System

Abstract

A system is provided.SOLUTION: A system comprising: means for creating a product based on a request from a user using a generative artificial intelligence model; means for assigning unique identification information to the product and creating metadata; means for generating a non-fungible token based on the metadata; means for storing the product and the metadata in a digital storage; and means for registering the unique identification information and the metadata of the product in a blockchain.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Currently, there is a lack of trust and traceability in the content generated by generative AI models. Specifically, it is unclear which AI model was used to create the product, or the source of the training data used, which raises suspicions about the product and concerns about copyright infringement. Furthermore, because there is no transparency regarding who created the product, when it was created, or what process it went through, the authenticity of the product cannot be guaranteed, posing a risk of losing the trust of users and creators. This is a factor hindering the widespread use and convenience of generative AI models. [Means for solving the problem]

[0005] To solve the above-mentioned problems, the present invention provides the following means. In a system that uses a generative artificial intelligence model to create a product based on a user request, a means is provided for assigning a unique identification to the product and creating metadata. A means is also provided for generating a non-fungible token (NFT) based on this metadata, and the product and metadata are securely stored in digital storage. The product's unique identification and metadata are then registered on a blockchain, ensuring traceability of the product's history and creation process. Furthermore, a means is provided that enables users to obtain metadata from the blockchain based on the product's unique identification and check detailed product information. This improves the reliability and transparency of the product and promotes the use of generative artificial intelligence models.

[0006] A "generative artificial intelligence model" is an algorithm or program that generates new content (e.g., images, text, audio, etc.) based on data.

[0007] A "user" is an individual or organization that submits a request to generate content using a generative artificial intelligence model.

[0008] A "product" is new content created by a generative artificial intelligence model.

[0009] "Unique identifier" refers to a code or value that uniquely identifies a specific product, such as a universally unique identifier (UUID).

[0010] "Metadata" is data that adds information related to the product, including the name of the generating AI model, the date and time of generation, and information about the training data used.

[0011] A "non-fungible token (NFT)" is a digital asset that uses blockchain technology to attach unique identification and metadata to a product.

[0012] "Digital storage" is a storage device or system for storing data electronically.

[0013] "Blockchain" is a digital ledger technology that is distributed and stored across multiple nodes, and is a means of ensuring the consistency and immutability of data.

[0014] A "transaction" refers to the operation or process when registering or updating data in a blockchain. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] The present invention relates to a system that uses a generative artificial intelligence model to create a product based on a user request and ensures traceability of the product. This system creates a product using a generative artificial intelligence model, assigns a unique identifier to the product, adds metadata, and generates a non-fungible token (NFT). Furthermore, the system stores the product in digital storage based on the metadata, and registers the product's unique identifier and metadata on a blockchain, thereby ensuring traceability of the product's provenance and creation process.

[0037] Program processing overview

[0038] 1. Creation of the product

[0039] A user accesses a system that uses a generative AI model from their own device and requests the creation of a product. The request includes specific details about the type and content they want to generate. For example, a user might send a request to the system saying, "Please create an image of a scene where a cat and a dog are painting a picture."

[0040] The server receives this request and processes the request as input data into a specific generative artificial intelligence model (e.g., an image generation model). The model generates a new product (in this case, an image) based on the input data.

[0041] 2. Adding metadata to the generated data and converting it into an NFT

[0042] The server assigns a unique identifier to the generated image, such as a Universal Unique Identifier (UUID), to distinguish the specific creation from other creations.

[0043] The server then generates metadata containing this identification information, including important information related to the product, such as the name of the generative AI model that created it, the date and time of its creation, and the source of the training data used, allowing the product's provenance and authenticity to be verified.

[0044] The server uses this metadata to generate an NFT, a digital asset that uses blockchain technology to bind a unique identifier and metadata to the artifact.

[0045] 3. Saving the Creation and NFT

[0046] The generated images and their metadata (NFTs) will be stored in a secure digital storage server that will take appropriate security measures to protect the stored data from tampering and unauthorized access.

[0047] 4. Registering on the Blockchain

[0048] The server registers the product's unique identity and metadata on the blockchain, a distributed digital ledger that ensures data consistency and immutability, providing a permanent record of when and how the product was created, ensuring traceability.

[0049] 5. Confirmation of product use and traceability

[0050] When a user uses a product, the device references the blockchain based on the product's unique identification information. For example, when a user opens an image generated on their device, metadata is retrieved from the blockchain to confirm which AI model created the image and the training data used. This ensures the user that the product is authentic and trustworthy.

[0051] Examples:

[0052] 1. A user sends a request to the system: "Generate an image of a cat and a dog playing together."

[0053] 2. The server receives this request and uses a generative artificial intelligence model to generate the requested image.

[0054] 3. The server assigns a unique identifier in the form of a UUID to the generated image and creates metadata including the name of the generating AI model, the date and time of generation, etc.

[0055] 4. The server generates an NFT based on the metadata and stores the image and NFT in digital storage.

[0056] 5. The server registers the unique identifier and metadata on the blockchain.

[0057] 6. When a user views an image on their device, metadata is retrieved from the blockchain to confirm detailed information such as the image generation process and the training data used.

[0058] This allows us to ensure that the products are trustworthy and promotes the use of generative artificial intelligence models.

[0059] The processing flow will be explained below.

[0060] Step 1:

[0061] A user accesses a system that uses a generative AI model from their own device and requests the creation of a product. The request includes specific details about the type and content they want to generate. For example, a user might enter a request such as, "Please create an image of a cat and a dog playing together."

[0062] Step 2:

[0063] The terminal receives the user's request and sends it to the server, which conveys the request as data containing specific requirements for the product.

[0064] Step 3:

[0065] The server receives a user request and issues a command to a specified generative artificial intelligence model (e.g., an image generation model) to process the request content.

[0066] Step 4:

[0067] A generative AI model generates new content (in this case, an image) based on input data (user requests). The generation process is carried out by an internal algorithm, and the resulting product is obtained.

[0068] Step 5:

[0069] The server assigns a unique identifier (e.g., UUID) to the generated image, which is used to distinguish the creation from other creations.

[0070] Step 6:

[0071] The server generates metadata associated with the generated image, including the name of the generative artificial intelligence model that created it, the date and time of generation, and the source of the training data used.

[0072] Step 7:

[0073] The server generates a non-fungible token (NFT) based on the generated metadata. The NFT is created using blockchain technology and digitally links the artifact and its metadata.

[0074] Step 8:

[0075] The server then stores the generated image and its metadata (NFT) in digital storage, which is managed to protect the data from tampering and unauthorized access.

[0076] Step 9:

[0077] The server registers the unique identification information and metadata of the product on the blockchain, where the consistency and immutability of the registered information are guaranteed.

[0078] Step 10:

[0079] When a user uses a product (e.g., an image), the device uses the unique identifier embedded in the product to retrieve the associated metadata from the blockchain.

[0080] Step 11:

[0081] The device displays the acquired metadata to the user, allowing the user to check the details of the creation process and the data used, ensuring the reliability and transparency of the creation.

[0082] Example 1

[0083] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0084] When creating products using generative machine learning models, it is important to ensure the authenticity and reliability of the products and the traceability of the creation process. Furthermore, a system is needed that allows products to be uniquely identified and enables tracking of their provenance and the data used.

[0085] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0086] In this invention, the server includes means for creating a product based on a user request using a generative machine learning model, means for assigning unique identification information to the product and creating attribute information, means for generating an irreplaceable code based on the attribute information, means for storing the product and attribute information in an electronic storage location, and means for registering the product's unique identification information and attribute information in distributed ledger technology. This makes it possible to guarantee the authenticity and reliability of the product and ensure the traceability of the creation process.

[0087] A "generative machine learning model" is a machine learning model that aims to automatically generate new digital objects based on input data.

[0088] "User" refers to a person or end user who requests the creation of a Product using the System.

[0089] A "request" is a request made by a user to a generative machine learning model to create a product, and refers to a prompt statement that includes specific content and conditions.

[0090] "Product" refers to digital data generated by a generative machine learning model, and can take the form of images, audio, text, etc.

[0091] A "unique identifier" is a unique identifier given to a product to distinguish it from other products, often in the form of a UUID.

[0092] "Attribute information" is data that contains additional information about the product, such as the name of the generative machine learning model that created the product, the date and time of creation, and the source of the training data used.

[0093] A "non-fungible code" is a digital asset that links a product's unique identification and attribute information, and is an NFT created using blockchain technology.

[0094] "Electronic Repository" means a digital storage location for the secure preservation of the Product and the Non-Fungible Code, with appropriate security measures in place to protect against tampering and unauthorized access.

[0095] "Distributed ledger technology" is a decentralized network technology used to ensure the consistency and immutability of data, and blockchain is a prime example.

[0096] This invention relates to a system that uses a generative machine learning model to create products based on user requests, and generates non-fungible tokens (NFTs) by assigning unique identification and attribute information to the products. This system ensures the authenticity and traceability of the products, and provides transparency and reliability in the creation process.

[0097] The specific system configuration mainly includes the following hardware and software:

[0098] 1. Hardware:

[0099] Server: A high-performance computing server for running generative machine learning models.

[0100] Terminal: A personal computer or smartphone used by a user to access the system.

[0101] 2. Software:

[0102] Generative machine learning models: For example, image generation models (e.g., DALL-E) are used.

[0103] Digital storage: For example, cloud storage services such as Amazon S3.

[0104] Distributed ledger technology: For example, the Ethereum blockchain and smart contracts.

[0105] System operation procedure

[0106] 1. Submitting your request

[0107] Users access the web application from their own devices and enter the type and details of the content they want to generate as a prompt, such as "Please generate an image of a cat and a dog playing together."

[0108] 2. Server receives and processes the request

[0109] The server receives user requests and inputs them into a generative machine learning model. The server forwards the input data to the model, which generates a new product (in this case, an image) based on the prompt. The server then receives the generated image data.

[0110] 3. Assigning identification and attribute information

[0111] The server assigns a unique identifier (UUID) to the generated image, and then generates attribute information such as the name of the generative machine learning model that created the image, the date and time of generation, and the source of the training data used.

[0112] 4. NFT Generation

[0113] The server generates an NFT based on the provided identification and attribute information. An NFT is a digital asset that uniquely links a product and its attribute information using blockchain technology. Specifically, the server passes the attribute information to a smart contract and issues the NFT.

[0114] 5. Saving the Creation and NFT

[0115] The server stores the artifact and NFT in secure digital storage, for example using a cloud storage service such as Amazon S3, ensuring the data is protected from tampering and unauthorized access.

[0116] 6. Blockchain registration

[0117] The server registers the unique identification and attribute information of the product in a distributed ledger technology, for example, using Ethereum smart contracts, to ensure the consistency and immutability of the data.

[0118] 7. Use of products by users and confirmation of traceability

[0119] When a user uses a product, for example by opening an image generated on their device, the device references the distributed ledger technology using the product's unique identification information. The device obtains attribute information from the distributed ledger technology and displays detailed information such as the product's generation process and the training data used, thereby ensuring the product's authenticity and reliability.

[0120] For example, a user inputs a prompt such as "Please generate an image of a cat and a dog playing together" and clicks the submit button. This operation causes the server to process the received request and create a product, ensuring the traceability of the product throughout the process.

[0121] This allows us to ensure that the products are trustworthy and facilitates the use of generative machine learning models.

[0122] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0123] Processing Steps

[0124] Step 1: User submits request

[0125] A user accesses the system using a terminal and enters a prompt containing details of the content they want to generate. For example, they enter a specific prompt such as "Please generate an image of a cat and a dog playing together" and click the submit button. This sends the prompt to the server (input). The server receives this prompt (output).

[0126] Step 2: The server receives and processes the request

[0127] The server receives the prompt sent by the user. Next, the server passes this prompt as input data to a generative machine learning model (e.g., DALL-E) (input). The generative machine learning model generates a new image based on the prompt (data processing). The server retrieves the generated image data (output).

[0128] Step 3: Adding identification and attribute information to the product

[0129] The server generates a unique identifier (e.g., UUID) for the generated image and assigns it to the image (input). Next, it generates attribute information including the name of the model that created the product, the date and time of generation, and the source of the training data used (data calculation). This assigns the necessary attribute information to the product (output).

[0130] Step 4: Generate an NFT

[0131] The server generates an NFT based on the provided identification information and attribute information (input). Specifically, the server passes the attribute information to a smart contract and issues an NFT on the blockchain (data calculation). This operation generates an NFT linked to the product (output).

[0132] Step 5: Save the creation and NFT

[0133] The server stores the resulting image file and the generated NFT in secure digital storage (e.g., Amazon S3) (input). During this process, the server implements security measures such as encryption and access restrictions to protect the data from tampering and unauthorized access (data processing). The storage is then completed (output).

[0134] Step 6: Register on the blockchain

[0135] The server registers the unique identification information and attribute information of the product in a distributed ledger technology (e.g., Ethereum) (input). The server writes this information to the blockchain as a transaction, ensuring its immutability and transparency (data calculation). The information is registered in the blockchain (output).

[0136] Step 7: Verify user product usage and traceability

[0137] When a user uses the product on their device, for example by opening a generated image, the device references the distributed ledger technology based on the product's unique identification information (input). The device retrieves attribute information from the blockchain and displays detailed information about the image generation process and the training data used so that the user can check it (data calculation). This allows the user to confirm the authenticity and reliability of the product (output).

[0138] keyword

[0139] Generative AI model, prompt sentence

[0140] (Application example 1)

[0141] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0142] When generating content using generative AI models, there is a lack of adequate means to ensure the traceability and reliability of the results. In particular, it is not easy to verify the provenance of content generated by users. There is also a lack of means for users to easily check the metadata of the results. This raises doubts about the reliability of the results, making it difficult to expand the use of generative AI models.

[0143] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0144] In this invention, the server includes means for creating a product based on a user request using a generative artificial intelligence model, means for assigning unique identification information to the product and creating metadata, means for generating a non-fungible token based on the metadata, means for storing the product and metadata in digital storage, means for registering the product's unique identification information and metadata in a blockchain, and means for a user to individually request a product using the generative artificial intelligence model and for confirming the traceability of the product's metadata using a prompt statement. This makes it possible to confirm the creation process and history of the product, thereby improving the reliability of the product.

[0145] A "generative artificial intelligence model" is a type of artificial intelligence that has the ability to create new products based on requests from users.

[0146] A "user" is a user of a terminal who requests a product using a generative artificial intelligence model.

[0147] A "product" is content created by a generative artificial intelligence model based on a user request.

[0148] "Unique identification information" refers to a unique identifier given to a created product to distinguish it from other products.

[0149] "Metadata" is data that contains important information related to the product, such as the date and time of production and the name of the generative artificial intelligence model used.

[0150] A "non-fungible token (NFT)" is a digital asset that binds a product with unique identification and metadata and is generated using blockchain.

[0151] "Digital storage" is a digital data preservation method for the secure storage of artifacts and their metadata.

[0152] A "blockchain" is a distributed digital ledger that ensures data consistency and immutability and is used to record unique identifiers and metadata.

[0153] A "prompt sentence" is a document used when a user requests the creation of a product, and is used to specify the specific content of the product.

[0154] "Traceability" refers to the ability to trace and confirm the history and production process of a produced product.

[0155] The present invention relates to a system that uses a generative artificial intelligence model to create products based on user requests and ensures traceability of the products. This system assigns unique identification information and metadata to the products, and generates non-fungible tokens (NFTs) based on the metadata, enabling the product's provenance to be tracked.

[0156] The entire system consists of a user terminal and a server. The user terminal is made up of devices such as smartphones and head-mounted displays, and communicates with the server via an interface. The server includes a generative AI model, digital storage, a blockchain module, and a metadata generation unit.

[0157] 1. Program Generation

[0158] The server uses a generative artificial intelligence model to create a product based on a user request. For example, if a user sends a prompt such as "Please generate a virtual tour of a future city," the server receives the request and generates the virtual tour using the generative artificial intelligence model.

[0159] The generated virtual tour is given a unique identifier, and metadata including the date and time of creation, model name, etc. is created. An NFT is generated based on this metadata and securely stored in digital storage along with the product. Furthermore, the product's unique identifier and metadata are registered on the blockchain, ensuring the product's provenance and creation process.

[0160] 2. Natural language processing explanation

[0161] When a user requests a product using a terminal, the server receives the request and creates the product using a generative artificial intelligence model. This process includes the following data processing and data calculations:

[0162] Hardware used:

[0163] User device (smartphone, head-mounted display)

[0164] server

[0165] Software used:

[0166] Generative artificial intelligence model (AI model)

[0167] Blockchain Module

[0168] Digital Storage Module

[0169] Metadata Generation Unit

[0170] When a product is created, the server assigns it a unique identifier (e.g., UUID) and generates metadata, including the creation date and time, the name of the model used, and the request details. An NFT is generated based on this metadata and the product and stored in digital storage. Furthermore, the unique identifier and metadata are registered on the blockchain, ensuring the traceability of the product.

[0171] 3. Examples of concrete examples and prompts

[0172] As a concrete example, consider the case where a user sends a request using a smartphone saying, "Please generate a virtual tour of a futuristic city." The server that receives this request generates the virtual tour using a dedicated generative AI model, assigns a unique identifier and metadata to the result, converts it into an NFT, and stores it in digital storage. Finally, the unique identifier and metadata are registered on the blockchain, maintaining the traceability of the result.

[0173] Example prompt sentence:

[0174] "Generate a virtual tour of a futuristic city"

[0175] "Generate a virtual tour of the Egyptian pyramids"

[0176] As described above, by using the system of the present invention, it becomes easier to confirm the history and production process of a product, improving reliability.

[0177] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0178] Step 1:

[0179] A user uses a terminal to input a prompt and send a request. The input prompt might be, for example, "Please generate a virtual tour of a future city." The terminal then sends this prompt to the server. The input is the user's request, and the output is the prompt sent to the server.

[0180] Step 2:

[0181] The server receives a prompt from the user and uses a generative artificial intelligence model to create a product. The input is the prompt and the output is the generated product. In this process, the AI ​​model analyzes the prompt and generates corresponding content (such as a virtual tour).

[0182] Step 3:

[0183] The server assigns a unique identifier to the product. The input is the product, and the output is the product with the unique identifier. Specifically, it generates a Universally Unique Identifier (UUID) and associates it with the product.

[0184] Step 4:

[0185] The server creates metadata for the product, including the date and time of creation, the name of the generative AI model used, the request details, etc. The input is the product with a unique identifier, and the output is the product and metadata.

[0186] Step 5:

[0187] The server generates a non-fungible token (NFT) based on the metadata. The input is the product and metadata, and the output is the generated NFT. In this process, the NFT is generated based on the metadata using blockchain technology.

[0188] Step 6:

[0189] The server stores the product and NFT in digital storage. The input is the product and NFT, and the output is the data stored in digital storage. The server takes appropriate security measures to store the data safely.

[0190] Step 7:

[0191] The server registers the unique identifier and metadata of the artifact on the blockchain. The input is the unique identifier and metadata, and the output is the data registered on the blockchain. This immutably records the provenance of the artifact.

[0192] Step 8:

[0193] A user sends a request from a terminal to check the traceability of a product. The input is a unique identification, and the output is the product's metadata. The user retrieves the metadata from the blockchain through the terminal and checks the product's creation process and history.

[0194] As described above, the traceability and reliability of the product are ensured through each processing step. By going through this series of steps, the product desired by the user is expected to be properly managed and its reliability increased.

[0195] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0196] This invention relates to a system that uses a generative artificial intelligence model to create products based on user requests and ensures traceability of those products. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system ensures that the products match the user's emotional state. This system consistently performs everything from product creation to storage, ensuring traceability, and emotion-based optimization.

[0197] Program processing overview

[0198] 1. Product creation request and emotion recognition

[0199] A user accesses a system that uses a generative AI model from their own device and requests the creation of a product. The request includes specific details about the type and content they want to generate. For example, a user might request, "Please create an image of a cat and a dog playing together."

[0200] Upon receiving a user request, the device collects emotional information (e.g., facial expressions, voice, text) to capture the user's emotional state. This information is then analyzed by an emotion engine to identify the user's current emotional state.

[0201] 2. Creation of the product

[0202] The server receives the user's request and the emotion information from the emotion engine, and then commands the generative AI model to create a product based on that information. The generative AI model generates new content (in this case, an image) based on this input data. The content of the generated image is adjusted according to the user's emotional state.

[0203] 3. Adding metadata to the generated data and converting it into an NFT

[0204] The server assigns a unique identifier (e.g., UUID) to the generated image, which is used to distinguish the creation from other creations.

[0205] The server then generates metadata containing this identification information, including the name of the generative artificial intelligence model that created the product, the date and time of creation, the source of the training data used, and the user's recognized emotional state.

[0206] The server uses this metadata to generate a non-fungible token (NFT), a digital asset that uses blockchain technology to associate a unique identifier and metadata with the product.

[0207] 4. Saving the Creation and NFT

[0208] The generated images and their metadata (NFTs) will be stored in a secure digital storage server that will take appropriate security measures to protect the stored data from tampering and unauthorized access.

[0209] 5. Registering on the Blockchain

[0210] The server registers the product's unique identity and metadata on the blockchain, a distributed digital ledger that ensures data consistency and immutability, providing a permanent record of when and how the product was created, ensuring traceability.

[0211] 6. Confirmation of product use and traceability

[0212] When a user uses a product, the device retrieves relevant metadata from the blockchain using the unique identification information embedded in the product. For example, when a user opens an image generated on their device, metadata can be retrieved from the blockchain to confirm which AI model created the image, as well as the training data and emotional information used. This ensures the authenticity and reliability of the product to the user.

[0213] Examples:

[0214] 1. A user requests the system to "generate an image of a cat and a dog playing together." The emotion engine analyzes the user's facial expressions and voice and recognizes the "joy" state.

[0215] 2. The device sends the request and emotion information to the server.

[0216] 3. The server issues commands to the generative artificial intelligence model to generate an image based on the user's request and "joy" emotion information.

[0217] 4. The server assigns a unique identifier in the form of a UUID to the generated image and creates metadata including the name of the generating AI model, the date and time of generation, the training data used, and emotional information.

[0218] 5. The server generates an NFT based on the metadata and stores the image and NFT in digital storage.

[0219] 6. The server registers the unique identifier and metadata on the blockchain.

[0220] 7. When a user views an image on their device, metadata is retrieved from the blockchain to provide details about how the image was created, the data used, and emotional information.

[0221] This system ensures that the outputs of generative AI models are in line with the user's emotions, and also ensures the reliability and transparency of the outputs.

[0222] The processing flow will be explained below.

[0223] Step 1:

[0224] A user accesses a system that uses a generative AI model from their own device and requests the creation of a product. The request includes specific details about the type and content they want to generate. For example, a user might enter a request such as, "Please create an image of a cat and a dog playing together."

[0225] Step 2:

[0226] Upon receiving a user request, the device simultaneously collects the user's emotional information (facial expressions, voice, text input, etc.), which is later analyzed by the emotion engine.

[0227] Step 3:

[0228] The device sends the collected emotional information to the emotion engine, which analyzes the user's emotional state. The emotion engine determines the user's current emotional state (e.g., joy, surprise, sadness, etc.) from the collected data.

[0229] Step 4:

[0230] The terminal transmits the user's request content and the analyzed emotion information to the server.

[0231] Step 5:

[0232] The server receives the user's request and emotional information, and based on that, commands the generative artificial intelligence model to create a product (image).

[0233] Step 6:

[0234] The generative AI model processes the user's request and emotional information as input data and generates new content (images). This output is adapted to the user's emotional state.

[0235] Step 7:

[0236] The server assigns a unique identifier (e.g., UUID) to the generated image, which distinguishes the creation from other creations.

[0237] Step 8:

[0238] The server generates metadata containing this identification information, including the name of the generated AI model, the date and time of generation, information about the training data used, and emotional information.

[0239] Step 9:

[0240] The server generates a non-fungible token (NFT) based on the generated metadata. An NFT is a digital asset that uses blockchain technology to associate a unique identifier and metadata with the product.

[0241] Step 10:

[0242] The server then stores the generated image and its metadata (NFT) in secure digital storage, where the data is protected from tampering and unauthorized access.

[0243] Step 11:

[0244] The server registers the artifact's unique identity and metadata on the blockchain, a distributed digital ledger that ensures data consistency and immutability.

[0245] Step 12:

[0246] When a user uses a product (e.g., an image), the device references the blockchain using the unique identifier embedded in the product to retrieve the associated metadata.

[0247] Step 13:

[0248] The device displays the acquired metadata to the user, allowing the user to see details of the creation process, data used, and recognized emotion information, ensuring the reliability and transparency of the creation.

[0249] Example 2

[0250] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0251] Conventional systems lacked the ability to reflect the user's emotional state when creating products using generative artificial intelligence models. They also faced the challenge of making it difficult to ensure traceability to guarantee the reliability and transparency of products. Furthermore, there was a lack of a way to register and manage the uniqueness of products and their associated information on the blockchain. This meant that users could not verify the authenticity of products or the creation process, which could lead to anxiety. Furthermore, products often did not meet the user's expectations or emotions.

[0252] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0253] In this invention, the server includes means for creating a product based on a user request using a generative artificial intelligence model, means for recognizing the user's emotional state and reflecting that information in the product, means for assigning a unique identification to the product and creating metadata, means for generating a non-fungible token based on the metadata, means for storing the product and metadata in digital storage, and means for registering the product's unique identification and metadata in a blockchain. This enables a highly traceable system in which products are tailored to the user's emotions and their reliability and transparency are guaranteed.

[0254] A "generative artificial intelligence model" is an artificial intelligence algorithm that has the ability to generate new content based on user requests.

[0255] An "emotion engine" is a software or hardware system that recognizes a user's emotional state and analyzes that information.

[0256] "Unique identification information" is a unique identifier given to a product to distinguish it from other products.

[0257] "Metadata" is data that describes information related to a product, including the product's identification information, the date and time of its creation, the model and dataset used to create it, and the user's emotional information.

[0258] A "non-fungible token (NFT)" is a digital token that uses blockchain technology to associate a unique identifier and metadata with a digital asset.

[0259] "Digital storage" is a storage device or service that stores data in electronic form.

[0260] "Blockchain" is a distributed digital ledger technology that ensures data consistency and immutability.

[0261] "User emotion information" is data related to the user's emotional state recognized from facial expressions, voice, and text.

[0262] This invention relates to a system that combines a generative AI model with an emotion engine to create products based on user requests and ensure the traceability of the products. This system aims to increase the reliability and transparency of the products by adding a function that reflects user emotions to conventional generative AI models.

[0263] The creation of a product begins when a user accesses the system by entering a prompt from their own device. The prompt includes the type of content they want to generate and specific details. For example, they can enter a request such as "Please create an image of a cat and a dog playing together."

[0264] The device receives a request from the user and simultaneously collects emotional information using a camera or microphone to recognize the user's emotional state. The collected emotional information (facial expressions, voice, text, etc.) is analyzed by an emotion engine to identify the user's current emotional state. This emotional information and the request content are then sent to the server.

[0265] The server receives the user's request and emotion information from the emotion engine, and commands the generative AI model to create a product. The generative AI model generates new content based on this input data. In this case, the generative AI model generates an "image of a cat and a dog playing together," and adjusts the content to reflect the user's emotion (e.g., "joy").

[0266] The server assigns a unique identifier in the form of a UUID to each generated image. This identifier is used to distinguish the generated image from other generated images. The server then generates metadata, including the identifier, the name of the generating AI model, the generation date and time, the training data source used, and the user's emotional information. Based on this metadata, the server generates a non-fungible token (NFT) and stores the generated image and the NFT in secure digital storage.

[0267] Additionally, the product's unique identity and metadata are registered on the blockchain, a distributed digital ledger that ensures data consistency and immutability, creating a permanent record of when and how the product was created.

[0268] When a user uses a product, the device retrieves relevant metadata from the blockchain using the unique identification information embedded in the product. For example, when a user views an image generated on their device, the device will display which generative AI model created the image, as well as the training data and emotional information used. This ensures the user that the product is authentic and trustworthy.

[0269] As a specific example, if a user requests, "Please generate an image of a cat and a dog playing together," the emotion engine analyzes the user's facial expressions and voice to recognize a "joy" state. The device then sends the request and emotional information to the server, which then issues commands to the generative AI model to generate an image based on the user's request and the "joy" emotional information. The generated image is then given a unique identifier in the form of a UUID, and metadata is created, including the name of the generating AI model, the date and time of generation, the training data used, and the emotional information. Finally, the generated image and NFT are stored in digital storage, and the unique identifier and metadata are registered on the blockchain, ensuring the authenticity and reliability of the image when the user views it on their device.

[0270] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0271] Step 1:

[0272] The user requests the creation of a product by entering a prompt sentence. The user enters "Please create an image of a cat and a dog playing together" into the input screen of the terminal and clicks the send button. As input, the prompt sentence is given to the terminal. The output is that the prompt sentence is sent to the terminal.

[0273] Step 2:

[0274] The device collects the user's emotional information. The device activates the camera and microphone to collect the user's facial expressions and voice. The emotion engine analyzes this data and identifies the user's emotional state. The user's facial expressions and voice data are provided to the device as input. The emotion engine analyzes this data and identifies the user's emotional state as "joy." The output is the identified emotional information.

[0275] Step 3:

[0276] The terminal sends a prompt sentence and emotional information to the server. As input, the terminal receives the prompt sentence and emotional information. The terminal incorporates this information into a packet and sends it to the server. The output is the request data and emotional information sent to the server.

[0277] Step 4:

[0278] The server receives the request content and emotional information. The server receives and analyzes the data sent from the terminal via the network protocol. The input is the prompt text and emotional information received by the server. The output is the analyzed request content and emotional information.

[0279] Step 5:

[0280] The server issues commands to the generative AI model to create a product. The server calls the generative AI model to create new content based on the received prompt and emotion information. The generative AI model uses this input data to generate a new image. The prompt and emotion information are given to the generative AI model as input. The output is the generated image.

[0281] Step 6:

[0282] The server assigns a unique identifier to the generated image. The server assigns an identifier in the form of a UUID to the generated image. The generated image is given to the server as input. The output is an image with a UUID assigned.

[0283] Step 7:

[0284] The server creates the metadata, which includes a unique identifier, the name of the generating AI model, the generation date and time, the training data used, and the user's emotional information. As input, the server is given an image with a UUID and information about its generation. The output is the generated metadata.

[0285] Step 8:

[0286] The server generates an NFT based on the metadata. The server uses the generated metadata to issue a non-fungible token (NFT) on the blockchain. The metadata is given to the server as input. The output is the generated NFT.

[0287] Step 9:

[0288] The server stores the generated images and metadata in digital storage. The server stores the generated images and metadata in secure digital storage. The generated images and metadata are given to the server as input. The output is the securely stored data.

[0289] Step 10:

[0290] The server registers the unique identifier and metadata on the blockchain. The server registers this information on the blockchain network to ensure traceability. As input, the server is given the unique identifier and metadata. The output is the data registered on the blockchain.

[0291] Step 11:

[0292] When a user uses a product, the device retrieves the metadata from the blockchain. When a user tries to view an image generated on the device, the device retrieves the metadata from the blockchain using a unique identifier. As input, the device is given the image's unique identifier. The output is the retrieved metadata.

[0293] Step 12:

[0294] The terminal displays the acquired metadata to the user. The terminal displays the acquired metadata on the screen, allowing the user to check the details of the creation process of the product, the data used, and the emotional information. The acquired metadata is given to the terminal as input. The output is the metadata displayed to the user.

[0295] (Application example 2)

[0296] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0297] Conventional product creation systems using generative AI models have issues such as insufficient means for ensuring the reliability and traceability of products, and lack of personalization that takes into account the user's emotional state toward the product. Furthermore, there are no systems in physical stores that can suggest products based on customer emotions, making it difficult to accurately grasp customer needs.

[0298] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0299] In this invention, the server includes a means for creating a product based on a user request using a generative artificial intelligence model, a means for assigning unique identification information to the product and creating metadata, and a means for adjusting the content of the product using an emotion engine so that the product matches the user's emotional state. This enables personalization based on the user's emotions while ensuring the reliability and traceability of the product. Furthermore, optimal product suggestions based on customer emotional information can be made in physical stores, improving the shopping experience.

[0300] A "generative artificial intelligence model" is an artificial intelligence software model that generates new content based on user requests.

[0301] A "product" is content, such as digital data such as images or text, created by a generative artificial intelligence model based on a user request.

[0302] "Unique identification information" means a unique identifier, such as a UUID (Universal Unique Identifier), assigned to a product to distinguish it from other products.

[0303] "Metadata" is data that describes information about a product, including the date and time the product was created, the learning data used, and the user's emotional information.

[0304] A "non-fungible token" is a digital asset that is associated with a product using blockchain technology and proves that the product is unique.

[0305] "Digital storage" is a storage device for electronically storing artifacts and metadata.

[0306] A "blockchain" is a distributed digital ledger that ensures the consistency and immutability of data.

[0307] An "emotion engine" is a software engine that recognizes a user's emotional state from their voice, facial expression, text, etc.

[0308] "Emotion information" is data relating to the user's emotional state acquired and analyzed by the emotion engine.

[0309] A "user" is an entity that utilizes the system to request the creation of a product.

[0310] "Brick and mortar store" refers to a physically existing retail store or commercial space, as opposed to an online store.

[0311] This invention relates to a system that uses a generative artificial intelligence model and an emotion engine to create products based on user requests and emotion information, and ensures the reliability and traceability of the products. In particular, this paper describes an "emotion-aware shopping assistant" that aims to improve the shopping experience in brick-and-mortar stores.

[0312] Program Overview

[0313] Hardware:

[0314] Smartphone

[0315] Smart Glasses

[0316] robot

[0317] software:

[0318] Generative AI model

[0319] Emotion Engine

[0320] Blockchain technology

[0321] Program processing flow

[0322] 1. User Emotion Recognition

[0323] The device (smartphone or smart glasses) captures the user's facial expressions through a camera, and the emotion engine analyzes them to recognize the user's emotional state. Voice input is also accepted, and the emotional state is analyzed from the voice data.

[0324] 2. Content Generation Request

[0325] The user can input the category of product they are looking for and their specific preferences through the terminal. They can also make requests by voice. For example, they can make a request such as, "Please suggest products that will help me relax."

[0326] 3. Creating generated content

[0327] The server instructs the generative AI model to create a product based on the user's request and the emotion information obtained from the emotion engine. The generative AI model then uses this information to generate the optimal product or content for the user.

[0328] 4. Adding traceability information

[0329] Each generated product is assigned a unique identification (UUID format), and metadata is created that includes the date and time of creation, usage data, emotional information, etc. This ensures the traceability of the product.

[0330] 5. NFT and storage

[0331] The server generates a non-fungible token (NFT) based on the generated metadata and stores the generated token and metadata in a secure digital storage. The generated token and metadata are registered on the blockchain, ensuring the consistency and immutability of the data.

[0332] 6. Presentation to the User

[0333] The terminal obtains metadata from the blockchain based on the product's unique identification information, and displays the product's traceability information to the user when proposing a product, allowing them to confirm its authenticity.

[0334] Specific examples

[0335] For example, if a user is tired and requests relaxation products in a physical store, the following prompt sentence is input to the generative AI model:

[0336] "Please suggest some relaxation products for tired users."

[0337] The generative AI model suggests relaxing aroma oils and massage devices, and displays traceability information such as the manufacturer and usage instructions. In this way, the present invention enables personalization based on the user's emotions, improving the shopping experience in physical stores.

[0338] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0339] Step 1:

[0340] emotion recognition

[0341] The device (smartphone or smart glasses) uses a camera to capture the user's facial expressions and also accepts voice input. This data is passed to an emotion engine, which analyzes the user's emotional state from their facial expressions and voice. Specifically, the emotion engine analyzes facial features and voice tones to identify emotions such as joy, sadness, fatigue, and excitement.

[0342] Input: User's facial expression data, voice data

[0343] Output: User's emotional information (happiness, sadness, fatigue, etc.)

[0344] Step 2:

[0345] Content Generation Request

[0346] The user operates the device and requests the desired product category and specific preferences through text input or voice input. For example, they might input, "Please suggest products that will help me relax." The device receives this request and sends it to the server.

[0347] Input: User request (text or voice)

[0348] Output: User request data

[0349] Step 3:

[0350] Creating generated content

[0351] The server receives the user's request data and the emotion information obtained from the emotion engine, and based on that, instructs the generative AI model to create a product. The generative AI model generates optimal products and content based on the prompt. For example, if the user is tired, it will suggest products with a relaxing effect.

[0352] Input: User request data, emotion information

[0353] Output: Generated content

[0354] Step 4:

[0355] Adding traceability information

[0356] The server assigns a unique identifier (UUID format) to the generated artifact and creates metadata including the creation date and time, usage data, emotional information, etc. This allows the authenticity and history of the artifact to be verified later.

[0357] Input: Generated content

[0358] Output: Unique identifier, metadata

[0359] Step 5:

[0360] NFT and storage

[0361] The server generates a non-fungible token (NFT) based on the generated metadata, then stores the generated token and metadata in secure digital storage, which protects the data from tampering and unauthorized access.

[0362] Input: Metadata

[0363] Output: NFT, stored artifact and metadata

[0364] Step 6:

[0365] Blockchain Registration

[0366] The server registers the unique identity and metadata of the artifact in the blockchain, which ensures the traceability and immutability of the artifact.

[0367] Input: Unique identifier, metadata

[0368] Output: Information registered on the blockchain

[0369] Step 7:

[0370] Presenting to the user

[0371] The terminal retrieves metadata from the blockchain based on the product's unique identification information and displays the product's traceability information to the user when proposing a product, allowing the user to confirm the authenticity of the proposed product.

[0372] Input: Unique Identifier

[0373] Output: Presentation of the product including traceability information

[0374] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0375] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0376] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0377] [Second embodiment]

[0378] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0379] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0380] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0381] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0382] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0383] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0384] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0385] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0386] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0387] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0388] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0389] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0390] The present invention relates to a system that uses a generative artificial intelligence model to create a product based on a user request and ensures traceability of the product. This system creates a product using a generative artificial intelligence model, assigns a unique identifier to the product, adds metadata, and generates a non-fungible token (NFT). Furthermore, the system stores the product in digital storage based on the metadata, and registers the product's unique identifier and metadata on a blockchain, thereby ensuring traceability of the product's provenance and creation process.

[0391] Program processing overview

[0392] 1. Creation of the product

[0393] A user accesses a system that uses a generative AI model from their own device and requests the creation of a product. The request includes specific details about the type and content they want to generate. For example, a user might send a request to the system saying, "Please create an image of a scene where a cat and a dog are painting a picture."

[0394] The server receives this request and processes the request as input data into a specific generative artificial intelligence model (e.g., an image generation model). The model generates a new product (in this case, an image) based on the input data.

[0395] 2. Adding metadata to the generated data and converting it into an NFT

[0396] The server assigns a unique identifier to the generated image, such as a Universal Unique Identifier (UUID), to distinguish the specific creation from other creations.

[0397] The server then generates metadata containing this identification information, including important information related to the product, such as the name of the generative AI model that created it, the date and time of its creation, and the source of the training data used, allowing the product's provenance and authenticity to be verified.

[0398] The server uses this metadata to generate an NFT, a digital asset that uses blockchain technology to bind a unique identifier and metadata to the artifact.

[0399] 3. Saving the Creation and NFT

[0400] The generated images and their metadata (NFTs) will be stored in a secure digital storage server that will take appropriate security measures to protect the stored data from tampering and unauthorized access.

[0401] 4. Registering on the Blockchain

[0402] The server registers the product's unique identity and metadata on the blockchain, a distributed digital ledger that ensures data consistency and immutability, providing a permanent record of when and how the product was created, ensuring traceability.

[0403] 5. Confirmation of product use and traceability

[0404] When a user uses a product, the device references the blockchain based on the product's unique identification information. For example, when a user opens an image generated on their device, metadata is retrieved from the blockchain to confirm which AI model created the image and the training data used. This ensures the user that the product is authentic and trustworthy.

[0405] Examples:

[0406] 1. A user sends a request to the system: "Generate an image of a cat and a dog playing together."

[0407] 2. The server receives this request and uses a generative artificial intelligence model to generate the requested image.

[0408] 3. The server assigns a unique identifier in the form of a UUID to the generated image and creates metadata including the name of the generating AI model, the date and time of generation, etc.

[0409] 4. The server generates an NFT based on the metadata and stores the image and NFT in digital storage.

[0410] 5. The server registers the unique identifier and metadata on the blockchain.

[0411] 6. When a user views an image on their device, metadata is retrieved from the blockchain to confirm detailed information such as the image generation process and the training data used.

[0412] This allows us to ensure that the products are trustworthy and promotes the use of generative artificial intelligence models.

[0413] The processing flow will be explained below.

[0414] Step 1:

[0415] A user accesses a system that uses a generative AI model from their own device and requests the creation of a product. The request includes specific details about the type and content they want to generate. For example, a user might enter a request such as, "Please create an image of a cat and a dog playing together."

[0416] Step 2:

[0417] The terminal receives the user's request and sends it to the server, which conveys the request as data containing specific requirements for the product.

[0418] Step 3:

[0419] The server receives a user request and issues a command to a specified generative artificial intelligence model (e.g., an image generation model) to process the request content.

[0420] Step 4:

[0421] A generative AI model generates new content (in this case, an image) based on input data (user requests). The generation process is carried out by an internal algorithm, and the resulting product is obtained.

[0422] Step 5:

[0423] The server assigns a unique identifier (e.g., UUID) to the generated image, which is used to distinguish the creation from other creations.

[0424] Step 6:

[0425] The server generates metadata associated with the generated image, including the name of the generative artificial intelligence model that created it, the date and time of generation, and the source of the training data used.

[0426] Step 7:

[0427] The server generates a non-fungible token (NFT) based on the generated metadata. The NFT is created using blockchain technology and digitally links the artifact and its metadata.

[0428] Step 8:

[0429] The server then stores the generated image and its metadata (NFT) in digital storage, which is managed to protect the data from tampering and unauthorized access.

[0430] Step 9:

[0431] The server registers the unique identification information and metadata of the product on the blockchain, where the consistency and immutability of the registered information are guaranteed.

[0432] Step 10:

[0433] When a user uses a product (e.g., an image), the device uses the unique identifier embedded in the product to retrieve the associated metadata from the blockchain.

[0434] Step 11:

[0435] The device displays the acquired metadata to the user, allowing the user to check the details of the creation process and the data used, ensuring the reliability and transparency of the creation.

[0436] Example 1

[0437] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0438] When creating products using generative machine learning models, it is important to ensure the authenticity and reliability of the products and the traceability of the creation process. Furthermore, a system is needed that allows products to be uniquely identified and enables tracking of their provenance and the data used.

[0439] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0440] In this invention, the server includes means for creating a product based on a user request using a generative machine learning model, means for assigning unique identification information to the product and creating attribute information, means for generating an irreplaceable code based on the attribute information, means for storing the product and attribute information in an electronic storage location, and means for registering the product's unique identification information and attribute information in distributed ledger technology. This makes it possible to guarantee the authenticity and reliability of the product and ensure the traceability of the creation process.

[0441] A "generative machine learning model" is a machine learning model that aims to automatically generate new digital objects based on input data.

[0442] "User" refers to a person or end user who requests the creation of a Product using the System.

[0443] A "request" is a request made by a user to a generative machine learning model to create a product, and refers to a prompt statement that includes specific content and conditions.

[0444] "Product" refers to digital data generated by a generative machine learning model, and can take the form of images, audio, text, etc.

[0445] A "unique identifier" is a unique identifier given to a product to distinguish it from other products, often in the form of a UUID.

[0446] "Attribute information" is data that contains additional information about the product, such as the name of the generative machine learning model that created the product, the date and time of creation, and the source of the training data used.

[0447] A "non-fungible code" is a digital asset that links a product's unique identification and attribute information, and is an NFT created using blockchain technology.

[0448] "Electronic Repository" means a digital storage location for the secure preservation of the Product and the Non-Fungible Code, with appropriate security measures in place to protect against tampering and unauthorized access.

[0449] "Distributed ledger technology" is a decentralized network technology used to ensure the consistency and immutability of data, and blockchain is a prime example.

[0450] This invention relates to a system that uses a generative machine learning model to create products based on user requests, and generates non-fungible tokens (NFTs) by assigning unique identification and attribute information to the products. This system ensures the authenticity and traceability of the products, and provides transparency and reliability in the creation process.

[0451] The specific system configuration mainly includes the following hardware and software:

[0452] 1. Hardware:

[0453] Server: A high-performance computing server for running generative machine learning models.

[0454] Terminal: A personal computer or smartphone used by a user to access the system.

[0455] 2. Software:

[0456] Generative machine learning models: For example, image generation models (e.g., DALL-E) are used.

[0457] Digital storage: For example, cloud storage services such as Amazon S3.

[0458] Distributed ledger technology: For example, the Ethereum blockchain and smart contracts.

[0459] System operation procedure

[0460] 1. Submitting your request

[0461] Users access the web application from their own devices and enter the type and details of the content they want to generate as a prompt, such as "Please generate an image of a cat and a dog playing together."

[0462] 2. Server receives and processes the request

[0463] The server receives user requests and inputs them into a generative machine learning model. The server forwards the input data to the model, which generates a new product (in this case, an image) based on the prompt. The server then receives the generated image data.

[0464] 3. Assigning identification and attribute information

[0465] The server assigns a unique identifier (UUID) to the generated image, and then generates attribute information such as the name of the generative machine learning model that created the image, the date and time of generation, and the source of the training data used.

[0466] 4. NFT Generation

[0467] The server generates an NFT based on the provided identification and attribute information. An NFT is a digital asset that uniquely links a product and its attribute information using blockchain technology. Specifically, the server passes the attribute information to a smart contract and issues the NFT.

[0468] 5. Saving the Creation and NFT

[0469] The server stores the artifact and NFT in secure digital storage, for example using a cloud storage service such as Amazon S3, ensuring the data is protected from tampering and unauthorized access.

[0470] 6. Blockchain registration

[0471] The server registers the unique identification and attribute information of the product in a distributed ledger technology, for example, using Ethereum smart contracts, to ensure the consistency and immutability of the data.

[0472] 7. Use of products by users and confirmation of traceability

[0473] When a user uses a product, for example by opening an image generated on their device, the device references the distributed ledger technology using the product's unique identification information. The device obtains attribute information from the distributed ledger technology and displays detailed information such as the product's generation process and the training data used, thereby ensuring the product's authenticity and reliability.

[0474] For example, a user inputs a prompt such as "Please generate an image of a cat and a dog playing together" and clicks the submit button. This operation causes the server to process the received request and create a product, ensuring the traceability of the product throughout the process.

[0475] This allows us to ensure that the products are trustworthy and facilitates the use of generative machine learning models.

[0476] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0477] Processing Steps

[0478] Step 1: User submits request

[0479] A user accesses the system using a terminal and enters a prompt containing details of the content they want to generate. For example, they enter a specific prompt such as "Please generate an image of a cat and a dog playing together" and click the submit button. This sends the prompt to the server (input). The server receives this prompt (output).

[0480] Step 2: The server receives and processes the request

[0481] The server receives the prompt sent by the user. Next, the server passes this prompt as input data to a generative machine learning model (e.g., DALL-E) (input). The generative machine learning model generates a new image based on the prompt (data processing). The server retrieves the generated image data (output).

[0482] Step 3: Adding identification and attribute information to the product

[0483] The server generates a unique identifier (e.g., UUID) for the generated image and assigns it to the image (input). Next, it generates attribute information including the name of the model that created the product, the date and time of generation, and the source of the training data used (data calculation). This assigns the necessary attribute information to the product (output).

[0484] Step 4: Generate an NFT

[0485] The server generates an NFT based on the provided identification information and attribute information (input). Specifically, the server passes the attribute information to a smart contract and issues an NFT on the blockchain (data calculation). This operation generates an NFT linked to the product (output).

[0486] Step 5: Save the creation and NFT

[0487] The server stores the resulting image file and the generated NFT in secure digital storage (e.g., Amazon S3) (input). During this process, the server implements security measures such as encryption and access restrictions to protect the data from tampering and unauthorized access (data processing). The storage is then completed (output).

[0488] Step 6: Register on the blockchain

[0489] The server registers the unique identification information and attribute information of the product in a distributed ledger technology (e.g., Ethereum) (input). The server writes this information to the blockchain as a transaction, ensuring its immutability and transparency (data calculation). The information is registered in the blockchain (output).

[0490] Step 7: Verify user product usage and traceability

[0491] When a user uses the product on their device, for example by opening a generated image, the device references the distributed ledger technology based on the product's unique identification information (input). The device retrieves attribute information from the blockchain and displays detailed information about the image generation process and the training data used so that the user can check it (data calculation). This allows the user to confirm the authenticity and reliability of the product (output).

[0492] keyword

[0493] Generative AI model, prompt sentence

[0494] (Application example 1)

[0495] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0496] When generating content using generative AI models, there is a lack of adequate means to ensure the traceability and reliability of the results. In particular, it is not easy to verify the provenance of content generated by users. There is also a lack of means for users to easily check the metadata of the results. This raises doubts about the reliability of the results, making it difficult to expand the use of generative AI models.

[0497] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0498] In this invention, the server includes means for creating a product based on a user request using a generative artificial intelligence model, means for assigning unique identification information to the product and creating metadata, means for generating a non-fungible token based on the metadata, means for storing the product and metadata in digital storage, means for registering the product's unique identification information and metadata in a blockchain, and means for a user to individually request a product using the generative artificial intelligence model and for confirming the traceability of the product's metadata using a prompt statement. This makes it possible to confirm the creation process and history of the product, thereby improving the reliability of the product.

[0499] A "generative artificial intelligence model" is a type of artificial intelligence that has the ability to create new products based on requests from users.

[0500] A "user" is a user of a terminal who requests a product using a generative artificial intelligence model.

[0501] A "product" is content created by a generative artificial intelligence model based on a user request.

[0502] "Unique identification information" refers to a unique identifier given to a created product to distinguish it from other products.

[0503] "Metadata" is data that contains important information related to the product, such as the date and time of production and the name of the generative artificial intelligence model used.

[0504] A "non-fungible token (NFT)" is a digital asset that binds a product with unique identification and metadata and is generated using blockchain.

[0505] "Digital storage" is a digital data preservation method for the secure storage of artifacts and their metadata.

[0506] A "blockchain" is a distributed digital ledger that ensures data consistency and immutability and is used to record unique identifiers and metadata.

[0507] A "prompt sentence" is a document used when a user requests the creation of a product, and is used to specify the specific content of the product.

[0508] "Traceability" refers to the ability to trace and confirm the history and production process of a produced product.

[0509] The present invention relates to a system that uses a generative artificial intelligence model to create products based on user requests and ensures traceability of the products. This system assigns unique identification information and metadata to the products, and generates non-fungible tokens (NFTs) based on the metadata, enabling the product's provenance to be tracked.

[0510] The entire system consists of a user terminal and a server. The user terminal is made up of devices such as smartphones and head-mounted displays, and communicates with the server via an interface. The server includes a generative AI model, digital storage, a blockchain module, and a metadata generation unit.

[0511] 1. Program Generation

[0512] The server uses a generative artificial intelligence model to create a product based on a user request. For example, if a user sends a prompt such as "Please generate a virtual tour of a future city," the server receives the request and generates the virtual tour using the generative artificial intelligence model.

[0513] The generated virtual tour is given a unique identifier, and metadata including the date and time of creation, model name, etc. is created. An NFT is generated based on this metadata and securely stored in digital storage along with the product. Furthermore, the product's unique identifier and metadata are registered on the blockchain, ensuring the product's provenance and creation process.

[0514] 2. Natural language processing explanation

[0515] When a user requests a product using a terminal, the server receives the request and creates the product using a generative artificial intelligence model. This process includes the following data processing and data calculations:

[0516] Hardware used:

[0517] User device (smartphone, head-mounted display)

[0518] server

[0519] Software used:

[0520] Generative artificial intelligence model (AI model)

[0521] Blockchain Module

[0522] Digital Storage Module

[0523] Metadata Generation Unit

[0524] When a product is created, the server assigns it a unique identifier (e.g., UUID) and generates metadata, including the creation date and time, the name of the model used, and the request details. An NFT is generated based on this metadata and the product and stored in digital storage. Furthermore, the unique identifier and metadata are registered on the blockchain, ensuring the traceability of the product.

[0525] 3. Examples of concrete examples and prompts

[0526] As a concrete example, consider the case where a user sends a request using a smartphone saying, "Please generate a virtual tour of a futuristic city." The server that receives this request generates the virtual tour using a dedicated generative AI model, assigns a unique identifier and metadata to the result, converts it into an NFT, and stores it in digital storage. Finally, the unique identifier and metadata are registered on the blockchain, maintaining the traceability of the result.

[0527] Example prompt sentence:

[0528] "Generate a virtual tour of a futuristic city"

[0529] "Generate a virtual tour of the Egyptian pyramids"

[0530] As described above, by using the system of the present invention, it becomes easier to confirm the history and production process of a product, improving reliability.

[0531] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0532] Step 1:

[0533] A user uses a terminal to input a prompt and send a request. The input prompt might be, for example, "Please generate a virtual tour of a future city." The terminal then sends this prompt to the server. The input is the user's request, and the output is the prompt sent to the server.

[0534] Step 2:

[0535] The server receives a prompt from the user and uses a generative artificial intelligence model to create a product. The input is the prompt and the output is the generated product. In this process, the AI ​​model analyzes the prompt and generates corresponding content (such as a virtual tour).

[0536] Step 3:

[0537] The server assigns a unique identifier to the product. The input is the product, and the output is the product with the unique identifier. Specifically, it generates a Universally Unique Identifier (UUID) and associates it with the product.

[0538] Step 4:

[0539] The server creates metadata for the product, including the date and time of creation, the name of the generative AI model used, the request details, etc. The input is the product with a unique identifier, and the output is the product and metadata.

[0540] Step 5:

[0541] The server generates a non-fungible token (NFT) based on the metadata. The input is the product and metadata, and the output is the generated NFT. In this process, the NFT is generated based on the metadata using blockchain technology.

[0542] Step 6:

[0543] The server stores the product and NFT in digital storage. The input is the product and NFT, and the output is the data stored in digital storage. The server takes appropriate security measures to store the data safely.

[0544] Step 7:

[0545] The server registers the unique identifier and metadata of the artifact on the blockchain. The input is the unique identifier and metadata, and the output is the data registered on the blockchain. This immutably records the provenance of the artifact.

[0546] Step 8:

[0547] A user sends a request from a terminal to check the traceability of a product. The input is a unique identification, and the output is the product's metadata. The user retrieves the metadata from the blockchain through the terminal and checks the product's creation process and history.

[0548] As described above, the traceability and reliability of the product are ensured through each processing step. By going through this series of steps, the product desired by the user is expected to be properly managed and its reliability increased.

[0549] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0550] This invention relates to a system that uses a generative artificial intelligence model to create products based on user requests and ensures traceability of those products. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system ensures that the products match the user's emotional state. This system consistently performs everything from product creation to storage, ensuring traceability, and emotion-based optimization.

[0551] Program processing overview

[0552] 1. Product creation request and emotion recognition

[0553] A user accesses a system that uses a generative AI model from their own device and requests the creation of a product. The request includes specific details about the type and content they want to generate. For example, a user might request, "Please create an image of a cat and a dog playing together."

[0554] Upon receiving a user request, the device collects emotional information (e.g., facial expressions, voice, text) to capture the user's emotional state. This information is then analyzed by an emotion engine to identify the user's current emotional state.

[0555] 2. Creation of the product

[0556] The server receives the user's request and the emotion information from the emotion engine, and then commands the generative AI model to create a product based on that information. The generative AI model generates new content (in this case, an image) based on this input data. The content of the generated image is adjusted according to the user's emotional state.

[0557] 3. Adding metadata to the generated data and converting it into an NFT

[0558] The server assigns a unique identifier (e.g., UUID) to the generated image, which is used to distinguish the creation from other creations.

[0559] The server then generates metadata containing this identification information, including the name of the generative artificial intelligence model that created the product, the date and time of creation, the source of the training data used, and the user's recognized emotional state.

[0560] The server uses this metadata to generate a non-fungible token (NFT), a digital asset that uses blockchain technology to associate a unique identifier and metadata with the product.

[0561] 4. Saving the Creation and NFT

[0562] The generated images and their metadata (NFTs) will be stored in a secure digital storage server that will take appropriate security measures to protect the stored data from tampering and unauthorized access.

[0563] 5. Registering on the Blockchain

[0564] The server registers the product's unique identity and metadata on the blockchain, a distributed digital ledger that ensures data consistency and immutability, providing a permanent record of when and how the product was created, ensuring traceability.

[0565] 6. Confirmation of product use and traceability

[0566] When a user uses a product, the device retrieves relevant metadata from the blockchain using the unique identification information embedded in the product. For example, when a user opens an image generated on their device, metadata can be retrieved from the blockchain to confirm which AI model created the image, as well as the training data and emotional information used. This ensures the authenticity and reliability of the product to the user.

[0567] Examples:

[0568] 1. A user requests the system to "generate an image of a cat and a dog playing together." The emotion engine analyzes the user's facial expressions and voice and recognizes the "joy" state.

[0569] 2. The device sends the request and emotion information to the server.

[0570] 3. The server issues commands to the generative artificial intelligence model to generate an image based on the user's request and "joy" emotion information.

[0571] 4. The server assigns a unique identifier in the form of a UUID to the generated image and creates metadata including the name of the generating AI model, the date and time of generation, the training data used, and emotional information.

[0572] 5. The server generates an NFT based on the metadata and stores the image and NFT in digital storage.

[0573] 6. The server registers the unique identifier and metadata on the blockchain.

[0574] 7. When a user views an image on their device, metadata is retrieved from the blockchain to provide details about how the image was created, the data used, and emotional information.

[0575] This system ensures that the outputs of generative AI models are in line with the user's emotions, and also ensures the reliability and transparency of the outputs.

[0576] The processing flow will be explained below.

[0577] Step 1:

[0578] A user accesses a system that uses a generative AI model from their own device and requests the creation of a product. The request includes specific details about the type and content they want to generate. For example, a user might enter a request such as, "Please create an image of a cat and a dog playing together."

[0579] Step 2:

[0580] Upon receiving a user request, the device simultaneously collects the user's emotional information (facial expressions, voice, text input, etc.), which is later analyzed by the emotion engine.

[0581] Step 3:

[0582] The device sends the collected emotional information to the emotion engine, which analyzes the user's emotional state. The emotion engine determines the user's current emotional state (e.g., joy, surprise, sadness, etc.) from the collected data.

[0583] Step 4:

[0584] The terminal transmits the user's request content and the analyzed emotion information to the server.

[0585] Step 5:

[0586] The server receives the user's request and emotional information, and based on that, commands the generative artificial intelligence model to create a product (image).

[0587] Step 6:

[0588] The generative AI model processes the user's request and emotional information as input data and generates new content (images). This output is adapted to the user's emotional state.

[0589] Step 7:

[0590] The server assigns a unique identifier (e.g., UUID) to the generated image, which distinguishes the creation from other creations.

[0591] Step 8:

[0592] The server generates metadata containing this identification information, including the name of the generated AI model, the date and time of generation, information about the training data used, and emotional information.

[0593] Step 9:

[0594] The server generates a non-fungible token (NFT) based on the generated metadata. An NFT is a digital asset that uses blockchain technology to associate a unique identifier and metadata with the product.

[0595] Step 10:

[0596] The server then stores the generated image and its metadata (NFT) in secure digital storage, where the data is protected from tampering and unauthorized access.

[0597] Step 11:

[0598] The server registers the artifact's unique identity and metadata on the blockchain, a distributed digital ledger that ensures data consistency and immutability.

[0599] Step 12:

[0600] When a user uses a product (e.g., an image), the device references the blockchain using the unique identifier embedded in the product to retrieve the associated metadata.

[0601] Step 13:

[0602] The device displays the acquired metadata to the user, allowing the user to see details of the creation process, data used, and recognized emotion information, ensuring the reliability and transparency of the creation.

[0603] Example 2

[0604] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0605] Conventional systems lacked the ability to reflect the user's emotional state when creating products using generative artificial intelligence models. They also faced the challenge of making it difficult to ensure traceability to guarantee the reliability and transparency of products. Furthermore, there was a lack of a way to register and manage the uniqueness of products and their associated information on the blockchain. This meant that users could not verify the authenticity of products or the creation process, which could lead to anxiety. Furthermore, products often did not meet the user's expectations or emotions.

[0606] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0607] In this invention, the server includes means for creating a product based on a user request using a generative artificial intelligence model, means for recognizing the user's emotional state and reflecting that information in the product, means for assigning a unique identification to the product and creating metadata, means for generating a non-fungible token based on the metadata, means for storing the product and metadata in digital storage, and means for registering the product's unique identification and metadata in a blockchain. This enables a highly traceable system in which products are tailored to the user's emotions and their reliability and transparency are guaranteed.

[0608] A "generative artificial intelligence model" is an artificial intelligence algorithm that has the ability to generate new content based on user requests.

[0609] An "emotion engine" is a software or hardware system that recognizes a user's emotional state and analyzes that information.

[0610] "Unique identification information" is a unique identifier given to a product to distinguish it from other products.

[0611] "Metadata" is data that describes information related to a product, including the product's identification information, the date and time of its creation, the model and dataset used to create it, and the user's emotional information.

[0612] A "non-fungible token (NFT)" is a digital token that uses blockchain technology to associate a unique identifier and metadata with a digital asset.

[0613] "Digital storage" is a storage device or service that stores data in electronic form.

[0614] "Blockchain" is a distributed digital ledger technology that ensures data consistency and immutability.

[0615] "User emotion information" is data related to the user's emotional state recognized from facial expressions, voice, and text.

[0616] This invention relates to a system that combines a generative AI model with an emotion engine to create products based on user requests and ensure the traceability of the products. This system aims to increase the reliability and transparency of the products by adding a function that reflects user emotions to conventional generative AI models.

[0617] The creation of a product begins when a user accesses the system by entering a prompt from their own device. The prompt includes the type of content they want to generate and specific details. For example, they can enter a request such as "Please create an image of a cat and a dog playing together."

[0618] The device receives a request from the user and simultaneously collects emotional information using a camera or microphone to recognize the user's emotional state. The collected emotional information (facial expressions, voice, text, etc.) is analyzed by an emotion engine to identify the user's current emotional state. This emotional information and the request content are then sent to the server.

[0619] The server receives the user's request and emotion information from the emotion engine, and commands the generative AI model to create a product. The generative AI model generates new content based on this input data. In this case, the generative AI model generates an "image of a cat and a dog playing together," and adjusts the content to reflect the user's emotion (e.g., "joy").

[0620] The server assigns a unique identifier in the form of a UUID to each generated image. This identifier is used to distinguish the generated image from other generated images. The server then generates metadata, including the identifier, the name of the generating AI model, the generation date and time, the training data source used, and the user's emotional information. Based on this metadata, the server generates a non-fungible token (NFT) and stores the generated image and the NFT in secure digital storage.

[0621] Additionally, the product's unique identity and metadata are registered on the blockchain, a distributed digital ledger that ensures data consistency and immutability, creating a permanent record of when and how the product was created.

[0622] When a user uses a product, the device retrieves relevant metadata from the blockchain using the unique identification information embedded in the product. For example, when a user views an image generated on their device, the device will display which generative AI model created the image, as well as the training data and emotional information used. This ensures the user that the product is authentic and trustworthy.

[0623] As a specific example, if a user requests, "Please generate an image of a cat and a dog playing together," the emotion engine analyzes the user's facial expressions and voice to recognize a "joy" state. The device then sends the request and emotional information to the server, which then issues commands to the generative AI model to generate an image based on the user's request and the "joy" emotional information. The generated image is then given a unique identifier in the form of a UUID, and metadata is created, including the name of the generating AI model, the date and time of generation, the training data used, and the emotional information. Finally, the generated image and NFT are stored in digital storage, and the unique identifier and metadata are registered on the blockchain, ensuring the authenticity and reliability of the image when the user views it on their device.

[0624] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0625] Step 1:

[0626] The user requests the creation of a product by entering a prompt sentence. The user enters "Please create an image of a cat and a dog playing together" into the input screen of the terminal and clicks the send button. As input, the prompt sentence is given to the terminal. The output is that the prompt sentence is sent to the terminal.

[0627] Step 2:

[0628] The device collects the user's emotional information. The device activates the camera and microphone to collect the user's facial expressions and voice. The emotion engine analyzes this data and identifies the user's emotional state. The user's facial expressions and voice data are provided to the device as input. The emotion engine analyzes this data and identifies the user's emotional state as "joy." The output is the identified emotional information.

[0629] Step 3:

[0630] The terminal sends a prompt sentence and emotional information to the server. As input, the terminal receives the prompt sentence and emotional information. The terminal incorporates this information into a packet and sends it to the server. The output is the request data and emotional information sent to the server.

[0631] Step 4:

[0632] The server receives the request content and emotional information. The server receives and analyzes the data sent from the terminal via the network protocol. The input is the prompt text and emotional information received by the server. The output is the analyzed request content and emotional information.

[0633] Step 5:

[0634] The server issues commands to the generative AI model to create a product. The server calls the generative AI model to create new content based on the received prompt and emotion information. The generative AI model uses this input data to generate a new image. The prompt and emotion information are given to the generative AI model as input. The output is the generated image.

[0635] Step 6:

[0636] The server assigns a unique identifier to the generated image. The server assigns an identifier in the form of a UUID to the generated image. The generated image is given to the server as input. The output is an image with a UUID assigned.

[0637] Step 7:

[0638] The server creates the metadata, which includes a unique identifier, the name of the generating AI model, the generation date and time, the training data used, and the user's emotional information. As input, the server is given an image with a UUID and information about its generation. The output is the generated metadata.

[0639] Step 8:

[0640] The server generates an NFT based on the metadata. The server uses the generated metadata to issue a non-fungible token (NFT) on the blockchain. The metadata is given to the server as input. The output is the generated NFT.

[0641] Step 9:

[0642] The server stores the generated images and metadata in digital storage. The server stores the generated images and metadata in secure digital storage. The generated images and metadata are given to the server as input. The output is the securely stored data.

[0643] Step 10:

[0644] The server registers the unique identifier and metadata on the blockchain. The server registers this information on the blockchain network to ensure traceability. As input, the server is given the unique identifier and metadata. The output is the data registered on the blockchain.

[0645] Step 11:

[0646] When a user uses a product, the device retrieves the metadata from the blockchain. When a user tries to view an image generated on the device, the device retrieves the metadata from the blockchain using a unique identifier. As input, the device is given the image's unique identifier. The output is the retrieved metadata.

[0647] Step 12:

[0648] The terminal displays the acquired metadata to the user. The terminal displays the acquired metadata on the screen, allowing the user to check the details of the creation process of the product, the data used, and the emotional information. The acquired metadata is given to the terminal as input. The output is the metadata displayed to the user.

[0649] (Application example 2)

[0650] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0651] Conventional product creation systems using generative AI models have issues such as insufficient means for ensuring the reliability and traceability of products, and lack of personalization that takes into account the user's emotional state toward the product. Furthermore, there are no systems in physical stores that can suggest products based on customer emotions, making it difficult to accurately grasp customer needs.

[0652] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0653] In this invention, the server includes a means for creating a product based on a user request using a generative artificial intelligence model, a means for assigning unique identification information to the product and creating metadata, and a means for adjusting the content of the product using an emotion engine so that the product matches the user's emotional state. This enables personalization based on the user's emotions while ensuring the reliability and traceability of the product. Furthermore, optimal product suggestions based on customer emotional information can be made in physical stores, improving the shopping experience.

[0654] A "generative artificial intelligence model" is an artificial intelligence software model that generates new content based on user requests.

[0655] A "product" is content, such as digital data such as images or text, created by a generative artificial intelligence model based on a user request.

[0656] "Unique identification information" means a unique identifier, such as a UUID (Universal Unique Identifier), assigned to a product to distinguish it from other products.

[0657] "Metadata" is data that describes information about a product, including the date and time the product was created, the learning data used, and the user's emotional information.

[0658] A "non-fungible token" is a digital asset that is associated with a product using blockchain technology and proves that the product is unique.

[0659] "Digital storage" is a storage device for electronically storing artifacts and metadata.

[0660] A "blockchain" is a distributed digital ledger that ensures the consistency and immutability of data.

[0661] An "emotion engine" is a software engine that recognizes a user's emotional state from their voice, facial expression, text, etc.

[0662] "Emotion information" is data relating to the user's emotional state acquired and analyzed by the emotion engine.

[0663] A "user" is an entity that utilizes the system to request the creation of a product.

[0664] "Brick and mortar store" refers to a physically existing retail store or commercial space, as opposed to an online store.

[0665] This invention relates to a system that uses a generative artificial intelligence model and an emotion engine to create products based on user requests and emotion information, and ensures the reliability and traceability of the products. In particular, this paper describes an "emotion-aware shopping assistant" that aims to improve the shopping experience in brick-and-mortar stores.

[0666] Program Overview

[0667] Hardware:

[0668] Smartphone

[0669] Smart Glasses

[0670] robot

[0671] software:

[0672] Generative AI model

[0673] Emotion Engine

[0674] Blockchain technology

[0675] Program processing flow

[0676] 1. User Emotion Recognition

[0677] The device (smartphone or smart glasses) captures the user's facial expressions through a camera, and the emotion engine analyzes them to recognize the user's emotional state. Voice input is also accepted, and the emotional state is analyzed from the voice data.

[0678] 2. Content Generation Request

[0679] The user can input the category of product they are looking for and their specific preferences through the terminal. They can also make requests by voice. For example, they can make a request such as, "Please suggest products that will help me relax."

[0680] 3. Creating generated content

[0681] The server instructs the generative AI model to create a product based on the user's request and the emotion information obtained from the emotion engine. The generative AI model then uses this information to generate the optimal product or content for the user.

[0682] 4. Adding traceability information

[0683] Each generated product is assigned a unique identification (UUID format), and metadata is created that includes the date and time of creation, usage data, emotional information, etc. This ensures the traceability of the product.

[0684] 5. NFT and storage

[0685] The server generates a non-fungible token (NFT) based on the generated metadata and stores the generated token and metadata in a secure digital storage. The generated token and metadata are registered on the blockchain, ensuring the consistency and immutability of the data.

[0686] 6. Presentation to the User

[0687] The terminal obtains metadata from the blockchain based on the product's unique identification information, and displays the product's traceability information to the user when proposing a product, allowing them to confirm its authenticity.

[0688] Specific examples

[0689] For example, if a user is tired and requests relaxation products in a physical store, the following prompt sentence is input to the generative AI model:

[0690] "Please suggest some relaxation products for tired users."

[0691] The generative AI model suggests relaxing aroma oils and massage devices, and displays traceability information such as the manufacturer and usage instructions. In this way, the present invention enables personalization based on the user's emotions, improving the shopping experience in physical stores.

[0692] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0693] Step 1:

[0694] emotion recognition

[0695] The device (smartphone or smart glasses) uses a camera to capture the user's facial expressions and also accepts voice input. This data is passed to an emotion engine, which analyzes the user's emotional state from their facial expressions and voice. Specifically, the emotion engine analyzes facial features and voice tones to identify emotions such as joy, sadness, fatigue, and excitement.

[0696] Input: User's facial expression data, voice data

[0697] Output: User's emotional information (happiness, sadness, fatigue, etc.)

[0698] Step 2:

[0699] Content Generation Request

[0700] The user operates the device and requests the desired product category and specific preferences through text input or voice input. For example, they might input, "Please suggest products that will help me relax." The device receives this request and sends it to the server.

[0701] Input: User request (text or voice)

[0702] Output: User request data

[0703] Step 3:

[0704] Creating generated content

[0705] The server receives the user's request data and the emotion information obtained from the emotion engine, and based on that, instructs the generative AI model to create a product. The generative AI model generates optimal products and content based on the prompt. For example, if the user is tired, it will suggest products with a relaxing effect.

[0706] Input: User request data, emotion information

[0707] Output: Generated content

[0708] Step 4:

[0709] Adding traceability information

[0710] The server assigns a unique identifier (UUID format) to the generated artifact and creates metadata including the creation date and time, usage data, emotional information, etc. This allows the authenticity and history of the artifact to be verified later.

[0711] Input: Generated content

[0712] Output: Unique identifier, metadata

[0713] Step 5:

[0714] NFT and storage

[0715] The server generates a non-fungible token (NFT) based on the generated metadata, then stores the generated token and metadata in secure digital storage, which protects the data from tampering and unauthorized access.

[0716] Input: Metadata

[0717] Output: NFT, stored artifact and metadata

[0718] Step 6:

[0719] Blockchain Registration

[0720] The server registers the unique identity and metadata of the artifact in the blockchain, which ensures the traceability and immutability of the artifact.

[0721] Input: Unique identifier, metadata

[0722] Output: Information registered on the blockchain

[0723] Step 7:

[0724] Presenting to the user

[0725] The terminal retrieves metadata from the blockchain based on the product's unique identification information and displays the product's traceability information to the user when proposing a product, allowing the user to confirm the authenticity of the proposed product.

[0726] Input: Unique Identifier

[0727] Output: Presentation of the product including traceability information

[0728] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0729] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0730] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0731] [Third embodiment]

[0732] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0733] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0734] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0735] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0736] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0737] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0738] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0739] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0740] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0741] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0742] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0743] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0744] The present invention relates to a system that uses a generative artificial intelligence model to create a product based on a user request and ensures traceability of the product. This system creates a product using a generative artificial intelligence model, assigns a unique identifier to the product, adds metadata, and generates a non-fungible token (NFT). Furthermore, the system stores the product in digital storage based on the metadata, and registers the product's unique identifier and metadata on a blockchain, thereby ensuring traceability of the product's provenance and creation process.

[0745] Program processing overview

[0746] 1. Creation of the product

[0747] A user accesses a system that uses a generative AI model from their own device and requests the creation of a product. The request includes specific details about the type and content they want to generate. For example, a user might send a request to the system saying, "Please create an image of a scene where a cat and a dog are painting a picture."

[0748] The server receives this request and processes the request as input data into a specific generative artificial intelligence model (e.g., an image generation model). The model generates a new product (in this case, an image) based on the input data.

[0749] 2. Adding metadata to the generated data and converting it into an NFT

[0750] The server assigns a unique identifier to the generated image, such as a Universal Unique Identifier (UUID), to distinguish the specific creation from other creations.

[0751] The server then generates metadata containing this identification information, including important information related to the product, such as the name of the generative AI model that created it, the date and time of its creation, and the source of the training data used, allowing the product's provenance and authenticity to be verified.

[0752] The server uses this metadata to generate an NFT, a digital asset that uses blockchain technology to bind a unique identifier and metadata to the artifact.

[0753] 3. Saving the Creation and NFT

[0754] The generated images and their metadata (NFTs) will be stored in a secure digital storage server that will take appropriate security measures to protect the stored data from tampering and unauthorized access.

[0755] 4. Registering on the Blockchain

[0756] The server registers the product's unique identity and metadata on the blockchain, a distributed digital ledger that ensures data consistency and immutability, providing a permanent record of when and how the product was created, ensuring traceability.

[0757] 5. Confirmation of product use and traceability

[0758] When a user uses a product, the device references the blockchain based on the product's unique identification information. For example, when a user opens an image generated on their device, metadata is retrieved from the blockchain to confirm which AI model created the image and the training data used. This ensures the user that the product is authentic and trustworthy.

[0759] Examples:

[0760] 1. A user sends a request to the system: "Generate an image of a cat and a dog playing together."

[0761] 2. The server receives this request and uses a generative artificial intelligence model to generate the requested image.

[0762] 3. The server assigns a unique identifier in the form of a UUID to the generated image and creates metadata including the name of the generating AI model, the date and time of generation, etc.

[0763] 4. The server generates an NFT based on the metadata and stores the image and NFT in digital storage.

[0764] 5. The server registers the unique identifier and metadata on the blockchain.

[0765] 6. When a user views an image on their device, metadata is retrieved from the blockchain to confirm detailed information such as the image generation process and the training data used.

[0766] This allows us to ensure that the products are trustworthy and promotes the use of generative artificial intelligence models.

[0767] The processing flow will be explained below.

[0768] Step 1:

[0769] A user accesses a system that uses a generative AI model from their own device and requests the creation of a product. The request includes specific details about the type and content they want to generate. For example, a user might enter a request such as, "Please create an image of a cat and a dog playing together."

[0770] Step 2:

[0771] The terminal receives the user's request and sends it to the server, which conveys the request as data containing specific requirements for the product.

[0772] Step 3:

[0773] The server receives a user request and issues a command to a specified generative artificial intelligence model (e.g., an image generation model) to process the request content.

[0774] Step 4:

[0775] A generative AI model generates new content (in this case, an image) based on input data (user requests). The generation process is carried out by an internal algorithm, and the resulting product is obtained.

[0776] Step 5:

[0777] The server assigns a unique identifier (e.g., UUID) to the generated image, which is used to distinguish the creation from other creations.

[0778] Step 6:

[0779] The server generates metadata associated with the generated image, including the name of the generative artificial intelligence model that created it, the date and time of generation, and the source of the training data used.

[0780] Step 7:

[0781] The server generates a non-fungible token (NFT) based on the generated metadata. The NFT is created using blockchain technology and digitally links the artifact and its metadata.

[0782] Step 8:

[0783] The server then stores the generated image and its metadata (NFT) in digital storage, which is managed to protect the data from tampering and unauthorized access.

[0784] Step 9:

[0785] The server registers the unique identification information and metadata of the product on the blockchain, where the consistency and immutability of the registered information are guaranteed.

[0786] Step 10:

[0787] When a user uses a product (e.g., an image), the device uses the unique identifier embedded in the product to retrieve the associated metadata from the blockchain.

[0788] Step 11:

[0789] The device displays the acquired metadata to the user, allowing the user to check the details of the creation process and the data used, ensuring the reliability and transparency of the creation.

[0790] Example 1

[0791] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0792] When creating products using generative machine learning models, it is important to ensure the authenticity and reliability of the products and the traceability of the creation process. Furthermore, a system is needed that allows products to be uniquely identified and enables tracking of their provenance and the data used.

[0793] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0794] In this invention, the server includes means for creating a product based on a user request using a generative machine learning model, means for assigning unique identification information to the product and creating attribute information, means for generating an irreplaceable code based on the attribute information, means for storing the product and attribute information in an electronic storage location, and means for registering the product's unique identification information and attribute information in distributed ledger technology. This makes it possible to guarantee the authenticity and reliability of the product and ensure the traceability of the creation process.

[0795] A "generative machine learning model" is a machine learning model that aims to automatically generate new digital objects based on input data.

[0796] "User" refers to a person or end user who requests the creation of a Product using the System.

[0797] A "request" is a request made by a user to a generative machine learning model to create a product, and refers to a prompt statement that includes specific content and conditions.

[0798] "Product" refers to digital data generated by a generative machine learning model, and can take the form of images, audio, text, etc.

[0799] A "unique identifier" is a unique identifier given to a product to distinguish it from other products, often in the form of a UUID.

[0800] "Attribute information" is data that contains additional information about the product, such as the name of the generative machine learning model that created the product, the date and time of creation, and the source of the training data used.

[0801] A "non-fungible code" is a digital asset that links a product's unique identification and attribute information, and is an NFT created using blockchain technology.

[0802] "Electronic Repository" means a digital storage location for the secure preservation of the Product and the Non-Fungible Code, with appropriate security measures in place to protect against tampering and unauthorized access.

[0803] "Distributed ledger technology" is a decentralized network technology used to ensure the consistency and immutability of data, and blockchain is a prime example.

[0804] This invention relates to a system that uses a generative machine learning model to create products based on user requests, and generates non-fungible tokens (NFTs) by assigning unique identification and attribute information to the products. This system ensures the authenticity and traceability of the products, and provides transparency and reliability in the creation process.

[0805] The specific system configuration mainly includes the following hardware and software:

[0806] 1. Hardware:

[0807] Server: A high-performance computing server for running generative machine learning models.

[0808] Terminal: A personal computer or smartphone used by a user to access the system.

[0809] 2. Software:

[0810] Generative machine learning models: For example, image generation models (e.g., DALL-E) are used.

[0811] Digital storage: For example, cloud storage services such as Amazon S3.

[0812] Distributed ledger technology: For example, the Ethereum blockchain and smart contracts.

[0813] System operation procedure

[0814] 1. Submitting your request

[0815] Users access the web application from their own devices and enter the type and details of the content they want to generate as a prompt, such as "Please generate an image of a cat and a dog playing together."

[0816] 2. Server receives and processes the request

[0817] The server receives user requests and inputs them into a generative machine learning model. The server forwards the input data to the model, which generates a new product (in this case, an image) based on the prompt. The server then receives the generated image data.

[0818] 3. Assigning identification and attribute information

[0819] The server assigns a unique identifier (UUID) to the generated image, and then generates attribute information such as the name of the generative machine learning model that created the image, the date and time of generation, and the source of the training data used.

[0820] 4. NFT Generation

[0821] The server generates an NFT based on the provided identification and attribute information. An NFT is a digital asset that uniquely links a product and its attribute information using blockchain technology. Specifically, the server passes the attribute information to a smart contract and issues the NFT.

[0822] 5. Saving the Creation and NFT

[0823] The server stores the artifact and NFT in secure digital storage, for example using a cloud storage service such as Amazon S3, ensuring the data is protected from tampering and unauthorized access.

[0824] 6. Blockchain registration

[0825] The server registers the unique identification and attribute information of the product in a distributed ledger technology, for example, using Ethereum smart contracts, to ensure the consistency and immutability of the data.

[0826] 7. Use of products by users and confirmation of traceability

[0827] When a user uses a product, for example by opening an image generated on their device, the device references the distributed ledger technology using the product's unique identification information. The device obtains attribute information from the distributed ledger technology and displays detailed information such as the product's generation process and the training data used, thereby ensuring the product's authenticity and reliability.

[0828] For example, a user inputs a prompt such as "Please generate an image of a cat and a dog playing together" and clicks the submit button. This operation causes the server to process the received request and create a product, ensuring the traceability of the product throughout the process.

[0829] This allows us to ensure that the products are trustworthy and facilitates the use of generative machine learning models.

[0830] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0831] Processing Steps

[0832] Step 1: User submits request

[0833] A user accesses the system using a terminal and enters a prompt containing details of the content they want to generate. For example, they enter a specific prompt such as "Please generate an image of a cat and a dog playing together" and click the submit button. This sends the prompt to the server (input). The server receives this prompt (output).

[0834] Step 2: The server receives and processes the request

[0835] The server receives the prompt sent by the user. Next, the server passes this prompt as input data to a generative machine learning model (e.g., DALL-E) (input). The generative machine learning model generates a new image based on the prompt (data processing). The server retrieves the generated image data (output).

[0836] Step 3: Adding identification and attribute information to the product

[0837] The server generates a unique identifier (e.g., UUID) for the generated image and assigns it to the image (input). Next, it generates attribute information including the name of the model that created the product, the date and time of generation, and the source of the training data used (data calculation). This assigns the necessary attribute information to the product (output).

[0838] Step 4: Generate an NFT

[0839] The server generates an NFT based on the provided identification information and attribute information (input). Specifically, the server passes the attribute information to a smart contract and issues an NFT on the blockchain (data calculation). This operation generates an NFT linked to the product (output).

[0840] Step 5: Save the creation and NFT

[0841] The server stores the resulting image file and the generated NFT in secure digital storage (e.g., Amazon S3) (input). During this process, the server implements security measures such as encryption and access restrictions to protect the data from tampering and unauthorized access (data processing). The storage is then completed (output).

[0842] Step 6: Register on the blockchain

[0843] The server registers the unique identification information and attribute information of the product in a distributed ledger technology (e.g., Ethereum) (input). The server writes this information to the blockchain as a transaction, ensuring its immutability and transparency (data calculation). The information is registered in the blockchain (output).

[0844] Step 7: Verify user product usage and traceability

[0845] When a user uses the product on their device, for example by opening a generated image, the device references the distributed ledger technology based on the product's unique identification information (input). The device retrieves attribute information from the blockchain and displays detailed information about the image generation process and the training data used so that the user can check it (data calculation). This allows the user to confirm the authenticity and reliability of the product (output).

[0846] keyword

[0847] Generative AI model, prompt sentence

[0848] (Application example 1)

[0849] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0850] When generating content using generative AI models, there is a lack of adequate means to ensure the traceability and reliability of the results. In particular, it is not easy to verify the provenance of content generated by users. There is also a lack of means for users to easily check the metadata of the results. This raises doubts about the reliability of the results, making it difficult to expand the use of generative AI models.

[0851] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0852] In this invention, the server includes means for creating a product based on a user request using a generative artificial intelligence model, means for assigning unique identification information to the product and creating metadata, means for generating a non-fungible token based on the metadata, means for storing the product and metadata in digital storage, means for registering the product's unique identification information and metadata in a blockchain, and means for a user to individually request a product using the generative artificial intelligence model and for confirming the traceability of the product's metadata using a prompt statement. This makes it possible to confirm the creation process and history of the product, thereby improving the reliability of the product.

[0853] A "generative artificial intelligence model" is a type of artificial intelligence that has the ability to create new products based on requests from users.

[0854] A "user" is a user of a terminal who requests a product using a generative artificial intelligence model.

[0855] A "product" is content created by a generative artificial intelligence model based on a user request.

[0856] "Unique identification information" refers to a unique identifier given to a created product to distinguish it from other products.

[0857] "Metadata" is data that contains important information related to the product, such as the date and time of production and the name of the generative artificial intelligence model used.

[0858] A "non-fungible token (NFT)" is a digital asset that binds a product with unique identification and metadata and is generated using blockchain.

[0859] "Digital storage" is a digital data preservation method for the secure storage of artifacts and their metadata.

[0860] A "blockchain" is a distributed digital ledger that ensures data consistency and immutability and is used to record unique identifiers and metadata.

[0861] A "prompt sentence" is a document used when a user requests the creation of a product, and is used to specify the specific content of the product.

[0862] "Traceability" refers to the ability to trace and confirm the history and production process of a produced product.

[0863] The present invention relates to a system that uses a generative artificial intelligence model to create products based on user requests and ensures traceability of the products. This system assigns unique identification information and metadata to the products, and generates non-fungible tokens (NFTs) based on the metadata, enabling the product's provenance to be tracked.

[0864] The entire system consists of a user terminal and a server. The user terminal is made up of devices such as smartphones and head-mounted displays, and communicates with the server via an interface. The server includes a generative AI model, digital storage, a blockchain module, and a metadata generation unit.

[0865] 1. Program Generation

[0866] The server uses a generative artificial intelligence model to create a product based on a user request. For example, if a user sends a prompt such as "Please generate a virtual tour of a future city," the server receives the request and generates the virtual tour using the generative artificial intelligence model.

[0867] The generated virtual tour is given a unique identifier, and metadata including the date and time of creation, model name, etc. is created. An NFT is generated based on this metadata and securely stored in digital storage along with the product. Furthermore, the product's unique identifier and metadata are registered on the blockchain, ensuring the product's provenance and creation process.

[0868] 2. Natural language processing explanation

[0869] When a user requests a product using a terminal, the server receives the request and creates the product using a generative artificial intelligence model. This process includes the following data processing and data calculations:

[0870] Hardware used:

[0871] User device (smartphone, head-mounted display)

[0872] server

[0873] Software used:

[0874] Generative artificial intelligence model (AI model)

[0875] Blockchain Module

[0876] Digital Storage Module

[0877] Metadata Generation Unit

[0878] When a product is created, the server assigns it a unique identifier (e.g., UUID) and generates metadata, including the creation date and time, the name of the model used, and the request details. An NFT is generated based on this metadata and the product and stored in digital storage. Furthermore, the unique identifier and metadata are registered on the blockchain, ensuring the traceability of the product.

[0879] 3. Examples of concrete examples and prompts

[0880] As a concrete example, consider the case where a user sends a request using a smartphone saying, "Please generate a virtual tour of a futuristic city." The server that receives this request generates the virtual tour using a dedicated generative AI model, assigns a unique identifier and metadata to the result, converts it into an NFT, and stores it in digital storage. Finally, the unique identifier and metadata are registered on the blockchain, maintaining the traceability of the result.

[0881] Example prompt sentence:

[0882] "Generate a virtual tour of a futuristic city"

[0883] "Generate a virtual tour of the Egyptian pyramids"

[0884] As described above, by using the system of the present invention, it becomes easier to confirm the history and production process of a product, improving reliability.

[0885] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0886] Step 1:

[0887] A user uses a terminal to input a prompt and send a request. The input prompt might be, for example, "Please generate a virtual tour of a future city." The terminal then sends this prompt to the server. The input is the user's request, and the output is the prompt sent to the server.

[0888] Step 2:

[0889] The server receives a prompt from the user and uses a generative artificial intelligence model to create a product. The input is the prompt and the output is the generated product. In this process, the AI ​​model analyzes the prompt and generates corresponding content (such as a virtual tour).

[0890] Step 3:

[0891] The server assigns a unique identifier to the product. The input is the product, and the output is the product with the unique identifier. Specifically, it generates a Universally Unique Identifier (UUID) and associates it with the product.

[0892] Step 4:

[0893] The server creates metadata for the product, including the date and time of creation, the name of the generative AI model used, the request details, etc. The input is the product with a unique identifier, and the output is the product and metadata.

[0894] Step 5:

[0895] The server generates a non-fungible token (NFT) based on the metadata. The input is the product and metadata, and the output is the generated NFT. In this process, the NFT is generated based on the metadata using blockchain technology.

[0896] Step 6:

[0897] The server stores the product and NFT in digital storage. The input is the product and NFT, and the output is the data stored in digital storage. The server takes appropriate security measures to store the data safely.

[0898] Step 7:

[0899] The server registers the unique identifier and metadata of the artifact on the blockchain. The input is the unique identifier and metadata, and the output is the data registered on the blockchain. This immutably records the provenance of the artifact.

[0900] Step 8:

[0901] A user sends a request from a terminal to check the traceability of a product. The input is a unique identification, and the output is the product's metadata. The user retrieves the metadata from the blockchain through the terminal and checks the product's creation process and history.

[0902] As described above, the traceability and reliability of the product are ensured through each processing step. By going through this series of steps, the product desired by the user is expected to be properly managed and its reliability increased.

[0903] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0904] This invention relates to a system that uses a generative artificial intelligence model to create products based on user requests and ensures traceability of those products. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system ensures that the products match the user's emotional state. This system consistently performs everything from product creation to storage, ensuring traceability, and emotion-based optimization.

[0905] Program processing overview

[0906] 1. Product creation request and emotion recognition

[0907] A user accesses a system that uses a generative AI model from their own device and requests the creation of a product. The request includes specific details about the type and content they want to generate. For example, a user might request, "Please create an image of a cat and a dog playing together."

[0908] Upon receiving a user request, the device collects emotional information (e.g., facial expressions, voice, text) to capture the user's emotional state. This information is then analyzed by an emotion engine to identify the user's current emotional state.

[0909] 2. Creation of the product

[0910] The server receives the user's request and the emotion information from the emotion engine, and then commands the generative AI model to create a product based on that information. The generative AI model generates new content (in this case, an image) based on this input data. The content of the generated image is adjusted according to the user's emotional state.

[0911] 3. Adding metadata to the generated data and converting it into an NFT

[0912] The server assigns a unique identifier (e.g., UUID) to the generated image, which is used to distinguish the creation from other creations.

[0913] The server then generates metadata containing this identification information, including the name of the generative artificial intelligence model that created the product, the date and time of creation, the source of the training data used, and the user's recognized emotional state.

[0914] The server uses this metadata to generate a non-fungible token (NFT), a digital asset that uses blockchain technology to associate a unique identifier and metadata with the product.

[0915] 4. Saving the Creation and NFT

[0916] The generated images and their metadata (NFTs) will be stored in a secure digital storage server that will take appropriate security measures to protect the stored data from tampering and unauthorized access.

[0917] 5. Registering on the Blockchain

[0918] The server registers the product's unique identity and metadata on the blockchain, a distributed digital ledger that ensures data consistency and immutability, providing a permanent record of when and how the product was created, ensuring traceability.

[0919] 6. Confirmation of product use and traceability

[0920] When a user uses a product, the device retrieves relevant metadata from the blockchain using the unique identification information embedded in the product. For example, when a user opens an image generated on their device, metadata can be retrieved from the blockchain to confirm which AI model created the image, as well as the training data and emotional information used. This ensures the authenticity and reliability of the product to the user.

[0921] Examples:

[0922] 1. A user requests the system to "generate an image of a cat and a dog playing together." The emotion engine analyzes the user's facial expressions and voice and recognizes the "joy" state.

[0923] 2. The device sends the request and emotion information to the server.

[0924] 3. The server issues commands to the generative artificial intelligence model to generate an image based on the user's request and "joy" emotion information.

[0925] 4. The server assigns a unique identifier in the form of a UUID to the generated image and creates metadata including the name of the generating AI model, the date and time of generation, the training data used, and emotional information.

[0926] 5. The server generates an NFT based on the metadata and stores the image and NFT in digital storage.

[0927] 6. The server registers the unique identifier and metadata on the blockchain.

[0928] 7. When a user views an image on their device, metadata is retrieved from the blockchain to provide details about how the image was created, the data used, and emotional information.

[0929] This system ensures that the outputs of generative AI models are in line with the user's emotions, and also ensures the reliability and transparency of the outputs.

[0930] The processing flow will be explained below.

[0931] Step 1:

[0932] A user accesses a system that uses a generative AI model from their own device and requests the creation of a product. The request includes specific details about the type and content they want to generate. For example, a user might enter a request such as, "Please create an image of a cat and a dog playing together."

[0933] Step 2:

[0934] Upon receiving a user request, the device simultaneously collects the user's emotional information (facial expressions, voice, text input, etc.), which is later analyzed by the emotion engine.

[0935] Step 3:

[0936] The device sends the collected emotional information to the emotion engine, which analyzes the user's emotional state. The emotion engine determines the user's current emotional state (e.g., joy, surprise, sadness, etc.) from the collected data.

[0937] Step 4:

[0938] The terminal transmits the user's request content and the analyzed emotion information to the server.

[0939] Step 5:

[0940] The server receives the user's request and emotional information, and based on that, commands the generative artificial intelligence model to create a product (image).

[0941] Step 6:

[0942] The generative AI model processes the user's request and emotional information as input data and generates new content (images). This output is adapted to the user's emotional state.

[0943] Step 7:

[0944] The server assigns a unique identifier (e.g., UUID) to the generated image, which distinguishes the creation from other creations.

[0945] Step 8:

[0946] The server generates metadata containing this identification information, including the name of the generated AI model, the date and time of generation, information about the training data used, and emotional information.

[0947] Step 9:

[0948] The server generates a non-fungible token (NFT) based on the generated metadata. An NFT is a digital asset that uses blockchain technology to associate a unique identifier and metadata with the product.

[0949] Step 10:

[0950] The server then stores the generated image and its metadata (NFT) in secure digital storage, where the data is protected from tampering and unauthorized access.

[0951] Step 11:

[0952] The server registers the artifact's unique identity and metadata on the blockchain, a distributed digital ledger that ensures data consistency and immutability.

[0953] Step 12:

[0954] When a user uses a product (e.g., an image), the device references the blockchain using the unique identifier embedded in the product to retrieve the associated metadata.

[0955] Step 13:

[0956] The device displays the acquired metadata to the user, allowing the user to see details of the creation process, data used, and recognized emotion information, ensuring the reliability and transparency of the creation.

[0957] Example 2

[0958] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0959] Conventional systems lacked the ability to reflect the user's emotional state when creating products using generative artificial intelligence models. They also faced the challenge of making it difficult to ensure traceability to guarantee the reliability and transparency of products. Furthermore, there was a lack of a way to register and manage the uniqueness of products and their associated information on the blockchain. This meant that users could not verify the authenticity of products or the creation process, which could lead to anxiety. Furthermore, products often did not meet the user's expectations or emotions.

[0960] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0961] In this invention, the server includes means for creating a product based on a user request using a generative artificial intelligence model, means for recognizing the user's emotional state and reflecting that information in the product, means for assigning a unique identification to the product and creating metadata, means for generating a non-fungible token based on the metadata, means for storing the product and metadata in digital storage, and means for registering the product's unique identification and metadata in a blockchain. This enables a highly traceable system in which products are tailored to the user's emotions and their reliability and transparency are guaranteed.

[0962] A "generative artificial intelligence model" is an artificial intelligence algorithm that has the ability to generate new content based on user requests.

[0963] An "emotion engine" is a software or hardware system that recognizes a user's emotional state and analyzes that information.

[0964] "Unique identification information" is a unique identifier given to a product to distinguish it from other products.

[0965] "Metadata" is data that describes information related to a product, including the product's identification information, the date and time of its creation, the model and dataset used to create it, and the user's emotional information.

[0966] A "non-fungible token (NFT)" is a digital token that uses blockchain technology to associate a unique identifier and metadata with a digital asset.

[0967] "Digital storage" is a storage device or service that stores data in electronic form.

[0968] "Blockchain" is a distributed digital ledger technology that ensures data consistency and immutability.

[0969] "User emotion information" is data related to the user's emotional state recognized from facial expressions, voice, and text.

[0970] This invention relates to a system that combines a generative AI model with an emotion engine to create products based on user requests and ensure the traceability of the products. This system aims to increase the reliability and transparency of the products by adding a function that reflects user emotions to conventional generative AI models.

[0971] The creation of a product begins when a user accesses the system by entering a prompt from their own device. The prompt includes the type of content they want to generate and specific details. For example, they can enter a request such as "Please create an image of a cat and a dog playing together."

[0972] The device receives a request from the user and simultaneously collects emotional information using a camera or microphone to recognize the user's emotional state. The collected emotional information (facial expressions, voice, text, etc.) is analyzed by an emotion engine to identify the user's current emotional state. This emotional information and the request content are then sent to the server.

[0973] The server receives the user's request and emotion information from the emotion engine, and commands the generative AI model to create a product. The generative AI model generates new content based on this input data. In this case, the generative AI model generates an "image of a cat and a dog playing together," and adjusts the content to reflect the user's emotion (e.g., "joy").

[0974] The server assigns a unique identifier in the form of a UUID to each generated image. This identifier is used to distinguish the generated image from other generated images. The server then generates metadata, including the identifier, the name of the generating AI model, the generation date and time, the training data source used, and the user's emotional information. Based on this metadata, the server generates a non-fungible token (NFT) and stores the generated image and the NFT in secure digital storage.

[0975] Additionally, the product's unique identity and metadata are registered on the blockchain, a distributed digital ledger that ensures data consistency and immutability, creating a permanent record of when and how the product was created.

[0976] When a user uses a product, the device retrieves relevant metadata from the blockchain using the unique identification information embedded in the product. For example, when a user views an image generated on their device, the device will display which generative AI model created the image, as well as the training data and emotional information used. This ensures the user that the product is authentic and trustworthy.

[0977] As a specific example, if a user requests, "Please generate an image of a cat and a dog playing together," the emotion engine analyzes the user's facial expressions and voice to recognize a "joy" state. The device then sends the request and emotional information to the server, which then issues commands to the generative AI model to generate an image based on the user's request and the "joy" emotional information. The generated image is then given a unique identifier in the form of a UUID, and metadata is created, including the name of the generating AI model, the date and time of generation, the training data used, and the emotional information. Finally, the generated image and NFT are stored in digital storage, and the unique identifier and metadata are registered on the blockchain, ensuring the authenticity and reliability of the image when the user views it on their device.

[0978] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0979] Step 1:

[0980] The user requests the creation of a product by entering a prompt sentence. The user enters "Please create an image of a cat and a dog playing together" into the input screen of the terminal and clicks the send button. As input, the prompt sentence is given to the terminal. The output is that the prompt sentence is sent to the terminal.

[0981] Step 2:

[0982] The device collects the user's emotional information. The device activates the camera and microphone to collect the user's facial expressions and voice. The emotion engine analyzes this data and identifies the user's emotional state. The user's facial expressions and voice data are provided to the device as input. The emotion engine analyzes this data and identifies the user's emotional state as "joy." The output is the identified emotional information.

[0983] Step 3:

[0984] The terminal sends a prompt sentence and emotional information to the server. As input, the terminal receives the prompt sentence and emotional information. The terminal incorporates this information into a packet and sends it to the server. The output is the request data and emotional information sent to the server.

[0985] Step 4:

[0986] The server receives the request content and emotional information. The server receives and analyzes the data sent from the terminal via the network protocol. The input is the prompt text and emotional information received by the server. The output is the analyzed request content and emotional information.

[0987] Step 5:

[0988] The server issues commands to the generative AI model to create a product. The server calls the generative AI model to create new content based on the received prompt and emotion information. The generative AI model uses this input data to generate a new image. The prompt and emotion information are given to the generative AI model as input. The output is the generated image.

[0989] Step 6:

[0990] The server assigns a unique identifier to the generated image. The server assigns an identifier in the form of a UUID to the generated image. The generated image is given to the server as input. The output is an image with a UUID assigned.

[0991] Step 7:

[0992] The server creates the metadata, which includes a unique identifier, the name of the generating AI model, the generation date and time, the training data used, and the user's emotional information. As input, the server is given an image with a UUID and information about its generation. The output is the generated metadata.

[0993] Step 8:

[0994] The server generates an NFT based on the metadata. The server uses the generated metadata to issue a non-fungible token (NFT) on the blockchain. The metadata is given to the server as input. The output is the generated NFT.

[0995] Step 9:

[0996] The server stores the generated images and metadata in digital storage. The server stores the generated images and metadata in secure digital storage. The generated images and metadata are given to the server as input. The output is the securely stored data.

[0997] Step 10:

[0998] The server registers the unique identifier and metadata on the blockchain. The server registers this information on the blockchain network to ensure traceability. As input, the server is given the unique identifier and metadata. The output is the data registered on the blockchain.

[0999] Step 11:

[1000] When a user uses a product, the device retrieves the metadata from the blockchain. When a user tries to view an image generated on the device, the device retrieves the metadata from the blockchain using a unique identifier. As input, the device is given the image's unique identifier. The output is the retrieved metadata.

[1001] Step 12:

[1002] The terminal displays the acquired metadata to the user. The terminal displays the acquired metadata on the screen, allowing the user to check the details of the creation process of the product, the data used, and the emotional information. The acquired metadata is given to the terminal as input. The output is the metadata displayed to the user.

[1003] (Application example 2)

[1004] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1005] Conventional product creation systems using generative AI models have issues such as insufficient means for ensuring the reliability and traceability of products, and lack of personalization that takes into account the user's emotional state toward the product. Furthermore, there are no systems in physical stores that can suggest products based on customer emotions, making it difficult to accurately grasp customer needs.

[1006] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1007] In this invention, the server includes a means for creating a product based on a user request using a generative artificial intelligence model, a means for assigning unique identification information to the product and creating metadata, and a means for adjusting the content of the product using an emotion engine so that the product matches the user's emotional state. This enables personalization based on the user's emotions while ensuring the reliability and traceability of the product. Furthermore, optimal product suggestions based on customer emotional information can be made in physical stores, improving the shopping experience.

[1008] A "generative artificial intelligence model" is an artificial intelligence software model that generates new content based on user requests.

[1009] A "product" is content, such as digital data such as images or text, created by a generative artificial intelligence model based on a user request.

[1010] "Unique identification information" means a unique identifier, such as a UUID (Universal Unique Identifier), assigned to a product to distinguish it from other products.

[1011] "Metadata" is data that describes information about a product, including the date and time the product was created, the learning data used, and the user's emotional information.

[1012] A "non-fungible token" is a digital asset that is associated with a product using blockchain technology and proves that the product is unique.

[1013] "Digital storage" is a storage device for electronically storing artifacts and metadata.

[1014] A "blockchain" is a distributed digital ledger that ensures the consistency and immutability of data.

[1015] An "emotion engine" is a software engine that recognizes a user's emotional state from their voice, facial expression, text, etc.

[1016] "Emotion information" is data relating to the user's emotional state acquired and analyzed by the emotion engine.

[1017] A "user" is an entity that utilizes the system to request the creation of a product.

[1018] "Brick and mortar store" refers to a physically existing retail store or commercial space, as opposed to an online store.

[1019] This invention relates to a system that uses a generative artificial intelligence model and an emotion engine to create products based on user requests and emotion information, and ensures the reliability and traceability of the products. In particular, this paper describes an "emotion-aware shopping assistant" that aims to improve the shopping experience in brick-and-mortar stores.

[1020] Program Overview

[1021] Hardware:

[1022] Smartphone

[1023] Smart Glasses

[1024] robot

[1025] software:

[1026] Generative AI model

[1027] Emotion Engine

[1028] Blockchain technology

[1029] Program processing flow

[1030] 1. User Emotion Recognition

[1031] The device (smartphone or smart glasses) captures the user's facial expressions through a camera, and the emotion engine analyzes them to recognize the user's emotional state. Voice input is also accepted, and the emotional state is analyzed from the voice data.

[1032] 2. Content Generation Request

[1033] The user can input the category of product they are looking for and their specific preferences through the terminal. They can also make requests by voice. For example, they can make a request such as, "Please suggest products that will help me relax."

[1034] 3. Creating generated content

[1035] The server instructs the generative AI model to create a product based on the user's request and the emotion information obtained from the emotion engine. The generative AI model then uses this information to generate the optimal product or content for the user.

[1036] 4. Adding traceability information

[1037] Each generated product is assigned a unique identification (UUID format), and metadata is created that includes the date and time of creation, usage data, emotional information, etc. This ensures the traceability of the product.

[1038] 5. NFT and storage

[1039] The server generates a non-fungible token (NFT) based on the generated metadata and stores the generated token and metadata in a secure digital storage. The generated token and metadata are registered on the blockchain, ensuring the consistency and immutability of the data.

[1040] 6. Presentation to the User

[1041] The terminal obtains metadata from the blockchain based on the product's unique identification information, and displays the product's traceability information to the user when proposing a product, allowing them to confirm its authenticity.

[1042] Specific examples

[1043] For example, if a user is tired and requests relaxation products in a physical store, the following prompt sentence is input to the generative AI model:

[1044] "Please suggest some relaxation products for tired users."

[1045] The generative AI model suggests relaxing aroma oils and massage devices, and displays traceability information such as the manufacturer and usage instructions. In this way, the present invention enables personalization based on the user's emotions, improving the shopping experience in physical stores.

[1046] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1047] Step 1:

[1048] emotion recognition

[1049] The device (smartphone or smart glasses) uses a camera to capture the user's facial expressions and also accepts voice input. This data is passed to an emotion engine, which analyzes the user's emotional state from their facial expressions and voice. Specifically, the emotion engine analyzes facial features and voice tones to identify emotions such as joy, sadness, fatigue, and excitement.

[1050] Input: User's facial expression data, voice data

[1051] Output: User's emotional information (happiness, sadness, fatigue, etc.)

[1052] Step 2:

[1053] Content Generation Request

[1054] The user operates the device and requests the desired product category and specific preferences through text input or voice input. For example, they might input, "Please suggest products that will help me relax." The device receives this request and sends it to the server.

[1055] Input: User request (text or voice)

[1056] Output: User request data

[1057] Step 3:

[1058] Creating generated content

[1059] The server receives the user's request data and the emotion information obtained from the emotion engine, and based on that, instructs the generative AI model to create a product. The generative AI model generates optimal products and content based on the prompt. For example, if the user is tired, it will suggest products with a relaxing effect.

[1060] Input: User request data, emotion information

[1061] Output: Generated content

[1062] Step 4:

[1063] Adding traceability information

[1064] The server assigns a unique identifier (UUID format) to the generated artifact and creates metadata including the creation date and time, usage data, emotional information, etc. This allows the authenticity and history of the artifact to be verified later.

[1065] Input: Generated content

[1066] Output: Unique identifier, metadata

[1067] Step 5:

[1068] NFT and storage

[1069] The server generates a non-fungible token (NFT) based on the generated metadata, then stores the generated token and metadata in secure digital storage, which protects the data from tampering and unauthorized access.

[1070] Input: Metadata

[1071] Output: NFT, stored artifact and metadata

[1072] Step 6:

[1073] Blockchain Registration

[1074] The server registers the unique identity and metadata of the artifact in the blockchain, which ensures the traceability and immutability of the artifact.

[1075] Input: Unique identifier, metadata

[1076] Output: Information registered on the blockchain

[1077] Step 7:

[1078] Presenting to the user

[1079] The terminal retrieves metadata from the blockchain based on the product's unique identification information and displays the product's traceability information to the user when proposing a product, allowing the user to confirm the authenticity of the proposed product.

[1080] Input: Unique Identifier

[1081] Output: Presentation of the product including traceability information

[1082] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1083] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1084] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1085] [Fourth embodiment]

[1086] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1087] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1088] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1089] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1090] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1091] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1092] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1093] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1094] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1095] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[1096] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1097] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1098] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1099] The present invention relates to a system that uses a generative artificial intelligence model to create a product based on a user request and ensures traceability of the product. This system creates a product using a generative artificial intelligence model, assigns a unique identifier to the product, adds metadata, and generates a non-fungible token (NFT). Furthermore, the system stores the product in digital storage based on the metadata, and registers the product's unique identifier and metadata on a blockchain, thereby ensuring traceability of the product's provenance and creation process.

[1100] Program processing overview

[1101] 1. Creation of the product

[1102] A user accesses a system that uses a generative AI model from their own device and requests the creation of a product. The request includes specific details about the type and content they want to generate. For example, a user might send a request to the system saying, "Please create an image of a scene where a cat and a dog are painting a picture."

[1103] The server receives this request and processes the request as input data into a specific generative artificial intelligence model (e.g., an image generation model). The model generates a new product (in this case, an image) based on the input data.

[1104] 2. Adding metadata to the generated data and converting it into an NFT

[1105] The server assigns a unique identifier to the generated image, such as a Universal Unique Identifier (UUID), to distinguish the specific creation from other creations.

[1106] The server then generates metadata containing this identification information, including important information related to the product, such as the name of the generative AI model that created it, the date and time of its creation, and the source of the training data used, allowing the product's provenance and authenticity to be verified.

[1107] The server uses this metadata to generate an NFT, a digital asset that uses blockchain technology to bind a unique identifier and metadata to the artifact.

[1108] 3. Saving the Creation and NFT

[1109] The generated images and their metadata (NFTs) will be stored in a secure digital storage server that will take appropriate security measures to protect the stored data from tampering and unauthorized access.

[1110] 4. Registering on the Blockchain

[1111] The server registers the product's unique identity and metadata on the blockchain, a distributed digital ledger that ensures data consistency and immutability, providing a permanent record of when and how the product was created, ensuring traceability.

[1112] 5. Confirmation of product use and traceability

[1113] When a user uses a product, the device references the blockchain based on the product's unique identification information. For example, when a user opens an image generated on their device, metadata is retrieved from the blockchain to confirm which AI model created the image and the training data used. This ensures the user that the product is authentic and trustworthy.

[1114] Examples:

[1115] 1. A user sends a request to the system: "Generate an image of a cat and a dog playing together."

[1116] 2. The server receives this request and uses a generative artificial intelligence model to generate the requested image.

[1117] 3. The server assigns a unique identifier in the form of a UUID to the generated image and creates metadata including the name of the generating AI model, the date and time of generation, etc.

[1118] 4. The server generates an NFT based on the metadata and stores the image and NFT in digital storage.

[1119] 5. The server registers the unique identifier and metadata on the blockchain.

[1120] 6. When a user views an image on their device, metadata is retrieved from the blockchain to confirm detailed information such as the image generation process and the training data used.

[1121] This allows us to ensure that the products are trustworthy and promotes the use of generative artificial intelligence models.

[1122] The processing flow will be explained below.

[1123] Step 1:

[1124] A user accesses a system that uses a generative AI model from their own device and requests the creation of a product. The request includes specific details about the type and content they want to generate. For example, a user might enter a request such as, "Please create an image of a cat and a dog playing together."

[1125] Step 2:

[1126] The terminal receives the user's request and sends it to the server, which conveys the request as data containing specific requirements for the product.

[1127] Step 3:

[1128] The server receives a user request and issues a command to a specified generative artificial intelligence model (e.g., an image generation model) to process the request content.

[1129] Step 4:

[1130] A generative AI model generates new content (in this case, an image) based on input data (user requests). The generation process is carried out by an internal algorithm, and the resulting product is obtained.

[1131] Step 5:

[1132] The server assigns a unique identifier (e.g., UUID) to the generated image, which is used to distinguish the creation from other creations.

[1133] Step 6:

[1134] The server generates metadata associated with the generated image, including the name of the generative artificial intelligence model that created it, the date and time of generation, and the source of the training data used.

[1135] Step 7:

[1136] The server generates a non-fungible token (NFT) based on the generated metadata. The NFT is created using blockchain technology and digitally links the artifact and its metadata.

[1137] Step 8:

[1138] The server then stores the generated image and its metadata (NFT) in digital storage, which is managed to protect the data from tampering and unauthorized access.

[1139] Step 9:

[1140] The server registers the unique identification information and metadata of the product on the blockchain, where the consistency and immutability of the registered information are guaranteed.

[1141] Step 10:

[1142] When a user uses a product (e.g., an image), the device uses the unique identifier embedded in the product to retrieve the associated metadata from the blockchain.

[1143] Step 11:

[1144] The device displays the acquired metadata to the user, allowing the user to check the details of the creation process and the data used, ensuring the reliability and transparency of the creation.

[1145] Example 1

[1146] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1147] When creating products using generative machine learning models, it is important to ensure the authenticity and reliability of the products and the traceability of the creation process. Furthermore, a system is needed that allows products to be uniquely identified and enables tracking of their provenance and the data used.

[1148] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1149] In this invention, the server includes means for creating a product based on a user request using a generative machine learning model, means for assigning unique identification information to the product and creating attribute information, means for generating an irreplaceable code based on the attribute information, means for storing the product and attribute information in an electronic storage location, and means for registering the product's unique identification information and attribute information in distributed ledger technology. This makes it possible to guarantee the authenticity and reliability of the product and ensure the traceability of the creation process.

[1150] A "generative machine learning model" is a machine learning model that aims to automatically generate new digital objects based on input data.

[1151] "User" refers to a person or end user who requests the creation of a Product using the System.

[1152] A "request" is a request made by a user to a generative machine learning model to create a product, and refers to a prompt statement that includes specific content and conditions.

[1153] "Product" refers to digital data generated by a generative machine learning model, and can take the form of images, audio, text, etc.

[1154] A "unique identifier" is a unique identifier given to a product to distinguish it from other products, often in the form of a UUID.

[1155] "Attribute information" is data that contains additional information about the product, such as the name of the generative machine learning model that created the product, the date and time of creation, and the source of the training data used.

[1156] A "non-fungible code" is a digital asset that links a product's unique identification and attribute information, and is an NFT created using blockchain technology.

[1157] "Electronic Repository" means a digital storage location for the secure preservation of the Product and the Non-Fungible Code, with appropriate security measures in place to protect against tampering and unauthorized access.

[1158] "Distributed ledger technology" is a decentralized network technology used to ensure the consistency and immutability of data, and blockchain is a prime example.

[1159] This invention relates to a system that uses a generative machine learning model to create products based on user requests, and generates non-fungible tokens (NFTs) by assigning unique identification and attribute information to the products. This system ensures the authenticity and traceability of the products, and provides transparency and reliability in the creation process.

[1160] The specific system configuration mainly includes the following hardware and software:

[1161] 1. Hardware:

[1162] Server: A high-performance computing server for running generative machine learning models.

[1163] Terminal: A personal computer or smartphone used by a user to access the system.

[1164] 2. Software:

[1165] Generative machine learning models: For example, image generation models (e.g., DALL-E) are used.

[1166] Digital storage: For example, cloud storage services such as Amazon S3.

[1167] Distributed ledger technology: For example, the Ethereum blockchain and smart contracts.

[1168] System operation procedure

[1169] 1. Submitting your request

[1170] Users access the web application from their own devices and enter the type and details of the content they want to generate as a prompt, such as "Please generate an image of a cat and a dog playing together."

[1171] 2. Server receives and processes the request

[1172] The server receives user requests and inputs them into a generative machine learning model. The server forwards the input data to the model, which generates a new product (in this case, an image) based on the prompt. The server then receives the generated image data.

[1173] 3. Assigning identification and attribute information

[1174] The server assigns a unique identifier (UUID) to the generated image, and then generates attribute information such as the name of the generative machine learning model that created the image, the date and time of generation, and the source of the training data used.

[1175] 4. NFT Generation

[1176] The server generates an NFT based on the provided identification and attribute information. An NFT is a digital asset that uniquely links a product and its attribute information using blockchain technology. Specifically, the server passes the attribute information to a smart contract and issues the NFT.

[1177] 5. Saving the Creation and NFT

[1178] The server stores the artifact and NFT in secure digital storage, for example using a cloud storage service such as Amazon S3, ensuring the data is protected from tampering and unauthorized access.

[1179] 6. Blockchain registration

[1180] The server registers the unique identification and attribute information of the product in a distributed ledger technology, for example, using Ethereum smart contracts, to ensure the consistency and immutability of the data.

[1181] 7. Use of products by users and confirmation of traceability

[1182] When a user uses a product, for example by opening an image generated on their device, the device references the distributed ledger technology using the product's unique identification information. The device obtains attribute information from the distributed ledger technology and displays detailed information such as the product's generation process and the training data used, thereby ensuring the product's authenticity and reliability.

[1183] For example, a user inputs a prompt such as "Please generate an image of a cat and a dog playing together" and clicks the submit button. This operation causes the server to process the received request and create a product, ensuring the traceability of the product throughout the process.

[1184] This allows us to ensure that the products are trustworthy and facilitates the use of generative machine learning models.

[1185] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1186] Processing Steps

[1187] Step 1: User submits request

[1188] A user accesses the system using a terminal and enters a prompt containing details of the content they want to generate. For example, they enter a specific prompt such as "Please generate an image of a cat and a dog playing together" and click the submit button. This sends the prompt to the server (input). The server receives this prompt (output).

[1189] Step 2: The server receives and processes the request

[1190] The server receives the prompt sent by the user. Next, the server passes this prompt as input data to a generative machine learning model (e.g., DALL-E) (input). The generative machine learning model generates a new image based on the prompt (data processing). The server retrieves the generated image data (output).

[1191] Step 3: Adding identification and attribute information to the product

[1192] The server generates a unique identifier (e.g., UUID) for the generated image and assigns it to the image (input). Next, it generates attribute information including the name of the model that created the product, the date and time of generation, and the source of the training data used (data calculation). This assigns the necessary attribute information to the product (output).

[1193] Step 4: Generate an NFT

[1194] The server generates an NFT based on the provided identification information and attribute information (input). Specifically, the server passes the attribute information to a smart contract and issues an NFT on the blockchain (data calculation). This operation generates an NFT linked to the product (output).

[1195] Step 5: Save the creation and NFT

[1196] The server stores the resulting image file and the generated NFT in secure digital storage (e.g., Amazon S3) (input). During this process, the server implements security measures such as encryption and access restrictions to protect the data from tampering and unauthorized access (data processing). The storage is then completed (output).

[1197] Step 6: Register on the blockchain

[1198] The server registers the unique identification information and attribute information of the product in a distributed ledger technology (e.g., Ethereum) (input). The server writes this information to the blockchain as a transaction, ensuring its immutability and transparency (data calculation). The information is registered in the blockchain (output).

[1199] Step 7: Verify user product usage and traceability

[1200] When a user uses the product on their device, for example by opening a generated image, the device references the distributed ledger technology based on the product's unique identification information (input). The device retrieves attribute information from the blockchain and displays detailed information about the image generation process and the training data used so that the user can check it (data calculation). This allows the user to confirm the authenticity and reliability of the product (output).

[1201] keyword

[1202] Generative AI model, prompt sentence

[1203] (Application example 1)

[1204] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1205] When generating content using generative AI models, there is a lack of adequate means to ensure the traceability and reliability of the results. In particular, it is not easy to verify the provenance of content generated by users. There is also a lack of means for users to easily check the metadata of the results. This raises doubts about the reliability of the results, making it difficult to expand the use of generative AI models.

[1206] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1207] In this invention, the server includes means for creating a product based on a user request using a generative artificial intelligence model, means for assigning unique identification information to the product and creating metadata, means for generating a non-fungible token based on the metadata, means for storing the product and metadata in digital storage, means for registering the product's unique identification information and metadata in a blockchain, and means for a user to individually request a product using the generative artificial intelligence model and for confirming the traceability of the product's metadata using a prompt statement. This makes it possible to confirm the creation process and history of the product, thereby improving the reliability of the product.

[1208] A "generative artificial intelligence model" is a type of artificial intelligence that has the ability to create new products based on requests from users.

[1209] A "user" is a user of a terminal who requests a product using a generative artificial intelligence model.

[1210] A "product" is content created by a generative artificial intelligence model based on a user request.

[1211] "Unique identification information" refers to a unique identifier given to a created product to distinguish it from other products.

[1212] "Metadata" is data that contains important information related to the product, such as the date and time of production and the name of the generative artificial intelligence model used.

[1213] A "non-fungible token (NFT)" is a digital asset that binds a product with unique identification and metadata and is generated using blockchain.

[1214] "Digital storage" is a digital data preservation method for the secure storage of artifacts and their metadata.

[1215] A "blockchain" is a distributed digital ledger that ensures data consistency and immutability and is used to record unique identifiers and metadata.

[1216] A "prompt sentence" is a document used when a user requests the creation of a product, and is used to specify the specific content of the product.

[1217] "Traceability" refers to the ability to trace and confirm the history and production process of a produced product.

[1218] The present invention relates to a system that uses a generative artificial intelligence model to create products based on user requests and ensures traceability of the products. This system assigns unique identification information and metadata to the products, and generates non-fungible tokens (NFTs) based on the metadata, enabling the product's provenance to be tracked.

[1219] The entire system consists of a user terminal and a server. The user terminal is made up of devices such as smartphones and head-mounted displays, and communicates with the server via an interface. The server includes a generative AI model, digital storage, a blockchain module, and a metadata generation unit.

[1220] 1. Program Generation

[1221] The server uses a generative artificial intelligence model to create a product based on a user request. For example, if a user sends a prompt such as "Please generate a virtual tour of a future city," the server receives the request and generates the virtual tour using the generative artificial intelligence model.

[1222] The generated virtual tour is given a unique identifier, and metadata including the date and time of creation, model name, etc. is created. An NFT is generated based on this metadata and securely stored in digital storage along with the product. Furthermore, the product's unique identifier and metadata are registered on the blockchain, ensuring the product's provenance and creation process.

[1223] 2. Natural language processing explanation

[1224] When a user requests a product using a terminal, the server receives the request and creates the product using a generative artificial intelligence model. This process includes the following data processing and data calculations:

[1225] Hardware used:

[1226] User device (smartphone, head-mounted display)

[1227] server

[1228] Software used:

[1229] Generative artificial intelligence model (AI model)

[1230] Blockchain Module

[1231] Digital Storage Module

[1232] Metadata Generation Unit

[1233] When a product is created, the server assigns it a unique identifier (e.g., UUID) and generates metadata, including the creation date and time, the name of the model used, and the request details. An NFT is generated based on this metadata and the product and stored in digital storage. Furthermore, the unique identifier and metadata are registered on the blockchain, ensuring the traceability of the product.

[1234] 3. Examples of concrete examples and prompts

[1235] As a concrete example, consider the case where a user sends a request using a smartphone saying, "Please generate a virtual tour of a futuristic city." The server that receives this request generates the virtual tour using a dedicated generative AI model, assigns a unique identifier and metadata to the result, converts it into an NFT, and stores it in digital storage. Finally, the unique identifier and metadata are registered on the blockchain, maintaining the traceability of the result.

[1236] Example prompt sentence:

[1237] "Generate a virtual tour of a futuristic city"

[1238] "Generate a virtual tour of the Egyptian pyramids"

[1239] As described above, by using the system of the present invention, it becomes easier to confirm the history and production process of a product, improving reliability.

[1240] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1241] Step 1:

[1242] A user uses a terminal to input a prompt and send a request. The input prompt might be, for example, "Please generate a virtual tour of a future city." The terminal then sends this prompt to the server. The input is the user's request, and the output is the prompt sent to the server.

[1243] Step 2:

[1244] The server receives a prompt from the user and uses a generative artificial intelligence model to create a product. The input is the prompt and the output is the generated product. In this process, the AI ​​model analyzes the prompt and generates corresponding content (such as a virtual tour).

[1245] Step 3:

[1246] The server assigns a unique identifier to the product. The input is the product, and the output is the product with the unique identifier. Specifically, it generates a Universally Unique Identifier (UUID) and associates it with the product.

[1247] Step 4:

[1248] The server creates metadata for the product, including the date and time of creation, the name of the generative AI model used, the request details, etc. The input is the product with a unique identifier, and the output is the product and metadata.

[1249] Step 5:

[1250] The server generates a non-fungible token (NFT) based on the metadata. The input is the product and metadata, and the output is the generated NFT. In this process, the NFT is generated based on the metadata using blockchain technology.

[1251] Step 6:

[1252] The server stores the product and NFT in digital storage. The input is the product and NFT, and the output is the data stored in digital storage. The server takes appropriate security measures to store the data safely.

[1253] Step 7:

[1254] The server registers the unique identifier and metadata of the artifact on the blockchain. The input is the unique identifier and metadata, and the output is the data registered on the blockchain. This immutably records the provenance of the artifact.

[1255] Step 8:

[1256] A user sends a request from a terminal to check the traceability of a product. The input is a unique identification, and the output is the product's metadata. The user retrieves the metadata from the blockchain through the terminal and checks the product's creation process and history.

[1257] As described above, the traceability and reliability of the product are ensured through each processing step. By going through this series of steps, the product desired by the user is expected to be properly managed and its reliability increased.

[1258] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1259] This invention relates to a system that uses a generative artificial intelligence model to create products based on user requests and ensures traceability of those products. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system ensures that the products match the user's emotional state. This system consistently performs everything from product creation to storage, ensuring traceability, and emotion-based optimization.

[1260] Program processing overview

[1261] 1. Product creation request and emotion recognition

[1262] A user accesses a system that uses a generative AI model from their own device and requests the creation of a product. The request includes specific details about the type and content they want to generate. For example, a user might request, "Please create an image of a cat and a dog playing together."

[1263] Upon receiving a user request, the device collects emotional information (e.g., facial expressions, voice, text) to capture the user's emotional state. This information is then analyzed by an emotion engine to identify the user's current emotional state.

[1264] 2. Creation of the product

[1265] The server receives the user's request and the emotion information from the emotion engine, and then commands the generative AI model to create a product based on that information. The generative AI model generates new content (in this case, an image) based on this input data. The content of the generated image is adjusted according to the user's emotional state.

[1266] 3. Adding metadata to the generated data and converting it into an NFT

[1267] The server assigns a unique identifier (e.g., UUID) to the generated image, which is used to distinguish the creation from other creations.

[1268] The server then generates metadata containing this identification information, including the name of the generative artificial intelligence model that created the product, the date and time of creation, the source of the training data used, and the user's recognized emotional state.

[1269] The server uses this metadata to generate a non-fungible token (NFT), a digital asset that uses blockchain technology to associate a unique identifier and metadata with the product.

[1270] 4. Saving the Creation and NFT

[1271] The generated images and their metadata (NFTs) will be stored in a secure digital storage server that will take appropriate security measures to protect the stored data from tampering and unauthorized access.

[1272] 5. Registering on the Blockchain

[1273] The server registers the product's unique identity and metadata on the blockchain, a distributed digital ledger that ensures data consistency and immutability, providing a permanent record of when and how the product was created, ensuring traceability.

[1274] 6. Confirmation of product use and traceability

[1275] When a user uses a product, the device retrieves relevant metadata from the blockchain using the unique identification information embedded in the product. For example, when a user opens an image generated on their device, metadata can be retrieved from the blockchain to confirm which AI model created the image, as well as the training data and emotional information used. This ensures the authenticity and reliability of the product to the user.

[1276] Examples:

[1277] 1. A user requests the system to "generate an image of a cat and a dog playing together." The emotion engine analyzes the user's facial expressions and voice and recognizes the "joy" state.

[1278] 2. The device sends the request and emotion information to the server.

[1279] 3. The server issues commands to the generative artificial intelligence model to generate an image based on the user's request and "joy" emotion information.

[1280] 4. The server assigns a unique identifier in the form of a UUID to the generated image and creates metadata including the name of the generating AI model, the date and time of generation, the training data used, and emotional information.

[1281] 5. The server generates an NFT based on the metadata and stores the image and NFT in digital storage.

[1282] 6. The server registers the unique identifier and metadata on the blockchain.

[1283] 7. When a user views an image on their device, metadata is retrieved from the blockchain to provide details about how the image was created, the data used, and emotional information.

[1284] This system ensures that the outputs of generative AI models are in line with the user's emotions, and also ensures the reliability and transparency of the outputs.

[1285] The processing flow will be explained below.

[1286] Step 1:

[1287] A user accesses a system that uses a generative AI model from their own device and requests the creation of a product. The request includes specific details about the type and content they want to generate. For example, a user might enter a request such as, "Please create an image of a cat and a dog playing together."

[1288] Step 2:

[1289] Upon receiving a user request, the device simultaneously collects the user's emotional information (facial expressions, voice, text input, etc.), which is later analyzed by the emotion engine.

[1290] Step 3:

[1291] The device sends the collected emotional information to the emotion engine, which analyzes the user's emotional state. The emotion engine determines the user's current emotional state (e.g., joy, surprise, sadness, etc.) from the collected data.

[1292] Step 4:

[1293] The terminal transmits the user's request content and the analyzed emotion information to the server.

[1294] Step 5:

[1295] The server receives the user's request and emotional information, and based on that, commands the generative artificial intelligence model to create a product (image).

[1296] Step 6:

[1297] The generative AI model processes the user's request and emotional information as input data and generates new content (images). This output is adapted to the user's emotional state.

[1298] Step 7:

[1299] The server assigns a unique identifier (e.g., UUID) to the generated image, which distinguishes the creation from other creations.

[1300] Step 8:

[1301] The server generates metadata containing this identification information, including the name of the generated AI model, the date and time of generation, information about the training data used, and emotional information.

[1302] Step 9:

[1303] The server generates a non-fungible token (NFT) based on the generated metadata. An NFT is a digital asset that uses blockchain technology to associate a unique identifier and metadata with the product.

[1304] Step 10:

[1305] The server then stores the generated image and its metadata (NFT) in secure digital storage, where the data is protected from tampering and unauthorized access.

[1306] Step 11:

[1307] The server registers the artifact's unique identity and metadata on the blockchain, a distributed digital ledger that ensures data consistency and immutability.

[1308] Step 12:

[1309] When a user uses a product (e.g., an image), the device references the blockchain using the unique identifier embedded in the product to retrieve the associated metadata.

[1310] Step 13:

[1311] The device displays the acquired metadata to the user, allowing the user to see details of the creation process, data used, and recognized emotion information, ensuring the reliability and transparency of the creation.

[1312] Example 2

[1313] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1314] Conventional systems lacked the ability to reflect the user's emotional state when creating products using generative artificial intelligence models. They also faced the challenge of making it difficult to ensure traceability to guarantee the reliability and transparency of products. Furthermore, there was a lack of a way to register and manage the uniqueness of products and their associated information on the blockchain. This meant that users could not verify the authenticity of products or the creation process, which could lead to anxiety. Furthermore, products often did not meet the user's expectations or emotions.

[1315] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1316] In this invention, the server includes means for creating a product based on a user request using a generative artificial intelligence model, means for recognizing the user's emotional state and reflecting that information in the product, means for assigning a unique identification to the product and creating metadata, means for generating a non-fungible token based on the metadata, means for storing the product and metadata in digital storage, and means for registering the product's unique identification and metadata in a blockchain. This enables a highly traceable system in which products are tailored to the user's emotions and their reliability and transparency are guaranteed.

[1317] A "generative artificial intelligence model" is an artificial intelligence algorithm that has the ability to generate new content based on user requests.

[1318] An "emotion engine" is a software or hardware system that recognizes a user's emotional state and analyzes that information.

[1319] "Unique identification information" is a unique identifier given to a product to distinguish it from other products.

[1320] "Metadata" is data that describes information related to a product, including the product's identification information, the date and time of its creation, the model and dataset used to create it, and the user's emotional information.

[1321] A "non-fungible token (NFT)" is a digital token that uses blockchain technology to associate a unique identifier and metadata with a digital asset.

[1322] "Digital storage" is a storage device or service that stores data in electronic form.

[1323] "Blockchain" is a distributed digital ledger technology that ensures data consistency and immutability.

[1324] "User emotion information" is data related to the user's emotional state recognized from facial expressions, voice, and text.

[1325] This invention relates to a system that combines a generative AI model with an emotion engine to create products based on user requests and ensure the traceability of the products. This system aims to increase the reliability and transparency of the products by adding a function that reflects user emotions to conventional generative AI models.

[1326] The creation of a product begins when a user accesses the system by entering a prompt from their own device. The prompt includes the type of content they want to generate and specific details. For example, they can enter a request such as "Please create an image of a cat and a dog playing together."

[1327] The device receives a request from the user and simultaneously collects emotional information using a camera or microphone to recognize the user's emotional state. The collected emotional information (facial expressions, voice, text, etc.) is analyzed by an emotion engine to identify the user's current emotional state. This emotional information and the request content are then sent to the server.

[1328] The server receives the user's request and emotion information from the emotion engine, and commands the generative AI model to create a product. The generative AI model generates new content based on this input data. In this case, the generative AI model generates an "image of a cat and a dog playing together," and adjusts the content to reflect the user's emotion (e.g., "joy").

[1329] The server assigns a unique identifier in the form of a UUID to each generated image. This identifier is used to distinguish the generated image from other generated images. The server then generates metadata, including the identifier, the name of the generating AI model, the generation date and time, the training data source used, and the user's emotional information. Based on this metadata, the server generates a non-fungible token (NFT) and stores the generated image and the NFT in secure digital storage.

[1330] Additionally, the product's unique identity and metadata are registered on the blockchain, a distributed digital ledger that ensures data consistency and immutability, creating a permanent record of when and how the product was created.

[1331] When a user uses a product, the device retrieves relevant metadata from the blockchain using the unique identification information embedded in the product. For example, when a user views an image generated on their device, the device will display which generative AI model created the image, as well as the training data and emotional information used. This ensures the user that the product is authentic and trustworthy.

[1332] As a specific example, if a user requests, "Please generate an image of a cat and a dog playing together," the emotion engine analyzes the user's facial expressions and voice to recognize a "joy" state. The device then sends the request and emotional information to the server, which then issues commands to the generative AI model to generate an image based on the user's request and the "joy" emotional information. The generated image is then given a unique identifier in the form of a UUID, and metadata is created, including the name of the generating AI model, the date and time of generation, the training data used, and the emotional information. Finally, the generated image and NFT are stored in digital storage, and the unique identifier and metadata are registered on the blockchain, ensuring the authenticity and reliability of the image when the user views it on their device.

[1333] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1334] Step 1:

[1335] The user requests the creation of a product by entering a prompt sentence. The user enters "Please create an image of a cat and a dog playing together" into the input screen of the terminal and clicks the send button. As input, the prompt sentence is given to the terminal. The output is that the prompt sentence is sent to the terminal.

[1336] Step 2:

[1337] The device collects the user's emotional information. The device activates the camera and microphone to collect the user's facial expressions and voice. The emotion engine analyzes this data and identifies the user's emotional state. The user's facial expressions and voice data are provided to the device as input. The emotion engine analyzes this data and identifies the user's emotional state as "joy." The output is the identified emotional information.

[1338] Step 3:

[1339] The terminal sends a prompt sentence and emotional information to the server. As input, the terminal receives the prompt sentence and emotional information. The terminal incorporates this information into a packet and sends it to the server. The output is the request data and emotional information sent to the server.

[1340] Step 4:

[1341] The server receives the request content and emotional information. The server receives and analyzes the data sent from the terminal via the network protocol. The input is the prompt text and emotional information received by the server. The output is the analyzed request content and emotional information.

[1342] Step 5:

[1343] The server issues commands to the generative AI model to create a product. The server calls the generative AI model to create new content based on the received prompt and emotion information. The generative AI model uses this input data to generate a new image. The prompt and emotion information are given to the generative AI model as input. The output is the generated image.

[1344] Step 6:

[1345] The server assigns a unique identifier to the generated image. The server assigns an identifier in the form of a UUID to the generated image. The generated image is given to the server as input. The output is an image with a UUID assigned.

[1346] Step 7:

[1347] The server creates the metadata, which includes a unique identifier, the name of the generating AI model, the generation date and time, the training data used, and the user's emotional information. As input, the server is given an image with a UUID and information about its generation. The output is the generated metadata.

[1348] Step 8:

[1349] The server generates an NFT based on the metadata. The server uses the generated metadata to issue a non-fungible token (NFT) on the blockchain. The metadata is given to the server as input. The output is the generated NFT.

[1350] Step 9:

[1351] The server stores the generated images and metadata in digital storage. The server stores the generated images and metadata in secure digital storage. The generated images and metadata are given to the server as input. The output is the securely stored data.

[1352] Step 10:

[1353] The server registers the unique identifier and metadata on the blockchain. The server registers this information on the blockchain network to ensure traceability. As input, the server is given the unique identifier and metadata. The output is the data registered on the blockchain.

[1354] Step 11:

[1355] When a user uses a product, the device retrieves the metadata from the blockchain. When a user tries to view an image generated on the device, the device retrieves the metadata from the blockchain using a unique identifier. As input, the device is given the image's unique identifier. The output is the retrieved metadata.

[1356] Step 12:

[1357] The terminal displays the acquired metadata to the user. The terminal displays the acquired metadata on the screen, allowing the user to check the details of the creation process of the product, the data used, and the emotional information. The acquired metadata is given to the terminal as input. The output is the metadata displayed to the user.

[1358] (Application example 2)

[1359] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1360] Conventional product creation systems using generative AI models have issues such as insufficient means for ensuring the reliability and traceability of products, and lack of personalization that takes into account the user's emotional state toward the product. Furthermore, there are no systems in physical stores that can suggest products based on customer emotions, making it difficult to accurately grasp customer needs.

[1361] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1362] In this invention, the server includes a means for creating a product based on a user request using a generative artificial intelligence model, a means for assigning unique identification information to the product and creating metadata, and a means for adjusting the content of the product using an emotion engine so that the product matches the user's emotional state. This enables personalization based on the user's emotions while ensuring the reliability and traceability of the product. Furthermore, optimal product suggestions based on customer emotional information can be made in physical stores, improving the shopping experience.

[1363] A "generative artificial intelligence model" is an artificial intelligence software model that generates new content based on user requests.

[1364] A "product" is content, such as digital data such as images or text, created by a generative artificial intelligence model based on a user request.

[1365] "Unique identification information" means a unique identifier, such as a UUID (Universal Unique Identifier), assigned to a product to distinguish it from other products.

[1366] "Metadata" is data that describes information about a product, including the date and time the product was created, the learning data used, and the user's emotional information.

[1367] A "non-fungible token" is a digital asset that is associated with a product using blockchain technology and proves that the product is unique.

[1368] "Digital storage" is a storage device for electronically storing artifacts and metadata.

[1369] A "blockchain" is a distributed digital ledger that ensures the consistency and immutability of data.

[1370] An "emotion engine" is a software engine that recognizes a user's emotional state from their voice, facial expression, text, etc.

[1371] "Emotion information" is data relating to the user's emotional state acquired and analyzed by the emotion engine.

[1372] A "user" is an entity that utilizes the system to request the creation of a product.

[1373] "Brick and mortar store" refers to a physically existing retail store or commercial space, as opposed to an online store.

[1374] This invention relates to a system that uses a generative artificial intelligence model and an emotion engine to create products based on user requests and emotion information, and ensures the reliability and traceability of the products. In particular, this paper describes an "emotion-aware shopping assistant" that aims to improve the shopping experience in brick-and-mortar stores.

[1375] Program Overview

[1376] Hardware:

[1377] Smartphone

[1378] Smart Glasses

[1379] robot

[1380] software:

[1381] Generative AI model

[1382] Emotion Engine

[1383] Blockchain technology

[1384] Program processing flow

[1385] 1. User Emotion Recognition

[1386] The device (smartphone or smart glasses) captures the user's facial expressions through a camera, and the emotion engine analyzes them to recognize the user's emotional state. Voice input is also accepted, and the emotional state is analyzed from the voice data.

[1387] 2. Content Generation Request

[1388] The user can input the category of product they are looking for and their specific preferences through the terminal. They can also make requests by voice. For example, they can make a request such as, "Please suggest products that will help me relax."

[1389] 3. Creating generated content

[1390] The server instructs the generative AI model to create a product based on the user's request and the emotion information obtained from the emotion engine. The generative AI model then uses this information to generate the optimal product or content for the user.

[1391] 4. Adding traceability information

[1392] Each generated product is assigned a unique identification (UUID format), and metadata is created that includes the date and time of creation, usage data, emotional information, etc. This ensures the traceability of the product.

[1393] 5. NFT and storage

[1394] The server generates a non-fungible token (NFT) based on the generated metadata and stores the generated token and metadata in a secure digital storage. The generated token and metadata are registered on the blockchain, ensuring the consistency and immutability of the data.

[1395] 6. Presentation to the User

[1396] The terminal obtains metadata from the blockchain based on the product's unique identification information, and displays the product's traceability information to the user when proposing a product, allowing them to confirm its authenticity.

[1397] Specific examples

[1398] For example, if a user is tired and requests relaxation products in a physical store, the following prompt sentence is input to the generative AI model:

[1399] "Please suggest some relaxation products for tired users."

[1400] The generative AI model suggests relaxing aroma oils and massage devices, and displays traceability information such as the manufacturer and usage instructions. In this way, the present invention enables personalization based on the user's emotions, improving the shopping experience in physical stores.

[1401] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1402] Step 1:

[1403] emotion recognition

[1404] The device (smartphone or smart glasses) uses a camera to capture the user's facial expressions and also accepts voice input. This data is passed to an emotion engine, which analyzes the user's emotional state from their facial expressions and voice. Specifically, the emotion engine analyzes facial features and voice tones to identify emotions such as joy, sadness, fatigue, and excitement.

[1405] Input: User's facial expression data, voice data

[1406] Output: User's emotional information (happiness, sadness, fatigue, etc.)

[1407] Step 2:

[1408] Content Generation Request

[1409] The user operates the device and requests the desired product category and specific preferences through text input or voice input. For example, they might input, "Please suggest products that will help me relax." The device receives this request and sends it to the server.

[1410] Input: User request (text or voice)

[1411] Output: User request data

[1412] Step 3:

[1413] Creating generated content

[1414] The server receives the user's request data and the emotion information obtained from the emotion engine, and based on that, instructs the generative AI model to create a product. The generative AI model generates optimal products and content based on the prompt. For example, if the user is tired, it will suggest products with a relaxing effect.

[1415] Input: User request data, emotion information

[1416] Output: Generated content

[1417] Step 4:

[1418] Adding traceability information

[1419] The server assigns a unique identifier (UUID format) to the generated artifact and creates metadata including the creation date and time, usage data, emotional information, etc. This allows the authenticity and history of the artifact to be verified later.

[1420] Input: Generated content

[1421] Output: Unique identifier, metadata

[1422] Step 5:

[1423] NFT and storage

[1424] The server generates a non-fungible token (NFT) based on the generated metadata, then stores the generated token and metadata in secure digital storage, which protects the data from tampering and unauthorized access.

[1425] Input: Metadata

[1426] Output: NFT, stored artifact and metadata

[1427] Step 6:

[1428] Blockchain Registration

[1429] The server registers the unique identity and metadata of the artifact in the blockchain, which ensures the traceability and immutability of the artifact.

[1430] Input: Unique identifier, metadata

[1431] Output: Information registered on the blockchain

[1432] Step 7:

[1433] Presenting to the user

[1434] The terminal retrieves metadata from the blockchain based on the product's unique identification information and displays the product's traceability information to the user when proposing a product, allowing the user to confirm the authenticity of the proposed product.

[1435] Input: Unique Identifier

[1436] Output: Presentation of the product including traceability information

[1437] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1438] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1439] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1440] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1441] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1442] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1443] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1444] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1445] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1446] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1447] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1448] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1449] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1450] 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.

[1451] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1452] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1453] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1454] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1455] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1456] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1457] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1458] The following is further disclosed regarding the above embodiment.

[1459] (Claim 1)

[1460] A means for generating a product based on a request from a user using a generative artificial intelligence model;

[1461] a means for providing a unique identifier for the artifact and creating metadata;

[1462] A means for generating non-fungible tokens based on the metadata;

[1463] means for storing the artifacts and metadata in digital storage;

[1464] and means for registering the unique identification and metadata of the product on the blockchain.

[1465] (Claim 2)

[1466] 10. The system of claim 1, further comprising means for a user to retrieve and display metadata of a product from the blockchain based on the unique identification information of the generated product.

[1467] (Claim 3)

[1468] 2. The system of claim 1, wherein the unique identification information assigned to the product is a universally unique identifier (UUID).

[1469] "Example 1"

[1470] (Claim 1)

[1471] A means for creating a product based on a user's request using a generative machine learning model;

[1472] a means for assigning unique identification information to the product and creating attribute information;

[1473] A means for generating a non-substitutable code based on attribute information;

[1474] means for storing the product and attribute information in an electronic repository;

[1475] and means for registering the unique identification information and attribute information of the product in distributed ledger technology.

[1476] (Claim 2)

[1477] 10. The system of claim 1, further comprising means for a user to obtain and display attribute information of the product from the distributed ledger technology based on the unique identification information of the generated product.

[1478] (Claim 3)

[1479] 10. The system of claim 1, wherein the unique identification information assigned to the product is a universally unique identifier.

[1480] "Application Example 1"

[1481] (Claim 1)

[1482] A means for generating a product based on a request from a user using a generative artificial intelligence model;

[1483] a means for providing a unique identifier for the artifact and creating metadata;

[1484] A means for generating non-fungible tokens based on the metadata;

[1485] means for storing the artifacts and metadata in digital storage;

[1486] a means for registering the unique identity and metadata of the product on the blockchain;

[1487] A means for a user to individually request a product using a generative artificial intelligence model and check the traceability of the product's metadata using prompt statements;

[1488] A system including:

[1489] (Claim 2)

[1490] 10. The system of claim 1, further comprising means for a user to retrieve and display metadata of a product from the blockchain based on the unique identification information of the generated product.

[1491] (Claim 3)

[1492] 2. The system of claim 1, wherein the unique identification information assigned to the product is a universally unique identifier (UUID).

[1493] "Example 2: Combining Emotion Engines"

[1494] (Claim 1)

[1495] A means for generating a product based on a request from a user using a generative artificial intelligence model;

[1496] means for recognizing the user's emotional state and reflecting that information in the product;

[1497] a means for providing a unique identifier for the artifact and creating metadata;

[1498] A means for generating non-fungible tokens based on the metadata;

[1499] means for storing the artifacts and metadata in digital storage;

[1500] and means for registering the unique identification and metadata of the product on the blockchain.

[1501] (Claim 2)

[1502] 10. The system of claim 1, further comprising means for a user to retrieve and display metadata of a product from the blockchain based on the unique identification information of the generated product.

[1503] (Claim 3)

[1504] 2. The system of claim 1, wherein the unique identification information assigned to the product is a universally unique identifier (UUID).

[1505] (Claim 4)

[1506] 10. The system of claim 1, further comprising means for transmitting a request for a product from a user terminal to a server and collecting emotion information of the user.

[1507] (Claim 5)

[1508] 10. The system of claim 1, further comprising means for analyzing the user's emotional information using an emotion engine and adjusting the content of the product according to the user's emotional state.

[1509] "Application example 2 when combining emotion engines"

[1510] (Claim 1)

[1511] A means for generating a product based on a request from a user using a generative artificial intelligence model;

[1512] a means for providing a unique identifier for the artifact and creating metadata;

[1513] A means for generating non-fungible tokens based on the metadata;

[1514] means for storing the artifacts and metadata in digital storage;

[1515] a means for registering the unique identity and metadata of the product on the blockchain;

[1516] means for adjusting the content of the product using the emotion engine so that the product is adapted to the user's emotional state;

[1517] means for including the user's emotion information acquired by the emotion engine in the metadata of the product;

[1518] A system including:

[1519] (Claim 2)

[1520] 10. The system of claim 1, further comprising means for a user to retrieve and display metadata of a product from the blockchain based on the unique identification information of the generated product.

[1521] (Claim 3)

[1522] 2. The system of claim 1, wherein the unique identification information assigned to the product is a unique identifier. [Explanation of symbols]

[1523] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for generating a product based on a request from a user using a generative artificial intelligence model; a means for providing a unique identifier for the artifact and creating metadata; A means for generating non-fungible tokens based on the metadata; means for storing the artifacts and metadata in digital storage; and means for registering the unique identification and metadata of the product on the blockchain.

2. The system of claim 1 , further comprising means for a user to retrieve and display metadata of a product from the blockchain based on the unique identification information of the created product.

3. 2. The system according to claim 1, wherein the unique identification information given to the product is a universally unique identifier.

Images