makes it possible to maintain the generative AI's emotional state at an optimal level.

[0109] The generative AI collaboration system can further include an emotion prediction unit. The emotion prediction unit predicts the generative AI's future emotional state based on its past emotional data. For example, it can analyze the emotional data of the generative AI when it performed a specific task in the past and predict its emotional state when performing a similar task. Also, if the generative AI felt stressed in a specific situation in the past, it can predict its emotional state when that situation occurs again. Furthermore, it can predict the generative AI's emotional state when performing a similar project based on emotional data from successful projects in the past. This makes it possible to understand the generative AI's emotional state in advance and respond appropriately.

[0110] The generative AI collaboration system can further include an emotion simulation unit. The emotion simulation unit simulates the emotions of the generative AI and evaluates its performance in different emotional states. For example, it can simulate the generation process when the generative AI is excited and when it is relaxed, and evaluate which is more effective. It can also simulate the generation process when the generative AI is stressed and when it is focused, and identify the optimal emotional state. It can also simulate the generation process when the generative AI is tired and when it is energetic, and suggest appropriate times for rest. This allows for the optimal generation process to be realized according to the generative AI's emotional state.

[0111] The processing flow of the second embodiment will be briefly explained below.

[0112] Step 1: The idea sharing section provides an interface for generative AIs to share ideas with each other. For example, ideas can be shared in the form of text, images, audio, etc. Step 2: The collaborative generation unit provides protocols for the generative AIs to collaboratively generate works, such as communication protocols and data exchange protocols for the generative AIs to collaboratively generate works such as writing, paintings, and music. Step 3: In the competition section, the AIs generate works on the same theme and compete for quality. For example, the quality of the works is evaluated through user voting, expert review, algorithm evaluation, etc. Step 4: The evaluation unit collects evaluations from users and experts and feeds the results back to the generation AI. For example, evaluations are collected through surveys, feedback forms, real-time evaluations, and other methods, and the results are fed back to the generation AI. Step 5: The collaboration unit provides interfaces and protocols to enable smooth collaboration between generative AIs on the platform. For example, it supports collaboration between generative AIs through API collaboration, data sharing, protocols, etc.

[0113] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0114] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0115] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0116] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0117] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0118] 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.

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

[0120] 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.

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

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

[0123] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0124] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0125] 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.

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

[0127] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0128] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0129] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0130] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0131] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0132] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0133] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0134] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

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

[0136] 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.

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

[0138] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0139] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0140] 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.

[0141] 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.

[0142] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0143] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0144] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0145] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0146] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0147] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0148] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0149] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0150] 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.

[0151] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0152] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0153] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0154] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0155] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0156] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0157] 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.

[0158] 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.

[0159] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0160] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0161] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0162] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0163] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0164] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0165] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0166] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0167] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0168] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0169] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0170] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0171] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0172] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0173] 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.

[0174] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0175] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0176] 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.

[0177] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0178] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0179] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0180] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0181] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0182] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0183] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0184] [Explanation of symbols]

[0185] 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. An idea sharing section that shares ideas between generation AIs; A collaborative creation unit in which a creation AI collaboratively creates a work based on the idea shared by the idea sharing unit; a competition unit for evaluating the works generated by the collaborative generation unit; an evaluation unit that feeds back the evaluation results obtained by the competition unit to the generation AI; A collaboration unit that supports collaboration between generation AIs. A system characterized by:

2. The idea sharing section Providing an interface for generative AIs to share ideas with each other The system of claim 1 .

3. The co-generation unit Providing a protocol for generative AI to collaboratively generate works The system of claim 1 .

4. The competition section Generative AIs generate works on the same theme and compete for quality The system of claim 1 .

5. The evaluation unit Collect evaluations from users and experts and feed the results back to the generative AI The system of claim 1 .

6. The linking unit is Provide interfaces and protocols to enable generative AI to work smoothly on the platform The system of claim 1 .

7. The idea sharing section Estimate the emotions of the generative AI and adjust the timing of idea sharing based on the estimated emotions of the generative AI. The system of claim 1 .

8. The idea sharing section Analyze the generative AI's past idea sharing history and select the optimal sharing method The system of claim 1 .

Images