system

Abstract

The system according to this embodiment aims to enable AI agent developers to effectively publish and sell their creations, and for users to find agents that meet their needs. [Solution] The system according to the embodiment comprises a publishing unit, a search unit, an access unit, and an evaluation unit. The publishing unit publishes and buys and sells agents. The search unit searches for and purchases agents that meet the user's needs. The access unit provides developers with access to a new customer base. The evaluation unit evaluates, classifies, and recommends agents using generative AI.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that it is difficult for developers of AI agents to effectively disclose and sell their works, and for users to find agents that meet their needs.

[0005] The system according to the embodiment aims to enable developers of AI agents to effectively disclose and sell their works, and for users to find agents that meet their needs.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a publishing unit, a search unit, an access unit, and an evaluation unit. The publishing unit publishes and buys / sells agents. The search unit searches for and purchases agents that meet the user's needs. The access unit provides developers with access to a new customer base. The evaluation unit evaluates, classifies, and recommends agents using generative AI. [Effects of the Invention]

[0007] The system according to this embodiment allows AI agent developers to effectively publish and sell their creations, and enables users to find agents that meet their needs. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The platform according to an embodiment of the present invention is a system that provides a platform where AI agent developers can publish and buy their creations. This system allows users to find and purchase agents that meet their needs, and enables developers to access new customer segments. The platform guarantees security and transparency for all transactions and provides quality assurance through a user review and rating system. For example, the platform allows for the classification and searching of agents in various categories, and users can choose agents according to their unique needs. Developers can market their agents and generate revenue. The platform also facilitates the creation of new business models and reflects market trends in line with the evolution of AI technology. The target audience is individual users of a wide range of ages and all businesses, from startups to large corporations. To address the difficulty of finding suitable AI agents and the limitations on access to new markets, the platform connects users and developers directly, making it easy to find agents that meet needs. Generative AI is used to evaluate, classify, and recommend AI agents within the platform. This allows the platform to efficiently connect AI agent developers and users, and to facilitate the publication, search, purchase, and evaluation of agents.

[0029] The platform according to this embodiment comprises a publishing unit, a search unit, an access unit, and an evaluation unit. The publishing unit handles the publishing and buying / selling of agents. For example, the publishing unit has the function of inputting agent information and publishing it on the platform. The publishing unit can also manage agent pricing and sales conditions. For example, the publishing unit provides an interface for inputting and publishing detailed agent information. The publishing unit also has the function of setting agent prices and managing sales conditions. Furthermore, the publishing unit can monitor the sales status of agents in real time and make adjustments as needed. The search unit searches for and purchases agents that meet the user's needs. For example, the search unit has the function of displaying relevant agents based on search queries entered by the user. The search unit can also filter search results based on agent categories and tags. For example, the search unit displays relevant agents based on keywords entered by the user. Furthermore, the search unit has the function of filtering search results based on agent categories and tags. Furthermore, the search unit can analyze the user's past search history and provide optimal search results. The access unit provides developers with access to new customer segments. The Access Department provides developers with tools to reach new customer segments when they publish their agents. The Access Department can also manage marketing campaigns and analyze customer data. For example, the Access Department provides developers with tools to reach new customer segments when they publish their agents. Furthermore, the Access Department has the functionality to manage marketing campaigns and analyze customer data. In addition, the Access Department can propose strategies for developers to reach new customer segments. The Evaluation Department uses generative AI to evaluate, classify, and recommend agents. For example, the Evaluation Department has the functionality to evaluate the performance and quality of agents and recommend them to users. The Evaluation Department can also guarantee agent quality based on user reviews and evaluation systems. For example, the Evaluation Department uses generative AI to evaluate the performance and quality of agents and recommend them to users.Furthermore, the evaluation unit has the function of guaranteeing agent quality based on user reviews and evaluation systems. In addition, the evaluation unit can recommend the most suitable agent to the user based on the agent evaluation results. As a result, the platform according to the embodiment can efficiently publish, search, access, and evaluate agents.

[0030] The Public Section handles the listing and buying / selling of agents. For example, it allows users to input agent information and publish it on the platform. Specifically, the Public Section provides an interface for entering detailed information such as the agent's name, description, functions, and usage instructions. This interface is user-friendly and designed to allow developers to easily input information. The Public Section can also manage agent pricing and sales conditions. For example, it provides options for setting agent prices and allows for detailed setting of sales conditions (e.g., license type, usage period, support availability). Furthermore, the Public Section can monitor agent sales in real time and make adjustments as needed. For instance, it can display agent sales figures and revenue in graphs and charts, providing developers with data to review their sales strategies. The Public Section also has a function to automatically adjust prices and sales conditions based on agent sales performance. This allows the Public Section to efficiently manage agent listings and buying / selling, supporting developers in maximizing their profits.

[0031] The search function searches for and purchases agents that meet the user's needs. For example, the search function has the function of displaying relevant agents based on the search query entered by the user. Specifically, the search function analyzes the keywords entered by the user and lists agents related to them. The search results are displayed along with information such as the agent's name, description, price, and rating, making it easy for the user to compare and select. The search function can also filter search results based on agent categories and tags. For example, the search result can be narrowed down by selecting a specific category (e.g., chatbot, image recognition, voice assistant, etc.) or tag (e.g., AI, machine learning, natural language processing, etc.). Furthermore, the search function can analyze the user's past search history and provide optimal search results. For example, it has the function of predicting the user's preferences and needs based on the keywords the user has searched for in the past and the agents they have purchased, and recommending agents based on that. This allows the search function to quickly and accurately find the agent the user is looking for, improving user convenience.

[0032] The Access Department provides developers with access to new customer segments. For example, when developers publish their agents, the Access Department provides tools to reach new customer segments. Specifically, the Access Department provides targeted marketing tools, allowing developers to create campaigns to promote their agents to specific customer segments. The Access Department can also manage marketing campaigns and analyze customer data. For example, the Access Department monitors campaign effectiveness in real time and provides metrics such as clicks, conversion rates, and ROI (Return on Investment). Furthermore, the Access Department can analyze customer data to understand customer behavior patterns and preferences, enabling the development of more effective marketing strategies. In addition, the Access Department can suggest strategies for developers to reach new customer segments. For example, based on customer data, the Access Department can perform targeting based on specific regions, age groups, and interests, and suggest the optimal marketing channels. This allows the Access Department to effectively reach new customer segments and boost agent sales.

[0033] The evaluation department uses generative AI to evaluate, classify, and recommend agents. For example, the evaluation department has the function of evaluating agent performance and quality and recommending them to users. Specifically, the evaluation department automatically evaluates agent performance and quality using generative AI. The generative AI analyzes agent operation logs and user feedback to evaluate agent reliability and usefulness. Furthermore, the evaluation department has the function of guaranteeing agent quality based on user reviews and the evaluation system. For example, the evaluation department collects reviews and evaluations provided by users after using an agent and uses them to evaluate agent quality. In addition, the evaluation department can recommend the most suitable agent to the user based on the agent evaluation results. For example, the evaluation department has the function of analyzing a user's past purchase history and evaluation history to recommend the agent best suited to the user's needs. This allows the evaluation department to make it easier for users to find high-quality agents and improve user satisfaction. Furthermore, the evaluation department can also provide feedback on agent evaluation results to developers and suggest areas for improvement. This allows the evaluation department to promote agent quality improvement and enhance the overall reliability of the platform.

[0034] The platform includes an assurance unit that guarantees the security and transparency of transactions. The assurance unit has functions such as encrypting and authenticating transactions. The assurance unit can also record transaction history and store it in an auditable format. For example, the assurance unit encrypts and securely stores transaction data. The assurance unit also has functions to authenticate users and prevent unauthorized access. Furthermore, the assurance unit can record transaction history and store it in an auditable format. This improves the security and transparency of transactions. Some or all of the above processes in the assurance unit may be performed using AI, for example, or not using AI. For example, the assurance unit can input transaction data into AI and entrust the execution of security measures to AI.

[0035] The platform includes an evaluation system unit that provides a user review and rating system. The evaluation system unit, for example, has a function for users to submit reviews to agents. The evaluation system unit can also analyze the content of reviews and calculate an agent's rating score. For example, the evaluation system unit provides an interface for users to submit reviews to agents. Furthermore, the evaluation system unit has a function to analyze the content of reviews and calculate an agent's rating score. In addition, the evaluation system unit can recommend the most suitable agent to the user based on the agent's rating results. This enables quality assurance through the user review and rating system. Some or all of the above-described processes in the evaluation system unit may be performed using AI, or not. For example, the evaluation system unit can input the review content into AI and leave the calculation of the rating score to the AI.

[0036] The platform includes a classification unit that categorizes and searches agents across various categories. The classification unit has functions such as classifying agents by technology field or application. It can also display relevant agents based on search queries entered by the user. For example, it classifies agents by technology field or application and displays relevant agents based on keywords entered by the user. Furthermore, the classification unit has the functionality to filter search results based on agent categories and tags. In addition, the classification unit can analyze the user's past search history to provide optimal search results. This makes agent classification and searching easier. Some or all of the above-described processes in the classification unit may be performed using AI, or not. For example, the classification unit can input agent data into AI and entrust the classification and search processes to the AI.

[0037] The platform includes a support unit that assists in the creation of new business models. The support unit, for example, has the function of providing developers with tools to build new business models. The support unit can also propose revenue models and service delivery methods. For example, the support unit provides developers with tools to build new business models. Furthermore, the support unit has the function of proposing revenue models and service delivery methods. In addition, the support unit can provide support to developers in realizing new business models. This supports the creation of new business models. Some or all of the above processes in the support unit may be performed using AI, for example, or not. For example, the support unit can input business model data into AI and entrust the AI ​​with the processing of proposals and support.

[0038] The platform includes a reflection unit that reflects market trends in line with the evolution of AI technology. The reflection unit has functions such as analyzing market trends and updating the platform's functions and services. It can also conduct competitive research and trend analysis to adjust the platform's strategy. For example, the reflection unit analyzes market trends and updates the platform's functions and services. Furthermore, the reflection unit has functions such as conducting competitive research and trend analysis to adjust the platform's strategy. In addition, the reflection unit can optimize the platform's functions and services in line with the evolution of AI technology. This ensures that market trends are reflected. Some or all of the above-described processes in the reflection unit may be performed using AI, or not. For example, the reflection unit can input market data into AI and entrust the AI ​​with trend analysis and strategy adjustment processes.

[0039] The publishing unit can analyze a developer's past publishing history and select the optimal publishing method. For example, the publishing unit can suggest a similar method based on the developer's past successful publishing methods. The publishing unit can also identify the most effective time of day from the developer's past publishing history and publish during that time. Furthermore, the publishing unit can analyze the developer's past publishing history and select the optimal platform for publishing. This makes it possible to select the optimal publishing method based on past publishing history. Some or all of the above processes in the publishing unit may be performed using AI, for example, or not. For example, the publishing unit can input the developer's publishing history data into AI and have the AI ​​select the optimal publishing method.

[0040] The publishing unit can filter agents based on the developer's current projects and areas of interest when publishing them. For example, the publishing unit can prioritize publishing agents related to the developer's current project. It can also filter and publish agents that are highly relevant based on the developer's areas of interest. Furthermore, the publishing unit can publish agents at the optimal time according to the progress of the developer's current project. This enables filtering based on the developer's projects and areas of interest. Some or all of the above processing in the publishing unit may be performed using AI, for example, or not. For example, the publishing unit can input the developer's project data into an AI and have the AI ​​perform the filtering process.

[0041] The publishing unit can prioritize the publication of highly relevant agents when publishing agents, taking into account the developer's geographical location information. For example, the publishing unit can prioritize the publication of regionally relevant agents based on the developer's geographical location information. Furthermore, the publishing unit can also publish agents aligned with regional trends, taking into account the developer's geographical location information. In addition, the publishing unit can prioritize the publication of agents that meet regional needs, based on the developer's geographical location information. This enables the publication of agents based on geographical location information. Some or all of the above processing in the publishing unit may be performed using AI, for example, or without AI. For example, the publishing unit can input the developer's geographical location data into AI and have the AI ​​perform the agent publication.

[0042] The publishing unit can analyze the developer's social media activity when publishing agents and publish relevant agents. For example, the publishing unit can publish the agents that are of the most interest based on the developer's social media activity. The publishing unit can also analyze the developer's social media activity and publish agents that meet the needs of the followers. Furthermore, the publishing unit can publish agents that are aligned with trends based on the developer's social media activity. This makes it possible to publish agents based on social media activity. Some or all of the above processing in the publishing unit may be performed using AI, for example, or not using AI. For example, the publishing unit can input the developer's social media data into AI and have the AI ​​perform the agent publishing.

[0043] The search unit can analyze the user's past search history and apply the optimal search algorithm during a search. For example, the search unit can display the most relevant search results based on the user's past search history. The search unit can also adjust the search algorithm based on the user's past search history to provide optimal results. Furthermore, the search unit can analyze the user's past search history to improve the accuracy of search results. This enables the application of the optimal search algorithm based on past search history. Some or all of the above processes in the search unit may be performed using AI, for example, or without AI. For example, the search unit can input the user's search history data into AI and have the AI ​​perform the application of the search algorithm.

[0044] The search unit can filter search results based on the user's current needs during a search. For example, the search unit prioritizes displaying the most relevant search results based on the user's current needs. The search unit can also filter search results considering the user's current needs. Furthermore, the search unit can adjust the display order of search results according to the user's current needs. This enables filtering of search results based on current needs. Some or all of the above processing in the search unit may be performed using AI, for example, or without AI. For example, the search unit can input user needs data into AI and have the AI ​​perform the filtering of search results.

[0045] The search unit can prioritize displaying highly relevant search results by considering the user's geographical location information during a search. For example, the search unit can prioritize displaying search results related to a region based on the user's geographical location information. Furthermore, the search unit can also display search results tailored to regional trends by considering the user's geographical location information. In addition, the search unit can prioritize displaying search results that meet regional needs based on the user's geographical location information. This enables the display of search results based on geographical location information. Some or all of the above processing in the search unit may be performed using AI, for example, or without AI. For example, the search unit can input the user's geographical location data into AI and have AI display the search results.

[0046] The search unit can analyze the user's social media activity during a search and display relevant search results. For example, the search unit can display search results that are of the user's greatest interest based on their social media activity. It can also analyze the user's social media activity and display search results tailored to the needs of their followers. Furthermore, the search unit can display trend-aligned search results based on the user's social media activity. This enables the display of search results based on social media activity. Some or all of the above-described processes in the search unit may be performed using AI, for example, or without AI. For example, the search unit can input the user's social media data into AI and have AI display the search results.

[0047] The access unit can analyze the developer's past access history and select the optimal access method at the time of access. For example, the access unit can select the most effective access method from the developer's past access history. The access unit can also perform access at the optimal time based on the developer's past access history. Furthermore, the access unit can analyze the developer's past access history and select the optimal platform for access. This makes it possible to select the optimal access method based on past access history. Some or all of the above processing in the access unit may be performed using AI, for example, or without AI. For example, the access unit can input the developer's access history data into AI and have the AI ​​perform the selection of the optimal access method.

[0048] The access unit can filter access based on the developer's current projects and areas of interest. For example, the access unit prioritizes access related to the project the developer is currently working on. It can also filter access based on the developer's areas of interest to ensure it is relevant. Furthermore, the access unit can perform access at the optimal time according to the progress of the developer's current project. This enables filtering of access based on the current project and areas of interest. Some or all of the above processing in the access unit may be performed using AI, or not. For example, the access unit can input the developer's project data into an AI and have the AI ​​perform the access filtering.

[0049] The access unit can prioritize highly relevant accesses by considering the developer's geographical location information during access. For example, the access unit can prioritize accesses related to a region based on the developer's geographical location information. Furthermore, the access unit can also prioritize accesses that align with regional trends by considering the developer's geographical location information. In addition, the access unit can prioritize accesses that meet regional needs based on the developer's geographical location information. This enables the determination of access priorities based on geographical location information. Some or all of the above processing in the access unit may be performed using AI, for example, or without AI. For example, the access unit can input the developer's geographical location data into AI and have the AI ​​determine the access priorities.

[0050] The access unit can analyze the developer's social media activity and perform relevant accesses when accessing content. For example, the access unit can perform accesses that are of the most interest to the developer based on their social media activity. The access unit can also analyze the developer's social media activity and perform accesses that meet the needs of their followers. Furthermore, the access unit can perform accesses that align with trends based on the developer's social media activity. This makes it possible to prioritize accesses based on social media activity. Some or all of the above processing in the access unit may be performed using AI, for example, or not. For example, the access unit can input the developer's social media data into AI and leave the execution of accesses to the AI.

[0051] The evaluation unit can analyze the agent's past evaluation history and apply the optimal evaluation algorithm during the evaluation process. For example, the evaluation unit can apply the most reliable evaluation algorithm based on the agent's past evaluation history. The evaluation unit can also adjust the evaluation algorithm based on the agent's past evaluation history to provide the optimal result. Furthermore, the evaluation unit can analyze the agent's past evaluation history to improve the accuracy of the evaluation. This makes it possible to apply the optimal evaluation algorithm based on past evaluation history. Some or all of the above processes in the evaluation unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the evaluation unit can input the agent's evaluation history data into a generative AI and have the generative AI execute the application of the evaluation algorithm.

[0052] The evaluation unit can apply different evaluation methods depending on the agent's category during evaluation. For example, the evaluation unit can select the optimal evaluation method depending on the agent's category. The evaluation unit can also apply different evaluation criteria for each agent's category. Furthermore, the evaluation unit can adjust the evaluation method based on the agent's category to provide the optimal result. This makes it possible to apply the optimal evaluation method according to the category. Some or all of the above processing in the evaluation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the evaluation unit can input agent category data into a generative AI and have the generative AI execute the application of the evaluation method.

[0053] The evaluation unit can perform evaluations while considering the geographical distribution of agents. For example, the evaluation unit can perform evaluations for each region based on the geographical distribution of agents. The evaluation unit can also perform evaluations that are tailored to the needs of each region, taking into account the geographical distribution of agents. Furthermore, the evaluation unit can apply evaluation criteria for each region based on the geographical distribution of agents. This makes geographical distribution-based evaluation possible. Some or all of the above-described processes in the evaluation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the evaluation unit can input the geographical distribution data of agents into a generative AI and leave the execution of the evaluation to the generative AI.

[0054] The evaluation unit can improve the accuracy of its evaluation by referring to the agent's relevant literature during the evaluation process. For example, the evaluation unit can improve the accuracy of its evaluation by referring to the agent's relevant literature. The evaluation unit can also adjust the evaluation criteria based on the agent's relevant literature. Furthermore, the evaluation unit can analyze the agent's relevant literature to improve the reliability of its evaluation. This makes it possible to improve the accuracy of evaluations based on relevant literature. Some or all of the above processes in the evaluation unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the evaluation unit can input the agent's relevant literature data into a generative AI and leave the execution of the evaluation to the generative AI.

[0055] The assurance unit can analyze the transaction history and select the optimal security measures. For example, the assurance unit can select the most effective security measures from the transaction history. The assurance unit can also adjust security measures based on the transaction history. Furthermore, the assurance unit can analyze the transaction history and improve the reliability of security. This makes it possible to select the optimal security measures based on the transaction history. Some or all of the above processes in the assurance unit may be performed using AI, for example, or not using AI. For example, the assurance unit can input transaction history data into AI and have the AI ​​perform the selection of security measures.

[0056] The assurance unit can analyze transaction history and provide information that contributes to improved transparency. For example, the assurance unit can provide information that contributes to improved transparency from the transaction history. The assurance unit can also adjust the method of ensuring transparency based on the transaction history. Furthermore, the assurance unit can analyze the transaction history and improve the reliability of transparency. This makes it possible to improve transparency based on the transaction history. Some or all of the above processing in the assurance unit may be performed using AI, for example, or without AI. For example, the assurance unit can input transaction history data into AI and have the AI ​​perform the task of providing information that contributes to improved transparency.

[0057] The evaluation system unit can analyze the review history and select the optimal evaluation system. For example, the evaluation system unit can select the most reliable evaluation system from the review history. The evaluation system unit can also adjust the evaluation system based on the review history. Furthermore, the evaluation system unit can analyze the review history and improve the reliability of the evaluation system. This makes it possible to select the optimal evaluation system based on the review history. Some or all of the above processes in the evaluation system unit may be performed using AI, for example, or without AI. For example, the evaluation system unit can input review history data into AI and have the AI ​​perform the selection of the evaluation system.

[0058] The evaluation system unit can analyze review history and provide information to improve the transparency of evaluations. For example, the evaluation system unit can provide information from the review history that contributes to improving transparency. The evaluation system unit can also adjust the transparency of evaluations based on the review history. Furthermore, the evaluation system unit can analyze the review history and improve the reliability of evaluations. This makes it possible to improve the transparency of evaluations based on the review history. Some or all of the above processing in the evaluation system unit may be performed using AI, for example, or without AI. For example, the evaluation system unit can input review history data into AI and have the AI ​​perform the task of providing information to improve the transparency of evaluations.

[0059] The classification unit can analyze the agent's history and select the optimal classification method. For example, the classification unit can select the most reliable classification method from the agent's history. The classification unit can also adjust the classification method based on the agent's history. Furthermore, the classification unit can analyze the agent's history to improve the reliability of the classification. This makes it possible to select the optimal classification method based on the agent's history. Some or all of the above processes in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can input agent history data into AI and have the AI ​​perform the selection of a classification method.

[0060] The classification unit can analyze the agent's history and provide information to improve the transparency of the classification. For example, the classification unit can provide information from the agent's history that contributes to improved transparency. The classification unit can also adjust the transparency of the classification based on the agent's history. Furthermore, the classification unit can analyze the agent's history and improve the reliability of the classification. This makes it possible to improve the transparency of the classification based on the agent's history. Some or all of the above processing in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can input agent history data into AI and have the AI ​​perform the task of providing information to improve the transparency of the classification.

[0061] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0062] The publishing unit can analyze the developer's past publishing history when publishing an agent and select the optimal publishing method. For example, it can suggest a similar method based on the developer's past successful publishing methods. The publishing unit can also identify the most effective time of day from the developer's past publishing history and publish during that time. Furthermore, the publishing unit can analyze the developer's past publishing history and select the optimal platform for publishing. This enables the selection of the optimal publishing method based on past publishing history. Some or all of the above processes in the publishing unit may be performed using AI, for example, or not. For example, the publishing unit can input the developer's publishing history data into AI and have the AI ​​select the optimal publishing method.

[0063] The access unit can filter access based on the developer's current projects and areas of interest. For example, it can prioritize access related to the project the developer is currently working on. The access unit can also filter access based on the developer's areas of interest to show only highly relevant access. Furthermore, the access unit can perform access at the optimal time according to the progress of the developer's current project. This enables filtering of access based on the current project and areas of interest. Some or all of the above processing in the access unit may be performed using AI, for example, or not. For example, the access unit can input the developer's project data into AI and have the AI ​​perform the access filtering.

[0064] The assurance unit can analyze the transaction history and select the optimal security measures. For example, it can select the most effective security measures from the transaction history. The assurance unit can also adjust security measures based on the transaction history. Furthermore, the assurance unit can analyze the transaction history and improve the reliability of security. This makes it possible to select the optimal security measures based on the transaction history. Some or all of the above processes in the assurance unit may be performed using AI, for example, or not using AI. For example, the assurance unit can input transaction history data into AI and have the AI ​​perform the selection of security measures.

[0065] The search unit can analyze the user's past search history and apply the optimal search algorithm during a search. For example, it can display the most relevant search results based on the user's past search history. The search unit can also adjust the search algorithm based on the user's past search history to provide the best results. Furthermore, the search unit can analyze the user's past search history to improve the accuracy of the search results. This makes it possible to apply the optimal search algorithm based on past search history. Some or all of the above processes in the search unit may be performed using AI, for example, or without AI. For example, the search unit can input the user's search history data into AI and have the AI ​​perform the application of the search algorithm.

[0066] The evaluation unit can analyze the agent's past evaluation history during evaluation and apply the optimal evaluation algorithm. For example, it can apply the most reliable evaluation algorithm based on the agent's past evaluation history. The evaluation unit can also adjust the evaluation algorithm based on the agent's past evaluation history to provide the optimal result. Furthermore, the evaluation unit can analyze the agent's past evaluation history to improve the accuracy of the evaluation. This makes it possible to apply the optimal evaluation algorithm based on past evaluation history. Some or all of the above processing in the evaluation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the evaluation unit can input the agent's evaluation history data into a generative AI and have the generative AI execute the application of the evaluation algorithm.

[0067] The classification unit can analyze the agent's history and select the optimal classification method. For example, it can select the most reliable classification method from the agent's history. The classification unit can also adjust the classification method based on the agent's history. Furthermore, the classification unit can analyze the agent's history to improve the reliability of the classification. This makes it possible to select the optimal classification method based on the agent's history. Some or all of the above processes in the classification unit may be performed using AI, for example, or not using AI. For example, the classification unit can input agent history data into AI and have the AI ​​perform the selection of a classification method.

[0068] The following briefly describes the processing flow for example form 1.

[0069] Step 1: The public listing section handles the listing and buying / selling of agents. Specifically, it has the function of inputting agent information and making it public on the platform. It also manages agent pricing and sales conditions, monitors sales status in real time, and makes adjustments as needed. Step 2: The search unit searches for and purchases agents that meet the user's needs. Specifically, it displays relevant agents based on the search query entered by the user and filters the search results based on agent categories and tags. It can also analyze the user's past search history to provide the most suitable search results. Step 3: The Access section provides developers with access to new customer segments. Specifically, it provides developers with tools to reach new customer segments when they publish their agents, manage marketing campaigns, and analyze customer data. It can also suggest strategies for developers to reach new customer segments. Step 4: The evaluation unit uses generational AI to evaluate, classify, and recommend agents. Specifically, it has the function of evaluating the performance and quality of agents and recommending them to users. It can also guarantee agent quality based on user reviews and evaluation systems, and recommend the most suitable agent to the user based on the evaluation results.

[0070] (Example of form 2) The platform according to an embodiment of the present invention is a system that provides a platform where AI agent developers can publish and buy their creations. This system allows users to find and purchase agents that meet their needs, and enables developers to access new customer segments. The platform guarantees security and transparency for all transactions and provides quality assurance through a user review and rating system. For example, the platform allows for the classification and searching of agents in various categories, and users can choose agents according to their unique needs. Developers can market their agents and generate revenue. The platform also facilitates the creation of new business models and reflects market trends in line with the evolution of AI technology. The target audience is individual users of a wide range of ages and all businesses, from startups to large corporations. To address the difficulty of finding suitable AI agents and the limitations on access to new markets, the platform connects users and developers directly, making it easy to find agents that meet needs. Generative AI is used to evaluate, classify, and recommend AI agents within the platform. This allows the platform to efficiently connect AI agent developers and users, and to facilitate the publication, search, purchase, and evaluation of agents.

[0071] The platform according to this embodiment comprises a publishing unit, a search unit, an access unit, and an evaluation unit. The publishing unit handles the publishing and buying / selling of agents. For example, the publishing unit has the function of inputting agent information and publishing it on the platform. The publishing unit can also manage agent pricing and sales conditions. For example, the publishing unit provides an interface for inputting and publishing detailed agent information. The publishing unit also has the function of setting agent prices and managing sales conditions. Furthermore, the publishing unit can monitor the sales status of agents in real time and make adjustments as needed. The search unit searches for and purchases agents that meet the user's needs. For example, the search unit has the function of displaying relevant agents based on search queries entered by the user. The search unit can also filter search results based on agent categories and tags. For example, the search unit displays relevant agents based on keywords entered by the user. Furthermore, the search unit has the function of filtering search results based on agent categories and tags. Furthermore, the search unit can analyze the user's past search history and provide optimal search results. The access unit provides developers with access to new customer segments. The Access Department provides developers with tools to reach new customer segments when they publish their agents. The Access Department can also manage marketing campaigns and analyze customer data. For example, the Access Department provides developers with tools to reach new customer segments when they publish their agents. Furthermore, the Access Department has the functionality to manage marketing campaigns and analyze customer data. In addition, the Access Department can propose strategies for developers to reach new customer segments. The Evaluation Department uses generative AI to evaluate, classify, and recommend agents. For example, the Evaluation Department has the functionality to evaluate the performance and quality of agents and recommend them to users. The Evaluation Department can also guarantee agent quality based on user reviews and evaluation systems. For example, the Evaluation Department uses generative AI to evaluate the performance and quality of agents and recommend them to users.Furthermore, the evaluation unit has the function of guaranteeing agent quality based on user reviews and evaluation systems. In addition, the evaluation unit can recommend the most suitable agent to the user based on the agent evaluation results. As a result, the platform according to the embodiment can efficiently publish, search, access, and evaluate agents.

[0072] The Public Section handles the listing and buying / selling of agents. For example, it allows users to input agent information and publish it on the platform. Specifically, the Public Section provides an interface for entering detailed information such as the agent's name, description, functions, and usage instructions. This interface is user-friendly and designed to allow developers to easily input information. The Public Section can also manage agent pricing and sales conditions. For example, it provides options for setting agent prices and allows for detailed setting of sales conditions (e.g., license type, usage period, support availability). Furthermore, the Public Section can monitor agent sales in real time and make adjustments as needed. For instance, it can display agent sales figures and revenue in graphs and charts, providing developers with data to review their sales strategies. The Public Section also has a function to automatically adjust prices and sales conditions based on agent sales performance. This allows the Public Section to efficiently manage agent listings and buying / selling, supporting developers in maximizing their profits.

[0073] The search function searches for and purchases agents that meet the user's needs. For example, the search function has the function of displaying relevant agents based on the search query entered by the user. Specifically, the search function analyzes the keywords entered by the user and lists agents related to them. The search results are displayed along with information such as the agent's name, description, price, and rating, making it easy for the user to compare and select. The search function can also filter search results based on agent categories and tags. For example, the search result can be narrowed down by selecting a specific category (e.g., chatbot, image recognition, voice assistant, etc.) or tag (e.g., AI, machine learning, natural language processing, etc.). Furthermore, the search function can analyze the user's past search history and provide optimal search results. For example, it has the function of predicting the user's preferences and needs based on the keywords the user has searched for in the past and the agents they have purchased, and recommending agents based on that. This allows the search function to quickly and accurately find the agent the user is looking for, improving user convenience.

[0074] The Access Department provides developers with access to new customer segments. For example, when developers publish their agents, the Access Department provides tools to reach new customer segments. Specifically, the Access Department provides targeted marketing tools, allowing developers to create campaigns to promote their agents to specific customer segments. The Access Department can also manage marketing campaigns and analyze customer data. For example, the Access Department monitors campaign effectiveness in real time and provides metrics such as clicks, conversion rates, and ROI (Return on Investment). Furthermore, the Access Department can analyze customer data to understand customer behavior patterns and preferences, enabling the development of more effective marketing strategies. In addition, the Access Department can suggest strategies for developers to reach new customer segments. For example, based on customer data, the Access Department can perform targeting based on specific regions, age groups, and interests, and suggest the optimal marketing channels. This allows the Access Department to effectively reach new customer segments and boost agent sales.

[0075] The evaluation department uses generative AI to evaluate, classify, and recommend agents. For example, the evaluation department has the function of evaluating agent performance and quality and recommending them to users. Specifically, the evaluation department automatically evaluates agent performance and quality using generative AI. The generative AI analyzes agent operation logs and user feedback to evaluate agent reliability and usefulness. Furthermore, the evaluation department has the function of guaranteeing agent quality based on user reviews and the evaluation system. For example, the evaluation department collects reviews and evaluations provided by users after using an agent and uses them to evaluate agent quality. In addition, the evaluation department can recommend the most suitable agent to the user based on the agent evaluation results. For example, the evaluation department has the function of analyzing a user's past purchase history and evaluation history to recommend the agent best suited to the user's needs. This allows the evaluation department to make it easier for users to find high-quality agents and improve user satisfaction. Furthermore, the evaluation department can also provide feedback on agent evaluation results to developers and suggest areas for improvement. This allows the evaluation department to promote agent quality improvement and enhance the overall reliability of the platform.

[0076] The platform includes an assurance unit that guarantees the security and transparency of transactions. The assurance unit has functions such as encrypting and authenticating transactions. The assurance unit can also record transaction history and store it in an auditable format. For example, the assurance unit encrypts and securely stores transaction data. The assurance unit also has functions to authenticate users and prevent unauthorized access. Furthermore, the assurance unit can record transaction history and store it in an auditable format. This improves the security and transparency of transactions. Some or all of the above processes in the assurance unit may be performed using AI, for example, or not using AI. For example, the assurance unit can input transaction data into AI and entrust the execution of security measures to AI.

[0077] The platform includes an evaluation system unit that provides a user review and rating system. The evaluation system unit, for example, has a function for users to submit reviews to agents. The evaluation system unit can also analyze the content of reviews and calculate an agent's rating score. For example, the evaluation system unit provides an interface for users to submit reviews to agents. Furthermore, the evaluation system unit has a function to analyze the content of reviews and calculate an agent's rating score. In addition, the evaluation system unit can recommend the most suitable agent to the user based on the agent's rating results. This enables quality assurance through the user review and rating system. Some or all of the above-described processes in the evaluation system unit may be performed using AI, or not. For example, the evaluation system unit can input the review content into AI and leave the calculation of the rating score to the AI.

[0078] The platform includes a classification unit that categorizes and searches agents across various categories. The classification unit has functions such as classifying agents by technology field or application. It can also display relevant agents based on search queries entered by the user. For example, it classifies agents by technology field or application and displays relevant agents based on keywords entered by the user. Furthermore, the classification unit has the functionality to filter search results based on agent categories and tags. In addition, the classification unit can analyze the user's past search history to provide optimal search results. This makes agent classification and searching easier. Some or all of the above-described processes in the classification unit may be performed using AI, or not. For example, the classification unit can input agent data into AI and entrust the classification and search processes to the AI.

[0079] The platform includes a support unit that assists in the creation of new business models. The support unit, for example, has the function of providing developers with tools to build new business models. The support unit can also propose revenue models and service delivery methods. For example, the support unit provides developers with tools to build new business models. Furthermore, the support unit has the function of proposing revenue models and service delivery methods. In addition, the support unit can provide support to developers in realizing new business models. This supports the creation of new business models. Some or all of the above processes in the support unit may be performed using AI, for example, or not. For example, the support unit can input business model data into AI and entrust the AI ​​with the processing of proposals and support.

[0080] The platform includes a reflection unit that reflects market trends in line with the evolution of AI technology. The reflection unit has functions such as analyzing market trends and updating the platform's functions and services. It can also conduct competitive research and trend analysis to adjust the platform's strategy. For example, the reflection unit analyzes market trends and updates the platform's functions and services. Furthermore, the reflection unit has functions such as conducting competitive research and trend analysis to adjust the platform's strategy. In addition, the reflection unit can optimize the platform's functions and services in line with the evolution of AI technology. This ensures that market trends are reflected. Some or all of the above-described processes in the reflection unit may be performed using AI, or not. For example, the reflection unit can input market data into AI and entrust the AI ​​with trend analysis and strategy adjustment processes.

[0081] The publishing unit can estimate the user's emotions and adjust the timing of agent release based on the estimated emotions. For example, if the user is excited, the publishing unit can immediately release the agent to maintain the user's excitement. If the user is relaxed, the publishing unit can release the agent at an optimal time to maintain the user's relaxed state. Furthermore, if the user is stressed, the publishing unit can delay the agent release to alleviate stress. This allows for adjustment of the release timing according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the publishing unit may be performed using AI, or not. For example, the publishing unit can input user emotion data into a generative AI and have the generative AI adjust the release timing.

[0082] The publishing unit can analyze a developer's past publishing history and select the optimal publishing method. For example, the publishing unit can suggest a similar method based on the developer's past successful publishing methods. The publishing unit can also identify the most effective time of day from the developer's past publishing history and publish during that time. Furthermore, the publishing unit can analyze the developer's past publishing history and select the optimal platform for publishing. This makes it possible to select the optimal publishing method based on past publishing history. Some or all of the above processes in the publishing unit may be performed using AI, for example, or not. For example, the publishing unit can input the developer's publishing history data into AI and have the AI ​​select the optimal publishing method.

[0083] The publishing unit can filter agents based on the developer's current projects and areas of interest when publishing them. For example, the publishing unit can prioritize publishing agents related to the developer's current project. It can also filter and publish agents that are highly relevant based on the developer's areas of interest. Furthermore, the publishing unit can publish agents at the optimal time according to the progress of the developer's current project. This enables filtering based on the developer's projects and areas of interest. Some or all of the above processing in the publishing unit may be performed using AI, for example, or not. For example, the publishing unit can input the developer's project data into an AI and have the AI ​​perform the filtering process.

[0084] The publishing unit can estimate the user's emotions and determine the priority of agents to publish based on the estimated emotions. For example, if the user is excited, the publishing unit will prioritize publishing the most popular agents. If the user is relaxed, the publishing unit can also prioritize publishing agents with relaxing effects. Furthermore, if the user is stressed, the publishing unit can prioritize publishing agents with stress-reducing effects. This makes it possible to determine agent priorities according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the publishing unit may be performed using AI, or not. For example, the publishing unit can input user emotion data into a generative AI and have the generative AI determine agent priorities.

[0085] The publishing unit can prioritize the publication of highly relevant agents when publishing agents, taking into account the developer's geographical location information. For example, the publishing unit can prioritize the publication of regionally relevant agents based on the developer's geographical location information. Furthermore, the publishing unit can also publish agents aligned with regional trends, taking into account the developer's geographical location information. In addition, the publishing unit can prioritize the publication of agents that meet regional needs, based on the developer's geographical location information. This enables the publication of agents based on geographical location information. Some or all of the above processing in the publishing unit may be performed using AI, for example, or without AI. For example, the publishing unit can input the developer's geographical location data into AI and have the AI ​​perform the agent publication.

[0086] The publishing unit can analyze the developer's social media activity when publishing agents and publish relevant agents. For example, the publishing unit can publish the agents that are of the most interest based on the developer's social media activity. The publishing unit can also analyze the developer's social media activity and publish agents that meet the needs of the followers. Furthermore, the publishing unit can publish agents that are aligned with trends based on the developer's social media activity. This makes it possible to publish agents based on social media activity. Some or all of the above processing in the publishing unit may be performed using AI, for example, or not using AI. For example, the publishing unit can input the developer's social media data into AI and have the AI ​​perform the agent publishing.

[0087] The search unit can estimate the user's emotions and adjust how search results are displayed based on the estimated emotions. For example, if the user is relaxed, the search unit can display detailed search results. If the user is in a hurry, the search unit can display concise search results that get straight to the point. Furthermore, if the user is excited, the search unit can display visually appealing search results. This makes it possible to adjust how search results are displayed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the search unit may be performed using AI, or not using AI. For example, the search unit can input user emotion data into a generative AI and have the generative AI adjust how search results are displayed.

[0088] The search unit can analyze the user's past search history and apply the optimal search algorithm during a search. For example, the search unit can display the most relevant search results based on the user's past search history. The search unit can also adjust the search algorithm based on the user's past search history to provide optimal results. Furthermore, the search unit can analyze the user's past search history to improve the accuracy of search results. This enables the application of the optimal search algorithm based on past search history. Some or all of the above processes in the search unit may be performed using AI, for example, or without AI. For example, the search unit can input the user's search history data into AI and have the AI ​​perform the application of the search algorithm.

[0089] The search unit can filter search results based on the user's current needs during a search. For example, the search unit prioritizes displaying the most relevant search results based on the user's current needs. The search unit can also filter search results considering the user's current needs. Furthermore, the search unit can adjust the display order of search results according to the user's current needs. This enables filtering of search results based on current needs. Some or all of the above processing in the search unit may be performed using AI, for example, or without AI. For example, the search unit can input user needs data into AI and have the AI ​​perform the filtering of search results.

[0090] The search unit can estimate the user's emotions and prioritize search results based on those emotions. For example, if the user is excited, the search unit may prioritize displaying the most popular search results. If the user is relaxed, the search unit may also prioritize displaying search results containing detailed information. Furthermore, if the user is in a hurry, the search unit may prioritize displaying concise search results. This enables the prioritization of search results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the search unit may be performed using AI, or not. For example, the search unit can input user emotion data into a generative AI and have the generative AI determine the priority of search results.

[0091] The search unit can prioritize displaying highly relevant search results by considering the user's geographical location information during a search. For example, the search unit can prioritize displaying search results related to a region based on the user's geographical location information. Furthermore, the search unit can also display search results tailored to regional trends by considering the user's geographical location information. In addition, the search unit can prioritize displaying search results that meet regional needs based on the user's geographical location information. This enables the display of search results based on geographical location information. Some or all of the above processing in the search unit may be performed using AI, for example, or without AI. For example, the search unit can input the user's geographical location data into AI and have AI display the search results.

[0092] The search unit can analyze the user's social media activity during a search and display relevant search results. For example, the search unit can display search results that are of the user's greatest interest based on their social media activity. It can also analyze the user's social media activity and display search results tailored to the needs of their followers. Furthermore, the search unit can display trend-aligned search results based on the user's social media activity. This enables the display of search results based on social media activity. Some or all of the above-described processes in the search unit may be performed using AI, for example, or without AI. For example, the search unit can input the user's social media data into AI and have AI display the search results.

[0093] The access unit can estimate the user's emotions and adjust the access method based on the estimated emotions. For example, if the user is relaxed, the access unit can provide an access method that includes detailed information. If the user is in a hurry, the access unit can also provide a concise access method that gets straight to the point. Furthermore, if the user is excited, the access unit can provide a visually appealing access method. This makes it possible to adjust the access method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the access unit may be performed using AI, for example, or not using AI. For example, the access unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the access method.

[0094] The access unit can analyze the developer's past access history and select the optimal access method at the time of access. For example, the access unit can select the most effective access method from the developer's past access history. The access unit can also perform access at the optimal time based on the developer's past access history. Furthermore, the access unit can analyze the developer's past access history and select the optimal platform for access. This makes it possible to select the optimal access method based on past access history. Some or all of the above processing in the access unit may be performed using AI, for example, or without AI. For example, the access unit can input the developer's access history data into AI and have the AI ​​perform the selection of the optimal access method.

[0095] The access unit can filter access based on the developer's current projects and areas of interest. For example, the access unit prioritizes access related to the project the developer is currently working on. It can also filter access based on the developer's areas of interest to ensure it is relevant. Furthermore, the access unit can perform access at the optimal time according to the progress of the developer's current project. This enables filtering of access based on the current project and areas of interest. Some or all of the above processing in the access unit may be performed using AI, or not. For example, the access unit can input the developer's project data into an AI and have the AI ​​perform the access filtering.

[0096] The access unit can estimate the user's emotions and determine access priorities based on the estimated emotions. For example, if the user is excited, the access unit will prioritize the most popular accesses. If the user is relaxed, the access unit can also prioritize accesses containing detailed information. Furthermore, if the user is in a hurry, the access unit can prioritize accesses that are concise and to the point. This enables the determination of access priorities according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the access unit may be performed using AI, or not. For example, the access unit can input user emotion data into a generative AI and have the generative AI determine access priorities.

[0097] The access unit can prioritize highly relevant accesses by considering the developer's geographical location information during access. For example, the access unit can prioritize accesses related to a region based on the developer's geographical location information. Furthermore, the access unit can also prioritize accesses that align with regional trends by considering the developer's geographical location information. In addition, the access unit can prioritize accesses that meet regional needs based on the developer's geographical location information. This enables the determination of access priorities based on geographical location information. Some or all of the above processing in the access unit may be performed using AI, for example, or without AI. For example, the access unit can input the developer's geographical location data into AI and have the AI ​​determine the access priorities.

[0098] The access unit can analyze the developer's social media activity and perform relevant accesses when accessing content. For example, the access unit can perform accesses that are of the most interest to the developer based on their social media activity. The access unit can also analyze the developer's social media activity and perform accesses that meet the needs of their followers. Furthermore, the access unit can perform accesses that align with trends based on the developer's social media activity. This makes it possible to prioritize accesses based on social media activity. Some or all of the above processing in the access unit may be performed using AI, for example, or not. For example, the access unit can input the developer's social media data into AI and leave the execution of accesses to the AI.

[0099] The evaluation unit can estimate the user's emotions and adjust the evaluation criteria based on the estimated emotions. For example, if the user is relaxed, the evaluation unit can provide detailed evaluation criteria. If the user is in a hurry, the evaluation unit can also provide concise evaluation criteria that get straight to the point. Furthermore, if the user is excited, the evaluation unit can provide visually appealing evaluation criteria. This makes it possible to adjust the evaluation criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or not using AI. For example, the evaluation unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the evaluation criteria.

[0100] The evaluation unit can analyze the agent's past evaluation history and apply the optimal evaluation algorithm during the evaluation process. For example, the evaluation unit can apply the most reliable evaluation algorithm based on the agent's past evaluation history. The evaluation unit can also adjust the evaluation algorithm based on the agent's past evaluation history to provide the optimal result. Furthermore, the evaluation unit can analyze the agent's past evaluation history to improve the accuracy of the evaluation. This makes it possible to apply the optimal evaluation algorithm based on past evaluation history. Some or all of the above processes in the evaluation unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the evaluation unit can input the agent's evaluation history data into a generative AI and have the generative AI execute the application of the evaluation algorithm.

[0101] The evaluation unit can apply different evaluation methods depending on the agent's category during evaluation. For example, the evaluation unit can select the optimal evaluation method depending on the agent's category. The evaluation unit can also apply different evaluation criteria for each agent's category. Furthermore, the evaluation unit can adjust the evaluation method based on the agent's category to provide the optimal result. This makes it possible to apply the optimal evaluation method according to the category. Some or all of the above processing in the evaluation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the evaluation unit can input agent category data into a generative AI and have the generative AI execute the application of the evaluation method.

[0102] The evaluation unit can estimate the user's emotions and adjust the display method of the evaluation results based on the estimated user emotions. For example, if the user is relaxed, the evaluation unit can display detailed evaluation results. If the user is in a hurry, the evaluation unit can also display concise evaluation results that get straight to the point. Furthermore, if the user is excited, the evaluation unit can display visually appealing evaluation results. This makes it possible to adjust the display method of evaluation results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the evaluation unit may be performed using a generative AI, or not using a generative AI. For example, the evaluation unit can input user emotion data into a generative AI and have the generative AI adjust the display method of the evaluation results.

[0103] The evaluation unit can perform evaluations while considering the geographical distribution of agents. For example, the evaluation unit can perform evaluations for each region based on the geographical distribution of agents. The evaluation unit can also perform evaluations that are tailored to the needs of each region, taking into account the geographical distribution of agents. Furthermore, the evaluation unit can apply evaluation criteria for each region based on the geographical distribution of agents. This makes geographical distribution-based evaluation possible. Some or all of the above-described processes in the evaluation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the evaluation unit can input the geographical distribution data of agents into a generative AI and leave the execution of the evaluation to the generative AI.

[0104] The evaluation unit can improve the accuracy of its evaluation by referring to the agent's relevant literature during the evaluation process. For example, the evaluation unit can improve the accuracy of its evaluation by referring to the agent's relevant literature. The evaluation unit can also adjust the evaluation criteria based on the agent's relevant literature. Furthermore, the evaluation unit can analyze the agent's relevant literature to improve the reliability of its evaluation. This makes it possible to improve the accuracy of evaluations based on relevant literature. Some or all of the above processes in the evaluation unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the evaluation unit can input the agent's relevant literature data into a generative AI and leave the execution of the evaluation to the generative AI.

[0105] The assurance unit can estimate the user's emotions and adjust security measures based on those emotions. For example, if the user is feeling anxious, the assurance unit can provide enhanced security measures. It can also provide standard security measures if the user is relaxed. Furthermore, if the user is in a hurry, the assurance unit can provide rapid security measures. This allows for the adjustment of security measures according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the assurance unit may be performed using AI, or not. For example, the assurance unit can input user emotion data into a generative AI and have the generative AI adjust security measures.

[0106] The assurance unit can analyze the transaction history and select the optimal security measures. For example, the assurance unit can select the most effective security measures from the transaction history. The assurance unit can also adjust security measures based on the transaction history. Furthermore, the assurance unit can analyze the transaction history and improve the reliability of security. This makes it possible to select the optimal security measures based on the transaction history. Some or all of the above processes in the assurance unit may be performed using AI, for example, or not using AI. For example, the assurance unit can input transaction history data into AI and have the AI ​​perform the selection of security measures.

[0107] The assurance unit can estimate the user's emotions and adjust the transparency assurance method based on the estimated user emotions. For example, if the user is feeling anxious, the assurance unit can provide a detailed transparency assurance method. It can also provide a normal transparency assurance method if the user is relaxed. Furthermore, if the user is in a hurry, the assurance unit can provide a rapid transparency assurance method. This allows for adjustment of the transparency assurance method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the assurance unit may be performed using AI, or not using AI. For example, the assurance unit can input user emotion data into a generative AI and have the generative AI adjust the transparency assurance method.

[0108] The assurance unit can analyze transaction history and provide information that contributes to improved transparency. For example, the assurance unit can provide information that contributes to improved transparency from the transaction history. The assurance unit can also adjust the method of ensuring transparency based on the transaction history. Furthermore, the assurance unit can analyze the transaction history and improve the reliability of transparency. This makes it possible to improve transparency based on the transaction history. Some or all of the above processing in the assurance unit may be performed using AI, for example, or without AI. For example, the assurance unit can input transaction history data into AI and have the AI ​​perform the task of providing information that contributes to improved transparency.

[0109] The evaluation system can estimate the user's emotions and adjust how reviews are displayed based on those emotions. For example, if the user is relaxed, the evaluation system can display a detailed review. If the user is in a hurry, it can display a concise review that gets straight to the point. Furthermore, if the user is excited, it can display a visually appealing review. This allows for adjustment of how reviews are displayed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the evaluation system may be performed using AI, or not. For example, the evaluation system can input user emotion data into a generative AI and have the generative AI adjust how reviews are displayed.

[0110] The evaluation system unit can analyze the review history and select the optimal evaluation system. For example, the evaluation system unit can select the most reliable evaluation system from the review history. The evaluation system unit can also adjust the evaluation system based on the review history. Furthermore, the evaluation system unit can analyze the review history and improve the reliability of the evaluation system. This makes it possible to select the optimal evaluation system based on the review history. Some or all of the above processes in the evaluation system unit may be performed using AI, for example, or without AI. For example, the evaluation system unit can input review history data into AI and have the AI ​​perform the selection of the evaluation system.

[0111] The evaluation system can estimate the user's emotions and determine the priority of evaluations based on the estimated emotions. For example, if the user is excited, the evaluation system may prioritize displaying the most popular evaluations. If the user is relaxed, the evaluation system may also prioritize displaying evaluations that contain detailed information. Furthermore, if the user is in a hurry, the evaluation system may prioritize displaying concise evaluations. This enables the system to prioritize evaluations according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the evaluation system may be performed using AI, or not. For example, the evaluation system can input user emotion data into a generative AI and have the generative AI determine the priority of evaluations.

[0112] The evaluation system unit can analyze review history and provide information to improve the transparency of evaluations. For example, the evaluation system unit can provide information from the review history that contributes to improving transparency. The evaluation system unit can also adjust the transparency of evaluations based on the review history. Furthermore, the evaluation system unit can analyze the review history and improve the reliability of evaluations. This makes it possible to improve the transparency of evaluations based on the review history. Some or all of the above processing in the evaluation system unit may be performed using AI, for example, or without AI. For example, the evaluation system unit can input review history data into AI and have the AI ​​perform the task of providing information to improve the transparency of evaluations.

[0113] The classification unit can estimate the user's emotions and adjust the classification criteria based on the estimated emotions. For example, if the user is relaxed, the classification unit can provide detailed classification criteria. If the user is in a hurry, it can also provide concise classification criteria that get straight to the point. Furthermore, if the user is excited, the classification unit can provide visually appealing classification criteria. This allows for adjustment of classification criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the classification unit may be performed using AI, or not using AI. For example, the classification unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of classification criteria.

[0114] The classification unit can analyze the agent's history and select the optimal classification method. For example, the classification unit can select the most reliable classification method from the agent's history. The classification unit can also adjust the classification method based on the agent's history. Furthermore, the classification unit can analyze the agent's history to improve the reliability of the classification. This makes it possible to select the optimal classification method based on the agent's history. Some or all of the above processes in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can input agent history data into AI and have the AI ​​perform the selection of a classification method.

[0115] The classification unit can estimate the user's emotions and adjust how the classification results are displayed based on the estimated emotions. For example, if the user is relaxed, the classification unit can display detailed classification results. If the user is in a hurry, the classification unit can also display concise classification results that get straight to the point. Furthermore, if the user is excited, the classification unit can display visually appealing classification results. This makes it possible to adjust how the classification results are displayed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the classification unit may be performed using AI, or not using AI. For example, the classification unit can input user emotion data into the generative AI and have the generative AI adjust how the classification results are displayed.

[0116] The classification unit can analyze the agent's history and provide information to improve the transparency of the classification. For example, the classification unit can provide information from the agent's history that contributes to improved transparency. The classification unit can also adjust the transparency of the classification based on the agent's history. Furthermore, the classification unit can analyze the agent's history and improve the reliability of the classification. This makes it possible to improve the transparency of the classification based on the agent's history. Some or all of the above processing in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can input agent history data into AI and have the AI ​​perform the task of providing information to improve the transparency of the classification.

[0117] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0118] The publishing unit can analyze the developer's past publishing history when publishing an agent and select the optimal publishing method. For example, it can suggest a similar method based on the developer's past successful publishing methods. The publishing unit can also identify the most effective time of day from the developer's past publishing history and publish during that time. Furthermore, the publishing unit can analyze the developer's past publishing history and select the optimal platform for publishing. This enables the selection of the optimal publishing method based on past publishing history. Some or all of the above processes in the publishing unit may be performed using AI, for example, or not. For example, the publishing unit can input the developer's publishing history data into AI and have the AI ​​select the optimal publishing method.

[0119] The search unit can estimate the user's emotions and adjust how search results are displayed based on the estimated emotions. For example, if the user is relaxed, it can display detailed search results. If the user is in a hurry, the search unit can display concise search results that get straight to the point. Furthermore, if the user is excited, the search unit can display visually appealing search results. This makes it possible to adjust how search results are displayed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the search unit may be performed using AI, or not using AI. For example, the search unit can input user emotion data into a generative AI and have the generative AI adjust how search results are displayed.

[0120] The access unit can filter access based on the developer's current projects and areas of interest. For example, it can prioritize access related to the project the developer is currently working on. The access unit can also filter access based on the developer's areas of interest to show only highly relevant access. Furthermore, the access unit can perform access at the optimal time according to the progress of the developer's current project. This enables filtering of access based on the current project and areas of interest. Some or all of the above processing in the access unit may be performed using AI, for example, or not. For example, the access unit can input the developer's project data into AI and have the AI ​​perform the access filtering.

[0121] The evaluation unit can estimate the user's emotions and adjust the evaluation criteria based on the estimated emotions. For example, if the user is relaxed, it can provide detailed evaluation criteria. If the user is in a hurry, the evaluation unit can provide concise evaluation criteria that get straight to the point. Furthermore, if the user is excited, the evaluation unit can provide visually appealing evaluation criteria. This allows for adjustment of evaluation criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the evaluation unit may be performed using AI, or not. For example, the evaluation unit can input user emotion data into a generative AI and have the generative AI adjust the evaluation criteria.

[0122] The assurance unit can analyze the transaction history and select the optimal security measures. For example, it can select the most effective security measures from the transaction history. The assurance unit can also adjust security measures based on the transaction history. Furthermore, the assurance unit can analyze the transaction history and improve the reliability of security. This makes it possible to select the optimal security measures based on the transaction history. Some or all of the above processes in the assurance unit may be performed using AI, for example, or not using AI. For example, the assurance unit can input transaction history data into AI and have the AI ​​perform the selection of security measures.

[0123] The publishing unit can estimate the user's emotions and adjust the timing of agent release based on the estimated emotions. For example, if the user is excited, the agent can be released immediately to maintain the user's excitement. The publishing unit can also release the agent at an optimal time if the user is relaxed, maintaining the user's relaxed state. Furthermore, if the publishing unit is stressed, the agent release can be delayed to alleviate stress. This allows for adjustment of the release timing according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the publishing unit may be performed using AI or not. For example, the publishing unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the release timing.

[0124] The search unit can analyze the user's past search history and apply the optimal search algorithm during a search. For example, it can display the most relevant search results based on the user's past search history. The search unit can also adjust the search algorithm based on the user's past search history to provide the best results. Furthermore, the search unit can analyze the user's past search history to improve the accuracy of the search results. This makes it possible to apply the optimal search algorithm based on past search history. Some or all of the above processes in the search unit may be performed using AI, for example, or without AI. For example, the search unit can input the user's search history data into AI and have the AI ​​perform the application of the search algorithm.

[0125] The evaluation unit can analyze the agent's past evaluation history during evaluation and apply the optimal evaluation algorithm. For example, it can apply the most reliable evaluation algorithm based on the agent's past evaluation history. The evaluation unit can also adjust the evaluation algorithm based on the agent's past evaluation history to provide the optimal result. Furthermore, the evaluation unit can analyze the agent's past evaluation history to improve the accuracy of the evaluation. This makes it possible to apply the optimal evaluation algorithm based on past evaluation history. Some or all of the above processing in the evaluation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the evaluation unit can input the agent's evaluation history data into a generative AI and have the generative AI execute the application of the evaluation algorithm.

[0126] The access unit can estimate the user's emotions and adjust the access method based on the estimated emotions. For example, if the user is relaxed, it can provide an access method that includes detailed information. If the user is in a hurry, the access unit can provide a concise access method that gets straight to the point. Furthermore, if the user is excited, the access unit can provide a visually appealing access method. This allows for adjustment of the access method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the access unit may be performed using AI, or not. For example, the access unit can input user emotion data into a generative AI and have the generative AI adjust the access method.

[0127] The classification unit can analyze the agent's history and select the optimal classification method. For example, it can select the most reliable classification method from the agent's history. The classification unit can also adjust the classification method based on the agent's history. Furthermore, the classification unit can analyze the agent's history to improve the reliability of the classification. This makes it possible to select the optimal classification method based on the agent's history. Some or all of the above processes in the classification unit may be performed using AI, for example, or not using AI. For example, the classification unit can input agent history data into AI and have the AI ​​perform the selection of a classification method.

[0128] The following briefly describes the processing flow for example form 2.

[0129] Step 1: The public listing section handles the listing and buying / selling of agents. Specifically, it has the function of inputting agent information and making it public on the platform. It also manages agent pricing and sales conditions, monitors sales status in real time, and makes adjustments as needed. Step 2: The search unit searches for and purchases agents that meet the user's needs. Specifically, it displays relevant agents based on the search query entered by the user and filters the search results based on agent categories and tags. It can also analyze the user's past search history to provide the most suitable search results. Step 3: The Access section provides developers with access to new customer segments. Specifically, it provides developers with tools to reach new customer segments when they publish their agents, manage marketing campaigns, and analyze customer data. It can also suggest strategies for developers to reach new customer segments. Step 4: The evaluation unit uses generational AI to evaluate, classify, and recommend agents. Specifically, it has the function of evaluating the performance and quality of agents and recommending them to users. It can also guarantee agent quality based on user reviews and evaluation systems, and recommend the most suitable agent to the user based on the evaluation results.

[0130] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0131] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0132] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0133] Each of the multiple elements described above, including the publishing unit, search unit, access unit, and evaluation unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the publishing unit is implemented by the control unit 46A of the smart device 14 and has the function of inputting agent information and publishing it on the platform. The search unit is also implemented by the control unit 46A of the smart device 14 and has the function of displaying relevant agents based on search queries entered by the user. The access unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides a tool for developers to reach new customer segments. The evaluation unit is implemented by the specific processing unit 290 of the data processing unit 12 and has the function of evaluating the performance and quality of agents using generated AI and recommending them to users. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0134] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0135] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0136] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0137] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0138] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0139] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0140] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0141] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

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

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

[0144] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

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

[0146] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

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

[0148] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0149] Each of the multiple elements described above, including the publishing unit, search unit, access unit, and evaluation unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the publishing unit is implemented by the control unit 46A of the smart glasses 214 and has the function of inputting agent information and publishing it on the platform. The search unit is also implemented by the control unit 46A of the smart glasses 214 and has the function of displaying relevant agents based on search queries entered by the user. The access unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides a tool for developers to reach new customer segments. The evaluation unit is implemented by the specific processing unit 290 of the data processing unit 12 and has the function of evaluating the performance and quality of agents using generated AI and recommending them to users. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0150] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0151] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0152] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0153] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0154] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0155] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0156] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0157] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0158] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

[0160] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0161] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0162] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0163] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0164] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0165] Each of the multiple elements described above, including the publishing unit, search unit, access unit, and evaluation unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the publishing unit is implemented by the control unit 46A of the headset terminal 314 and has the function of inputting agent information and publishing it on the platform. The search unit is also implemented by the control unit 46A of the headset terminal 314 and has the function of displaying relevant agents based on search queries entered by the user. The access unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides a tool for developers to reach new customer segments. The evaluation unit is implemented by the specific processing unit 290 of the data processing unit 12 and has the function of evaluating the performance and quality of agents using generated AI and recommending them to users. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0166] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0167] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0168] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0169] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0170] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0171] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0172] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0173] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0174] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0175] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0176] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0177] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0178] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0179] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0180] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0181] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0182] Each of the multiple elements described above, including the publishing unit, search unit, access unit, and evaluation unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the publishing unit is implemented by the control unit 46A of the robot 414 and has the function of inputting agent information and publishing it on the platform. The search unit is also implemented by the control unit 46A of the robot 414 and has the function of displaying relevant agents based on search queries entered by the user. The access unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides a tool for developers to reach new customer segments. The evaluation unit is implemented by the specific processing unit 290 of the data processing unit 12 and has the function of evaluating the performance and quality of agents using generated AI and recommending them to the user. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0183] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0184] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0185] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0186] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0187] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0188] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0189] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0190] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0191] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0192] 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.

[0193] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0194] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0195] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0196] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0197] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0198] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0199] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0200] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0201] (Note 1) The public section handles the public listing and trading of agents, A search unit that searches for and purchases agents that meet the user's needs, An access unit that provides developers with access to a new customer base, It includes an evaluation unit that uses generational AI to evaluate, classify, and recommend agents. A system characterized by the following features. (Note 2) It includes an assurance unit to guarantee the security and transparency of transactions. The system described in Appendix 1, characterized by the features described herein. (Note 3) It includes an evaluation system section that provides user reviews and rating systems. The system described in Appendix 1, characterized by the features described herein. (Note 4) It features a classification unit that allows for the classification and searching of agents across various categories. The system described in Appendix 1, characterized by the features described herein. (Note 5) We support the creation of new business models and have a dedicated support department. The system described in Appendix 1, characterized by the features described herein. (Note 6) It features a reflection section that incorporates market trends in line with the evolution of AI technology. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned public section is, It estimates user sentiment and adjusts the timing of agent releases based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned public section is, Analyze the developer's past publishing history and select the optimal publishing method. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned public section is, When publishing agents, filtering is performed based on the developers' current projects and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned public section is, It estimates the user's sentiment and determines the priority of which agents to publish based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned public section is, When publishing agents, prioritize publishing agents that are highly relevant, taking into account the developer's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned public section is, When releasing an agent, analyze the developer's social media activity and release relevant agents. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned search unit, It estimates the user's sentiment and adjusts how search results are displayed based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned search unit, When a search is performed, the system analyzes the user's past search history and applies the most suitable search algorithm. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned search unit, When searching, filter search results based on the user's current needs. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned search unit, It estimates the user's emotions and determines the priority of search results based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned search unit, When searching, the system prioritizes displaying more relevant search results by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned search unit, When you search, we analyze your social media activity and display relevant search results. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned access unit is It estimates the user's emotions and adjusts the access method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned access unit is When accessing the system, the system analyzes the developer's past access history to select the optimal access method. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned access unit is When access is made, access is filtered based on the developer's current projects and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned access unit is It estimates user sentiment and determines access priorities based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned access unit is When accessing a system, the system prioritizes relevant accesses by considering the developer's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned access unit is When accessing a website, the system analyzes the developer's social media activity and performs relevant access. The system described in Appendix 1, characterized by the features described herein. (Note 25) The evaluation unit described above, It estimates the user's emotions and adjusts the evaluation criteria based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The evaluation unit, During the evaluation process, the agent's past evaluation history is analyzed to apply the most suitable evaluation algorithm. The system described in Appendix 1, characterized by the features described herein. (Note 27) The evaluation unit, During evaluation, different evaluation methods are applied depending on the agent's category. The system described in Appendix 1, characterized by the features described herein. (Note 28) The evaluation unit, The system estimates the user's emotions and adjusts how the evaluation results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The evaluation unit, During the evaluation, the geographical distribution of the agents will be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 30) The evaluation unit, During evaluation, refer to relevant literature on the agent to improve the accuracy of the evaluation. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned warranty section is, It estimates user sentiment and adjusts security measures based on the estimated user sentiment. The system described in Appendix 2, characterized by the features described herein. (Note 32) The aforementioned warranty section is, Analyze the transaction history and select the most suitable security measures. The system described in Appendix 2, characterized by the features described herein. (Note 33) The aforementioned warranty section is, We estimate user sentiment and adjust transparency measures based on the estimated user sentiment. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned warranty section is, We analyze transaction history and provide information that contributes to improved transparency. The system described in Appendix 2, characterized by the features described herein. (Note 35) The aforementioned evaluation system unit is It estimates user sentiment and adjusts how reviews are displayed based on that estimated sentiment. The system described in Appendix 3, characterized by the features described herein. (Note 36) The aforementioned evaluation system unit is Analyze the review history and select the optimal rating system. The system described in Appendix 3, characterized by the features described herein. (Note 37) The aforementioned evaluation system unit is It estimates the user's emotions and determines the priority of evaluations based on the estimated user emotions. The system described in Appendix 3, characterized by the features described herein. (Note 38) The aforementioned evaluation system unit is We analyze review history and provide information to improve the transparency of ratings. The system described in Appendix 3, characterized by the features described herein. (Note 39) The aforementioned classification unit is It estimates the user's emotions and adjusts the classification criteria based on the estimated user emotions. The system described in Appendix 4, characterized by the features described herein. (Note 40) The aforementioned classification unit is Analyze the agent's history and select the optimal classification method. The system described in Appendix 4, characterized by the features described herein. (Note 41) The aforementioned classification unit is It estimates the user's emotions and adjusts how the classification results are displayed based on the estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 42) The aforementioned classification unit is We analyze agent histories and provide information to improve the transparency of classification. The system described in Appendix 4, characterized by the features described herein. [Explanation of symbols]

[0202] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The public department handles the public listing and trading of agents, A search unit that searches for and purchases agents that meet the user's needs, An access unit that provides developers with access to a new customer base, It includes an evaluation unit that uses generational AI to evaluate, classify, and recommend agents. A system characterized by the following features.

2. It includes an assurance unit to guarantee the security and transparency of transactions. The system according to feature 1.

3. It includes an evaluation system section that provides user reviews and rating systems. The system according to feature 1.

4. It features a classification unit that allows for the classification and searching of agents across various categories. The system according to feature 1.

5. We support the creation of new business models and have a dedicated support department. The system according to feature 1.

6. It features a reflection section that reflects market trends in line with the evolution of AI technology. The system according to feature 1.

7. The aforementioned public section is, It estimates user sentiment and adjusts the timing of agent releases based on the estimated user sentiment. The system according to feature 1.

8. The aforementioned public section is, Analyze the developer's past publishing history and select the optimal publishing method. The system according to feature 1.

9. The aforementioned public section is, When publishing agents, filtering is performed based on the developers' current projects and areas of interest. The system according to feature 1.

10. The aforementioned public section is, It estimates the user's sentiment and determines the priority of which agents to publish based on the estimated user sentiment. The system according to feature 1.

Images