system

Abstract

The system according to this embodiment aims to provide a highly reliable and stable AI agent. [Solution] The system according to this embodiment comprises a supply unit, a review unit, and an evaluation unit. The supply unit handles AI agents. The review unit reviews the AI ​​agents provided by the supply unit and eliminates suspicious AI agents. The evaluation unit evaluates the AI ​​agents reviewed by the review unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, it is difficult to ensure the reliability and stability of AI agents, and there is a risk that there may be malicious or low-precision AIs.

[0005] The system according to the embodiment aims to provide an AI agent with high reliability and stability.

Means for Solving the Problems

[0006] The system according to the embodiment includes a providing unit, a reviewing unit, and an evaluating unit. The providing unit handles AI agents. The reviewing unit reviews the AI agents provided by the providing unit and eliminates suspicious AI agents. The evaluating unit evaluates the AI agents reviewed by the reviewing unit. [Effects of the Invention]

[0007] The system according to this embodiment can provide a highly reliable and stable AI agent. [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 signed communication interface (I / F) is an interface that includes a communication processor and an antenna. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface 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 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. Also, the reception device 38, the output device 40, and the camera 42 are 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 system according to an embodiment of the present invention is a system that provides a platform to solve problems such as the difficulty of AI cooperation, malicious AI, and low-accuracy AI in the coming era of multi-AI agents. This platform system provides a platform for handling AI agents, ensuring stability and reliability for businesses and general users. Next, the platform system provides high-quality AI agents by screening and eliminating suspicious AI agents, similar to the App Store. For example, the platform system provides a platform for handling AI agents. This platform enables multiple AI agents to work together. For example, AI agents can work together between different devices such as IoT devices and robots. This improves stability and reliability for businesses and general users. Next, the platform system screens the AI ​​agents provided on the platform. Specifically, it performs operational checks and virus checks on AI agents to eliminate suspicious AI agents. This allows users to use AI agents with peace of mind. Furthermore, the platform system has functions to make it easier to find high-quality AI agents provided on the platform. For example, it introduces user review and evaluation systems so that users can easily find high-quality AI agents. This allows users to select an AI agent that suits them. This platform system, through co-creation with ARM's platform, aims for consistent integration from IoT to agents. This allows the platform system to ensure the stability and reliability of AI agents, providing users with high-quality AI agents.

[0029] The platform system according to this embodiment comprises a provisioning unit, a reviewing unit, and an evaluation unit. The provisioning unit provides a platform for handling AI agents. The provisioning unit enables, for example, multiple AI agents to work together. For example, the provisioning unit enables AI agents to work together across different devices, such as IoT devices and robots. The provisioning unit enables, for example, AI agents to share data and cooperate to perform tasks across different devices. The provisioning unit enables, for example, AI agents to communicate in real time and work together across different devices. The reviewing unit reviews the AI ​​agents provided by the provisioning unit and eliminates suspicious AI agents. The reviewing unit performs, for example, operational checks and virus checks on AI agents. For example, as operational checks of AI agents, the reviewing unit verifies the operation of AI agents using test cases. For example, as a virus check of AI agents, the reviewing unit verifies the safety of AI agents using virus scanning software. For example, the reviewing unit checks the operating environment of AI agents and confirms that AI agents are functioning correctly. The evaluation unit evaluates the AI ​​agents reviewed by the reviewing unit. The evaluation unit can easily find high-quality AI agents by, for example, introducing user reviews and evaluation systems. The evaluation unit can, for example, collect user reviews and evaluate AI agents. The evaluation unit can, for example, evaluate AI agents using an evaluation system. The evaluation unit can, for example, verify the reliability of user reviews and set up a scoring method for evaluations. The evaluation unit can, for example, set evaluation items and weight the evaluations. As a result, the platform system according to the embodiment can ensure the stability and reliability of AI agents and provide users with high-quality AI agents.

[0030] The provider offers a platform for handling AI agents. For example, the provider enables multiple AI agents to work together. Specifically, the provider is designed to allow AI agents to work collaboratively across different devices, such as IoT devices and robots. For instance, in a smart home environment, an AI agent can interact with various devices in the home (smart speakers, lighting, security cameras, etc.) and automatically perform a series of tasks based on user instructions. The provider enables AI agents to share data and collaborate to perform tasks across different devices. For example, an AI agent can control smart home appliances to provide an optimal environment based on user schedule information obtained from a smartphone. Furthermore, the provider enables AI agents to communicate and work collaboratively in real time across different devices. This allows AI agents to, for example, receive data from sensors in real time and quickly take appropriate action based on the situation. In addition, the provider includes functions to monitor the operation of AI agents and perform updates and maintenance as needed. This allows the provider to always offer AI agents incorporating the latest technology and meet user needs.

[0031] The review department reviews the AI ​​agents provided by the service providers and eliminates any suspicious ones. Specifically, the review department performs operational checks and virus checks on the AI ​​agents. For example, as part of operational checks, the review department verifies the operation of the AI ​​agents using test cases. Test cases are scenarios designed to confirm whether the AI ​​agents operate as expected, and they verify operation under various conditions. As part of virus checks, the review department verifies the security of the AI ​​agents using virus scanning software. Virus scanning software analyzes the AI ​​agent's code and data to check for malware or malicious code. Furthermore, the review department checks the operating environment of the AI ​​agents to ensure that they function correctly. For example, it verifies whether the AI ​​agents operate correctly in specific hardware and software environments and checks for compatibility issues. Through these review processes, the review department ensures the quality and security of the AI ​​agents provided by the service providers, enabling them to provide users with reliable AI agents.

[0032] The Evaluation Department evaluates AI agents that have been reviewed by the Screening Department. Specifically, the Evaluation Department introduces user reviews and evaluation systems to make it easy to find high-quality AI agents. For example, the Evaluation Department collects user reviews and evaluates AI agents. User reviews are feedback from users who have actually used the AI ​​agents and provide evaluations of the AI ​​agents' performance and usability. The Evaluation Department uses an evaluation system to evaluate AI agents. The evaluation system sets evaluation items such as the AI ​​agent's performance, reliability, and user satisfaction, and scores based on each item. For example, it evaluates the AI ​​agent's response speed and accuracy, the ease of use of the user interface, etc., and calculates an overall evaluation score. Furthermore, the Evaluation Department verifies the reliability of user reviews and sets the scoring method for evaluations. For example, it evaluates the content of reviews and the reliability of reviewers to eliminate fraudulent reviews and biased evaluations. The Evaluation Department also sets evaluation items and weights the evaluations. For example, if it places importance on the evaluation of the AI ​​agent's performance, it assigns a high weight to the performance evaluation score. In this way, the Evaluation Department provides useful information to users and makes it easy to find high-quality AI agents.

[0033] The service provider enables multiple AI agents to work together. For example, the service provider provides a communication protocol for multiple AI agents to work together. For example, the service provider provides a data sharing method for multiple AI agents to share data. For example, the service provider provides a cooperation method for multiple AI agents to work together to perform tasks. This allows multiple AI agents to work together to provide more advanced services. Some or all of the above-described processes in the service provider may be performed using AI, or not using AI. For example, the service provider can improve the efficiency of cooperation by using an AI model to manage the coordination of multiple AI agents.

[0034] The review department performs operational checks and virus checks on AI agents. For example, as part of operational checks, the review department verifies the operation of AI agents using test cases. For example, as part of virus checks on AI agents, the review department verifies the security of AI agents using virus scanning software. For example, the review department checks the operating environment of AI agents and confirms that AI agents are functioning correctly. This ensures the security and reliability of AI agents. Some or all of the above processes performed by the review department may be carried out using AI, for example, or without AI. For example, the review department can improve the efficiency of operational checks by using an AI model to perform operational checks on AI agents.

[0035] The evaluation department can easily find high-quality AI agents by introducing user reviews and evaluation systems. For example, the evaluation department collects user reviews and evaluates AI agents. For example, the evaluation department uses an evaluation system to evaluate AI agents. For example, the evaluation department verifies the reliability of user reviews and sets up a scoring method for evaluations. For example, the evaluation department sets evaluation items and assigns weights to the evaluations. This makes it easy for users to find high-quality AI agents. Some or all of the above processes in the evaluation department may be performed using AI, for example, or not using AI. For example, the evaluation department can improve the accuracy of its evaluations by using an AI model that analyzes user reviews.

[0036] The service provider will enhance collaboration with IoT devices through co-creation with ARM's platform. For example, the service provider will jointly develop with ARM's platform to enhance collaboration with IoT devices. For example, the service provider will enable data sharing with IoT devices through cooperation with ARM's platform. For example, the service provider will unify communication protocols with IoT devices through collaboration with ARM's platform. This will enable the provision of a wider range of services by enhancing collaboration with IoT devices. Some or all of the above processes in the service provider may be performed using AI, for example, or without AI. For example, the service provider can improve the efficiency of collaboration by using an AI model to manage collaboration with ARM's platform.

[0037] The evaluation unit proposes the most suitable AI agent to the user based on the evaluation results of the AI ​​agents. The evaluation unit, for example, analyzes the evaluation results of the AI ​​agents and proposes the most suitable AI agent to the user. The evaluation unit, for example, selects the most suitable AI agent based on the user's needs. The evaluation unit, for example, performs a performance evaluation of the AI ​​agents and proposes the most suitable AI agent to the user. In this way, user satisfaction is improved by proposing the most suitable AI agent to the user. Some or all of the above processes in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can improve the accuracy of its proposals by using an AI model to analyze the evaluation results of the AI ​​agents.

[0038] The service provider analyzes the user's past usage history and selects the most suitable AI agent. For example, the service provider prioritizes providing AI agents that the user has frequently used in the past. For example, the service provider predicts and provides AI agents to be used during specific time periods based on the user's past usage history. For example, the service provider analyzes the user's past usage history and proposes the most efficient AI agent. This improves user convenience by providing the most suitable AI agent based on the user's past usage history. Some or all of the above processes in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the user's past usage history data into a generating AI and have the generating AI select the most suitable AI agent.

[0039] The service provider filters and provides AI agents based on the user's current projects and areas of interest. For example, the service provider provides AI agents related to the project the user is currently working on. For example, the service provider prioritizes providing relevant AI agents based on the user's areas of interest. For example, the service provider suggests the optimal AI agent according to the progress of the user's current project. This improves user satisfaction by providing AI agents that meet the user's current needs. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the user's current project data into a generating AI and have the generating AI perform the filtering of the optimal AI agent.

[0040] The service provider prioritizes providing highly relevant AI agents based on the user's geographical location information. For example, the service provider provides an AI agent relevant to the user's current location. For example, the service provider suggests the optimal AI agent based on the user's geographical location information. For example, the service provider prioritizes providing an AI agent that is easily accessible from the user's current location. This improves user convenience by providing the optimal AI agent based on the user's geographical location information. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the user's geographical location data into a generating AI and have the generating AI select highly relevant AI agents.

[0041] The service provider analyzes the user's social media activity and provides relevant AI agents. For example, the service provider provides AI agents related to topics the user has shown interest in on social media. For example, the service provider suggests the optimal AI agent based on the user's social media activity. For example, the service provider analyzes the user's social media activity history and provides relevant AI agents preferentially. This improves user satisfaction by providing the optimal AI agent based on the user's social media activity. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the user's social media activity data into a generating AI and have the generating AI select relevant AI agents.

[0042] The review unit improves the accuracy of its review by considering the interrelationships of AI agents. For example, when multiple AI agents work together, the review unit considers their interrelationships during the review process. For example, the review unit checks the data exchange and communication protocols between AI agents to improve the accuracy of its review. For example, the review unit analyzes the interdependencies of AI agents to improve the accuracy of its review. In this way, the accuracy of the review is improved by considering the interrelationships of AI agents. Some or all of the above processes in the review unit may be performed using AI, or not using AI. For example, the review unit can input data on the interrelationships of AI agents into a generating AI and have the generating AI perform the improvement of the review accuracy.

[0043] The review department conducts its review by considering the attribute information of the AI ​​agent's developer. The review department considers, for example, the AI ​​agent's developer's past performance. The review department improves the accuracy of its review based on, for example, the developer's area of ​​expertise and experience. The review department analyzes the developer's attribute information and prioritizes reviewing highly reliable AI agents. This improves the accuracy of the review by considering the attribute information of the AI ​​agent's developer. Some or all of the above processes in the review department may be performed using AI, for example, or not using AI. For example, the review department can input the AI ​​agent's developer attribute information data into a generating AI and have the generating AI perform the task of improving the accuracy of the review.

[0044] The review department conducts reviews considering the geographical distribution of AI agents. The review department conducts reviews based on, for example, the service area of ​​the AI ​​agent. The review department conducts reviews considering the characteristics of each region according to the geographical distribution. The review department analyzes the geographical distribution and reviews AI agents suitable for use in a specific region. This makes it possible to conduct reviews according to the characteristics of each region by considering the geographical distribution of AI agents. Some or all of the above processes in the review department may be performed using AI, for example, or not using AI. For example, the review department can input geographical distribution data of AI agents into a generating AI and have the generating AI perform improvements to the accuracy of the review.

[0045] The review department improves the accuracy of its review by referring to relevant literature on the AI ​​agent. For example, the review department refers to relevant literature to understand the technical background of the AI ​​agent. For example, the review department improves the accuracy of its review by confirming the operating principles of the AI ​​agent based on the relevant literature. For example, the review department analyzes relevant literature to evaluate the reliability of the AI ​​agent. In this way, the accuracy of the review is improved by referring to relevant literature. Some or all of the above processes in the review department may be performed using AI, for example, or not using AI. For example, the review department can input the relevant literature data of the AI ​​agent into a generating AI and have the generating AI perform the improvement of the review accuracy.

[0046] The evaluation unit predicts the current evaluation by referring to past evaluation data. The evaluation unit predicts the current evaluation based on past evaluation data, for example. The evaluation unit analyzes past evaluation data to understand evaluation trends, for example. The evaluation unit predicts and displays the current evaluation by referring to past evaluation data, for example. This improves the accuracy of the evaluation by predicting the current evaluation based on past evaluation data. Some or all of the above processes in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can input past evaluation data into a generating AI and have the generating AI perform the prediction of the current evaluation.

[0047] The evaluation unit applies different evaluation and analysis methods to each category of AI agent. For example, the evaluation unit applies evaluation and analysis methods that are appropriate to the characteristics of each category. For example, the evaluation unit sets evaluation criteria for each category and performs the evaluation. For example, the evaluation unit compares the evaluation results for each category and proposes the optimal AI agent. This improves the accuracy of the evaluation by applying evaluation and analysis methods that are appropriate to the characteristics of each category. Some or all of the above processes in the evaluation unit may be performed using AI, or not using AI. For example, the evaluation unit can input category data of AI agents into a generating AI and have the generating AI perform the application of evaluation and analysis methods.

[0048] The evaluation unit analyzes changes in evaluation based on the timing of AI agent provision. The evaluation unit analyzes changes in evaluation based on the timing of AI agent provision, for example. The evaluation unit compares evaluation data for each provision period to understand evaluation trends. The evaluation unit analyzes changes in evaluation according to the provision period and proposes the optimal AI agent. This allows the evaluation trends to be understood by comparing evaluation data for each provision period. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can input AI agent provision data into a generating AI and have the generating AI perform an analysis of changes in evaluation.

[0049] The evaluation unit analyzes the evaluation by referring to relevant market data for the AI ​​agent. The evaluation unit analyzes the evaluation based on relevant market data for the AI ​​agent, for example. The evaluation unit evaluates the AI ​​agent by referring to market data, for example. The evaluation unit analyzes market data and displays the evaluation results for the AI ​​agent, for example. This improves the accuracy of the evaluation by performing the evaluation based on relevant market data. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without using AI. For example, the evaluation unit can input relevant market data for the AI ​​agent into a generating AI and have the generating AI perform the evaluation analysis.

[0050] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0051] The service provider can also analyze the user's past usage history and select the most suitable AI agent. For example, it can prioritize providing AI agents that the user has frequently used in the past. It can predict and provide AI agents to be used during specific time periods based on the user's past usage history. It can analyze the user's past usage history and propose the most efficient AI agent. In this way, by providing the most suitable AI agent based on the user's past usage history, user convenience can be improved. Some or all of the above processes in the service provider may be performed using AI or not. For example, the service provider can input the user's past usage history data into a generating AI and have the generating AI select the most suitable AI agent.

[0052] The service provider can also prioritize providing highly relevant AI agents based on the user's geographical location information. For example, it can provide an AI agent relevant to the user's current location. It can suggest the optimal AI agent based on the user's geographical location information. It can prioritize providing AI agents that are easily accessible from the user's current location. This improves user convenience by providing the optimal AI agent based on the user's geographical location information. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input the user's geographical location information data into a generating AI and have the generating AI select highly relevant AI agents.

[0053] The evaluation unit can also propose the most suitable AI agent to the user based on the evaluation results of the AI ​​agents. For example, it can analyze the evaluation results of the AI ​​agents and propose the most suitable AI agent to the user. It can select the most suitable AI agent based on the user's needs. It can evaluate the performance of the AI ​​agents and propose the most suitable AI agent to the user. In this way, user satisfaction can be improved by proposing the most suitable AI agent to the user. Some or all of the above processes in the evaluation unit may be performed using AI or not. For example, the evaluation unit can improve the accuracy of its proposals by using an AI model to analyze the evaluation results of the AI ​​agents.

[0054] The service provider can also analyze a user's social media activity and provide relevant AI agents. For example, it can provide AI agents related to topics the user has shown interest in on social media. It can suggest the most suitable AI agent based on the user's social media activity. It can analyze a user's social media activity history and prioritize providing relevant AI agents. This can improve user satisfaction by providing the most suitable AI agent based on the user's social media activity. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input user social media activity data into a generating AI and have the generating AI select relevant AI agents.

[0055] The review department can also improve the accuracy of its reviews by considering the interrelationships of AI agents. For example, when multiple AI agents work together, the review will take their interrelationships into consideration. The review will improve accuracy by checking the data exchange and communication protocols between AI agents. The review will improve accuracy by analyzing the interdependencies of AI agents. In this way, the accuracy of the review can be improved by considering the interrelationships of AI agents. Some or all of the above processes in the review department may be performed using AI or not. For example, the review department can input data on the interrelationships of AI agents into a generating AI and have the generating AI perform the task of improving the accuracy of the review.

[0056] The review department can also conduct reviews by considering the attribute information of the AI ​​agent's developer. For example, it can consider the AI ​​agent's developer's past performance. It can improve the accuracy of the review based on the developer's area of ​​expertise and experience. It can analyze the developer's attribute information and prioritize reviewing highly reliable AI agents. In this way, the accuracy of the review can be improved by considering the attribute information of the AI ​​agent's developer. Some or all of the above processes in the review department may be performed using AI or not. For example, the review department can input AI agent developer attribute information data into a generating AI and have the generating AI perform the task of improving the accuracy of the review.

[0057] The following briefly describes the processing flow for example form 1.

[0058] Step 1: The provider provides a platform for handling AI agents. The provider enables multiple AI agents to work together, for example, AI agents can work collaboratively across different devices such as IoT devices and robots. The provider enables AI agents to share data across different devices, collaborate to perform tasks, communicate in real time, and work together. Step 2: The review department reviews the AI ​​agents provided by the provider department and eliminates any suspicious ones. The review department verifies the operation of the AI ​​agents and performs virus checks, verifies the operation of the AI ​​agents using test cases, and confirms the safety of the AI ​​agents using virus scanning software. The review department also checks the operating environment of the AI ​​agents and confirms that the AI ​​agents are functioning correctly. Step 3: The evaluation department evaluates the AI ​​agents reviewed by the screening department. The evaluation department implements user reviews and evaluation systems to easily identify high-quality AI agents. The evaluation department collects user reviews, evaluates AI agents using the evaluation system, verifies the reliability of user reviews, and sets up scoring methods for evaluations. The evaluation department also sets evaluation criteria and assigns weights to the evaluations.

[0059] (Example of form 2) The platform system according to an embodiment of the present invention is a system that provides a platform to solve problems such as the difficulty of AI cooperation, malicious AI, and low-accuracy AI in the coming era of multi-AI agents. This platform system provides a platform for handling AI agents, ensuring stability and reliability for businesses and general users. Next, the platform system provides high-quality AI agents by screening and eliminating suspicious AI agents, similar to the App Store. For example, the platform system provides a platform for handling AI agents. This platform enables multiple AI agents to work together. For example, AI agents can work together between different devices such as IoT devices and robots. This improves stability and reliability for businesses and general users. Next, the platform system screens the AI ​​agents provided on the platform. Specifically, it performs operational checks and virus checks on AI agents to eliminate suspicious AI agents. This allows users to use AI agents with peace of mind. Furthermore, the platform system has functions to make it easier to find high-quality AI agents provided on the platform. For example, it introduces user review and evaluation systems so that users can easily find high-quality AI agents. This allows users to select an AI agent that suits them. This platform system, through co-creation with ARM's platform, aims for consistent integration from IoT to agents. This allows the platform system to ensure the stability and reliability of AI agents, providing users with high-quality AI agents.

[0060] The platform system according to this embodiment comprises a provisioning unit, a reviewing unit, and an evaluation unit. The provisioning unit provides a platform for handling AI agents. The provisioning unit enables, for example, multiple AI agents to work together. For example, the provisioning unit enables AI agents to work together across different devices, such as IoT devices and robots. The provisioning unit enables, for example, AI agents to share data and cooperate to perform tasks across different devices. The provisioning unit enables, for example, AI agents to communicate in real time and work together across different devices. The reviewing unit reviews the AI ​​agents provided by the provisioning unit and eliminates suspicious AI agents. The reviewing unit performs, for example, operational checks and virus checks on AI agents. For example, as operational checks of AI agents, the reviewing unit verifies the operation of AI agents using test cases. For example, as a virus check of AI agents, the reviewing unit verifies the safety of AI agents using virus scanning software. For example, the reviewing unit checks the operating environment of AI agents and confirms that AI agents are functioning correctly. The evaluation unit evaluates the AI ​​agents reviewed by the reviewing unit. The evaluation unit can easily find high-quality AI agents by, for example, introducing user reviews and evaluation systems. The evaluation unit can, for example, collect user reviews and evaluate AI agents. The evaluation unit can, for example, evaluate AI agents using an evaluation system. The evaluation unit can, for example, verify the reliability of user reviews and set up a scoring method for evaluations. The evaluation unit can, for example, set evaluation items and weight the evaluations. As a result, the platform system according to the embodiment can ensure the stability and reliability of AI agents and provide users with high-quality AI agents.

[0061] The provider offers a platform for handling AI agents. For example, the provider enables multiple AI agents to work together. Specifically, the provider is designed to allow AI agents to work collaboratively across different devices, such as IoT devices and robots. For instance, in a smart home environment, an AI agent can interact with various devices in the home (smart speakers, lighting, security cameras, etc.) and automatically perform a series of tasks based on user instructions. The provider enables AI agents to share data and collaborate to perform tasks across different devices. For example, an AI agent can control smart home appliances to provide an optimal environment based on user schedule information obtained from a smartphone. Furthermore, the provider enables AI agents to communicate and work collaboratively in real time across different devices. This allows AI agents to, for example, receive data from sensors in real time and quickly take appropriate action based on the situation. In addition, the provider includes functions to monitor the operation of AI agents and perform updates and maintenance as needed. This allows the provider to always offer AI agents incorporating the latest technology and meet user needs.

[0062] The review department reviews the AI ​​agents provided by the service providers and eliminates any suspicious ones. Specifically, the review department performs operational checks and virus checks on the AI ​​agents. For example, as part of operational checks, the review department verifies the operation of the AI ​​agents using test cases. Test cases are scenarios designed to confirm whether the AI ​​agents operate as expected, and they verify operation under various conditions. As part of virus checks, the review department verifies the security of the AI ​​agents using virus scanning software. Virus scanning software analyzes the AI ​​agent's code and data to check for malware or malicious code. Furthermore, the review department checks the operating environment of the AI ​​agents to ensure that they function correctly. For example, it verifies whether the AI ​​agents operate correctly in specific hardware and software environments and checks for compatibility issues. Through these review processes, the review department ensures the quality and security of the AI ​​agents provided by the service providers, enabling them to provide users with reliable AI agents.

[0063] The Evaluation Department evaluates AI agents that have been reviewed by the Screening Department. Specifically, the Evaluation Department introduces user reviews and evaluation systems to make it easy to find high-quality AI agents. For example, the Evaluation Department collects user reviews and evaluates AI agents. User reviews are feedback from users who have actually used the AI ​​agents and provide evaluations of the AI ​​agents' performance and usability. The Evaluation Department uses an evaluation system to evaluate AI agents. The evaluation system sets evaluation items such as the AI ​​agent's performance, reliability, and user satisfaction, and scores based on each item. For example, it evaluates the AI ​​agent's response speed and accuracy, the ease of use of the user interface, etc., and calculates an overall evaluation score. Furthermore, the Evaluation Department verifies the reliability of user reviews and sets the scoring method for evaluations. For example, it evaluates the content of reviews and the reliability of reviewers to eliminate fraudulent reviews and biased evaluations. The Evaluation Department also sets evaluation items and weights the evaluations. For example, if it places importance on the evaluation of the AI ​​agent's performance, it assigns a high weight to the performance evaluation score. In this way, the Evaluation Department provides useful information to users and makes it easy to find high-quality AI agents.

[0064] The service provider enables multiple AI agents to work together. For example, the service provider provides a communication protocol for multiple AI agents to work together. For example, the service provider provides a data sharing method for multiple AI agents to share data. For example, the service provider provides a cooperation method for multiple AI agents to work together to perform tasks. This allows multiple AI agents to work together to provide more advanced services. Some or all of the above-described processes in the service provider may be performed using AI, or not using AI. For example, the service provider can improve the efficiency of cooperation by using an AI model to manage the coordination of multiple AI agents.

[0065] The review department performs operational checks and virus checks on AI agents. For example, as part of operational checks, the review department verifies the operation of AI agents using test cases. For example, as part of virus checks on AI agents, the review department verifies the security of AI agents using virus scanning software. For example, the review department checks the operating environment of AI agents and confirms that AI agents are functioning correctly. This ensures the security and reliability of AI agents. Some or all of the above processes performed by the review department may be carried out using AI, for example, or without AI. For example, the review department can improve the efficiency of operational checks by using an AI model to perform operational checks on AI agents.

[0066] The evaluation department can easily find high-quality AI agents by introducing user reviews and evaluation systems. For example, the evaluation department collects user reviews and evaluates AI agents. For example, the evaluation department uses an evaluation system to evaluate AI agents. For example, the evaluation department verifies the reliability of user reviews and sets up a scoring method for evaluations. For example, the evaluation department sets evaluation items and assigns weights to the evaluations. This makes it easy for users to find high-quality AI agents. Some or all of the above processes in the evaluation department may be performed using AI, for example, or not using AI. For example, the evaluation department can improve the accuracy of its evaluations by using an AI model that analyzes user reviews.

[0067] The service provider will enhance collaboration with IoT devices through co-creation with ARM's platform. For example, the service provider will jointly develop with ARM's platform to enhance collaboration with IoT devices. For example, the service provider will enable data sharing with IoT devices through cooperation with ARM's platform. For example, the service provider will unify communication protocols with IoT devices through collaboration with ARM's platform. This will enable the provision of a wider range of services by enhancing collaboration with IoT devices. Some or all of the above processes in the service provider may be performed using AI, for example, or without AI. For example, the service provider can improve the efficiency of collaboration by using an AI model to manage collaboration with ARM's platform.

[0068] The evaluation unit proposes the most suitable AI agent to the user based on the evaluation results of the AI ​​agents. The evaluation unit, for example, analyzes the evaluation results of the AI ​​agents and proposes the most suitable AI agent to the user. The evaluation unit, for example, selects the most suitable AI agent based on the user's needs. The evaluation unit, for example, performs a performance evaluation of the AI ​​agents and proposes the most suitable AI agent to the user. In this way, user satisfaction is improved by proposing the most suitable AI agent to the user. Some or all of the above processes in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can improve the accuracy of its proposals by using an AI model to analyze the evaluation results of the AI ​​agents.

[0069] The service provider estimates the user's emotions and adjusts the timing of AI agent delivery based on the estimated emotions. For example, if the user is stressed, the service provider will deliver the AI ​​agent at a time when the user can relax. For example, if the user is concentrating, the service provider will deliver the AI ​​agent without interrupting their work. For example, if the user is in a hurry, the service provider will quickly deliver the necessary AI agent. This improves user satisfaction by delivering the AI ​​agent at a time that matches 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 service provider may be performed using AI or not using AI. For example, the service provider can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0070] The service provider analyzes the user's past usage history and selects the most suitable AI agent. For example, the service provider prioritizes providing AI agents that the user has frequently used in the past. For example, the service provider predicts and provides AI agents to be used during specific time periods based on the user's past usage history. For example, the service provider analyzes the user's past usage history and proposes the most efficient AI agent. This improves user convenience by providing the most suitable AI agent based on the user's past usage history. Some or all of the above processes in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the user's past usage history data into a generating AI and have the generating AI select the most suitable AI agent.

[0071] The service provider filters and provides AI agents based on the user's current projects and areas of interest. For example, the service provider provides AI agents related to the project the user is currently working on. For example, the service provider prioritizes providing relevant AI agents based on the user's areas of interest. For example, the service provider suggests the optimal AI agent according to the progress of the user's current project. This improves user satisfaction by providing AI agents that meet the user's current needs. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the user's current project data into a generating AI and have the generating AI perform the filtering of the optimal AI agent.

[0072] The service provider estimates the user's emotions and determines the priority of the AI ​​agents to provide based on the estimated emotions. For example, if the user is stressed, the service provider will prioritize providing an AI agent that helps the user relax. For example, if the user is concentrating, the service provider will prioritize providing an AI agent that supports the user's work. For example, if the user is in a hurry, the service provider will prioritize providing an AI agent that can respond quickly. This improves user satisfaction by providing AI agents with priorities 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 service provider may be performed using AI or not using AI. For example, the service provider can input user emotion data into a generative AI and have the generative AI determine the priority of the AI ​​agents to provide.

[0073] The service provider prioritizes providing highly relevant AI agents based on the user's geographical location information. For example, the service provider provides an AI agent relevant to the user's current location. For example, the service provider suggests the optimal AI agent based on the user's geographical location information. For example, the service provider prioritizes providing an AI agent that is easily accessible from the user's current location. This improves user convenience by providing the optimal AI agent based on the user's geographical location information. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the user's geographical location data into a generating AI and have the generating AI select highly relevant AI agents.

[0074] The service provider analyzes the user's social media activity and provides relevant AI agents. For example, the service provider provides AI agents related to topics the user has shown interest in on social media. For example, the service provider suggests the optimal AI agent based on the user's social media activity. For example, the service provider analyzes the user's social media activity history and provides relevant AI agents preferentially. This improves user satisfaction by providing the optimal AI agent based on the user's social media activity. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the user's social media activity data into a generating AI and have the generating AI select relevant AI agents.

[0075] The review unit estimates the user's emotions and adjusts the review criteria based on the estimated emotions. For example, if the user is stressed, the review unit will relax the review criteria and conduct a quick review. For example, if the user is relaxed, the review unit will conduct a detailed review to improve accuracy. For example, if the user is in a hurry, the review unit will simplify the review criteria and conduct a quick review. This improves the efficiency and accuracy of the review by applying review criteria that are appropriate 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 review unit may be performed using AI or not. For example, the review unit can input user emotion data into a generative AI and have the generative AI adjust the review criteria.

[0076] The review unit improves the accuracy of its review by considering the interrelationships of AI agents. For example, when multiple AI agents work together, the review unit considers their interrelationships during the review process. For example, the review unit checks the data exchange and communication protocols between AI agents to improve the accuracy of its review. For example, the review unit analyzes the interdependencies of AI agents to improve the accuracy of its review. In this way, the accuracy of the review is improved by considering the interrelationships of AI agents. Some or all of the above processes in the review unit may be performed using AI, or not using AI. For example, the review unit can input data on the interrelationships of AI agents into a generating AI and have the generating AI perform the improvement of the review accuracy.

[0077] The review department conducts its review by considering the attribute information of the AI ​​agent's developer. The review department considers, for example, the AI ​​agent's developer's past performance. The review department improves the accuracy of its review based on, for example, the developer's area of ​​expertise and experience. The review department analyzes the developer's attribute information and prioritizes reviewing highly reliable AI agents. This improves the accuracy of the review by considering the attribute information of the AI ​​agent's developer. Some or all of the above processes in the review department may be performed using AI, for example, or not using AI. For example, the review department can input the AI ​​agent's developer attribute information data into a generating AI and have the generating AI perform the task of improving the accuracy of the review.

[0078] The review unit estimates the user's emotions and adjusts the order in which the review results are displayed based on the estimated emotions. For example, if the user is stressed, the review unit will prioritize displaying important review results. For example, if the user is relaxed, the review unit will display detailed review results in a sequential manner. For example, if the user is in a hurry, the review unit will prioritize displaying concise review results. This improves user convenience by displaying review results in an order that suits 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 review unit may be performed using AI or not. For example, the review unit can input user emotion data into a generative AI and have the generative AI adjust the display order of the review results.

[0079] The review department conducts reviews considering the geographical distribution of AI agents. The review department conducts reviews based on, for example, the service area of ​​the AI ​​agent. The review department conducts reviews considering the characteristics of each region according to the geographical distribution. The review department analyzes the geographical distribution and reviews AI agents suitable for use in a specific region. This makes it possible to conduct reviews according to the characteristics of each region by considering the geographical distribution of AI agents. Some or all of the above processes in the review department may be performed using AI, for example, or not using AI. For example, the review department can input geographical distribution data of AI agents into a generating AI and have the generating AI perform improvements to the accuracy of the review.

[0080] The review department improves the accuracy of its review by referring to relevant literature on the AI ​​agent. For example, the review department refers to relevant literature to understand the technical background of the AI ​​agent. For example, the review department improves the accuracy of its review by confirming the operating principles of the AI ​​agent based on the relevant literature. For example, the review department analyzes relevant literature to evaluate the reliability of the AI ​​agent. In this way, the accuracy of the review is improved by referring to relevant literature. Some or all of the above processes in the review department may be performed using AI, for example, or not using AI. For example, the review department can input the relevant literature data of the AI ​​agent into a generating AI and have the generating AI perform the improvement of the review accuracy.

[0081] The evaluation unit estimates the user's emotions and adjusts the display method of the evaluation based on the estimated user emotions. For example, if the user is nervous, the evaluation unit provides a simple and highly visible display method. For example, if the user is relaxed, the evaluation unit provides a display method that includes detailed information. For example, if the user is in a hurry, the evaluation unit provides a display method that gets straight to the point. This improves user convenience by providing a display method that suits the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without 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.

[0082] The evaluation unit predicts the current evaluation by referring to past evaluation data. The evaluation unit predicts the current evaluation based on past evaluation data, for example. The evaluation unit analyzes past evaluation data to understand evaluation trends, for example. The evaluation unit predicts and displays the current evaluation by referring to past evaluation data, for example. This improves the accuracy of the evaluation by predicting the current evaluation based on past evaluation data. Some or all of the above processes in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can input past evaluation data into a generating AI and have the generating AI perform the prediction of the current evaluation.

[0083] The evaluation unit applies different evaluation and analysis methods to each category of AI agent. For example, the evaluation unit applies evaluation and analysis methods that are appropriate to the characteristics of each category. For example, the evaluation unit sets evaluation criteria for each category and performs the evaluation. For example, the evaluation unit compares the evaluation results for each category and proposes the optimal AI agent. This improves the accuracy of the evaluation by applying evaluation and analysis methods that are appropriate to the characteristics of each category. Some or all of the above processes in the evaluation unit may be performed using AI, or not using AI. For example, the evaluation unit can input category data of AI agents into a generating AI and have the generating AI perform the application of evaluation and analysis methods.

[0084] The evaluation unit estimates the user's emotions and adjusts the importance of evaluations based on the estimated emotions. For example, if the user is nervous, the evaluation unit prioritizes displaying important evaluation results. For example, if the user is relaxed, the evaluation unit displays detailed evaluation results in a sequential manner. For example, if the user is in a hurry, the evaluation unit prioritizes displaying concise evaluation results. This improves user convenience by displaying evaluation results with importance levels corresponding 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 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 importance of evaluations.

[0085] The evaluation unit analyzes changes in evaluation based on the timing of AI agent provision. The evaluation unit analyzes changes in evaluation based on the timing of AI agent provision, for example. The evaluation unit compares evaluation data for each provision period to understand evaluation trends. The evaluation unit analyzes changes in evaluation according to the provision period and proposes the optimal AI agent. This allows the evaluation trends to be understood by comparing evaluation data for each provision period. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can input AI agent provision data into a generating AI and have the generating AI perform an analysis of changes in evaluation.

[0086] The evaluation unit analyzes the evaluation by referring to relevant market data for the AI ​​agent. The evaluation unit analyzes the evaluation based on relevant market data for the AI ​​agent, for example. The evaluation unit evaluates the AI ​​agent by referring to market data, for example. The evaluation unit analyzes market data and displays the evaluation results for the AI ​​agent, for example. This improves the accuracy of the evaluation by performing the evaluation based on relevant market data. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without using AI. For example, the evaluation unit can input relevant market data for the AI ​​agent into a generating AI and have the generating AI perform the evaluation analysis.

[0087] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0088] The service provider can also estimate the user's emotions and adjust how the AI ​​agent is provided based on the estimated emotions. For example, if the user is stressed, a relaxing AI agent can be provided. If the user is concentrating, an AI agent that supports their work can be provided. If the user is in a hurry, an AI agent that can respond quickly can be provided. By adjusting how the AI ​​agent is provided according to the user's emotions, user satisfaction can be improved. Emotion estimation is achieved using an emotion engine or generative AI, etc. Some or all of the above processing in the service provider may be performed using AI or not using AI. For example, the service provider can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0089] The service provider can also analyze the user's past usage history and select the most suitable AI agent. For example, it can prioritize providing AI agents that the user has frequently used in the past. It can predict and provide AI agents to be used during specific time periods based on the user's past usage history. It can analyze the user's past usage history and propose the most efficient AI agent. In this way, by providing the most suitable AI agent based on the user's past usage history, user convenience can be improved. Some or all of the above processes in the service provider may be performed using AI or not. For example, the service provider can input the user's past usage history data into a generating AI and have the generating AI select the most suitable AI agent.

[0090] The review department can also estimate the user's emotions when verifying the operation of the AI ​​agent and performing virus checks, and adjust the review criteria based on the estimated user emotions. For example, if the user is stressed, the review criteria can be relaxed and the review can be performed quickly. If the user is relaxed, a detailed review can be performed to improve accuracy. If the user is in a hurry, the review criteria can be simplified and the review can be performed quickly. In this way, the efficiency and accuracy of the review can be improved by applying review criteria that correspond to the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI, etc. Some or all of the above processing in the review department may be performed using AI or not. For example, the review department can input user emotion data into a generative AI and have the generative AI perform the adjustment of the review criteria.

[0091] The evaluation unit can also estimate the user's emotions and adjust the display method of the evaluation based on the estimated user emotions. For example, if the user is nervous, a simple and highly visible display method is provided. If the user is relaxed, a display method including detailed information is provided. If the user is in a hurry, a display method that gets straight to the point is provided. This improves user convenience by providing a display method that suits the user's emotions. Emotion estimation is achieved using an emotion engine or a generative 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 display method of the evaluation.

[0092] The service provider can also prioritize providing highly relevant AI agents based on the user's geographical location information. For example, it can provide an AI agent relevant to the user's current location. It can suggest the optimal AI agent based on the user's geographical location information. It can prioritize providing AI agents that are easily accessible from the user's current location. This improves user convenience by providing the optimal AI agent based on the user's geographical location information. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input the user's geographical location information data into a generating AI and have the generating AI select highly relevant AI agents.

[0093] The evaluation unit can also propose the most suitable AI agent to the user based on the evaluation results of the AI ​​agents. For example, it can analyze the evaluation results of the AI ​​agents and propose the most suitable AI agent to the user. It can select the most suitable AI agent based on the user's needs. It can evaluate the performance of the AI ​​agents and propose the most suitable AI agent to the user. In this way, user satisfaction can be improved by proposing the most suitable AI agent to the user. Some or all of the above processes in the evaluation unit may be performed using AI or not. For example, the evaluation unit can improve the accuracy of its proposals by using an AI model to analyze the evaluation results of the AI ​​agents.

[0094] The service provider can also analyze a user's social media activity and provide relevant AI agents. For example, it can provide AI agents related to topics the user has shown interest in on social media. It can suggest the most suitable AI agent based on the user's social media activity. It can analyze a user's social media activity history and prioritize providing relevant AI agents. This can improve user satisfaction by providing the most suitable AI agent based on the user's social media activity. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input user social media activity data into a generating AI and have the generating AI select relevant AI agents.

[0095] The review department can also improve the accuracy of its reviews by considering the interrelationships of AI agents. For example, when multiple AI agents work together, the review will take their interrelationships into consideration. The review will improve accuracy by checking the data exchange and communication protocols between AI agents. The review will improve accuracy by analyzing the interdependencies of AI agents. In this way, the accuracy of the review can be improved by considering the interrelationships of AI agents. Some or all of the above processes in the review department may be performed using AI or not. For example, the review department can input data on the interrelationships of AI agents into a generating AI and have the generating AI perform the task of improving the accuracy of the review.

[0096] The evaluation unit can also estimate the user's emotions and adjust the importance of evaluations based on the estimated emotions. For example, if the user is nervous, important evaluation results are displayed preferentially. If the user is relaxed, detailed evaluation results are displayed in order. If the user is in a hurry, concise evaluation results are displayed preferentially. This improves user convenience by displaying evaluation results with importance levels that match the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI. Some or all of the above-described processes 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 importance of evaluations.

[0097] The review department can also conduct reviews by considering the attribute information of the AI ​​agent's developer. For example, it can consider the AI ​​agent's developer's past performance. It can improve the accuracy of the review based on the developer's area of ​​expertise and experience. It can analyze the developer's attribute information and prioritize reviewing highly reliable AI agents. In this way, the accuracy of the review can be improved by considering the attribute information of the AI ​​agent's developer. Some or all of the above processes in the review department may be performed using AI or not. For example, the review department can input AI agent developer attribute information data into a generating AI and have the generating AI perform the task of improving the accuracy of the review.

[0098] The following briefly describes the processing flow for example form 2.

[0099] Step 1: The provider provides a platform for handling AI agents. The provider enables multiple AI agents to work together, for example, AI agents can work collaboratively across different devices such as IoT devices and robots. The provider enables AI agents to share data across different devices, collaborate to perform tasks, communicate in real time, and work together. Step 2: The review department reviews the AI ​​agents provided by the provider department and eliminates any suspicious ones. The review department verifies the operation of the AI ​​agents and performs virus checks, verifies the operation of the AI ​​agents using test cases, and confirms the safety of the AI ​​agents using virus scanning software. The review department also checks the operating environment of the AI ​​agents and confirms that the AI ​​agents are functioning correctly. Step 3: The evaluation department evaluates the AI ​​agents reviewed by the screening department. The evaluation department implements user reviews and evaluation systems to easily identify high-quality AI agents. The evaluation department collects user reviews, evaluates AI agents using the evaluation system, verifies the reliability of user reviews, and sets up scoring methods for evaluations. The evaluation department also sets evaluation criteria and assigns weights to the evaluations.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] Each of the multiple elements described above, including the provisioning unit, reviewing unit, and evaluation unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the provisioning unit is implemented by the control unit 46A of the smart device 14, enabling multiple AI agents to work together. The reviewing unit is implemented by the identification processing unit 290 of the data processing unit 12, performing operational verification and virus checks of AI agents. The evaluation unit is implemented by the control unit 46A of the smart device 14, introducing user reviews and evaluation systems to easily identify high-quality AI agents. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0104] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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).

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.).

[0116] 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.

[0117] 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.

[0118] 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.

[0119] Each of the multiple elements described above, including the provisioning unit, reviewing unit, and evaluation unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the provisioning unit is implemented by the control unit 46A of the smart glasses 214, enabling multiple AI agents to work together. The reviewing unit is implemented by the identification processing unit 290 of the data processing unit 12, performing operational verification and virus checks of AI agents. The evaluation unit is implemented by the control unit 46A of the smart glasses 214, introducing a user review and evaluation system to easily identify high-quality AI agents. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0120] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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).

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.).

[0132] 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.

[0133] 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.

[0134] 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.

[0135] Each of the multiple elements described above, including the provisioning unit, reviewing unit, and evaluation unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the provisioning unit is implemented by the control unit 46A of the headset terminal 314, enabling multiple AI agents to work together. The reviewing unit is implemented by the identification processing unit 290 of the data processing unit 12, performing operational verification and virus checks of AI agents. The evaluation unit is implemented by the control unit 46A of the headset terminal 314, introducing user reviews and evaluation systems to easily identify high-quality AI agents. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0136] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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).

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.).

[0149] 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.

[0150] 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.

[0151] 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.

[0152] Each of the multiple elements described above, including the supply unit, review unit, and evaluation unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the supply unit is implemented by the control unit 46A of the robot 414, enabling multiple AI agents to work together. The review unit is implemented by the identification processing unit 290 of the data processing unit 12, performing operational verification and virus checks of AI agents. The evaluation unit is implemented by the control unit 46A of the robot 414, introducing user reviews and evaluation systems to easily identify high-quality AI agents. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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."

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] (Note 1) The department that handles AI agents, A review unit that screens the AI ​​agents provided by the aforementioned provision unit and eliminates suspicious AI agents, The system comprises an evaluation unit that evaluates the AI ​​agents reviewed by the aforementioned review unit. A system characterized by the following features. (Note 2) The aforementioned supply unit is, This enables multiple AI agents to work together in a coordinated manner. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned review department, Perform operational checks and virus scans on the AI ​​agent. The system described in Appendix 1, characterized by the features described herein. (Note 4) The evaluation unit described above, By implementing user reviews and rating systems, it's easy to find high-quality AI agents. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned supply unit is, By co-creating with ARM's platform, we will strengthen our collaboration with IoT devices. The system described in Appendix 1, characterized by the features described herein. (Note 6) The evaluation unit described above, Based on the evaluation results of the AI ​​agents, we will suggest the most suitable AI agent for the user. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned supply unit is, It estimates the user's emotions and adjusts the timing of AI agent responses based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned supply unit is, The system analyzes the user's past usage history to select the most suitable AI agent. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned supply unit is, We filter and provide AI agents based on the user's current projects and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned supply unit is, It estimates the user's emotions and determines the priority of the AI ​​agents to provide based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned supply unit is, Based on the user's geographical location, we prioritize providing highly relevant AI agents. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned supply unit is, Analyzes users' social media activity and provides relevant AI agents. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned review department, We estimate the user's emotions and adjust the review criteria based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned review department, Improving the accuracy of the review process by considering the interrelationships of AI agents. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned review department, The review process takes into account the attribute information of the AI ​​agent's developer. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned review department, The system estimates the user's emotions and adjusts the order in which the review results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned review department, The evaluation process takes into account the geographical distribution of AI agents. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned review department, Improve the accuracy of the review process by referring to relevant literature on AI agents. The system described in Appendix 1, characterized by the features described herein. (Note 19) The evaluation unit described above, It estimates the user's sentiment and adjusts how ratings are displayed based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 20) The evaluation unit described above, Predicting current evaluations by referring to past evaluation data. The system described in Appendix 1, characterized by the features described herein. (Note 21) The evaluation unit described above, Apply different evaluation and analysis methods to each category of AI agent. The system described in Appendix 1, characterized by the features described herein. (Note 22) The evaluation unit described above, It estimates the user's emotions and adjusts the importance of the evaluation based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The evaluation unit described above, Analyze changes in evaluation based on the timing of AI agent deployment. The system described in Appendix 1, characterized by the features described herein. (Note 24) The evaluation unit described above, We analyze the evaluation by referring to relevant market data for AI agents. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0172] 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 department that handles AI agents, A review unit reviews the AI ​​agents provided by the aforementioned provision unit and eliminates suspicious AI agents, The system includes an evaluation unit that evaluates the AI ​​agents reviewed by the aforementioned review unit. A system characterized by the following features.

2. The aforementioned supply unit is, This enables multiple AI agents to work together in a coordinated manner. The system according to feature 1.

3. The aforementioned review department, Perform operational checks and virus scans on the AI ​​agent. The system according to feature 1.

4. The evaluation unit, By implementing user reviews and rating systems, it's easy to find high-quality AI agents. The system according to feature 1.

5. The aforementioned supply unit is, By co-creating with ARM's platform, we will strengthen our collaboration with IoT devices. The system according to feature 1.

6. The evaluation unit, Based on the evaluation results of the AI ​​agents, we propose the most suitable AI agent for the user. The system according to feature 1.

7. The aforementioned supply unit is, It estimates the user's emotions and adjusts the timing of AI agent responses based on the estimated emotions. The system according to feature 1.

8. The aforementioned supply unit is, The system analyzes the user's past usage history and selects the most suitable AI agent. The system according to feature 1.

Images