system

Abstract

We provide the system. [Solution] Information gathering means for collecting agent performance data, user feedback, and usage frequency, An evaluation means for evaluating the market value of an agent based on the data collected by the aforementioned collection means, A generation means that generates digital assets including agent ownership information based on the market value evaluated by the evaluation means, A trading method that provides users with an interactive interface that allows them to trade digital assets generated in a virtual space, A means of updating ownership information through transactions and enabling the use of agents in the virtual space, A system that includes this.

Description

Technical Field

[0004] , , , ,

[0005] , , , , ,

[0003] , , ,

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including 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 recent years, a large number of agent technologies have emerged in the market, making it difficult for users to find the optimal agent. At the same time, developers lack criteria for transparently and fairly evaluating the performance and reliability of agents, thus facing the problem of difficulty in obtaining appropriate benefits. Furthermore, when conducting transactions on digital assets of agents, transparency and immutability need to be guaranteed. The present invention aims to solve these problems.

Means for Solving the Problems

[0005] This invention provides an information gathering means for collecting agent performance data, user feedback, and usage frequency. Based on the collected data, it configures an evaluation means that evaluates the market value of the agent using a machine learning algorithm, and provides a generation means that includes the agent's ownership information as a digital asset based on the evaluated market value. Furthermore, it solves the above problems by providing users with an interface that allows trading of this generated digital asset, updating ownership information through trading, and constructing a system equipped with a management means that guarantees transparency and immutability using blockchain technology.

[0006] "Information gathering means" refers to functions and devices for effectively collecting agent performance data, user feedback, and usage frequency.

[0007] "Evaluation means" refers to functions or devices that execute algorithms or processes for calculating the market value of an agent based on collected data.

[0008] "Generation means" refers to functions or devices for creating digital assets, including agent ownership information, based on evaluation results.

[0009] A "marketplace" refers to an interface or platform that allows users to view and trade digitally generated assets.

[0010] A "management mechanism" refers to a function or device that updates ownership information of digital assets through transactions and uses blockchain technology to guarantee its transparency and immutability. [Brief explanation of the drawing]

[0011] [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. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] 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.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0015] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0017] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0018] 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 A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] As shown in Figure 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.

[0022] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0023] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0024] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input 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 device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0025] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (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.

[0026] 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.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 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.

[0029] The 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.

[0030] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0031] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0032] The present invention provides a platform that efficiently collects and processes agent performance data, user feedback, and usage frequency, and enables agents to be traded as digital assets. The following is a specific example of how to implement the system.

[0033] First, the server collects various data generated while the agent is running. This data collection includes agent response time, user reviews, and how often the agent is used. This data is stored in the server's database and used for later analysis.

[0034] Next, the server evaluates the market value of the agents based on the collected data. Here, the server utilizes machine learning algorithms to analyze the collected data and calculate a fair evaluation score. This evaluation score indicates the performance and reliability of the agents.

[0035] Based on the assessed market value, the server generates the agent's digital assets, specifically NFTs. These NFTs contain the agent's identification information, ownership information, and evaluation score, and their transparency and immutability are guaranteed by managing them using blockchain technology.

[0036] The generated NFTs can be viewed on the marketplace via the user's device. Here, users can check detailed information about each agent and make purchases or bids. The marketplace provides an intuitive interface to facilitate smooth transactions.

[0037] When a user purchases an agent, the server uses its transaction management function to ensure the security of the transaction. Once the transaction is complete, ownership of the NFT is transferred to the user, and a record of this is left on the blockchain.

[0038] This system allows users to efficiently trade reliable agents, and developers to receive appropriate compensation based on the agents' performance. Through its implementation, it realizes a digital asset platform that is both innovative and practical.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The server collects various data in real time as the agent operates. This includes response time, task completion rate, user reviews, and usage frequency data. The collected data is stored in the server's database.

[0042] Step 2:

[0043] The server analyzes the collected data to assess its market value. It uses machine learning algorithms to process the data and calculate the agent's performance score. This score indicates the agent's quality and reliability and is used as a standard for fair evaluation.

[0044] Step 3:

[0045] The server generates NFTs (Non-Factor Transactions) for agents based on their evaluated performance scores. These NFTs contain the agent's basic information and ownership details. The generated NFTs are managed using blockchain technology and recorded on the network to ensure transparency and immutability.

[0046] Step 4:

[0047] The device provides users with NFT information through a marketplace interface. Users can view agent performance scores and prices, and make purchases or offers. This interface is designed for intuitive user experience.

[0048] Step 5:

[0049] If a user decides to purchase an agent, they proceed with the purchase process on the marketplace. They select the agent they wish to purchase, enter their payment information, and confirm the transaction.

[0050] Step 6:

[0051] The server receives the user's purchase request and simultaneously approves the payment. Once the payment is complete, ownership of the NFT is transferred to the user and recorded on the blockchain.

[0052] Step 7:

[0053] Users can start using the purchased agent on their own device and utilize the functions and services provided by the agent. In this way, users can efficiently and safely trade and use agents.

[0054] (Example 1)

[0055] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0056] Existing agent trading systems have challenges in accurately evaluating agent performance and market value, and in utilizing this information in transactions, making transparent and reliable trading difficult. Furthermore, there is a lack of effective methods to prevent fraud in recording and managing ownership information.

[0057] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0058] In this invention, the server includes means for collecting performance information, user feedback, and usage frequency; means for calculating evaluation values ​​based on the collected information; and means for generating digital assets including identification information and ownership information. This makes it possible to accurately evaluate the performance and market value of agents and to realize reliable transactions. Furthermore, by using distributed ledger technology as a management means, the transparency and immutability of ownership information are guaranteed, and fraud can be prevented.

[0059] An "information processing device" is a general term for electronic devices that have the functions of collecting, analyzing, and storing data.

[0060] "Performance information" refers to an indicator that shows the speed and efficiency of the agent when it performs processing.

[0061] "User feedback" refers to opinions and evaluations from users regarding the agent's functions and services.

[0062] "Usage frequency" refers to information indicating how often a particular agent is used.

[0063] "Information gathering means" refers to methods and technologies for collecting agent performance information, user feedback, and usage frequency.

[0064] "Evaluation value" is an indicator that quantifies the agent's performance and market value.

[0065] "Evaluation methods" refer to the techniques and methods used to analyze collected data and assess the value of an agent.

[0066] "Identification information" refers to information used to distinguish a particular agent from other agents.

[0067] "Ownership information" refers to information regarding the ownership of digital assets and agents.

[0068] "Digital assets" are a general term for data and files that exist electronically and possess specific value.

[0069] "Generative means" refers to the processes and technologies used to create new digital assets.

[0070] "Transaction tools" refer to methods or interfaces for trading digital assets between users.

[0071] "Management means" refers to the processes or technologies for managing ownership information and for transferring and recording ownership.

[0072] "Distributed ledger technology" refers to decentralized database technology, including blockchain, that provides transparency and immutability.

[0073] This system is centered around a server, which acts as an information processing device, and aims to digitize agents as assets through the collection and analysis of performance information, user feedback, and usage frequency. Specifically, the server uses sensors and interfaces for data collection to gather data on the operational status of agents and stores this data in a database. The collected data is analyzed using machine learning algorithms to calculate an evaluation value for the agents. For example, a high-performance server is used as hardware, and machine learning frameworks such as TENSORFLOW® and PyTorch are utilized as software to model performance information.

[0074] Based on the agent's evaluation score, the server generates digital assets, specifically NFTs, containing identification and ownership information. This generation is automated using smart contracts, and the authenticity and immutability of the generated NFTs are guaranteed by blockchain technology. For example, a platform like Ethereum is used to record transactions on the blockchain.

[0075] The terminal provides a marketplace that users can access. This marketplace displays detailed information about NFTs with a user-friendly interface, allowing users to browse, bid on, and purchase agents' digital assets. Users conduct transactions on the marketplace, and after a purchase, ownership information is updated on the blockchain by the server's management function.

[0076] A concrete example is an NFT of a travel agent that proposes travel plans. Users check the travel planning AI's rating and past user reviews on their device before deciding to purchase. After purchase, ownership is recorded on the blockchain and securely transferred to the user. To streamline this process, a generative AI model is introduced to appeal to the user with the benefits of the purchase using appropriate prompt messages. An example of a prompt message might be, "By using this AI planner, we will instantly create the best travel plan just for you."

[0077] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0078] Step 1:

[0079] The server receives performance information, user feedback, and usage frequency data collected while the agent is running. This data is retrieved through sensors and log files and stored in a structured format in the database. Inputs include raw data from the agent, while outputs include organized and stored database records.

[0080] Step 2:

[0081] The server analyzes the information stored in the database using machine learning algorithms. Here, an evaluation model is used to calculate an evaluation value that indicates the market value of the agent. For example, the algorithm quantifies the indicator by comparing it with past performance data. The input is various performance indicators retrieved from the database, and the output is the calculated evaluation value.

[0082] Step 3:

[0083] The server generates a digital asset (NFT) containing identification and ownership information based on the evaluation value. A smart contract is used to register this digital asset on the blockchain, ensuring the transparency and immutability of the NFT. The inputs are the evaluation value and agent identification information, and the output is the generated NFT.

[0084] Step 4:

[0085] The terminal displays detailed information about the generated NFTs through the marketplace accessed by the user. It provides a user-friendly interface, allowing users to browse, bid on, and purchase NFTs. User interface design is crucial in this step. The input is the publicly available information of the NFT, and the output is visual information for the user.

[0086] Step 5:

[0087] When a user purchases an NFT, the server manages the entire transaction process, ensuring everything from payment processing to ownership transfer is handled securely. After the purchase is complete, a smart contract updates the ownership information on the blockchain. Transactions are securely managed and recorded. The input is the user's purchase intent and payment information, and the output is the updated ownership information.

[0088] Step 6:

[0089] The server collects post-transaction data again and stores it in a database for future analysis. A feedback loop is established to facilitate continuous improvement and enhance user satisfaction, preparing for the next cycle. Inputs are transaction results and user feedback, and output is the updated database record.

[0090] (Application Example 1)

[0091] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0092] Traditional agent trading systems have made it difficult to accurately assess the market value of agents and to conduct transactions transparently and securely. Furthermore, there has been a lack of appropriate interfaces for effectively utilizing agents in a virtual space, highlighting the need for improved user experience. A new system is needed to address these challenges and enable more efficient trading and utilization of agents.

[0093] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0094] In this invention, the server includes information gathering means for collecting agent performance data, user feedback, and usage frequency; evaluation means for evaluating the market value of the agent based on the data collected by the gathering means; generation means for generating digital assets including ownership information of the agent based on the market value evaluated by the evaluation means; trading means for providing users with an interactive interface that allows trading of the digital assets generated in the virtual space; and updating means for updating ownership information through trading and making the agent usable in the virtual space. This makes it possible to accurately evaluate the market value of the agent and to trade and utilize it safely and smoothly in the virtual space.

[0095] "Information gathering means" refers to functions for efficiently collecting performance data, user feedback, and usage frequency related to the operation of the agent.

[0096] "Evaluation means" refers to a function that uses data collected through information gathering means to objectively quantify and evaluate the market value of an agent using machine learning algorithms and the like.

[0097] The "generation method" is a function that generates digital assets, including agent identification information and ownership information, based on the market value obtained by the evaluation method, and records them on the blockchain as NFTs.

[0098] A "trading instrument" is a function that provides an interactive interface that allows users to intuitively trade digital assets generated in a virtual space.

[0099] The "update mechanism" is a function that, upon completion of a transaction, uses blockchain technology to accurately update the ownership information of digital assets and ensures their usability within the agent's virtual space.

[0100] To implement this invention, a server with multiple functions and a terminal accessible to users are used. The server collects and evaluates data, and manages the creation and trading of digital assets.

[0101] The server collects performance data, user feedback, and usage frequency data from the agents while they are running. MongoDB is used as the database to store data in real time. Next, a machine learning algorithm implemented in Python is used to analyze the collected data and quantify the market value of the agents. This allows for an evaluation of the agents' reliability and performance.

[0102] Subsequently, the server generates an agent NFT using the Ethereum blockchain based on the evaluation results. This NFT contains the agent's identification and ownership information, guaranteeing transparency and immutability of ownership. Users can access an interactive interface built with React.js from their devices to view and trade this NFT. These transactions are managed by Smart Contracts, and ownership information is updated simultaneously with the completion of the transaction.

[0103] In a typical virtual store, users enter the store using a smartphone or head-mounted display and explore products using a generated agent as a guide. For example, in an apparel shop, the agent might offer virtual try-ons to complement the user's shopping experience.

[0104] By using the following example prompts for a generative AI model, users can efficiently find the agent they are looking for:

[0105] "We are looking for a virtual agent who can try on the latest fashion. Please recommend a highly marketable agent."

[0106] This system will enable smoother trading of digital assets in virtual spaces and provide users with a new and valuable experience.

[0107] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0108] Step 1:

[0109] The server collects performance data, user feedback, and usage frequency in real time from the environment in which the agent is running. It uses raw data obtained from sensors and logs as input. This data is stored in MongoDB and preprocessed to improve data consistency and search efficiency. The output is a tidy dataset.

[0110] Step 2:

[0111] The server inputs the collected dataset into a machine learning algorithm implemented in Python. The model calculates a weighted average of the agent's response time and user ratings, generating a score to evaluate performance. The output is a numerical value representing the agent's market value.

[0112] Step 3:

[0113] The server generates an agent NFT on the blockchain using its assessed market value. The input is data containing the agent's identification and ownership information. A Smart Contract is used to record this information on the Ethereum network, ensuring transparency and immutability of ownership. The output is the generated NFT.

[0114] Step 4:

[0115] Users access an interactive trading interface built with React.js through their device. Inputs from the server include NFT metadata and transaction information. Users can purchase or bid on NFTs while viewing market value and feedback. Output is transaction completion information.

[0116] Step 5:

[0117] The server updates the NFT ownership information on the blockchain via Smart Contract after the transaction is completed. The input is the new owner information and transaction details. The output is the updated ownership and the blockchain record that proves it.

[0118] Step 6:

[0119] Users utilize their NFTs within the virtual store using smartphones or head-mounted displays. The server constructs the virtual experience provided by the agent and inputs its prompts into a generating AI model. The output is customized virtual instructions and guides to enhance the user experience.

[0120] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0121] The present invention includes a system that digitizes agents based on agent performance data and user feedback, combined with an emotion engine that recognizes user emotions.

[0122] First, the server collects various data in real time generated during the use of services provided by the agent. This information collection includes performance data such as response time and success rate, as well as user feedback and usage trends. Furthermore, the emotion engine monitors user interactions and analyzes the user's emotional state from inputs such as text and voice.

[0123] This collected data is stored in the server's database and used for the next processing step. The server uses machine learning algorithms based on the collected data to calculate the market value of the agent. In this process, user emotion data obtained by the emotion engine is included in the evaluation, and the appropriateness of the agent's response to the user's emotions is added as an evaluation criterion.

[0124] Next, based on the assessed market value, the server generates an NFT (Non-Factor) as the agent's digital asset. This NFT incorporates the agent's performance, responsiveness to user emotions, and ownership information. The NFT is managed using robust blockchain technology, ensuring the transparency and immutability of the digital asset.

[0125] The device provides users with an interface that allows them to browse NFTs through a marketplace. Users can use this interface to view agent details and make purchases or bids. The interface is designed with user-friendliness in mind.

[0126] Users select agents they are interested in and proceed with purchases and transactions using the marketplace. Once a transaction is complete, the server updates the transaction record, transfers ownership of the NFT to the user, and records it on the blockchain.

[0127] This system provides users with an environment where they can secure intelligent agents capable of recognizing emotions and conduct transactions at fair prices. For developers, it allows them to strengthen their agents' market position and increase revenue.

[0128] The following describes the processing flow.

[0129] Step 1:

[0130] The server continuously collects performance data, user feedback, and usage frequency while the agent is running. At this stage, the emotion engine also operates, analyzing emotional data from the user's text and voice to understand their emotional state in real time.

[0131] Step 2:

[0132] The server stores the collected performance and sentiment data in a database. Based on the stored data, it initiates a process to evaluate the market value of the agent using machine learning algorithms. Here, agent responsiveness, task success rate, and positive or negative user sentiment responses are used as evaluation metrics.

[0133] Step 3:

[0134] The server generates an agent NFT based on the evaluation results. This NFT includes evaluation scores, ownership information, and additional characteristics based on sentiment data. Blockchain technology is used in this generation process to ensure the transparency and immutability of the NFT.

[0135] Step 4:

[0136] The user's device displays agent NFTs in a marketplace interface. Users can check agent performance, sentiment characteristics, price, and other details, and make purchase decisions based on that information.

[0137] Step 5:

[0138] When a user wants to purchase a specific agent, they indicate their purchase intent on the marketplace. They select a payment option and proceed with the purchase. Once the transaction is complete, payment is confirmed.

[0139] Step 6:

[0140] The server transfers ownership of the NFT to the user after the user completes the payment. This information is then recorded on the blockchain to ensure transparency and immutability of the transaction history.

[0141] Step 7:

[0142] Users can utilize the purchased agents on their own devices and enjoy the agent's performance and the services it provides. In particular, they can experience improved interaction quality through emotion recognition.

[0143] (Example 2)

[0144] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0145] Traditional digital agents have lacked sufficient market valuation that adequately reflects emotional information from user interactions, resulting in difficulties in accurately determining their market value. Furthermore, methods for ensuring transparency and immutability of ownership information as digital assets have been insufficient. These challenges lead to decreased trust and convenience for users and lost revenue opportunities for developers.

[0146] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0147] In this invention, the server includes means for comprehensively collecting agent performance information, user feedback, and usage trends; sentiment analysis means for analyzing the user's emotional state based on the information collected by the means; and means for evaluating the agent's market value by including the sentiment information revealed by the analysis means in the evaluation criteria. This enables a more precise evaluation of market value that reflects the user's sentiment information, as well as guarantees transparency and immutability of ownership information.

[0148] An "agent" is a software program that runs on a computer and provides specific services to the user.

[0149] "Performance information" refers to performance data such as response time and success rate recorded while the agent is running.

[0150] "User feedback" refers to information such as feedback and evaluations that users provide regarding their use of the agent.

[0151] "Usage trends" refer to patterns that show how users most frequently use the agent.

[0152] "Emotional state" refers to the emotional situation and reactions of a user, analyzed from their text messages and voice input.

[0153] "Market value" is a quantitative measure of the value an agent occupies in the market, and is calculated based on user ratings and emotional adaptability.

[0154] "Digital assets" are valuable assets represented in digital format, including agent characteristic information and ownership information.

[0155] "Ownership information" refers to information that indicates which user owns a digital asset.

[0156] "Generation means" refers to the processes and methods used to build digital assets.

[0157] "Display means" refers to a function that provides an interface for users to view and trade digital assets.

[0158] "Revision measures" refer to methods used to update ownership information of digital assets and ensure their reliability.

[0159] This system consists of three layers: server, terminal, and user. The server is responsible for collecting various data in real time generated when using the services provided by the agent. Specifically, the server comprehensively collects performance information, usage trends, and user feedback through APIs, and further analyzes the emotional state of users from their text and voice input using an emotion analysis engine. This information is stored in a database system (e.g., MySQL®, MongoDB).

[0160] The server also uses machine learning algorithms to evaluate the market value of agents based on the collected data. This evaluation process utilizes data analysis tools such as Python's Scikit-learn, and the resulting sentiment information is included in the market value calculation criteria. Based on these results, an NFT (Non-Fungible Token) is generated as a digital asset containing agent characteristic information and ownership information. The generated NFT is deployed on the Ethereum blockchain in accordance with the ERC-721 standard, ensuring the transparency and immutability of the asset.

[0161] The device provides an interface for users to access, browse, and trade digital assets in a marketplace. This interface is built using frontend technologies such as React.js and is designed to allow users to view agent profile information and feedback from past users.

[0162] Users can view details of agents they are interested in through their devices and proceed with transactions on the marketplace. During transactions, the server uses smart contracts to update ownership information and record it on the blockchain, ensuring the security and reliability of ownership transfers. This system improves the market valuation of agents and creates an environment where users can properly acquire agents that understand emotions.

[0163] As a concrete example, consider a scenario where a user inputs the prompt "I want to make a simple dinner that my family can enjoy today" into the AI ​​model. In this case, the agent analyzes the user's wishes and provides the most suitable recipe. In this way, the agent's response, which reflects emotional information, is incorporated into the market value assessment.

[0164] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0165] Step 1:

[0166] The server collects agent performance information, user feedback, and usage trends in real time. Specifically, it first converts the raw data received via the API into JSON format. The input is agent usage history data, and the output is formatted JSON data. This formatted data undergoes validation and cleaning before being stored in the database.

[0167] Step 2:

[0168] The server uses an emotion analysis engine to analyze the user's emotional state from text or voice input. The input is text or voice data, and the output is a tag indicating the emotional state. Leveraging natural language processing libraries, particularly for emotion recognition and classification, it generates emotion labels such as positive, negative, and neutral.

[0169] Step 3:

[0170] The server uses collected performance information and analyzed sentiment data to evaluate the market value of agents using machine learning algorithms. In this step, a model trained on historical data is used to quantify the value of the agents. The input is performance information and sentiment labels, and the output is the evaluated market value. Evaluation metrics are calculated using regression analysis and clustering methods with Scikit-learn.

[0171] Step 4:

[0172] The server generates a digital asset (NFT) containing agent trait information and ownership information based on its assessed market value. The input is the assessed market value and agent metadata, and the output is the generated NFT. The NFT is deployed on the blockchain using an ERC-721 standard smart contract. This process involves writing the generated NFT to the Ethereum network.

[0173] Step 5:

[0174] The terminal provides an interface for users to view and trade NFTs. Inputs are user prompts and browser actions, while output is detailed agent information displayed. The UI, built using React.js, is dynamically updated to allow users to access the marketplace and view NFT trading information.

[0175] Step 6:

[0176] Users select an NFT from an agent they are interested in using the marketplace and proceed with the purchase. The input is the user's selection and payment information, and the output is confirmation of the transfer of ownership. The server executes the transaction via a smart contract, updates the ownership information, and records it on the blockchain. This ensures a secure and reliable transfer of ownership.

[0177] (Application Example 2)

[0178] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0179] In recent years, the agent and digital services market has seen a shift from simply evaluating user interaction to quantifying emotional value and reflecting it in market value. Furthermore, the need to improve the user experience using emotion recognition technology while accurately measuring its effects remains a challenge.

[0180] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0181] In this invention, the server includes information gathering means for collecting agent performance data, user feedback, and usage frequency; evaluation means for evaluating the market value of the agent based on the data collected by the gathering means; and marketplace means for providing users with an interface on which the generated digital assets can be traded. This makes it possible to incorporate sentiment data into the evaluation of market value.

[0182] "Information gathering means" refers to functions for collecting agent performance data, user feedback, and usage frequency.

[0183] "Evaluation method" refers to a function that analyzes and evaluates the market value of an agent based on collected data.

[0184] A "generation method" refers to a function for generating digital assets based on their assessed market value.

[0185] A "marketplace mechanism" is a function that provides users with an interface through which generated digital assets can be traded.

[0186] "Management means" refers to a function for updating ownership information of digital assets through transactions.

[0187] "Emotion recognition means" refers to a function that analyzes the emotional state of the agent's users and collects emotional data.

[0188] To implement this invention, a server plays a central role. The server collects agent performance data, user feedback, and usage frequency in real time as an information gathering tool. This can be done by using an emotion analysis engine (for example, Affectiva or Microsoft® Azure®'s Emotion API) as an emotion recognition tool to collect user emotion data.

[0189] The server stores this collected data in a database and uses machine learning algorithms (e.g., TensorFlow or PyTorch) as an evaluation tool to assess the market value of the agents. The evaluation includes the agents' responsiveness to user emotions, and emotional data is reflected in the evaluation.

[0190] Next, the server generates digital assets in NFT format based on evaluations as a means of generation. These NFTs include agent performance, responsiveness to user emotions, and ownership information. By utilizing blockchain technology (e.g., Ethereum), the ownership information of the NFTs is managed with transparency and immutability.

[0191] The terminal provides users with a tradable interface as a marketplace. Users can use this interface to view agent details and proceed with purchases or bids. Once a transaction is complete, the server's management system updates the ownership information and records it on the blockchain.

[0192] As a concrete example, when evaluating digital art created by an artist, emotional data is collected from viewers' smartphones, and an NFT (Non-Functional Tome) is generated based on that data, assessing its market value. This system allows artists to offer their digital art to the market in a way that reflects the emotional value of their work.

[0193] An example of a prompt for a generative AI model is as follows: "Analyze the emotional impact of the following digital artwork and evaluate its market value. Based on the acquired data, generate the artwork as an NFT."

[0194] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0195] Step 1:

[0196] The server collects agent performance data, user feedback, and usage frequency in real time using data collection methods. This process stores data in a database and simultaneously analyzes the user's emotional state using an emotion analysis engine. Inputs include agent operational information and user voice and text data, while output is structured performance and emotion data.

[0197] Step 2:

[0198] The server uses a machine learning algorithm to evaluate the market value of agents based on the collected data. The algorithm processes the input data, performing feedback trend analysis and sentiment responsiveness analysis, and then quantifies the market value. The output is the evaluated market value.

[0199] Step 3:

[0200] The server generates NFTs (Non-Factor-Based Digital Assets) based on their assessed market value. The input is the assessed value; this is used to create an NFT structure, and associated ownership information is added. The output is the newly generated NFT.

[0201] Step 4:

[0202] The terminal presents NFTs generated through a marketplace to the user. The input is NFT data, which is visualized and presented on the interface to provide user interaction for transactions. The output is the NFT information actually viewed by the user.

[0203] Step 5:

[0204] Users purchase NFTs from agents through the marketplace and proceed with the transaction. Since the transaction may be completed based on user input, the output includes the transaction completion status and updated ownership information.

[0205] Step 6:

[0206] The server uses a management mechanism to update the NFT ownership information after the transaction is completed and records it on the blockchain. The input is the completed transaction information, and the ownership change is performed as a data calculation. The output is an immutable transaction record.

[0207] 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.

[0208] Data generation model 58 is a type 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> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0209] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0210] [Second Embodiment]

[0211] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0212] 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.

[0213] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0214] 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.

[0215] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0216] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0217] 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.

[0218] 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 using the processor 28. The storage 32 stores the specific processing program 56.

[0219] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0220] The 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.

[0221] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0222] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0223] The present invention provides a platform that efficiently collects and processes agent performance data, user feedback, and usage frequency, and enables agents to be traded as digital assets. The following is a specific example of how to implement the system.

[0224] First, the server collects various data generated while the agent is running. This data collection includes agent response time, user reviews, and how often the agent is used. This data is stored in the server's database and used for later analysis.

[0225] Next, the server evaluates the market value of the agents based on the collected data. Here, the server utilizes machine learning algorithms to analyze the collected data and calculate a fair evaluation score. This evaluation score indicates the performance and reliability of the agents.

[0226] Based on the assessed market value, the server generates the agent's digital assets, specifically NFTs. These NFTs contain the agent's identification information, ownership information, and evaluation score, and their transparency and immutability are guaranteed by managing them using blockchain technology.

[0227] The generated NFTs can be viewed on the marketplace via the user's device. Here, users can check detailed information about each agent and make purchases or bids. The marketplace provides an intuitive interface to facilitate smooth transactions.

[0228] When a user purchases an agent, the server uses its transaction management function to ensure the security of the transaction. Once the transaction is complete, ownership of the NFT is transferred to the user, and a record of this is left on the blockchain.

[0229] This system allows users to efficiently trade reliable agents, and developers to receive appropriate compensation based on the agents' performance. Through its implementation, it realizes a digital asset platform that is both innovative and practical.

[0230] The following describes the processing flow.

[0231] Step 1:

[0232] The server collects various data in real time as the agent operates. This includes response time, task completion rate, user reviews, and usage frequency data. The collected data is stored in the server's database.

[0233] Step 2:

[0234] The server analyzes the collected data to assess its market value. It uses machine learning algorithms to process the data and calculate the agent's performance score. This score indicates the agent's quality and reliability and is used as a standard for fair evaluation.

[0235] Step 3:

[0236] The server generates NFTs (Non-Factor Transactions) for agents based on their evaluated performance scores. These NFTs contain the agent's basic information and ownership details. The generated NFTs are managed using blockchain technology and recorded on the network to ensure transparency and immutability.

[0237] Step 4:

[0238] The device provides users with NFT information through a marketplace interface. Users can view agent performance scores and prices, and make purchases or offers. This interface is designed for intuitive user experience.

[0239] Step 5:

[0240] If a user decides to purchase an agent, they proceed with the purchase process on the marketplace. They select the agent they wish to purchase, enter their payment information, and confirm the transaction.

[0241] Step 6:

[0242] The server receives the user's purchase request and simultaneously approves the payment. Once the payment is complete, ownership of the NFT is transferred to the user and recorded on the blockchain.

[0243] Step 7:

[0244] Users can start using the purchased agent on their own device and utilize the functions and services provided by the agent. In this way, users can efficiently and safely trade and use agents.

[0245] (Example 1)

[0246] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0247] Existing agent trading systems have challenges in accurately evaluating agent performance and market value, and in utilizing this information in transactions, making transparent and reliable trading difficult. Furthermore, there is a lack of effective methods to prevent fraud in recording and managing ownership information.

[0248] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0249] In this invention, the server includes means for collecting performance information, user feedback, and usage frequency; means for calculating evaluation values ​​based on the collected information; and means for generating digital assets including identification information and ownership information. This makes it possible to accurately evaluate the performance and market value of agents and to realize reliable transactions. Furthermore, by using distributed ledger technology as a management means, the transparency and immutability of ownership information are guaranteed, and fraud can be prevented.

[0250] An "information processing device" is a general term for electronic devices that have the functions of collecting, analyzing, and storing data.

[0251] "Performance information" refers to an indicator that shows the speed and efficiency of the agent when it performs processing.

[0252] "User feedback" refers to opinions and evaluations from users regarding the agent's functions and services.

[0253] "Usage frequency" refers to information indicating how often a particular agent is used.

[0254] "Information gathering means" refers to methods and technologies for collecting agent performance information, user feedback, and usage frequency.

[0255] "Evaluation value" is an indicator that quantifies the agent's performance and market value.

[0256] "Evaluation methods" refer to the techniques and methods used to analyze collected data and assess the value of an agent.

[0257] "Identification information" refers to information used to distinguish a particular agent from other agents.

[0258] "Ownership information" refers to information regarding the ownership of digital assets and agents.

[0259] "Digital assets" are a general term for data and files that exist electronically and possess specific value.

[0260] "Generative means" refers to the processes and technologies used to create new digital assets.

[0261] "Transaction tools" refer to methods or interfaces for trading digital assets between users.

[0262] "Management means" refers to the processes or technologies for managing ownership information and for transferring and recording ownership.

[0263] "Distributed ledger technology" refers to decentralized database technology, including blockchain, that provides transparency and immutability.

[0264] This system is centered around a server, which acts as an information processing device, and aims to digitize agents as assets through the collection and analysis of performance information, user feedback, and usage frequency. Specifically, the server uses sensors and interfaces for data collection to gather data on the operational status of agents and stores this data in a database. The collected data is analyzed using machine learning algorithms to calculate an evaluation value for the agents. For example, a high-performance server is used as hardware, and machine learning frameworks such as TensorFlow and PyTorch are utilized as software to model performance information.

[0265] Based on the agent's evaluation score, the server generates digital assets, specifically NFTs, containing identification and ownership information. This generation is automated using smart contracts, and the authenticity and immutability of the generated NFTs are guaranteed by blockchain technology. For example, a platform like Ethereum is used to record transactions on the blockchain.

[0266] The terminal provides a marketplace that users can access. This marketplace displays detailed information about NFTs with a user-friendly interface, allowing users to browse, bid on, and purchase agents' digital assets. Users conduct transactions on the marketplace, and after a purchase, ownership information is updated on the blockchain by the server's management function.

[0267] A concrete example is an NFT of a travel agent that proposes travel plans. Users check the travel planning AI's rating and past user reviews on their device before deciding to purchase. After purchase, ownership is recorded on the blockchain and securely transferred to the user. To streamline this process, a generative AI model is introduced to appeal to the user with the benefits of the purchase using appropriate prompt messages. An example of a prompt message might be, "By using this AI planner, we will instantly create the best travel plan just for you."

[0268] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0269] Step 1:

[0270] The server receives performance information, user feedback, and usage frequency data collected while the agent is running. This data is retrieved through sensors and log files and stored in a structured format in the database. Inputs include raw data from the agent, while outputs include organized and stored database records.

[0271] Step 2:

[0272] The server analyzes the information stored in the database using machine learning algorithms. Here, an evaluation model is used to calculate an evaluation value that indicates the market value of the agent. For example, the algorithm quantifies the indicator by comparing it with past performance data. The input is various performance indicators retrieved from the database, and the output is the calculated evaluation value.

[0273] Step 3:

[0274] The server generates a digital asset (NFT) containing identification and ownership information based on the evaluation value. A smart contract is used to register this digital asset on the blockchain, ensuring the transparency and immutability of the NFT. The inputs are the evaluation value and agent identification information, and the output is the generated NFT.

[0275] Step 4:

[0276] The terminal displays detailed information about the generated NFTs through the marketplace accessed by the user. It provides a user-friendly interface, allowing users to browse, bid on, and purchase NFTs. User interface design is crucial in this step. The input is the publicly available information of the NFT, and the output is visual information for the user.

[0277] Step 5:

[0278] When a user purchases an NFT, the server manages the entire transaction process, ensuring everything from payment processing to ownership transfer is handled securely. After the purchase is complete, a smart contract updates the ownership information on the blockchain. Transactions are securely managed and recorded. The input is the user's purchase intent and payment information, and the output is the updated ownership information.

[0279] Step 6:

[0280] The server collects post-transaction data again and stores it in a database for future analysis. A feedback loop is established to facilitate continuous improvement and enhance user satisfaction, preparing for the next cycle. Inputs are transaction results and user feedback, and output is the updated database record.

[0281] (Application Example 1)

[0282] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0283] In the conventional agent trading system, it has been difficult to accurately evaluate the market value of an agent and conduct its transactions transparently and securely. In addition, there has been a lack of an appropriate interface for effectively using agents within a virtual space, and an improvement in the user experience has been demanded. It is necessary to provide a new system that solves these problems and enables agents to be traded and utilized more efficiently.

[0284] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following respective means.

[0285] In this invention, the server includes an information collection means for collecting the performance data, user feedback, and usage frequency of an agent, an evaluation means for evaluating the market value of the agent based on the data collected by the collection means, a generation means for generating a digital asset including the ownership information of the agent based on the market value evaluated by the evaluation means, a trading means for providing the user with an interactive interface enabling the trading of the digital asset generated in the virtual space, and an update means for updating the ownership information by the transaction and enabling the use of the agent within the virtual space. Thereby, it becomes possible to accurately evaluate the market value of the agent and conduct transactions and utilization safely and smoothly in the virtual space.

[0286] The "information collection means" is a function for efficiently collecting the performance data, user feedback, and usage frequency related to the operation of the agent.

[0287] The "evaluation means" is a function for objectively quantifying and evaluating the market value of the agent by using the data collected by the information collection means and utilizing a machine learning algorithm or the like.

[0288] The "generation means" is a function for generating a digital asset including the identification information and ownership information of the agent based on the market value obtained by the evaluation means and recording it on the blockchain as an NFT.

[0289] A "trading instrument" is a function that provides an interactive interface that allows users to intuitively trade digital assets generated in a virtual space.

[0290] The "update mechanism" is a function that, upon completion of a transaction, uses blockchain technology to accurately update the ownership information of digital assets and ensures their usability within the agent's virtual space.

[0291] To implement this invention, a server with multiple functions and a terminal accessible to users are used. The server collects and evaluates data, and manages the creation and trading of digital assets.

[0292] The server collects performance data, user feedback, and usage frequency data from the agents while they are running. MongoDB is used as the database to store data in real time. Next, a machine learning algorithm implemented in Python is used to analyze the collected data and quantify the market value of the agents. This allows for an evaluation of the agents' reliability and performance.

[0293] Subsequently, the server generates an agent NFT using the Ethereum blockchain based on the evaluation results. This NFT contains the agent's identification and ownership information, guaranteeing transparency and immutability of ownership. Users can access an interactive interface built with React.js from their devices to view and trade this NFT. These transactions are managed by Smart Contracts, and ownership information is updated simultaneously with the completion of the transaction.

[0294] In a typical virtual store, users enter the store using a smartphone or head-mounted display and explore products using a generated agent as a guide. For example, in an apparel shop, the agent might offer virtual try-ons to complement the user's shopping experience.

[0295] By using the following example prompts for a generative AI model, users can efficiently find the agent they are looking for:

[0296] "We are looking for a virtual agent who can try on the latest fashion. Please recommend a highly marketable agent."

[0297] This system will enable smoother trading of digital assets in virtual spaces and provide users with a new and valuable experience.

[0298] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0299] Step 1:

[0300] The server collects performance data, user feedback, and usage frequency in real time from the environment in which the agent is running. It uses raw data obtained from sensors and logs as input. This data is stored in MongoDB and preprocessed to improve data consistency and search efficiency. The output is a tidy dataset.

[0301] Step 2:

[0302] The server inputs the collected dataset into a machine learning algorithm implemented in Python. The model calculates a weighted average of the agent's response time and user ratings, generating a score to evaluate performance. The output is a numerical value representing the agent's market value.

[0303] Step 3:

[0304] The server uses the evaluated market value to generate the agent's NFT on the blockchain. As input, data including the agent's identification information and ownership information is provided. Record it on the Ethereum network using a Smart Contract to ensure the transparency and immutability of ownership. The output is the generated NFT.

[0305] Step 4:

[0306] The user accesses an interactive trading interface built with React.js through the terminal. The input obtained from the server is the NFT's metadata and trading information. The user can purchase or bid on the NFT while referring to the market value and feedback. The output is the information on the conclusion of the transaction.

[0307] Step 5:

[0308] After the transaction is completed, the server updates the NFT's ownership information on the blockchain through the Smart Contract. The input is the new owner information and transaction details. The output is the updated ownership and the blockchain record proving it.

[0309] Step 6:

[0310] The user uses a smartphone or a head-mounted display to utilize the owned NFT in a virtual store. The server constructs a virtual experience provided by the agent and inputs the prompt text into the generative AI model. The output is customized virtual instructions and guides for improving the user experience.

[0311] Furthermore, an emotion engine for estimating the user's emotions may be combined. That is, the specific processing unit 290 may estimate the user's emotions using the emotion identification model 59 and perform specific processing using the user's emotions.

[0312] The present invention includes a system that digitizes agents based on agent performance data and user feedback, combined with an emotion engine that recognizes user emotions.

[0313] First, the server collects various data in real time generated during the use of services provided by the agent. This information collection includes performance data such as response time and success rate, as well as user feedback and usage trends. Furthermore, the emotion engine monitors user interactions and analyzes the user's emotional state from inputs such as text and voice.

[0314] This collected data is stored in the server's database and used for the next processing step. The server uses machine learning algorithms based on the collected data to calculate the market value of the agent. In this process, user emotion data obtained by the emotion engine is included in the evaluation, and the appropriateness of the agent's response to the user's emotions is added as an evaluation criterion.

[0315] Next, based on the assessed market value, the server generates an NFT (Non-Factor) as the agent's digital asset. This NFT incorporates the agent's performance, responsiveness to user emotions, and ownership information. The NFT is managed using robust blockchain technology, ensuring the transparency and immutability of the digital asset.

[0316] The device provides users with an interface that allows them to browse NFTs through a marketplace. Users can use this interface to view agent details and make purchases or bids. The interface is designed with user-friendliness in mind.

[0317] Users select agents they are interested in and proceed with purchases and transactions using the marketplace. Once a transaction is complete, the server updates the transaction record, transfers ownership of the NFT to the user, and records it on the blockchain.

[0318] This system provides users with an environment where they can secure intelligent agents capable of recognizing emotions and conduct transactions at fair prices. For developers, it allows them to strengthen their agents' market position and increase revenue.

[0319] The following describes the processing flow.

[0320] Step 1:

[0321] The server continuously collects performance data, user feedback, and usage frequency while the agent is running. At this stage, the emotion engine also operates, analyzing emotional data from the user's text and voice to understand their emotional state in real time.

[0322] Step 2:

[0323] The server stores the collected performance and sentiment data in a database. Based on the stored data, it initiates a process to evaluate the market value of the agent using machine learning algorithms. Here, agent responsiveness, task success rate, and positive or negative user sentiment responses are used as evaluation metrics.

[0324] Step 3:

[0325] The server generates an agent NFT based on the evaluation results. This NFT includes evaluation scores, ownership information, and additional characteristics based on sentiment data. Blockchain technology is used in this generation process to ensure the transparency and immutability of the NFT.

[0326] Step 4:

[0327] The user's device displays agent NFTs in a marketplace interface. Users can check agent performance, sentiment characteristics, price, and other details, and make purchase decisions based on that information.

[0328] Step 5:

[0329] When a user wants to purchase a specific agent, they indicate their purchase intent on the marketplace. They select a payment option and proceed with the purchase. Once the transaction is complete, payment is confirmed.

[0330] Step 6:

[0331] The server transfers ownership of the NFT to the user after the user completes the payment. This information is then recorded on the blockchain to ensure transparency and immutability of the transaction history.

[0332] Step 7:

[0333] Users can utilize the purchased agents on their own devices and enjoy the agent's performance and the services it provides. In particular, they can experience improved interaction quality through emotion recognition.

[0334] (Example 2)

[0335] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0336] Traditional digital agents have lacked sufficient market valuation that adequately reflects emotional information from user interactions, resulting in difficulties in accurately determining their market value. Furthermore, methods for ensuring transparency and immutability of ownership information as digital assets have been insufficient. These challenges lead to decreased trust and convenience for users and lost revenue opportunities for developers.

[0337] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0338] In this invention, the server includes means for comprehensively collecting agent performance information, user feedback, and usage trends; sentiment analysis means for analyzing the user's emotional state based on the information collected by the means; and means for evaluating the agent's market value by including the sentiment information revealed by the analysis means in the evaluation criteria. This enables a more precise evaluation of market value that reflects the user's sentiment information, as well as guarantees transparency and immutability of ownership information.

[0339] An "agent" is a software program that runs on a computer and provides specific services to the user.

[0340] "Performance information" refers to performance data such as response time and success rate recorded while the agent is running.

[0341] "User feedback" refers to information such as feedback and evaluations that users provide regarding their use of the agent.

[0342] "Usage trends" refer to patterns that show how users most frequently use the agent.

[0343] "Emotional state" refers to the emotional situation and reactions of a user, analyzed from their text messages and voice input.

[0344] "Market value" is a quantitative measure of the value an agent occupies in the market, and is calculated based on user ratings and emotional adaptability.

[0345] "Digital assets" are valuable assets represented in digital format, including agent characteristic information and ownership information.

[0346] "Ownership information" refers to information that indicates which user owns a digital asset.

[0347] "Generation means" refers to the processes and methods used to build digital assets.

[0348] "Display means" refers to a function that provides an interface for users to view and trade digital assets.

[0349] "Revision measures" refer to methods used to update ownership information of digital assets and ensure their reliability.

[0350] This system consists of three layers: server, terminal, and user. The server is responsible for collecting various data in real time generated when the agent uses its services. Specifically, the server comprehensively collects performance information, usage trends, and user feedback through APIs, and further analyzes the emotional state of users from their text and voice input using an emotion analysis engine. This information is stored in a database system (e.g., MySQL, MongoDB).

[0351] The server also uses machine learning algorithms to evaluate the market value of agents based on the collected data. This evaluation process utilizes data analysis tools such as Python's Scikit-learn, and the resulting sentiment information is included in the market value calculation criteria. Based on these results, an NFT (Non-Fungible Token) is generated as a digital asset containing agent characteristic information and ownership information. The generated NFT is deployed on the Ethereum blockchain in accordance with the ERC-721 standard, ensuring the transparency and immutability of the asset.

[0352] The device provides an interface for users to access, browse, and trade digital assets in a marketplace. This interface is built using frontend technologies such as React.js and is designed to allow users to view agent profile information and feedback from past users.

[0353] Users can view details of agents they are interested in through their devices and proceed with transactions on the marketplace. During transactions, the server uses smart contracts to update ownership information and record it on the blockchain, ensuring the security and reliability of ownership transfers. This system improves the market valuation of agents and creates an environment where users can properly acquire agents that understand emotions.

[0354] As a concrete example, consider a scenario where a user inputs the prompt "I want to make a simple dinner that my family can enjoy today" into the AI ​​model. In this case, the agent analyzes the user's wishes and provides the most suitable recipe. In this way, the agent's response, which reflects emotional information, is incorporated into the market value assessment.

[0355] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0356] Step 1:

[0357] The server collects agent performance information, user feedback, and usage trends in real time. Specifically, it first converts the raw data received via the API into JSON format. The input is agent usage history data, and the output is formatted JSON data. This formatted data undergoes validation and cleaning before being stored in the database.

[0358] Step 2:

[0359] The server uses an emotion analysis engine to analyze the user's emotional state from text or voice input. The input is text or voice data, and the output is a tag indicating the emotional state. Leveraging natural language processing libraries, particularly for emotion recognition and classification, it generates emotion labels such as positive, negative, and neutral.

[0360] Step 3:

[0361] The server uses collected performance information and analyzed sentiment data to evaluate the market value of agents using machine learning algorithms. In this step, a model trained on historical data is used to quantify the value of the agents. The input is performance information and sentiment labels, and the output is the evaluated market value. Evaluation metrics are calculated using regression analysis and clustering methods with Scikit-learn.

[0362] Step 4:

[0363] The server generates a digital asset (NFT) containing agent trait information and ownership information based on its assessed market value. The input is the assessed market value and agent metadata, and the output is the generated NFT. The NFT is deployed on the blockchain using an ERC-721 standard smart contract. This process involves writing the generated NFT to the Ethereum network.

[0364] Step 5:

[0365] The terminal provides an interface for users to view and trade NFTs. Inputs are user prompts and browser actions, while output is detailed agent information displayed. The UI, built using React.js, is dynamically updated to allow users to access the marketplace and view NFT trading information.

[0366] Step 6:

[0367] Users select an NFT from an agent they are interested in using the marketplace and proceed with the purchase. The input is the user's selection and payment information, and the output is confirmation of the transfer of ownership. The server executes the transaction via a smart contract, updates the ownership information, and records it on the blockchain. This ensures a secure and reliable transfer of ownership.

[0368] (Application Example 2)

[0369] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0370] In recent years, the agent and digital services market has seen a shift from simply evaluating user interaction to quantifying emotional value and reflecting it in market value. Furthermore, the need to improve the user experience using emotion recognition technology while accurately measuring its effects remains a challenge.

[0371] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0372] In this invention, the server includes information gathering means for collecting agent performance data, user feedback, and usage frequency; evaluation means for evaluating the market value of the agent based on the data collected by the gathering means; and marketplace means for providing users with an interface on which the generated digital assets can be traded. This makes it possible to incorporate sentiment data into the evaluation of market value.

[0373] "Information gathering means" refers to functions for collecting agent performance data, user feedback, and usage frequency.

[0374] "Evaluation method" refers to a function that analyzes and evaluates the market value of an agent based on collected data.

[0375] A "generation method" refers to a function for generating digital assets based on their assessed market value.

[0376] A "marketplace mechanism" is a function that provides users with an interface through which generated digital assets can be traded.

[0377] "Management means" refers to a function for updating ownership information of digital assets through transactions.

[0378] "Emotion recognition means" refers to a function that analyzes the emotional state of the agent's users and collects emotional data.

[0379] To implement this invention, a server plays a central role. The server collects agent performance data, user feedback, and usage frequency in real time as an information gathering tool. This can be done by using an emotion analysis engine (for example, Affectiva or Microsoft Azure's Emotion API) as an emotion recognition tool to collect user emotion data.

[0380] The server stores this collected data in a database and uses machine learning algorithms (e.g., TensorFlow or PyTorch) as an evaluation tool to assess the market value of the agents. The evaluation includes the agents' responsiveness to user emotions, and emotional data is reflected in the evaluation.

[0381] Next, the server generates digital assets in NFT format based on evaluations as a means of generation. These NFTs include agent performance, responsiveness to user emotions, and ownership information. By utilizing blockchain technology (e.g., Ethereum), the ownership information of the NFTs is managed with transparency and immutability.

[0382] The terminal provides users with a tradable interface as a marketplace. Users can use this interface to view agent details and proceed with purchases or bids. Once a transaction is complete, the server's management system updates the ownership information and records it on the blockchain.

[0383] As a concrete example, when evaluating digital art created by an artist, emotional data is collected from viewers' smartphones, and an NFT (Non-Functional Tome) is generated based on that data, assessing its market value. This system allows artists to offer their digital art to the market in a way that reflects the emotional value of their work.

[0384] An example of a prompt for a generative AI model is as follows: "Analyze the emotional impact of the following digital artwork and evaluate its market value. Based on the acquired data, generate the artwork as an NFT."

[0385] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0386] Step 1:

[0387] The server collects agent performance data, user feedback, and usage frequency in real time using data collection methods. This process stores data in a database and simultaneously analyzes the user's emotional state using an emotion analysis engine. Inputs include agent operational information and user voice and text data, while output is structured performance and emotion data.

[0388] Step 2:

[0389] The server uses a machine learning algorithm to evaluate the market value of agents based on the collected data. The algorithm processes the input data, performing feedback trend analysis and sentiment responsiveness analysis, and then quantifies the market value. The output is the evaluated market value.

[0390] Step 3:

[0391] The server generates NFTs (Non-Factor-Based Digital Assets) based on their assessed market value. The input is the assessed value; this is used to create an NFT structure, and associated ownership information is added. The output is the newly generated NFT.

[0392] Step 4:

[0393] The terminal presents NFTs generated through a marketplace to the user. The input is NFT data, which is visualized and presented on the interface to provide user interaction for transactions. The output is the NFT information actually viewed by the user.

[0394] Step 5:

[0395] Users purchase NFTs from agents through the marketplace and proceed with the transaction. Since the transaction may be completed based on user input, the output includes the transaction completion status and updated ownership information.

[0396] Step 6:

[0397] The server uses a management mechanism to update the NFT ownership information after the transaction is completed and records it on the blockchain. The input is the completed transaction information, and the ownership change is performed as a data calculation. The output is an immutable transaction record.

[0398] 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.

[0399] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0400] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0401] [Third Embodiment]

[0402] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0403] 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.

[0404] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0405] 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.

[0406] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0407] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0408] 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.

[0409] 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.

[0410] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0411] The 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.

[0412] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0413] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0414] The present invention provides a platform that efficiently collects and processes agent performance data, user feedback, and usage frequency, and enables agents to be traded as digital assets. The following is a specific example of how to implement the system.

[0415] First, the server collects various data generated while the agent is running. This data collection includes agent response time, user reviews, and how often the agent is used. This data is stored in the server's database and used for later analysis.

[0416] Next, the server evaluates the market value of the agents based on the collected data. Here, the server utilizes machine learning algorithms to analyze the collected data and calculate a fair evaluation score. This evaluation score indicates the performance and reliability of the agents.

[0417] Based on the assessed market value, the server generates the agent's digital assets, specifically NFTs. These NFTs contain the agent's identification information, ownership information, and evaluation score, and their transparency and immutability are guaranteed by managing them using blockchain technology.

[0418] The generated NFTs can be viewed on the marketplace via the user's device. Here, users can check detailed information about each agent and make purchases or bids. The marketplace provides an intuitive interface to facilitate smooth transactions.

[0419] When a user purchases an agent, the server uses its transaction management function to ensure the security of the transaction. Once the transaction is complete, ownership of the NFT is transferred to the user, and a record of this is left on the blockchain.

[0420] This system allows users to efficiently trade reliable agents, and developers to receive appropriate compensation based on the agents' performance. Through its implementation, it realizes a digital asset platform that is both innovative and practical.

[0421] The following describes the processing flow.

[0422] Step 1:

[0423] The server collects various data in real time as the agent operates. This includes response time, task completion rate, user reviews, and usage frequency data. The collected data is stored in the server's database.

[0424] Step 2:

[0425] The server analyzes the collected data to assess its market value. It uses machine learning algorithms to process the data and calculate the agent's performance score. This score indicates the agent's quality and reliability and is used as a standard for fair evaluation.

[0426] Step 3:

[0427] The server generates NFTs (Non-Factor Transactions) for agents based on their evaluated performance scores. These NFTs contain the agent's basic information and ownership details. The generated NFTs are managed using blockchain technology and recorded on the network to ensure transparency and immutability.

[0428] Step 4:

[0429] The device provides users with NFT information through a marketplace interface. Users can view agent performance scores and prices, and make purchases or offers. This interface is designed for intuitive user experience.

[0430] Step 5:

[0431] If a user decides to purchase an agent, they proceed with the purchase process on the marketplace. They select the agent they wish to purchase, enter their payment information, and confirm the transaction.

[0432] Step 6:

[0433] The server receives the user's purchase request and simultaneously approves the payment. Once the payment is complete, ownership of the NFT is transferred to the user and recorded on the blockchain.

[0434] Step 7:

[0435] Users can start using the purchased agent on their own device and utilize the functions and services provided by the agent. In this way, users can efficiently and safely trade and use agents.

[0436] (Example 1)

[0437] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0438] Existing agent trading systems have challenges in accurately evaluating agent performance and market value, and in utilizing this information in transactions, making transparent and reliable trading difficult. Furthermore, there is a lack of effective methods to prevent fraud in recording and managing ownership information.

[0439] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0440] In this invention, the server includes means for collecting performance information, user feedback, and usage frequency; means for calculating evaluation values ​​based on the collected information; and means for generating digital assets including identification information and ownership information. This makes it possible to accurately evaluate the performance and market value of agents and to realize reliable transactions. Furthermore, by using distributed ledger technology as a management means, the transparency and immutability of ownership information are guaranteed, and fraud can be prevented.

[0441] An "information processing device" is a general term for electronic devices that have the functions of collecting, analyzing, and storing data.

[0442] "Performance information" refers to an indicator that shows the speed and efficiency of the agent when it performs processing.

[0443] "User feedback" refers to opinions and evaluations from users regarding the agent's functions and services.

[0444] "Usage frequency" refers to information indicating how often a particular agent is used.

[0445] "Information gathering means" refers to methods and technologies for collecting agent performance information, user feedback, and usage frequency.

[0446] "Evaluation value" is an indicator that quantifies the agent's performance and market value.

[0447] "Evaluation methods" refer to the techniques and methods used to analyze collected data and assess the value of an agent.

[0448] "Identification information" refers to information used to distinguish a particular agent from other agents.

[0449] "Ownership information" refers to information regarding the ownership of digital assets and agents.

[0450] "Digital assets" are a general term for data and files that exist electronically and possess specific value.

[0451] "Generative means" refers to the processes and technologies used to create new digital assets.

[0452] "Transaction tools" refer to methods or interfaces for trading digital assets between users.

[0453] "Management means" refers to the processes or technologies for managing ownership information and for transferring and recording ownership.

[0454] "Distributed ledger technology" refers to decentralized database technology, including blockchain, that provides transparency and immutability.

[0455] This system is centered around a server, which acts as an information processing device, and aims to digitize agents as assets through the collection and analysis of performance information, user feedback, and usage frequency. Specifically, the server uses sensors and interfaces for data collection to gather data on the operational status of agents and stores this data in a database. The collected data is analyzed using machine learning algorithms to calculate an evaluation value for the agents. For example, a high-performance server is used as hardware, and machine learning frameworks such as TensorFlow and PyTorch are utilized as software to model performance information.

[0456] Based on the agent's evaluation score, the server generates digital assets, specifically NFTs, containing identification and ownership information. This generation is automated using smart contracts, and the authenticity and immutability of the generated NFTs are guaranteed by blockchain technology. For example, a platform like Ethereum is used to record transactions on the blockchain.

[0457] The terminal provides a marketplace that users can access. This marketplace displays detailed information about NFTs with a user-friendly interface, allowing users to browse, bid on, and purchase agents' digital assets. Users conduct transactions on the marketplace, and after a purchase, ownership information is updated on the blockchain by the server's management function.

[0458] A concrete example is an NFT of a travel agent that proposes travel plans. Users check the travel planning AI's rating and past user reviews on their device before deciding to purchase. After purchase, ownership is recorded on the blockchain and securely transferred to the user. To streamline this process, a generative AI model is introduced to appeal to the user with the benefits of the purchase using appropriate prompt messages. An example of a prompt message might be, "By using this AI planner, we will instantly create the best travel plan just for you."

[0459] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0460] Step 1:

[0461] The server receives performance information, user feedback, and usage frequency data collected while the agent is running. This data is retrieved through sensors and log files and stored in a structured format in the database. Inputs include raw data from the agent, while outputs include organized and stored database records.

[0462] Step 2:

[0463] The server analyzes the information stored in the database using machine learning algorithms. Here, an evaluation model is used to calculate an evaluation value that indicates the market value of the agent. For example, the algorithm quantifies the indicator by comparing it with past performance data. The input is various performance indicators retrieved from the database, and the output is the calculated evaluation value.

[0464] Step 3:

[0465] The server generates a digital asset (NFT) containing identification and ownership information based on the evaluation value. A smart contract is used to register this digital asset on the blockchain, ensuring the transparency and immutability of the NFT. The inputs are the evaluation value and agent identification information, and the output is the generated NFT.

[0466] Step 4:

[0467] The terminal displays detailed information about the generated NFTs through the marketplace accessed by the user. It provides a user-friendly interface, allowing users to browse, bid on, and purchase NFTs. User interface design is crucial in this step. The input is the publicly available information of the NFT, and the output is visual information for the user.

[0468] Step 5:

[0469] When a user purchases an NFT, the server manages the entire transaction process, ensuring everything from payment processing to ownership transfer is handled securely. After the purchase is complete, a smart contract updates the ownership information on the blockchain. Transactions are securely managed and recorded. The input is the user's purchase intent and payment information, and the output is the updated ownership information.

[0470] Step 6:

[0471] The server collects post-transaction data again and stores it in a database for future analysis. A feedback loop is established to facilitate continuous improvement and enhance user satisfaction, preparing for the next cycle. Inputs are transaction results and user feedback, and output is the updated database record.

[0472] (Application Example 1)

[0473] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0474] Traditional agent trading systems have made it difficult to accurately assess the market value of agents and to conduct transactions transparently and securely. Furthermore, there has been a lack of appropriate interfaces for effectively utilizing agents in a virtual space, highlighting the need for improved user experience. A new system is needed to address these challenges and enable more efficient trading and utilization of agents.

[0475] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0476] In this invention, the server includes information gathering means for collecting agent performance data, user feedback, and usage frequency; evaluation means for evaluating the market value of the agent based on the data collected by the gathering means; generation means for generating digital assets including ownership information of the agent based on the market value evaluated by the evaluation means; trading means for providing users with an interactive interface that allows trading of the digital assets generated in the virtual space; and updating means for updating ownership information through trading and making the agent usable in the virtual space. This makes it possible to accurately evaluate the market value of the agent and to trade and utilize it safely and smoothly in the virtual space.

[0477] "Information gathering means" refers to functions for efficiently collecting performance data, user feedback, and usage frequency related to the operation of the agent.

[0478] "Evaluation means" refers to a function that uses data collected through information gathering means to objectively quantify and evaluate the market value of an agent using machine learning algorithms and the like.

[0479] The "generation method" is a function that generates digital assets, including agent identification information and ownership information, based on the market value obtained by the evaluation method, and records them on the blockchain as NFTs.

[0480] A "trading instrument" is a function that provides an interactive interface that allows users to intuitively trade digital assets generated in a virtual space.

[0481] The "update mechanism" is a function that, upon completion of a transaction, uses blockchain technology to accurately update the ownership information of digital assets and ensures their usability within the agent's virtual space.

[0482] To implement this invention, a server with multiple functions and a terminal accessible to users are used. The server collects and evaluates data, and manages the creation and trading of digital assets.

[0483] The server collects performance data, user feedback, and usage frequency data from the agents while they are running. MongoDB is used as the database to store data in real time. Next, a machine learning algorithm implemented in Python is used to analyze the collected data and quantify the market value of the agents. This allows for an evaluation of the agents' reliability and performance.

[0484] Subsequently, the server generates an agent NFT using the Ethereum blockchain based on the evaluation results. This NFT contains the agent's identification and ownership information, guaranteeing transparency and immutability of ownership. Users can access an interactive interface built with React.js from their devices to view and trade this NFT. These transactions are managed by Smart Contracts, and ownership information is updated simultaneously with the completion of the transaction.

[0485] In a typical virtual store, users enter the store using a smartphone or head-mounted display and explore products using a generated agent as a guide. For example, in an apparel shop, the agent might offer virtual try-ons to complement the user's shopping experience.

[0486] By using the following example prompts for a generative AI model, users can efficiently find the agent they are looking for:

[0487] "We are looking for a virtual agent who can try on the latest fashion. Please recommend a highly marketable agent."

[0488] This system will enable smoother trading of digital assets in virtual spaces and provide users with a new and valuable experience.

[0489] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0490] Step 1:

[0491] The server collects performance data, user feedback, and usage frequency in real time from the environment in which the agent is running. It uses raw data obtained from sensors and logs as input. This data is stored in MongoDB and preprocessed to improve data consistency and search efficiency. The output is a tidy dataset.

[0492] Step 2:

[0493] The server inputs the collected dataset into a machine learning algorithm implemented in Python. The model calculates a weighted average of the agent's response time and user ratings, generating a score to evaluate performance. The output is a numerical value representing the agent's market value.

[0494] Step 3:

[0495] The server generates an agent NFT on the blockchain using its assessed market value. The input is data containing the agent's identification and ownership information. A Smart Contract is used to record this information on the Ethereum network, ensuring transparency and immutability of ownership. The output is the generated NFT.

[0496] Step 4:

[0497] Users access an interactive trading interface built with React.js through their device. Inputs from the server include NFT metadata and transaction information. Users can purchase or bid on NFTs while viewing market value and feedback. Output is transaction completion information.

[0498] Step 5:

[0499] The server updates the NFT ownership information on the blockchain via Smart Contract after the transaction is completed. The input is the new owner information and transaction details. The output is the updated ownership and the blockchain record that proves it.

[0500] Step 6:

[0501] Users utilize their NFTs within the virtual store using smartphones or head-mounted displays. The server constructs the virtual experience provided by the agent and inputs its prompts into a generating AI model. The output is customized virtual instructions and guides to enhance the user experience.

[0502] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0503] The present invention includes a system that digitizes agents based on agent performance data and user feedback, combined with an emotion engine that recognizes user emotions.

[0504] First, the server collects various data in real time generated during the use of services provided by the agent. This information collection includes performance data such as response time and success rate, as well as user feedback and usage trends. Furthermore, the emotion engine monitors user interactions and analyzes the user's emotional state from inputs such as text and voice.

[0505] This collected data is stored in the server's database and used for the next processing step. The server uses machine learning algorithms based on the collected data to calculate the market value of the agent. In this process, user emotion data obtained by the emotion engine is included in the evaluation, and the appropriateness of the agent's response to the user's emotions is added as an evaluation criterion.

[0506] Next, based on the assessed market value, the server generates an NFT (Non-Factor) as the agent's digital asset. This NFT incorporates the agent's performance, responsiveness to user emotions, and ownership information. The NFT is managed using robust blockchain technology, ensuring the transparency and immutability of the digital asset.

[0507] The device provides users with an interface that allows them to browse NFTs through a marketplace. Users can use this interface to view agent details and make purchases or bids. The interface is designed with user-friendliness in mind.

[0508] Users select agents they are interested in and proceed with purchases and transactions using the marketplace. Once a transaction is complete, the server updates the transaction record, transfers ownership of the NFT to the user, and records it on the blockchain.

[0509] This system provides users with an environment where they can secure intelligent agents capable of recognizing emotions and conduct transactions at fair prices. For developers, it allows them to strengthen their agents' market position and increase revenue.

[0510] The following describes the processing flow.

[0511] Step 1:

[0512] The server continuously collects performance data, user feedback, and usage frequency while the agent is running. At this stage, the emotion engine also operates, analyzing emotional data from the user's text and voice to understand their emotional state in real time.

[0513] Step 2:

[0514] The server stores the collected performance and sentiment data in a database. Based on the stored data, it initiates a process to evaluate the market value of the agent using machine learning algorithms. Here, agent responsiveness, task success rate, and positive or negative user sentiment responses are used as evaluation metrics.

[0515] Step 3:

[0516] The server generates an agent NFT based on the evaluation results. This NFT includes evaluation scores, ownership information, and additional characteristics based on sentiment data. Blockchain technology is used in this generation process to ensure the transparency and immutability of the NFT.

[0517] Step 4:

[0518] The user's device displays agent NFTs in a marketplace interface. Users can check agent performance, sentiment characteristics, price, and other details, and make purchase decisions based on that information.

[0519] Step 5:

[0520] When a user wants to purchase a specific agent, they indicate their purchase intent on the marketplace. They select a payment option and proceed with the purchase. Once the transaction is complete, payment is confirmed.

[0521] Step 6:

[0522] The server transfers ownership of the NFT to the user after the user completes the payment. This information is then recorded on the blockchain to ensure transparency and immutability of the transaction history.

[0523] Step 7:

[0524] Users can utilize the purchased agents on their own devices and enjoy the agent's performance and the services it provides. In particular, they can experience improved interaction quality through emotion recognition.

[0525] (Example 2)

[0526] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0527] Traditional digital agents have lacked sufficient market valuation that adequately reflects emotional information from user interactions, resulting in difficulties in accurately determining their market value. Furthermore, methods for ensuring transparency and immutability of ownership information as digital assets have been insufficient. These challenges lead to decreased trust and convenience for users and lost revenue opportunities for developers.

[0528] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0529] In this invention, the server includes means for comprehensively collecting agent performance information, user feedback, and usage trends; sentiment analysis means for analyzing the user's emotional state based on the information collected by the means; and means for evaluating the agent's market value by including the sentiment information revealed by the analysis means in the evaluation criteria. This enables a more precise evaluation of market value that reflects the user's sentiment information, as well as guarantees transparency and immutability of ownership information.

[0530] An "agent" is a software program that runs on a computer and provides specific services to the user.

[0531] "Performance information" refers to performance data such as response time and success rate recorded while the agent is running.

[0532] "User feedback" refers to information such as feedback and evaluations that users provide regarding their use of the agent.

[0533] "Usage trends" refer to patterns that show how users most frequently use the agent.

[0534] "Emotional state" refers to the emotional situation and reactions of a user, analyzed from their text messages and voice input.

[0535] "Market value" is a quantitative measure of the value an agent occupies in the market, and is calculated based on user ratings and emotional adaptability.

[0536] "Digital assets" are valuable assets represented in digital format, including agent characteristic information and ownership information.

[0537] "Ownership information" refers to information that indicates which user owns a digital asset.

[0538] "Generation means" refers to the processes and methods used to build digital assets.

[0539] "Display means" refers to a function that provides an interface for users to view and trade digital assets.

[0540] "Revision measures" refer to methods used to update ownership information of digital assets and ensure their reliability.

[0541] This system consists of three layers: server, terminal, and user. The server is responsible for collecting various data in real time generated when the agent uses its services. Specifically, the server comprehensively collects performance information, usage trends, and user feedback through APIs, and further analyzes the emotional state of users from their text and voice input using an emotion analysis engine. This information is stored in a database system (e.g., MySQL, MongoDB).

[0542] The server also uses machine learning algorithms to evaluate the market value of agents based on the collected data. This evaluation process utilizes data analysis tools such as Python's Scikit-learn, and the resulting sentiment information is included in the market value calculation criteria. Based on these results, an NFT (Non-Fungible Token) is generated as a digital asset containing agent characteristic information and ownership information. The generated NFT is deployed on the Ethereum blockchain in accordance with the ERC-721 standard, ensuring the transparency and immutability of the asset.

[0543] The device provides an interface for users to access, browse, and trade digital assets in a marketplace. This interface is built using frontend technologies such as React.js and is designed to allow users to view agent profile information and feedback from past users.

[0544] Users can view details of agents they are interested in through their devices and proceed with transactions on the marketplace. During transactions, the server uses smart contracts to update ownership information and record it on the blockchain, ensuring the security and reliability of ownership transfers. This system improves the market valuation of agents and creates an environment where users can properly acquire agents that understand emotions.

[0545] As a concrete example, consider a scenario where a user inputs the prompt "I want to make a simple dinner that my family can enjoy today" into the AI ​​model. In this case, the agent analyzes the user's wishes and provides the most suitable recipe. In this way, the agent's response, which reflects emotional information, is incorporated into the market value assessment.

[0546] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0547] Step 1:

[0548] The server collects agent performance information, user feedback, and usage trends in real time. Specifically, it first converts the raw data received via the API into JSON format. The input is agent usage history data, and the output is formatted JSON data. This formatted data undergoes validation and cleaning before being stored in the database.

[0549] Step 2:

[0550] The server uses an emotion analysis engine to analyze the user's emotional state from text or voice input. The input is text or voice data, and the output is a tag indicating the emotional state. Leveraging natural language processing libraries, particularly for emotion recognition and classification, it generates emotion labels such as positive, negative, and neutral.

[0551] Step 3:

[0552] The server uses collected performance information and analyzed sentiment data to evaluate the market value of agents using machine learning algorithms. In this step, a model trained on historical data is used to quantify the value of the agents. The input is performance information and sentiment labels, and the output is the evaluated market value. Evaluation metrics are calculated using regression analysis and clustering methods with Scikit-learn.

[0553] Step 4:

[0554] The server generates a digital asset (NFT) containing agent trait information and ownership information based on its assessed market value. The input is the assessed market value and agent metadata, and the output is the generated NFT. The NFT is deployed on the blockchain using an ERC-721 standard smart contract. This process involves writing the generated NFT to the Ethereum network.

[0555] Step 5:

[0556] The terminal provides an interface for users to view and trade NFTs. Inputs are user prompts and browser actions, while output is detailed agent information displayed. The UI, built using React.js, is dynamically updated to allow users to access the marketplace and view NFT trading information.

[0557] Step 6:

[0558] Users select an NFT from an agent they are interested in using the marketplace and proceed with the purchase. The input is the user's selection and payment information, and the output is confirmation of the transfer of ownership. The server executes the transaction via a smart contract, updates the ownership information, and records it on the blockchain. This ensures a secure and reliable transfer of ownership.

[0559] (Application Example 2)

[0560] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0561] In recent years, the agent and digital services market has seen a shift from simply evaluating user interaction to quantifying emotional value and reflecting it in market value. Furthermore, the need to improve the user experience using emotion recognition technology while accurately measuring its effects remains a challenge.

[0562] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0563] In this invention, the server includes information gathering means for collecting agent performance data, user feedback, and usage frequency; evaluation means for evaluating the market value of the agent based on the data collected by the gathering means; and marketplace means for providing users with an interface on which the generated digital assets can be traded. This makes it possible to incorporate sentiment data into the evaluation of market value.

[0564] "Information gathering means" refers to functions for collecting agent performance data, user feedback, and usage frequency.

[0565] "Evaluation method" refers to a function that analyzes and evaluates the market value of an agent based on collected data.

[0566] A "generation method" refers to a function for generating digital assets based on their assessed market value.

[0567] A "marketplace mechanism" is a function that provides users with an interface through which generated digital assets can be traded.

[0568] "Management means" refers to a function for updating ownership information of digital assets through transactions.

[0569] "Emotion recognition means" refers to a function that analyzes the emotional state of the agent's users and collects emotional data.

[0570] To implement this invention, a server plays a central role. The server collects agent performance data, user feedback, and usage frequency in real time as an information gathering tool. This can be done by using an emotion analysis engine (for example, Affectiva or Microsoft Azure's Emotion API) as an emotion recognition tool to collect user emotion data.

[0571] The server stores this collected data in a database and uses machine learning algorithms (e.g., TensorFlow or PyTorch) as an evaluation tool to assess the market value of the agents. The evaluation includes the agents' responsiveness to user emotions, and emotional data is reflected in the evaluation.

[0572] Next, the server generates digital assets in NFT format based on evaluations as a means of generation. These NFTs include agent performance, responsiveness to user emotions, and ownership information. By utilizing blockchain technology (e.g., Ethereum), the ownership information of the NFTs is managed with transparency and immutability.

[0573] The terminal provides users with a tradable interface as a marketplace. Users can use this interface to view agent details and proceed with purchases or bids. Once a transaction is complete, the server's management system updates the ownership information and records it on the blockchain.

[0574] As a concrete example, when evaluating digital art created by an artist, emotional data is collected from viewers' smartphones, and an NFT (Non-Functional Tome) is generated based on that data, assessing its market value. This system allows artists to offer their digital art to the market in a way that reflects the emotional value of their work.

[0575] An example of a prompt for a generative AI model is as follows: "Analyze the emotional impact of the following digital artwork and evaluate its market value. Based on the acquired data, generate the artwork as an NFT."

[0576] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0577] Step 1:

[0578] The server collects agent performance data, user feedback, and usage frequency in real time using data collection methods. This process stores data in a database and simultaneously analyzes the user's emotional state using an emotion analysis engine. Inputs include agent operational information and user voice and text data, while output is structured performance and emotion data.

[0579] Step 2:

[0580] The server uses a machine learning algorithm to evaluate the market value of agents based on the collected data. The algorithm processes the input data, performing feedback trend analysis and sentiment responsiveness analysis, and then quantifies the market value. The output is the evaluated market value.

[0581] Step 3:

[0582] The server generates NFTs (Non-Factor-Based Digital Assets) based on their assessed market value. The input is the assessed value; this is used to create an NFT structure, and associated ownership information is added. The output is the newly generated NFT.

[0583] Step 4:

[0584] The terminal presents NFTs generated through a marketplace to the user. The input is NFT data, which is visualized and presented on the interface to provide user interaction for transactions. The output is the NFT information actually viewed by the user.

[0585] Step 5:

[0586] Users purchase NFTs from agents through the marketplace and proceed with the transaction. Since the transaction may be completed based on user input, the output includes the transaction completion status and updated ownership information.

[0587] Step 6:

[0588] The server uses a management mechanism to update the NFT ownership information after the transaction is completed and records it on the blockchain. The input is the completed transaction information, and the ownership change is performed as a data calculation. The output is an immutable transaction record.

[0589] 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.

[0590] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0591] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0592] [Fourth Embodiment]

[0593] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0594] 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.

[0595] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0596] 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.

[0597] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0598] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0599] 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.

[0600] 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. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0601] 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.

[0602] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0603] The 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.

[0604] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0605] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0606] The present invention provides a platform that efficiently collects and processes agent performance data, user feedback, and usage frequency, and enables agents to be traded as digital assets. The following is a specific example of how to implement the system.

[0607] First, the server collects various data generated while the agent is running. This data collection includes agent response time, user reviews, and how often the agent is used. This data is stored in the server's database and used for later analysis.

[0608] Next, the server evaluates the market value of the agents based on the collected data. Here, the server utilizes machine learning algorithms to analyze the collected data and calculate a fair evaluation score. This evaluation score indicates the performance and reliability of the agents.

[0609] Based on the assessed market value, the server generates the agent's digital assets, specifically NFTs. These NFTs contain the agent's identification information, ownership information, and evaluation score, and their transparency and immutability are guaranteed by managing them using blockchain technology.

[0610] The generated NFTs can be viewed on the marketplace via the user's device. Here, users can check detailed information about each agent and make purchases or bids. The marketplace provides an intuitive interface to facilitate smooth transactions.

[0611] When a user purchases an agent, the server uses its transaction management function to ensure the security of the transaction. Once the transaction is complete, ownership of the NFT is transferred to the user, and a record of this is left on the blockchain.

[0612] This system allows users to efficiently trade reliable agents, and developers to receive appropriate compensation based on the agents' performance. Through its implementation, it realizes a digital asset platform that is both innovative and practical.

[0613] The following describes the processing flow.

[0614] Step 1:

[0615] The server collects various data in real time as the agent operates. This includes response time, task completion rate, user reviews, and usage frequency data. The collected data is stored in the server's database.

[0616] Step 2:

[0617] The server analyzes the collected data to assess its market value. It uses machine learning algorithms to process the data and calculate the agent's performance score. This score indicates the agent's quality and reliability and is used as a standard for fair evaluation.

[0618] Step 3:

[0619] The server generates NFTs (Non-Factor Transactions) for agents based on their evaluated performance scores. These NFTs contain the agent's basic information and ownership details. The generated NFTs are managed using blockchain technology and recorded on the network to ensure transparency and immutability.

[0620] Step 4:

[0621] The device provides users with NFT information through a marketplace interface. Users can view agent performance scores and prices, and make purchases or offers. This interface is designed for intuitive user experience.

[0622] Step 5:

[0623] If a user decides to purchase an agent, they proceed with the purchase process on the marketplace. They select the agent they wish to purchase, enter their payment information, and confirm the transaction.

[0624] Step 6:

[0625] The server receives the user's purchase request and simultaneously approves the payment. Once the payment is complete, ownership of the NFT is transferred to the user and recorded on the blockchain.

[0626] Step 7:

[0627] Users can start using the purchased agent on their own device and utilize the functions and services provided by the agent. In this way, users can efficiently and safely trade and use agents.

[0628] (Example 1)

[0629] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0630] Existing agent trading systems have challenges in accurately evaluating agent performance and market value, and in utilizing this information in transactions, making transparent and reliable trading difficult. Furthermore, there is a lack of effective methods to prevent fraud in recording and managing ownership information.

[0631] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0632] In this invention, the server includes means for collecting performance information, user feedback, and usage frequency; means for calculating evaluation values ​​based on the collected information; and means for generating digital assets including identification information and ownership information. This makes it possible to accurately evaluate the performance and market value of agents and to realize reliable transactions. Furthermore, by using distributed ledger technology as a management means, the transparency and immutability of ownership information are guaranteed, and fraud can be prevented.

[0633] An "information processing device" is a general term for electronic devices that have the functions of collecting, analyzing, and storing data.

[0634] "Performance information" refers to an indicator that shows the speed and efficiency of the agent when it performs processing.

[0635] "User feedback" refers to opinions and evaluations from users regarding the agent's functions and services.

[0636] "Usage frequency" refers to information indicating how often a particular agent is used.

[0637] "Information gathering means" refers to methods and technologies for collecting agent performance information, user feedback, and usage frequency.

[0638] "Evaluation value" is an indicator that quantifies the agent's performance and market value.

[0639] "Evaluation methods" refer to the techniques and methods used to analyze collected data and assess the value of an agent.

[0640] "Identification information" refers to information used to distinguish a particular agent from other agents.

[0641] "Ownership information" refers to information regarding the ownership of digital assets and agents.

[0642] "Digital assets" are a general term for data and files that exist electronically and possess specific value.

[0643] "Generative means" refers to the processes and technologies used to create new digital assets.

[0644] "Transaction tools" refer to methods or interfaces for trading digital assets between users.

[0645] "Management means" refers to the processes or technologies for managing ownership information and for transferring and recording ownership.

[0646] "Distributed ledger technology" refers to decentralized database technology, including blockchain, that provides transparency and immutability.

[0647] This system is centered around a server, which acts as an information processing device, and aims to digitize agents as assets through the collection and analysis of performance information, user feedback, and usage frequency. Specifically, the server uses sensors and interfaces for data collection to gather data on the operational status of agents and stores this data in a database. The collected data is analyzed using machine learning algorithms to calculate an evaluation value for the agents. For example, a high-performance server is used as hardware, and machine learning frameworks such as TensorFlow and PyTorch are utilized as software to model performance information.

[0648] Based on the agent's evaluation score, the server generates digital assets, specifically NFTs, containing identification and ownership information. This generation is automated using smart contracts, and the authenticity and immutability of the generated NFTs are guaranteed by blockchain technology. For example, a platform like Ethereum is used to record transactions on the blockchain.

[0649] The terminal provides a marketplace that users can access. This marketplace displays detailed information about NFTs with a user-friendly interface, allowing users to browse, bid on, and purchase agents' digital assets. Users conduct transactions on the marketplace, and after a purchase, ownership information is updated on the blockchain by the server's management function.

[0650] A concrete example is an NFT of a travel agent that proposes travel plans. Users check the travel planning AI's rating and past user reviews on their device before deciding to purchase. After purchase, ownership is recorded on the blockchain and securely transferred to the user. To streamline this process, a generative AI model is introduced to appeal to the user with the benefits of the purchase using appropriate prompt messages. An example of a prompt message might be, "By using this AI planner, we will instantly create the best travel plan just for you."

[0651] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0652] Step 1:

[0653] The server receives performance information, user feedback, and usage frequency data collected while the agent is running. This data is retrieved through sensors and log files and stored in a structured format in the database. Inputs include raw data from the agent, while outputs include organized and stored database records.

[0654] Step 2:

[0655] The server analyzes the information stored in the database using machine learning algorithms. Here, an evaluation model is used to calculate an evaluation value that indicates the market value of the agent. For example, the algorithm quantifies the indicator by comparing it with past performance data. The input is various performance indicators retrieved from the database, and the output is the calculated evaluation value.

[0656] Step 3:

[0657] The server generates a digital asset (NFT) containing identification and ownership information based on the evaluation value. A smart contract is used to register this digital asset on the blockchain, ensuring the transparency and immutability of the NFT. The inputs are the evaluation value and agent identification information, and the output is the generated NFT.

[0658] Step 4:

[0659] The terminal displays detailed information about the generated NFTs through the marketplace accessed by the user. It provides a user-friendly interface, allowing users to browse, bid on, and purchase NFTs. User interface design is crucial in this step. The input is the publicly available information of the NFT, and the output is visual information for the user.

[0660] Step 5:

[0661] When a user purchases an NFT, the server manages the entire transaction process, ensuring everything from payment processing to ownership transfer is handled securely. After the purchase is complete, a smart contract updates the ownership information on the blockchain. Transactions are securely managed and recorded. The input is the user's purchase intent and payment information, and the output is the updated ownership information.

[0662] Step 6:

[0663] The server collects post-transaction data again and stores it in a database for future analysis. A feedback loop is established to facilitate continuous improvement and enhance user satisfaction, preparing for the next cycle. Inputs are transaction results and user feedback, and output is the updated database record.

[0664] (Application Example 1)

[0665] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0666] Traditional agent trading systems have made it difficult to accurately assess the market value of agents and to conduct transactions transparently and securely. Furthermore, there has been a lack of appropriate interfaces for effectively utilizing agents in a virtual space, highlighting the need for improved user experience. A new system is needed to address these challenges and enable more efficient trading and utilization of agents.

[0667] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0668] In this invention, the server includes information gathering means for collecting agent performance data, user feedback, and usage frequency; evaluation means for evaluating the market value of the agent based on the data collected by the gathering means; generation means for generating digital assets including ownership information of the agent based on the market value evaluated by the evaluation means; trading means for providing users with an interactive interface that allows trading of the digital assets generated in the virtual space; and updating means for updating ownership information through trading and making the agent usable in the virtual space. This makes it possible to accurately evaluate the market value of the agent and to trade and utilize it safely and smoothly in the virtual space.

[0669] "Information gathering means" refers to functions for efficiently collecting performance data, user feedback, and usage frequency related to the operation of the agent.

[0670] "Evaluation means" refers to a function that uses data collected through information gathering means to objectively quantify and evaluate the market value of an agent using machine learning algorithms and the like.

[0671] The "generation method" is a function that generates digital assets, including agent identification information and ownership information, based on the market value obtained by the evaluation method, and records them on the blockchain as NFTs.

[0672] A "trading instrument" is a function that provides an interactive interface that allows users to intuitively trade digital assets generated in a virtual space.

[0673] The "update mechanism" is a function that, upon completion of a transaction, uses blockchain technology to accurately update the ownership information of digital assets and ensures their usability within the agent's virtual space.

[0674] To implement this invention, a server with multiple functions and a terminal accessible to users are used. The server collects and evaluates data, and manages the creation and trading of digital assets.

[0675] The server collects performance data, user feedback, and usage frequency data from the agents while they are running. MongoDB is used as the database to store data in real time. Next, a machine learning algorithm implemented in Python is used to analyze the collected data and quantify the market value of the agents. This allows for an evaluation of the agents' reliability and performance.

[0676] Subsequently, the server generates an agent NFT using the Ethereum blockchain based on the evaluation results. This NFT contains the agent's identification and ownership information, guaranteeing transparency and immutability of ownership. Users can access an interactive interface built with React.js from their devices to view and trade this NFT. These transactions are managed by Smart Contracts, and ownership information is updated simultaneously with the completion of the transaction.

[0677] In a typical virtual store, users enter the store using a smartphone or head-mounted display and explore products using a generated agent as a guide. For example, in an apparel shop, the agent might offer virtual try-ons to complement the user's shopping experience.

[0678] By using the following example prompts for a generative AI model, users can efficiently find the agent they are looking for:

[0679] "We are looking for a virtual agent who can try on the latest fashion. Please recommend a highly marketable agent."

[0680] This system will enable smoother trading of digital assets in virtual spaces and provide users with a new and valuable experience.

[0681] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0682] Step 1:

[0683] The server collects performance data, user feedback, and usage frequency in real time from the environment in which the agent is running. It uses raw data obtained from sensors and logs as input. This data is stored in MongoDB and preprocessed to improve data consistency and search efficiency. The output is a tidy dataset.

[0684] Step 2:

[0685] The server inputs the collected dataset into a machine learning algorithm implemented in Python. The model calculates a weighted average of the agent's response time and user ratings, generating a score to evaluate performance. The output is a numerical value representing the agent's market value.

[0686] Step 3:

[0687] The server generates an agent NFT on the blockchain using its assessed market value. The input is data containing the agent's identification and ownership information. A Smart Contract is used to record this information on the Ethereum network, ensuring transparency and immutability of ownership. The output is the generated NFT.

[0688] Step 4:

[0689] Users access an interactive trading interface built with React.js through their device. Inputs from the server include NFT metadata and transaction information. Users can purchase or bid on NFTs while viewing market value and feedback. Output is transaction completion information.

[0690] Step 5:

[0691] The server updates the NFT ownership information on the blockchain via Smart Contract after the transaction is completed. The input is the new owner information and transaction details. The output is the updated ownership and the blockchain record that proves it.

[0692] Step 6:

[0693] Users utilize their NFTs within the virtual store using smartphones or head-mounted displays. The server constructs the virtual experience provided by the agent and inputs its prompts into a generating AI model. The output is customized virtual instructions and guides to enhance the user experience.

[0694] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0695] The present invention includes a system that digitizes agents based on agent performance data and user feedback, combined with an emotion engine that recognizes user emotions.

[0696] First, the server collects various data in real time generated during the use of services provided by the agent. This information collection includes performance data such as response time and success rate, as well as user feedback and usage trends. Furthermore, the emotion engine monitors user interactions and analyzes the user's emotional state from inputs such as text and voice.

[0697] This collected data is stored in the server's database and used for the next processing step. The server uses machine learning algorithms based on the collected data to calculate the market value of the agent. In this process, user emotion data obtained by the emotion engine is included in the evaluation, and the appropriateness of the agent's response to the user's emotions is added as an evaluation criterion.

[0698] Next, based on the assessed market value, the server generates an NFT (Non-Factor) as the agent's digital asset. This NFT incorporates the agent's performance, responsiveness to user emotions, and ownership information. The NFT is managed using robust blockchain technology, ensuring the transparency and immutability of the digital asset.

[0699] The device provides users with an interface that allows them to browse NFTs through a marketplace. Users can use this interface to view agent details and make purchases or bids. The interface is designed with user-friendliness in mind.

[0700] Users select agents they are interested in and proceed with purchases and transactions using the marketplace. Once a transaction is complete, the server updates the transaction record, transfers ownership of the NFT to the user, and records it on the blockchain.

[0701] This system provides users with an environment where they can secure intelligent agents capable of recognizing emotions and conduct transactions at fair prices. For developers, it allows them to strengthen their agents' market position and increase revenue.

[0702] The following describes the processing flow.

[0703] Step 1:

[0704] The server continuously collects performance data, user feedback, and usage frequency while the agent is running. At this stage, the emotion engine also operates, analyzing emotional data from the user's text and voice to understand their emotional state in real time.

[0705] Step 2:

[0706] The server stores the collected performance and sentiment data in a database. Based on the stored data, it initiates a process to evaluate the market value of the agent using machine learning algorithms. Here, agent responsiveness, task success rate, and positive or negative user sentiment responses are used as evaluation metrics.

[0707] Step 3:

[0708] The server generates an agent NFT based on the evaluation results. This NFT includes evaluation scores, ownership information, and additional characteristics based on sentiment data. Blockchain technology is used in this generation process to ensure the transparency and immutability of the NFT.

[0709] Step 4:

[0710] The user's device displays agent NFTs in a marketplace interface. Users can check agent performance, sentiment characteristics, price, and other details, and make purchase decisions based on that information.

[0711] Step 5:

[0712] When a user wants to purchase a specific agent, they indicate their purchase intent on the marketplace. They select a payment option and proceed with the purchase. Once the transaction is complete, payment is confirmed.

[0713] Step 6:

[0714] The server transfers ownership of the NFT to the user after the user completes the payment. This information is then recorded on the blockchain to ensure transparency and immutability of the transaction history.

[0715] Step 7:

[0716] Users can utilize the purchased agents on their own devices and enjoy the agent's performance and the services it provides. In particular, they can experience improved interaction quality through emotion recognition.

[0717] (Example 2)

[0718] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0719] Traditional digital agents have lacked sufficient market valuation that adequately reflects emotional information from user interactions, resulting in difficulties in accurately determining their market value. Furthermore, methods for ensuring transparency and immutability of ownership information as digital assets have been insufficient. These challenges lead to decreased trust and convenience for users and lost revenue opportunities for developers.

[0720] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0721] In this invention, the server includes means for comprehensively collecting agent performance information, user feedback, and usage trends; sentiment analysis means for analyzing the user's emotional state based on the information collected by the means; and means for evaluating the agent's market value by including the sentiment information revealed by the analysis means in the evaluation criteria. This enables a more precise evaluation of market value that reflects the user's sentiment information, as well as guarantees transparency and immutability of ownership information.

[0722] An "agent" is a software program that runs on a computer and provides specific services to the user.

[0723] "Performance information" refers to performance data such as response time and success rate recorded while the agent is running.

[0724] "User feedback" refers to information such as feedback and evaluations that users provide regarding their use of the agent.

[0725] "Usage trends" refer to patterns that show how users most frequently use the agent.

[0726] "Emotional state" refers to the emotional situation and reactions of a user, analyzed from their text messages and voice input.

[0727] "Market value" is a quantitative measure of the value an agent occupies in the market, and is calculated based on user ratings and emotional adaptability.

[0728] "Digital assets" are valuable assets represented in digital format, including agent characteristic information and ownership information.

[0729] "Ownership information" refers to information that indicates which user owns a digital asset.

[0730] "Generation means" refers to the processes and methods used to build digital assets.

[0731] "Display means" refers to a function that provides an interface for users to view and trade digital assets.

[0732] "Revision measures" refer to methods used to update ownership information of digital assets and ensure their reliability.

[0733] This system consists of three layers: server, terminal, and user. The server is responsible for collecting various data in real time generated when the agent uses its services. Specifically, the server comprehensively collects performance information, usage trends, and user feedback through APIs, and further analyzes the emotional state of users from their text and voice input using an emotion analysis engine. This information is stored in a database system (e.g., MySQL, MongoDB).

[0734] The server also uses machine learning algorithms to evaluate the market value of agents based on the collected data. This evaluation process utilizes data analysis tools such as Python's Scikit-learn, and the resulting sentiment information is included in the market value calculation criteria. Based on these results, an NFT (Non-Fungible Token) is generated as a digital asset containing agent characteristic information and ownership information. The generated NFT is deployed on the Ethereum blockchain in accordance with the ERC-721 standard, ensuring the transparency and immutability of the asset.

[0735] The device provides an interface for users to access, browse, and trade digital assets in a marketplace. This interface is built using frontend technologies such as React.js and is designed to allow users to view agent profile information and feedback from past users.

[0736] Users can view details of agents they are interested in through their devices and proceed with transactions on the marketplace. During transactions, the server uses smart contracts to update ownership information and record it on the blockchain, ensuring the security and reliability of ownership transfers. This system improves the market valuation of agents and creates an environment where users can properly acquire agents that understand emotions.

[0737] As a concrete example, consider a scenario where a user inputs the prompt "I want to make a simple dinner that my family can enjoy today" into the AI ​​model. In this case, the agent analyzes the user's wishes and provides the most suitable recipe. In this way, the agent's response, which reflects emotional information, is incorporated into the market value assessment.

[0738] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0739] Step 1:

[0740] The server collects agent performance information, user feedback, and usage trends in real time. Specifically, it first converts the raw data received via the API into JSON format. The input is agent usage history data, and the output is formatted JSON data. This formatted data undergoes validation and cleaning before being stored in the database.

[0741] Step 2:

[0742] The server uses an emotion analysis engine to analyze the user's emotional state from text or voice input. The input is text or voice data, and the output is a tag indicating the emotional state. Leveraging natural language processing libraries, particularly for emotion recognition and classification, it generates emotion labels such as positive, negative, and neutral.

[0743] Step 3:

[0744] The server uses collected performance information and analyzed sentiment data to evaluate the market value of agents using machine learning algorithms. In this step, a model trained on historical data is used to quantify the value of the agents. The input is performance information and sentiment labels, and the output is the evaluated market value. Evaluation metrics are calculated using regression analysis and clustering methods with Scikit-learn.

[0745] Step 4:

[0746] The server generates a digital asset (NFT) containing agent trait information and ownership information based on its assessed market value. The input is the assessed market value and agent metadata, and the output is the generated NFT. The NFT is deployed on the blockchain using an ERC-721 standard smart contract. This process involves writing the generated NFT to the Ethereum network.

[0747] Step 5:

[0748] The terminal provides an interface for users to view and trade NFTs. Inputs are user prompts and browser actions, while output is detailed agent information displayed. The UI, built using React.js, is dynamically updated to allow users to access the marketplace and view NFT trading information.

[0749] Step 6:

[0750] Users select an NFT from an agent they are interested in using the marketplace and proceed with the purchase. The input is the user's selection and payment information, and the output is confirmation of the transfer of ownership. The server executes the transaction via a smart contract, updates the ownership information, and records it on the blockchain. This ensures a secure and reliable transfer of ownership.

[0751] (Application Example 2)

[0752] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0753] In recent years, the agent and digital services market has seen a shift from simply evaluating user interaction to quantifying emotional value and reflecting it in market value. Furthermore, the need to improve the user experience using emotion recognition technology while accurately measuring its effects remains a challenge.

[0754] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0755] In this invention, the server includes information gathering means for collecting agent performance data, user feedback, and usage frequency; evaluation means for evaluating the market value of the agent based on the data collected by the gathering means; and marketplace means for providing users with an interface on which the generated digital assets can be traded. This makes it possible to incorporate sentiment data into the evaluation of market value.

[0756] "Information gathering means" refers to functions for collecting agent performance data, user feedback, and usage frequency.

[0757] "Evaluation method" refers to a function that analyzes and evaluates the market value of an agent based on collected data.

[0758] A "generation method" refers to a function for generating digital assets based on their assessed market value.

[0759] A "marketplace mechanism" is a function that provides users with an interface through which generated digital assets can be traded.

[0760] "Management means" refers to a function for updating ownership information of digital assets through transactions.

[0761] "Emotion recognition means" refers to a function that analyzes the emotional state of the agent's users and collects emotional data.

[0762] To implement this invention, a server plays a central role. The server collects agent performance data, user feedback, and usage frequency in real time as an information gathering tool. This can be done by using an emotion analysis engine (for example, Affectiva or Microsoft Azure's Emotion API) as an emotion recognition tool to collect user emotion data.

[0763] The server stores this collected data in a database and uses machine learning algorithms (e.g., TensorFlow or PyTorch) as an evaluation tool to assess the market value of the agents. The evaluation includes the agents' responsiveness to user emotions, and emotional data is reflected in the evaluation.

[0764] Next, the server generates digital assets in NFT format based on evaluations as a means of generation. These NFTs include agent performance, responsiveness to user emotions, and ownership information. By utilizing blockchain technology (e.g., Ethereum), the ownership information of the NFTs is managed with transparency and immutability.

[0765] The terminal provides users with a tradable interface as a marketplace. Users can use this interface to view agent details and proceed with purchases or bids. Once a transaction is complete, the server's management system updates the ownership information and records it on the blockchain.

[0766] As a concrete example, when evaluating digital art created by an artist, emotional data is collected from viewers' smartphones, and an NFT (Non-Functional Tome) is generated based on that data, assessing its market value. This system allows artists to offer their digital art to the market in a way that reflects the emotional value of their work.

[0767] An example of a prompt for a generative AI model is as follows: "Analyze the emotional impact of the following digital artwork and evaluate its market value. Based on the acquired data, generate the artwork as an NFT."

[0768] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0769] Step 1:

[0770] The server collects agent performance data, user feedback, and usage frequency in real time using data collection methods. This process stores data in a database and simultaneously analyzes the user's emotional state using an emotion analysis engine. Inputs include agent operational information and user voice and text data, while output is structured performance and emotion data.

[0771] Step 2:

[0772] The server uses a machine learning algorithm to evaluate the market value of agents based on the collected data. The algorithm processes the input data, performing feedback trend analysis and sentiment responsiveness analysis, and then quantifies the market value. The output is the evaluated market value.

[0773] Step 3:

[0774] The server generates NFTs (Non-Factor-Based Digital Assets) based on their assessed market value. The input is the assessed value; this is used to create an NFT structure, and associated ownership information is added. The output is the newly generated NFT.

[0775] Step 4:

[0776] The terminal presents NFTs generated through a marketplace to the user. The input is NFT data, which is visualized and presented on the interface to provide user interaction for transactions. The output is the NFT information actually viewed by the user.

[0777] Step 5:

[0778] Users purchase NFTs from agents through the marketplace and proceed with the transaction. Since the transaction may be completed based on user input, the output includes the transaction completion status and updated ownership information.

[0779] Step 6:

[0780] The server uses a management mechanism to update the NFT ownership information after the transaction is completed and records it on the blockchain. The input is the completed transaction information, and the ownership change is performed as a data calculation. The output is an immutable transaction record.

[0781] 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.

[0782] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0783] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0784] 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.

[0785] Figure 9 shows an 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.

[0786] 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.

[0787] 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.

[0788] 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, motorcycles, etc., 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, for example, based 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.

[0789] 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."

[0790] 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.

[0791] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0792] 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 of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0793] 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.

[0794] 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.

[0795] 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.

[0796] 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.

[0797] 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.

[0798] 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.

[0799] 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.

[0800] 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 the like 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.

[0801] 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.

[0802] The following is further disclosed regarding the embodiments described above.

[0803] (Claim 1)

[0804] Information gathering means for collecting agent performance data, user feedback, and usage frequency,

[0805] An evaluation means for evaluating the market value of an agent based on the data collected by the aforementioned collection means,

[0806] A generation means that generates digital assets including agent ownership information based on the market value evaluated by the evaluation means,

[0807] A marketplace mechanism that provides users with an interface to trade the generated digital assets,

[0808] A management method for updating ownership information through transactions,

[0809] A system that includes this.

[0810] (Claim 2)

[0811] The system according to claim 1, wherein the evaluation means quantifies the market value of the agent using a machine learning algorithm.

[0812] (Claim 3)

[0813] The system according to claim 1, wherein the management means uses blockchain technology to ensure the transparency and immutability of ownership information.

[0814] "Example 1"

[0815] (Claim 1)

[0816] The information processing device includes an information collection means for collecting performance information, user feedback, and usage frequency,

[0817] An evaluation means that calculates an evaluation value based on the information collected by the aforementioned information collection means,

[0818] A generation means that generates digital assets including identification information and ownership information based on the evaluation value calculated by the evaluation means,

[0819] A trading means that provides users with an interface that allows them to trade the generated digital assets,

[0820] A management method for updating ownership information through transactions,

[0821] A system that includes this.

[0822] (Claim 2)

[0823] The system according to claim 1, wherein the evaluation means calculates an evaluation value using machine learning.

[0824] (Claim 3)

[0825] The system according to claim 1, wherein the management means uses distributed ledger technology to ensure transparency and immutability of ownership information.

[0826] "Application Example 1"

[0827] (Claim 1)

[0828] Information gathering means for collecting agent performance data, user feedback, and usage frequency,

[0829] An evaluation means for evaluating the market value of an agent based on the data collected by the aforementioned collection means,

[0830] A generation means that generates digital assets including agent ownership information based on the market value evaluated by the evaluation means,

[0831] A trading method that provides users with an interactive interface that allows them to trade digital assets generated in a virtual space,

[0832] A means of updating ownership information through transactions and enabling the use of agents in the virtual space,

[0833] A system that includes this.

[0834] (Claim 2)

[0835] The system according to claim 1, wherein the evaluation means uses a machine learning algorithm to quantify the market value of an agent and evaluates its value based on its specific functions in a virtual environment.

[0836] (Claim 3)

[0837] The system according to claim 1, wherein the update means uses blockchain technology to ensure transparency and immutability of ownership information and maintains a transaction history in a virtual space.

[0838] "Example 2 of combining an emotion engine"

[0839] (Claim 1)

[0840] A means of comprehensively collecting agent performance information, user feedback, and usage trends,

[0841] An emotion analysis means for analyzing the user's emotional state based on the information collected by the aforementioned means,

[0842] A means for evaluating the market value of an agent by including the emotional information revealed by the aforementioned analysis means in the evaluation criteria,

[0843] A means for constructing a digital asset including agent characteristic information and ownership information based on the market value evaluated by the aforementioned evaluation means,

[0844] A means of supplying users with an exchangeable display means for the constructed digital assets,

[0845] A means of revising ownership information through exchange,

[0846] A system that includes this.

[0847] (Claim 2)

[0848] The system according to claim 1, wherein the evaluation means quantifies the market value of the agent using machine learning technology.

[0849] (Claim 3)

[0850] The system according to claim 1, wherein the revision means uses distributed ledger technology to ensure the visibility and immutability of ownership information.

[0851] "Application example 2 when combining with an emotional engine"

[0852] (Claim 1)

[0853] Information gathering means for collecting agent performance data, user feedback, and usage frequency,

[0854] An evaluation means for evaluating the market value of an agent based on the data collected by the aforementioned collection means,

[0855] A generation means that generates digital assets including agent ownership information based on the market value evaluated by the evaluation means,

[0856] A marketplace mechanism that provides users with an interface to trade the generated digital assets,

[0857] A management method for updating ownership information through transactions,

[0858] An emotion recognition means that analyzes the emotional state of the agent's users and collects emotional data,

[0859] Means for reflecting the emotional data analyzed by the aforementioned emotion recognition means in the evaluation,

[0860] A system that includes this.

[0861] (Claim 2)

[0862] The system according to claim 1, wherein the evaluation means uses a machine learning algorithm to quantify the market value of the agent.

[0863] (Claim 3)

[0864] The system according to claim 1, wherein the management means uses blockchain technology to ensure transparency and immutability of ownership information. [Explanation of Symbols]

[0865] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Information gathering means for collecting agent performance data, user feedback, and usage frequency, An evaluation means for evaluating the market value of an agent based on the data collected by the aforementioned collection means, A generation means that generates digital assets including agent ownership information based on the market value evaluated by the evaluation means, A trading method that provides users with an interactive interface that allows them to trade digital assets generated in a virtual space, A means of updating ownership information through transactions and enabling the use of agents in the virtual space, A system that includes this.

2. The system according to claim 1, wherein the evaluation means uses a machine learning algorithm to quantify the market value of the agent and evaluates the value based on its specific functions in a virtual environment.

3. The system according to claim 1, wherein the update means uses blockchain technology to ensure transparency and immutability of ownership information and maintains a transaction history in a virtual space.

Images