system

Abstract

We provide the system. [Solution] A means for receiving user input and inputting the image of clothing as text or image, A means for analyzing the user input, creating an appropriate image generation prompt, and sending it to the server, A generation means for generating an image based on the prompt, A means for searching for the most suitable clothing item from a database of clothing items based on the generated image, A means for returning the proposed clothing items and generated images to the user, A method for generating model images wearing clothes to be sold using AI, A means for reflecting the generated model image on the product page, A system including a means for the user to confirm and purchase the proposed clothing items.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In conventional online fashion platforms, it is difficult for users to specifically convey the image of the clothing they desire, and it takes a lot of time and effort to find suitable products. Furthermore, it is difficult for sellers to prepare images to make their products look more attractive. In particular, for individual sellers and used goods sellers, there is a problem that it is difficult to prepare professional-looking images. These problems have led to a decrease in user satisfaction, difficulty in selling products, and an increase in waste loss due to inventory accumulation.

Means for Solving the Problems

[0005] This invention provides a system that allows users to input their desired clothing image as text or images, creates appropriate image generation prompts based on that input, and generates images using AI. Furthermore, it includes means for making optimal suggestions from a database of clothing items based on the generated images. In addition, it provides a system that allows individual sellers and sellers of used goods to easily create professional-looking images by generating model images of the clothes being sold using AI and reflecting them on the product page. As a result, users can easily choose clothing, and sellers can make their products look more attractive, leading to increased sales and reduced waste.

[0006] 1. "User input" refers to information provided by system users through text, images, etc.

[0007] 2. An "image generation prompt" is a set of instructions that the AI ​​uses to generate a specific image based on user input.

[0008] 3. "Generation means" refers to technical means for generating images based on user input using AI.

[0009] 4. "Database search" is the process of finding data that matches specific criteria from a database of clothing items.

[0010] 5. "Suggestion method" refers to a function that presents the user with the most suitable clothing items.

[0011] 6. "Model image generation means" refers to a technology for using AI to create images of models wearing the clothing that will be sold.

[0012] 7. "Reflecting on the product page" refers to the process of displaying the generated model images and suggested clothing item information on the product sales page.

[0013] 8. The "purchase process" refers to the series of steps a user takes to select and actually purchase a suggested clothing item. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention is a system that begins with the user inputting an image of the clothing they desire. Based on that image, AI suggests appropriate clothing items, and further generates and presents images of a model wearing those outfits. This system goes through multiple processing steps between the user, the terminal, and the server to improve user satisfaction and seller convenience.

[0036] System Configuration

[0037] user:

[0038] Users use their devices to input an image of the clothing they want. Specifically, they can enter their request in text or upload a reference image.

[0039] Example: Launch the app on your smartphone or computer and type "a casual style with a denim jacket, black leggings, and sneakers" into the text box. Alternatively, upload an image of your favorite outfit.

[0040] Terminal:

[0041] The terminal analyzes the input data received from the user and creates an appropriate image generation prompt.

[0042] This prompt is sent to the server to request image generation by AI.

[0043] Furthermore, the suggested results and generated images returned from the server are displayed to the user.

[0044] server:

[0045] Based on prompts received from the terminal, the server uses image generation AI to generate an image that reproduces the specified clothing style.

[0046] Based on the generated image, the system searches for similar items in its clothing item database and provides optimal suggestions.

[0047] Additionally, if necessary, model images of customers wearing the clothing items being sold will be generated and displayed on the product pages.

[0048] Program processing details

[0049] Receiving and analyzing user input

[0050] User inputs clothing image: Users send requests to the system by entering text or images on their device.

[0051] The terminal analyzes the input: The terminal processes the input data using natural language processing and image analysis techniques to create specific image generation prompts.

[0052] Creating a prompt and sending it to the server

[0053] The terminal generates the prompt: Based on the analysis results, it forms the appropriate prompt. For example, if the user enters "casual denim jacket, black leggings, and sneakers," the terminal will generate the prompt "generate image: casual denim jacket with black leggings and sneakers."

[0054] The terminal sends a prompt to the server: It generates and sends an API request to send a prompt to the server.

[0055] Image generation and product suggestions

[0056] The server receives a prompt and generates an image: The server uses an image generation AI to generate an image of the specified clothing.

[0057] The server searches the database: Based on the generated image, it searches the database of clothing items for the best suggestions. These suggestions are then sent back to the user.

[0058] Displaying results to the user and generating model images.

[0059] The server returns the results to the user: it sends a list of suggested clothing items and the generated images back to the user's device.

[0060] The device displays the results to the user: The returned results are displayed to the user in an easy-to-read format. This allows the user to review the suggested items and consider purchasing them.

[0061] The server generates model images and displays them on the product page: If necessary, AI generates model images of the clothing being sold and displays them on the product page. This allows sellers to easily provide professional-looking images.

[0062] This system allows users to easily find clothing that best suits their image, and enables sellers to create more appealing product pages.

[0063] The following describes the processing flow.

[0064] Step 1:

[0065] user:

[0066] Enter the image of the clothing you're looking for.

[0067] Example: The user enters "a casual denim jacket, black leggings, and sneakers" into the text box and uploads reference images as needed.

[0068] Step 2:

[0069] Terminal:

[0070] Receives and analyzes user input.

[0071] Example: Analyze text and images to extract keywords such as "casual," "denim jacket," "black leggings," and "sneakers."

[0072] Step 3:

[0073] Terminal:

[0074] Create an appropriate image generation prompt.

[0075] Example: Based on the extracted keywords, create a prompt that says "generate image: casual denim jacket with black leggings and sneakers".

[0076] Step 4:

[0077] Terminal:

[0078] Send the created prompt to the server.

[0079] Example: Use an API request to send the prompt "generate image: casual denim jacket with black leggings and sneakers" to the server.

[0080] Step 5:

[0081] server:

[0082] Receive the prompt and pass it to the image generation AI.

[0083] Example: Analyze the received prompt and input it into an AI image generation model (e.g., GAN or Diffusion model).

[0084] Step 6:

[0085] server:

[0086] The image generation AI generates images of the specified clothing style.

[0087] Example: Generate an image of a "casual denim jacket, black leggings, and sneakers."

[0088] Step 7:

[0089] server:

[0090] The generated image is used to search a database of clothing items.

[0091] Example: Using visual recognition technology based on the generated image, search a database for related items such as a denim jacket, black leggings, and sneakers.

[0092] Step 8:

[0093] server:

[0094] The search results and generated images are sent back to the device.

[0095] Example: A list of suggested products (product ID, name, price, detail link) and generated coordinated images are returned to the device in JSON format.

[0096] Step 9:

[0097] Terminal:

[0098] The suggested clothing items and generated images are displayed to the user.

[0099] Example: Display the generated image and a list of products on the app screen, and provide a link to each product.

[0100] Step 10:

[0101] user:

[0102] Review the suggested clothing items and add the ones you like to your cart.

[0103] Example: Click the "Add to Cart" button for a denim jacket you like.

[0104] Step 11:

[0105] user:

[0106] Proceed with the purchase process.

[0107] Example: Enter your payment information on the purchase screen and click the "Confirm Order" button.

[0108] Step 12:

[0109] Terminal:

[0110] The purchase information is sent to the server and the transaction is processed.

[0111] Example: Purchase information is sent to the server, which then checks inventory and processes payment.

[0112] Step 13:

[0113] server:

[0114] If necessary, generate model images wearing the clothing that will be sold.

[0115] Example: The server uses AI to generate images of a model wearing a denim jacket.

[0116] Step 14:

[0117] server:

[0118] The generated model image is reflected on the product page.

[0119] Example: Save a new model image to the database and display it on the product page.

[0120] These steps make it easy for users to find and purchase clothing that matches their image. Additionally, sellers can easily display their products in a professional manner.

[0121] (Example 1)

[0122] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0123] Traditional online shopping systems lacked the means to support users in visualizing the specific clothing they wanted, forcing them to choose their outfits themselves based on a lot of information. This was time-consuming and laborious, sometimes resulting in a decrease in purchase intent. Furthermore, sellers lacked the means to easily generate professional images to showcase their products attractively. To meet the needs of both users and sellers, there is a need for more efficient and accurate clothing item suggestions and the provision of visual information.

[0124] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0125] In this invention, the server includes means for receiving user input and inputting an image of clothing as text or an image; means for analyzing the user input and creating an appropriate image generation prompt and sending it to the server; means for generating an image based on the prompt; means for searching for the optimal clothing item from a database of clothing items based on the generated image; means for returning the suggested clothing item and the generated image to the user; means for generating a model image of the clothing being sold using artificial intelligence; means for reflecting the generated model image on the product page; means for the user to confirm the suggested clothing item and proceed with the purchase; processing means for the terminal to analyze user input using natural language processing technology and image analysis technology; transmission means for sending the prompt generated by the terminal to the server via an API request; means for the server to search the database based on the generated image and create a suggestion list; transmission means for the server to generate an API response and return it to the user's terminal; and display means for the terminal to display the results to the user. As a result, users can easily find the optimal item based on their desired image of clothing, and sellers can easily create and provide professional product images.

[0126] "User input" refers to text or images that a user provides to the system.

[0127] "Clothing image" refers to text or images that specifically describe the type of clothing the user desires.

[0128] An "image generation prompt" is a set of instructions used to request an AI model to generate an image based on the user's input data.

[0129] A "server" is a central processing unit that analyzes user input, creates image generation prompts, performs database searches based on the generated images, and suggests the most suitable clothing items.

[0130] "Generation means" refers to a function that generates images based on user requests using a generation AI model.

[0131] A "database" is a storage device that systematically stores and allows retrieval of information about clothing items.

[0132] The "suggestion method" refers to a function that selects the most suitable clothing items from a database based on the generated image and suggests them to the user.

[0133] "Artificial intelligence" refers to the technology that enables computers to learn, reason, and improve themselves by mimicking human intelligence.

[0134] "Natural language processing technology" refers to the technology of analyzing and understanding human language, and is used to analyze the meaning of text data.

[0135] "Image analysis technology" refers to techniques for extracting specific information from image data.

[0136] An "API request" is a request from one software program to another program to perform a specific function.

[0137] An "API response" is the response that another software program returns to an API request.

[0138] "Display means" refers to a function that presents results in an easy-to-understand manner on the user's terminal.

[0139] This invention is a system designed to simplify the user's clothing selection process and assist sellers in creating attractive product pages. This system achieves improved user satisfaction and seller convenience through multiple processing steps involving the user, terminal, and server.

[0140] Overall system configuration

[0141] user:

[0142] Users input their desired clothing image using a smartphone or computer application. Specifically, they can enter their request in text or upload reference images.

[0143] Specific example:

[0144] Enter "A casual style consisting of a denim jacket, black leggings, and sneakers" into the text box.

[0145] Alternatively, upload an image of your favorite outfit.

[0146] Terminal:

[0147] The terminal analyzes the input data received from the user and creates an appropriate image generation prompt. This prompt is sent to the server, requesting AI-generated image generation. Furthermore, the suggested results and generated image returned from the server are displayed to the user.

[0148] Example of technology used:

[0149] For natural language processing techniques, we use Python's NLTK library and spaCy.

[0150] For image analysis, we use OpenCV and TENSORFLOW®.

[0151] server:

[0152] Based on prompts received from the terminal, the server uses image generation AI to generate an image that replicates the specified clothing style. Based on this generated image, it searches a database of clothing items for similar products and makes optimal suggestions. If necessary, it generates model images of the clothing items being sold and displays them on the product page.

[0153] Example of technology used:

[0154] For image generation, we use OpenAI's DALL-E and Stability AI's Stable Diffusion as generation AI models.

[0155] SQL or NoSQL database technologies are used for searching the database.

[0156] Specific processing details of the system

[0157] Receiving and analyzing user input:

[0158] The user inputs an image of the clothing they are looking for as text or an image. The device analyzes the received input data using natural language processing and image analysis technologies to form a specific image generation prompt. For example, if the user inputs "casual denim jacket, black leggings, and sneakers," the prompt "generate image: casual denim jacket with black leggings and sneakers" will be generated.

[0159] Example of a prompt:

[0160] "generate image: casual denim jacket with black leggings and sneakers"

[0161] Sending the prompt to the server:

[0162] The system generates an API request to send the prompt generated by the terminal to the server, and then sends it to the server using an HTTP POST request or similar method.

[0163] Image generation:

[0164] Based on the received prompt, the server uses an image generation AI to generate an image of the specified clothing. The generated image is temporarily stored.

[0165] Product proposal generation:

[0166] Based on the generated image, the server searches the database and suggests similar clothing items. These suggestions are tailored to the user's needs.

[0167] Returning and displaying results to the user:

[0168] The server sends the generated image and suggested clothing items together in an API response to the user's device. The device then displays the received results to the user.

[0169] Generating model images and updating product pages as needed:

[0170] The server uses AI to generate images of models wearing clothing items as needed, and displays them on the product page. This allows sellers to easily create and provide professional product images.

[0171] This system makes it easy for users to find the perfect outfit to match their image, and also allows sellers to create more appealing product pages.

[0172] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0173] Step 1:

[0174] The user enters an image of the clothing they want to wear.

[0175] Input: Text or reference image

[0176] Specific actions: The user uses a smartphone or computer application and enters "a casual style with a denim jacket, black leggings, and sneakers" into a text box. Alternatively, they can upload an image of their favorite outfit.

[0177] Output: Text or image data entered by the user.

[0178] Step 2:

[0179] The terminal analyzes user input.

[0180] Input: Text or image data entered by the user.

[0181] Specific operation: The device analyzes text using natural language processing techniques (e.g., Python's NLTK library or spaCy). It also analyzes image data using image analysis techniques (e.g., OpenCV or TensorFlow).

[0182] Output: Information based on the clothing image obtained from the analysis (e.g., "casual denim jacket with black leggings and sneakers")

[0183] Step 3:

[0184] The terminal generates the prompt.

[0185] Input: Information based on clothing images obtained from the analysis results.

[0186] Specific operation: The device creates a prompt suitable for the generated AI model. For example, the prompt "generate image: casual denim jacket with black leggings and sneakers" is generated.

[0187] Output: Generated prompt message

[0188] Step 4:

[0189] The terminal sends a prompt to the server.

[0190] Input: Generated prompt message

[0191] Specific operation: The terminal generates an HTTP POST request and sends the generated prompt message to the server as an API request.

[0192] Output: Prompt message sent to the server

[0193] Step 5:

[0194] The server receives the prompt and generates the image.

[0195] Input: Prompt message sent from the terminal

[0196] Specific operation: The server uses an image generation AI (e.g., OpenAI's DALL-E or Stability AI's Stable Diffusion) to generate an image of the specified clothing. The generated image is temporarily stored.

[0197] Output: Image of the generated clothing

[0198] Step 6:

[0199] The server searches the database and generates product suggestions.

[0200] Input: Image of the generated clothing

[0201] Specific operation: The server searches a database of clothing items based on the generated image. This search uses SQL or NoSQL database technology. The most suitable clothing item is selected from the search results.

[0202] Output: List of suggested optimal clothing items

[0203] Step 7:

[0204] The server returns the results to the user.

[0205] Input: A list of generated images and suggested clothing items.

[0206] Specific operation: The server generates an API response and sends the generated image and a list of suggested clothing items to the user's device.

[0207] Output: A list of images and clothing items returned to the user's device.

[0208] Step 8:

[0209] The device displays the results to the user.

[0210] Input: List of images and clothing items returned from the server.

[0211] Specific operation: The device displays the received results on the user's screen. The UI allows the user to easily review the suggested items.

[0212] Output: A list of images and clothing items displayed on the user's screen.

[0213] Step 9:

[0214] The server generates model images as needed and displays them on the product page.

[0215] Input: Settings for generating data and model images of clothing items to be sold.

[0216] Specific operation: The server uses AI to generate images of models wearing clothing items and displays them on the product page.

[0217] Output: Model image reflected on the product page

[0218] (Application Example 1)

[0219] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0220] Traditional online shopping sites have presented challenges, such as users spending a lot of time and effort finding clothing items that match their desired fashion style. Furthermore, the sheer number of product options often overwhelms users, making it difficult to choose the right items. Additionally, product images alone are often insufficient to convey how the items will look when worn, potentially diminishing purchasing intent. This invention aims to solve these problems and provide a system that improves the user's purchasing experience.

[0221] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0222] This invention includes a server that generates specific prompt text based on the fashion style entered by the user and sends it to an image generation AI model; a server that displays a list of related clothing items based on the generated model image; a server that allows the user to click on a clothing item to go to a details page and complete the purchase process; and a server that collects post-purchase feedback. This makes it possible for the user to easily find appropriate clothing items that match their desired fashion style, visually confirm them with model images, and purchase them on the spot.

[0223] "User input" refers to the user specifying their desired clothing image to the system using text or images.

[0224] An "image generation prompt" is a text message that generates specific instructions based on user input and sends to an image generation AI model.

[0225] An "image generation AI model" is an artificial intelligence that generates images of specified clothing based on the input prompt text.

[0226] "Clothing items" is a term that refers to fashion-related products and accessories, and includes a range of products included in the database.

[0227] A "database" is an information management system that systematically stores information about clothing items.

[0228] A "model image" is an image of a model wearing the generated clothing image, and is generated to present it visually to the user.

[0229] A "prompt message" is text generated by analyzing user input and contains specific instructions for the image generation AI model.

[0230] The "product list" is a list of related clothing items suggested based on the generated model image.

[0231] A "details page" is a webpage or screen that displays detailed information about a suggested clothing item.

[0232] "Feedback" refers to the opinions and impressions that users provide after a purchase, and is used to improve the system and enhance the user experience.

[0233] This invention relates to a system that suggests clothing items that accurately reflect the user's desired fashion style and allows them to purchase those items. This system optimizes the user experience and purchase process through the coordinated operation of user input, terminals, and servers.

[0234] System Overview

[0235] 1. User input

[0236] Users access the system using smartphones or personal computers.

[0237] Users can enter a text description of their desired outfit or upload a reference image.

[0238] 2. Terminal processing

[0239] The terminal will be equipped with an interface for receiving user input.

[0240] Text input is analyzed using a natural language processing library (e.g., spaCy).

[0241] For image input, an image analysis library (e.g., OpenCV) is used.

[0242] The input data is analyzed, and specific prompt messages are generated.

[0243] Specific example: If the user enters "a casual summer dress to wear on the beach in summer," the prompt "generate image: casual summer dress for beach" will be generated.

[0244] 3. Server processing

[0245] Receives prompt messages sent from the terminal.

[0246] Using an image generation AI model (e.g., OpenAI's DALL-E), images of clothing based on prompt text are generated.

[0247] Based on the generated image, the system searches for related products in a database of clothing items (e.g., MySQL®).

[0248] Send the search results and generated images to the device.

[0249] 4. Display and Purchase Process

[0250] The device displays a list of suggested clothing items and generated images to the user.

[0251] Users can click on suggested items to go to the details page and proceed with the purchase.

[0252] An interface is provided for collecting post-purchase feedback.

[0253] Examples of specific cases and prompt statements

[0254] Specific example:

[0255] 1. The user enters the text, "A casual dress perfect for spring cherry blossom viewing."

[0256] 2. The terminal generates the prompt message "generate image: casual spring dress for cherry blossom viewing".

[0257] 3. The server sends the generated prompt message to the image generation AI model and generates the corresponding image.

[0258] 4. Search the database of clothing items for related products and display them to the user along with a list of suggestions.

[0259] 5. The user navigates to the product details page and makes a purchase.

[0260] Hardware and software to be used

[0261] Hardware: Smartphones, PCs, servers, GPUs (as needed)

[0262] Software: Mobile app development frameworks (e.g., React Native), natural language processing libraries (e.g., spaCy), image analysis libraries (e.g., OpenCV), AI image generation models (e.g., OpenAI's DALL-E), API request libraries (e.g., Axios), database management systems (e.g., MySQL), frontend libraries (e.g., React.js)

[0263] In this way, a system is created that suggests clothing items that best suit the image entered by the user, allowing them to easily purchase them after visual confirmation.

[0264] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0265] Step 1:

[0266] Users access the system using their smartphones or computers. They then enter an image of their desired clothing style into a text box, or upload a reference image. This allows the system to retrieve the user's fashion preferences. The input is in text or image format, and this information is then analyzed.

[0267] Step 2:

[0268] The terminal receives user input and calls natural language processing libraries (e.g., spaCy) or image analysis libraries (e.g., OpenCV) to analyze its content. For text input, natural language processing converts the content into structured data (such as key-value pairs). For image input, image analysis techniques are used to extract image features. Based on these analysis results, a specific prompt message (e.g., "generate image: casual summer dress for beach") is generated. The input is user text or images, and the output is a specific prompt message.

[0269] Step 3:

[0270] The generated prompt message is sent from the terminal to the server. An API request library (e.g., Axios) and a communication protocol (e.g., HTTP) are used in this process. The terminal formats the prompt message into an API request format and sends it to the server. The input is the generated prompt message, and the output is the request sent to the server.

[0271] Step 4:

[0272] The server passes the received prompt message to an image generation AI model (e.g., OpenAI's DALL-E), and generates an image based on that prompt. The AI ​​model analyzes the generation prompt and generates an image with the specified clothing. The input is the prompt message, and the output is the generated image.

[0273] Step 5:

[0274] The server uses a database management system (e.g., MySQL) to search for clothing items based on the generated image. This search extracts the most suitable specific clothing item using the image analysis results and relevant metadata. The input is the generated image, and the output is a list of related clothing items.

[0275] Step 6:

[0276] The server returns the generated image and the list of searched clothing items to the terminal. The input is the search result and the generated image, and the output is the data to be sent to the terminal.

[0277] Step 7:

[0278] The terminal displays the received data to the user. Specifically, it provides a user interface that can beautifully display the list of proposed clothing items and the generated image. The input is the data from the server, and the output is the display on the user interface.

[0279] Step 8:

[0280] The user clicks on the proposed item to move to the detailed page. On that detailed page, the detailed information, price, and purchase button of each item are displayed. The user can perform the purchase procedure here. The input is the clothing item list, and the output is the transition to the detailed page.

[0281] Step 9:

[0282] After the purchase is completed, the user accesses the interface for providing feedback. The terminal receives the feedback from the user and sends it to the server. This feedback can be used to improve the system and enhance the user experience. The input is the user's feedback, and the output is the data to be sent to the server.

[0283] Through the above steps, a system is realized that enables the user to easily find their desired fashion style, visually confirm it, and purchase it on the spot.

[0284] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform specific processing using the user's emotion.

[0285] This invention is a system that allows users to input an image of the clothing they desire, based on which AI proposes appropriate clothing items, and further realizes a coordination proposal considering the user's emotional state by using an emotion engine. This system improves user satisfaction and enhances the convenience for producers through multiple processing steps among the user, the terminal, and the server.

[0286] System Configuration

[0287] User:

[0288] The user uses the terminal to input an image of the clothing they desire. Specifically, they can input requests in text or upload a reference image.

[0289] Furthermore, the emotion engine detects and analyzes the user's expression, voice, and biometric information to grasp the user's current emotional state.

[0290] Example: Launch an app on a smartphone or computer, enter "a style combining a casual denim jacket, black leggings, and sneakers" in the text box. Or upload an image of a favorite coordination, and the emotion engine analyzes the expression and voice with the camera and microphone.

[0291] Terminal:

[0292] The terminal analyzes the input data and emotion data received from the user and creates an appropriate image generation prompt.

[0293] This prompt is sent to the server to request image generation by AI.

[0294] Furthermore, the proposal results and generated images sent back from the server are displayed to the user.

[0295] Server:

[0296] The server generates an image that reproduces the specified clothing style using an image generation AI based on the prompt received from the terminal.

[0297] Based on the generated image, similar products are searched from the database of clothing items, and an optimal proposal is made.

[0298] The proposed items are adjusted based on the emotional state analyzed by the emotion engine.

[0299] If necessary, an AI-generated model image of the clothing item for sale is generated and reflected on the product page.

[0300] Contents of program processing

[0301] User input and emotion recognition

[0302] The user inputs an image of clothing: By the user inputting text or an image on the terminal, a request is sent to the system.

[0303] The emotion engine recognizes emotions: Analyzes the user's expression, voice, and biometric information to grasp the current emotional state. For example, if the user has a smiling face, it detects the emotional state of "joy".

[0304] Prompt creation and transmission to the server

[0305] The terminal analyzes the input and emotions: Generates an appropriate prompt based on the text, image, and emotional state. For example, if the user desires casual clothing and is in an emotional state of "joy", an appropriate prompt is created.

[0306] The terminal sends the prompt to the server: Sends the prompt to the server through the API and requests the necessary processing.

[0307] Image generation and product proposal

[0308] The server receives a prompt and generates an image: The server uses an image generation AI to generate an image of the specified clothing style.

[0309] The server searches the database: Based on the generated image, it searches the database of clothing items for the most suitable item.

[0310] The server adjusts suggestions based on the user's emotional state: It selects items from the search results that are appropriate for the user's emotional state and adjusts the suggestions accordingly.

[0311] Displaying results to the user and generating model images.

[0312] The server returns results to the user: it sends a list of suggested clothing items and generated images back to the user's device. The suggestions take the user's emotional state into consideration.

[0313] The device displays the results to the user: The returned results are displayed to the user in an easy-to-read format. This allows the user to review the suggested items and consider purchasing them.

[0314] The server generates model images and displays them on the product page: If necessary, it generates model images of the clothing being sold and displays them on the product page.

[0315] This system will allow users to easily find the perfect outfit to match their emotional state, and sellers will be able to easily display their products in a professional way.

[0316] The following describes the processing flow.

[0317] Step 1:

[0318] user:

[0319] Enter the image of the clothing you're looking for.

[0320] Example: The user enters "a casual denim jacket, black leggings, and sneakers" into a text box and uploads reference images as needed. They also send facial expressions and voice information using a camera and microphone that support the emotion engine.

[0321] Step 2:

[0322] Terminal:

[0323] Receives and analyzes user input.

[0324] Example: Analyze text and images to extract keywords such as "casual," "denim jacket," "black leggings," and "sneakers."

[0325] Step 3:

[0326] Terminal:

[0327] Use an emotion engine to recognize the user's emotions.

[0328] For example, a camera captures the user's facial expressions, and a voice recognition system analyzes the tone of their voice to determine their emotional state, such as whether they are happy or depressed.

[0329] Step 4:

[0330] Terminal:

[0331] Create an appropriate image generation prompt.

[0332] Example: Based on the extracted keywords and recognized emotional state, create a prompt that says, "generate image: casual denim jacket with black leggings and sneakers for a happy mood."

[0333] Step 5:

[0334] Terminal:

[0335] Send the created prompt to the server.

[0336] Example: Use an API request to send the prompt "generate image: casual denim jacket with black leggings and sneakers for a happy mood" to the server.

[0337] Step 6:

[0338] server:

[0339] Receive the prompt and pass it to the image generation AI.

[0340] Example: Analyze the received prompt and input it into an AI image generation model (e.g., GAN or Diffusion model).

[0341] Step 7:

[0342] server:

[0343] The image generation AI generates images of the specified clothing style.

[0344] Example: Generate an image of a "casual denim jacket, black leggings, and sneakers."

[0345] Step 8:

[0346] server:

[0347] The generated image is used to search a database of clothing items.

[0348] Example: Using visual recognition technology based on the generated image, search a database for related items such as a denim jacket, black leggings, and sneakers.

[0349] Step 9:

[0350] server:

[0351] Adjust product suggestions based on the results of the emotion engine.

[0352] Example: Select the most suitable product from the search results based on the user's emotional state and adjust the suggestion list accordingly.

[0353] Step 10:

[0354] server:

[0355] The search results and generated images are sent back to the device.

[0356] Example: A list of suggested products (product ID, name, price, detail link) and generated coordinated images are returned to the device in JSON format.

[0357] Step 11:

[0358] Terminal:

[0359] The suggested clothing items and generated images are displayed to the user.

[0360] Example: Display the generated image and a list of products on the app screen, and provide a link to each product.

[0361] Step 12:

[0362] user:

[0363] Review the suggested clothing items and add the ones you like to your cart.

[0364] Example: Click the "Add to Cart" button for a denim jacket you like.

[0365] Step 13:

[0366] user:

[0367] Proceed with the purchase process.

[0368] Example: Enter your payment information on the purchase screen and click the "Confirm Order" button.

[0369] Step 14:

[0370] Terminal:

[0371] The purchase information is sent to the server and the transaction is processed.

[0372] Example: Purchase information is sent to the server, which then checks inventory and processes payment.

[0373] Step 15:

[0374] server:

[0375] If necessary, generate model images wearing the clothing that will be sold.

[0376] Example: The server uses AI to generate images of a model wearing a denim jacket.

[0377] Step 16:

[0378] server:

[0379] The generated model image is reflected on the product page.

[0380] Example: Save a new model image to the database and display it on the product page.

[0381] These steps make it easy for users to find and purchase clothing that matches their image and emotional state. It also allows sellers to easily display their products in a professional manner.

[0382] (Example 2)

[0383] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0384] Conventional clothing coordination suggestion systems often fail to adequately satisfy users because they suggest clothing items without considering the user's emotional state. Furthermore, they struggle to accurately meet user needs by failing to provide suggestions based on specific images the user desires. Additionally, the professional presentation of products was not sufficiently automated, leading to cumbersome and inconvenient product selection processes.

[0385] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0386] In this invention, the server includes means for receiving user input and inputting an image of clothing as text or an image; means for detecting the user's facial expressions, voice, and biometric information and analyzing their emotional state; means for analyzing the user input and emotional state, creating an appropriate image generation prompt and sending it to the server; means for generating an image based on the prompt; means for searching for the optimal clothing item from a database of clothing items based on the generated image; means for adjusting the suggested clothing item considering the emotional state; means for returning the suggested clothing item and the generated image to the user; means for the user to confirm the suggested clothing item and proceed with the purchase; means for generating a model image wearing the clothing to be sold based on the generated image; and means for reflecting the generated model image on the product page. This makes it possible to suggest the optimal clothing that matches the user's emotional state, and allows sellers to easily present their products in a professional way.

[0387] "User input" refers to information that users provide to the system in the form of text or images describing their clothing preferences.

[0388] "Emotional state" refers to the user's current emotional state, analyzed based on factors such as facial expressions, voice, and biometric information.

[0389] An "image generation prompt" is text information created based on user input and emotional state, used to instruct the image generation AI.

[0390] "Generation means" refers to a method or apparatus for generating an image based on an image generation prompt.

[0391] A "database" is a collection of data that stores information about clothing items.

[0392] "Adjustment means" refers to methods or devices for appropriately modifying the suggested content, taking into account the generated image and the user's emotional state.

[0393] "Return method" refers to a method or device for sending back the proposed clothing items and generated images to the user.

[0394] The "purchase process" refers to the series of steps a user takes to review suggested clothing items and actually purchase them.

[0395] "Model images" are images of people wearing the clothing that will be sold, and they are generated by AI.

[0396] A "product page" is a webpage on an online shopping site that displays product information.

[0397] This invention is a system in which a user inputs an image of the clothing they desire, and based on that, artificial intelligence (AI) suggests appropriate clothing items. Furthermore, by using an emotion engine, it realizes coordinate suggestions that take into account the user's emotional state. This system improves user satisfaction and enhances convenience for sellers through multiple processing steps between the user, terminal, and server.

[0398] Users input clothing ideas using devices such as smartphones and computers. Specifically, users can enter their requests in text or upload reference images. In addition, the user's facial expressions, voice, and biometric information are analyzed by an emotion engine via the device's camera and microphone to understand their current emotional state. For example, a user might launch the app and enter "a casual denim jacket, black leggings, and sneakers" into the text box. Alternatively, they could upload an image of their favorite outfit, and the emotion engine would analyze their facial expressions and voice using the camera and microphone.

[0399] The device analyzes input and sentiment data received from the user and creates an appropriate image generation prompt. This prompt is sent to the server to request image generation by AI. The software used includes RESTful APIs and HTTP communication libraries (e.g., Axios or Fetch API). An example of a prompt might be "a denim jacket, black leggings, and sneakers that give a casual and fun impression."

[0400] The server generates an image that reproduces the specified clothing style using image generation AI (e.g., OpenAI's DALL-E or Stable Diffusion) based on prompts received from the terminal. Based on the generated image, it searches for similar items in a database of clothing items (e.g., MySQL or MongoDB) and makes optimal suggestions. It also adjusts the suggestions based on the emotional state analyzed by the emotion engine. For example, if the user is in an "enjoyable" emotional state, it will prioritize suggesting items with bright colors and positive designs.

[0401] The server returns the generated image and a list of suggested clothing items to the terminal. The terminal displays these results to the user, who then reviews the suggested items and consider purchasing them. Additionally, if necessary, the server uses AI to generate model images of the clothing being sold and displays them on the product page. For example, GANs technology can be used to generate an image of a model wearing a denim jacket, which is then displayed on the product page of the e-commerce site.

[0402] This system allows users to easily find the perfect outfit to match their emotional state, and enables sellers to easily display their products in a professional manner.

[0403] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0404] System program processing details

[0405] Flow of processing steps and specific actions

[0406] Step 1:

[0407] The user enters an image of the clothing they want to wear.

[0408] Input: The user enters an image of the clothing they want to wear into the terminal using text or images.

[0409] Specific actions: The user uses a smartphone or computer to type "a casual style consisting of a denim jacket, black leggings, and sneakers" into a text box. Alternatively, they can upload an image of an outfit they would like to use as a reference.

[0410] Output: The input text or image file.

[0411] Step 2:

[0412] The device recognizes the user's emotions.

[0413] Input: The device collects the user's facial expressions, voice, and biometric information using its camera and microphone.

[0414] Specific operation: The device captures and analyzes the user's real-time facial expressions and voice through its built-in camera and microphone. For example, the camera detects the user's smile, and the microphone analyzes their voice tone.

[0415] Output: The user's emotional state (e.g., "joy" or "sadness").

[0416] Step 3:

[0417] The terminal creates the prompt.

[0418] Input: User input data (text or image) and emotional state.

[0419] Specific operation: The terminal analyzes input text with its text analysis engine and analyzes uploaded images with its image analysis engine. It integrates emotional state data to generate appropriate image generation prompts.

[0420] Output: Generated image generation prompt (example prompt: "A denim jacket, black leggings, and sneakers for a casual and fun look").

[0421] Step 4:

[0422] The terminal sends a prompt to the server.

[0423] Input: The generated prompt.

[0424] Specific operation: The generated prompt is sent to the server via the API in JSON format. Libraries used include, for example, Axios and the Fetch API.

[0425] Output: Prompt data sent to the server.

[0426] Step 5:

[0427] The server generates the image.

[0428] Input: Prompt data.

[0429] Specific operation: The server uses image generation AI (e.g., OpenAI's DALL-E or Stable Diffusion) to generate images based on prompts.

[0430] Output: Images of the generated clothing styles.

[0431] Step 6:

[0432] The server searches the product database.

[0433] Input: The generated image.

[0434] Specific operation: Analyze images generated using image recognition technology and search for similar items in a database of clothing items (e.g., MySQL or MongoDB).

[0435] Output: A list of suggested clothing items.

[0436] Step 7:

[0437] The server adjusts the suggestion, taking emotions into consideration.

[0438] Input: User's emotional state and a list of suggested clothing items.

[0439] Specific operation: Based on emotional state data, select the most suitable items from the suggested items and adjust the list.

[0440] Output: A list of optimal clothing items adjusted based on emotional state.

[0441] Step 8:

[0442] The server sends the results back to the terminal.

[0443] Input: A list of optimal clothing items and the generated images.

[0444] Specific action: The suggestion list and images are sent back to the device in JSON format.

[0445] Output: Result data sent to the terminal.

[0446] Step 9:

[0447] The device displays the results to the user.

[0448] Input: Result data sent from the server.

[0449] Specific actions: The app screen displays a list of suggested clothing items and generated images, allowing the user to view detailed information.

[0450] Output: Suggested images and a list of clothing items displayed to the user.

[0451] Step 10:

[0452] The server generates model images as needed and displays them on the product page.

[0453] Input: Information about the suggested clothing items.

[0454] Specific operation: Using GANs technology, model images wearing the proposed clothing items are generated and posted on the product page of the e-commerce site.

[0455] Output: Model image reflected on the product page.

[0456] (Application Example 2)

[0457] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0458] Traditional online shopping systems have struggled to appropriately suggest clothing styles that users desire. In particular, the lack of consideration for the user's emotional state often leads to low user satisfaction. Furthermore, if the suggested clothing is not visually appealing, purchasing intent decreases. This results in problems such as low repeat purchase rates and limited sales.

[0459] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for analyzing user input and the user's emotional state, creating an appropriate image generation prompt and sending it to the server, means for searching for the optimal clothing item from a database of clothing items based on the generated image, adjusting the suggested content considering the user's emotional state, and means for generating model images of the clothing being sold using artificial intelligence. This makes it possible to provide optimal clothing suggestions tailored to the user's emotional state while also creating visually appealing suggestions, thereby improving user satisfaction and increasing purchasing intent.

[0460] "User input" refers to users providing information about their desired clothing in the form of text or images.

[0461] "Emotional state" refers to the psychological state of a user, as analyzed from their facial expressions, voice, and other factors.

[0462] An "image generation prompt" refers to a set of instructions that generate an image of a specified clothing style based on user input and emotional state.

[0463] A "server" refers to a computer system that receives user input and emotional states, and performs analysis, image generation, and database searches.

[0464] "Generation method" refers to the process of generating images of a specified clothing style using image generation AI.

[0465] A "database" refers to a storage system where information about clothing items is accumulated.

[0466] "Search method" refers to the process of finding the most suitable clothing items from a database based on the generated images.

[0467] "Suggested content" refers to information that provides the user with the most suitable clothing items based on user input and emotional state.

[0468] "Artificial intelligence" refers to computer systems that perform intelligent tasks by utilizing machine learning and data analysis technologies.

[0469] A "model image" refers to an image that makes it appear as if the suggested clothing items are actually being worn.

[0470] A "product page" refers to a webpage on an online shopping site that showcases a product.

[0471] "Purchase process" refers to the series of steps a user takes to actually buy the suggested clothing items.

[0472] This invention is a system that allows a user to input an image of the clothing they desire, and based on that, an AI suggests appropriate clothing items. Furthermore, by using an emotion engine, it enables coordinated outfit suggestions that take into account the user's emotional state. This system includes three main components: the user, the terminal, and the server.

[0473] System Configuration

[0474] user

[0475] Users input their desired clothing image using their smartphone or computer. Specifically, they can enter their request in text or upload reference images. Furthermore, the emotion engine detects and analyzes the user's facial expressions, voice, and biometric information to understand the user's current emotional state.

[0476] Specific example:

[0477] Launch the app on your smartphone or computer and type "a casual style consisting of a denim jacket, black leggings, and sneakers" into the text box.

[0478] Upload an image of your favorite outfit.

[0479] The camera and microphone are used to analyze facial expressions and voice, which are then processed by an emotion engine.

[0480] terminal

[0481] The terminal analyzes input data and sentiment data received from the user and creates an appropriate image generation prompt. This is the process of generating prompt sentences to instruct the generation AI model (e.g., DALL-E2 or MidJourney). This prompt is sent to the server to request image generation by the AI.

[0482] server

[0483] The server uses image generation AI to generate an image that replicates the specified clothing style based on prompts received from the terminal. Based on this generated image, it searches for similar products in a database of clothing items (e.g., MySQL or Elasticsearch®) and makes optimal suggestions. The suggested items are adjusted based on the emotional state analyzed by the emotion engine. If necessary, the AI ​​generates model images of the clothing items being sold and displays them on the product page.

[0484] Specific example:

[0485] Example of prompt format: "Female model with a casual denim jacket, black leggings, sneakers, and a smile"

[0486] The server generates images using DALL-E2 or MidJourney.

[0487] Search for the most suitable clothing items from databases such as MySQL and Elasticsearch.

[0488] Program processing details

[0489] 1. User Input Reception and Emotion Recognition: Users input text and images on their devices, and their emotions are analyzed using the camera and microphone. This allows the system to capture the user's desired clothing and emotional state.

[0490] 2. Creating and sending image generation prompts: Based on the received input data and sentiment data, the terminal generates prompt sentences that instruct the image generation AI model and sends them to the server.

[0491] 3. Image generation and database search: The server generates an image based on the received prompt message and searches the database for the most suitable clothing item based on the generated image.

[0492] 4. Suggestion adjustment based on emotional state: Select items from the searched items that are appropriate for the user's emotional state and adjust the suggested content accordingly.

[0493] 5. Display to the user and model image generation: The server returns a list of suggested clothing items and generated images to the user, which the device displays. If necessary, the AI-generated model images are reflected on the product page.

[0494] This allows users to easily find the perfect outfit to match their emotional state and receive visually convincing suggestions. Salespeople can display products with a professional look, potentially improving sales and customer satisfaction.

[0495] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0496] Step 1:

[0497] The system receives user input. Users input images of their desired clothing style using their smartphones or computers, either as text or images. For example, they might type "a casual denim jacket, black leggings, and sneakers" into a text box, or upload a reference image. The input data is then transferred to the device.

[0498] Step 2:

[0499] The device acquires emotional data. It uses its camera and microphone to capture the user's facial expressions and voice, which are then analyzed by an emotion engine. For example, if the user is smiling, the device detects an emotional state of "joy." This emotional data is also stored on the device.

[0500] Step 3:

[0501] Creating an image generation prompt. The terminal analyzes the received user input and sentiment data and creates a prompt message to pass to the generation AI model based on that analysis. The prompt message reflects the user's desired clothing and emotional state. The generated prompt message might look like this: "A smiling female model wearing a casual denim jacket, black leggings, and sneakers." This prompt message is then sent to the server.

[0502] Step 4:

[0503] Image generation. Based on the prompt message received from the terminal, the server uses a generation AI model (e.g., DALL-E2 or MidJourney) to generate an image of the specified clothing style. The generated image is temporarily stored on the server.

[0504] Step 5:

[0505] Database search. The server searches a database of clothing items (e.g., MySQL or Elasticsearch) for the most suitable clothing item based on the generated image. The input is the generated image, and the output is a list of clothing items as search results.

[0506] Step 6:

[0507] Adjusting the suggested items. The server takes emotional data into consideration and selects the most suitable items from the list of clothing items obtained in the previous step, based on the user's emotional state. For example, it prioritizes brightly colored items that match the emotion of "joy." This adjusted list is stored on the server.

[0508] Step 7:

[0509] Return of results. The server returns a list of adjusted clothing items and the generated images to the terminal. The terminal receives this and displays it to the user.

[0510] Step 8:

[0511] Model image generation. If necessary, the server uses artificial intelligence to generate model images of the clothing being sold. These generated model images are reflected on the product page, allowing users to visually confirm the product.

[0512] Step 9:

[0513] Purchase procedure. The user reviews the clothing items suggested on their device, selects the items they like, and proceeds with the purchase. Finally, purchase completion information for the selected items is sent to the server.

[0514] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0515] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0516] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0517] [Second Embodiment]

[0518] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0519] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0520] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0521] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0522] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0523] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0524] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0525] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0526] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0527] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0528] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0529] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0530] This invention is a system that begins with the user inputting an image of the clothing they desire. Based on that image, AI suggests appropriate clothing items, and further generates and presents images of a model wearing those outfits. This system goes through multiple processing steps between the user, the terminal, and the server to improve user satisfaction and seller convenience.

[0531] System Configuration

[0532] user:

[0533] Users use their devices to input an image of the clothing they want. Specifically, they can enter their request in text or upload a reference image.

[0534] Example: Launch the app on your smartphone or computer and type "a casual style with a denim jacket, black leggings, and sneakers" into the text box. Alternatively, upload an image of your favorite outfit.

[0535] Terminal:

[0536] The terminal analyzes the input data received from the user and creates an appropriate image generation prompt.

[0537] This prompt is sent to the server to request image generation by AI.

[0538] Furthermore, the suggested results and generated images returned from the server are displayed to the user.

[0539] server:

[0540] Based on prompts received from the terminal, the server uses image generation AI to generate an image that reproduces the specified clothing style.

[0541] Based on the generated image, the system searches for similar items in its clothing item database and provides optimal suggestions.

[0542] Additionally, if necessary, model images of customers wearing the clothing items being sold will be generated and displayed on the product pages.

[0543] Program processing details

[0544] Receiving and analyzing user input

[0545] User inputs clothing image: Users send requests to the system by entering text or images on their device.

[0546] The terminal analyzes the input: The terminal processes the input data using natural language processing and image analysis techniques to create specific image generation prompts.

[0547] Creating a prompt and sending it to the server

[0548] The terminal generates the prompt: Based on the analysis results, it forms the appropriate prompt. For example, if the user enters "casual denim jacket, black leggings, and sneakers," the terminal will generate the prompt "generate image: casual denim jacket with black leggings and sneakers."

[0549] The terminal sends a prompt to the server: It generates and sends an API request to send a prompt to the server.

[0550] Image generation and product suggestions

[0551] The server receives a prompt and generates an image: The server uses an image generation AI to generate an image of the specified clothing.

[0552] The server searches the database: Based on the generated image, it searches the database of clothing items for the best suggestions. These suggestions are then sent back to the user.

[0553] Displaying results to the user and generating model images.

[0554] The server returns the results to the user: it sends a list of suggested clothing items and the generated images back to the user's device.

[0555] The device displays the results to the user: The returned results are displayed to the user in an easy-to-read format. This allows the user to review the suggested items and consider purchasing them.

[0556] The server generates model images and displays them on the product page: If necessary, AI generates model images of the clothing being sold and displays them on the product page. This allows sellers to easily provide professional-looking images.

[0557] This system allows users to easily find clothing that best suits their image, and enables sellers to create more appealing product pages.

[0558] The following describes the processing flow.

[0559] Step 1:

[0560] user:

[0561] Enter the image of the clothing you're looking for.

[0562] Example: The user enters "a casual denim jacket, black leggings, and sneakers" into the text box and uploads reference images as needed.

[0563] Step 2:

[0564] Terminal:

[0565] Receives and analyzes user input.

[0566] Example: Analyze text and images to extract keywords such as "casual," "denim jacket," "black leggings," and "sneakers."

[0567] Step 3:

[0568] Terminal:

[0569] Create an appropriate image generation prompt.

[0570] Example: Based on the extracted keywords, create a prompt that says "generate image: casual denim jacket with black leggings and sneakers".

[0571] Step 4:

[0572] Terminal:

[0573] Send the created prompt to the server.

[0574] Example: Use an API request to send the prompt "generate image: casual denim jacket with black leggings and sneakers" to the server.

[0575] Step 5:

[0576] server:

[0577] Receive the prompt and pass it to the image generation AI.

[0578] Example: Analyze the received prompt and input it into an AI image generation model (e.g., GAN or Diffusion model).

[0579] Step 6:

[0580] server:

[0581] The image generation AI generates images of the specified clothing style.

[0582] Example: Generate an image of a "casual denim jacket, black leggings, and sneakers."

[0583] Step 7:

[0584] server:

[0585] The generated image is used to search a database of clothing items.

[0586] Example: Using visual recognition technology based on the generated image, search a database for related items such as a denim jacket, black leggings, and sneakers.

[0587] Step 8:

[0588] server:

[0589] The search results and generated images are sent back to the device.

[0590] Example: A list of suggested products (product ID, name, price, detail link) and generated coordinated images are returned to the device in JSON format.

[0591] Step 9:

[0592] Terminal:

[0593] The suggested clothing items and generated images are displayed to the user.

[0594] Example: Display the generated image and a list of products on the app screen, and provide a link to each product.

[0595] Step 10:

[0596] user:

[0597] Review the suggested clothing items and add the ones you like to your cart.

[0598] Example: Click the "Add to Cart" button for a denim jacket you like.

[0599] Step 11:

[0600] user:

[0601] Proceed with the purchase process.

[0602] Example: Enter your payment information on the purchase screen and click the "Confirm Order" button.

[0603] Step 12:

[0604] Terminal:

[0605] The purchase information is sent to the server and the transaction is processed.

[0606] Example: Purchase information is sent to the server, which then checks inventory and processes payment.

[0607] Step 13:

[0608] server:

[0609] If necessary, generate model images wearing the clothing that will be sold.

[0610] Example: The server uses AI to generate images of a model wearing a denim jacket.

[0611] Step 14:

[0612] server:

[0613] The generated model image is reflected on the product page.

[0614] Example: Save a new model image to the database and display it on the product page.

[0615] These steps make it easy for users to find and purchase clothing that matches their image. Additionally, sellers can easily display their products in a professional manner.

[0616] (Example 1)

[0617] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0618] Traditional online shopping systems lacked the means to support users in visualizing the specific clothing they wanted, forcing them to choose their outfits themselves based on a lot of information. This was time-consuming and laborious, sometimes resulting in a decrease in purchase intent. Furthermore, sellers lacked the means to easily generate professional images to showcase their products attractively. To meet the needs of both users and sellers, there is a need for more efficient and accurate clothing item suggestions and the provision of visual information.

[0619] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0620] In this invention, the server includes means for receiving user input and inputting an image of clothing as text or an image; means for analyzing the user input and creating an appropriate image generation prompt and sending it to the server; means for generating an image based on the prompt; means for searching for the optimal clothing item from a database of clothing items based on the generated image; means for returning the suggested clothing item and the generated image to the user; means for generating a model image of the clothing being sold using artificial intelligence; means for reflecting the generated model image on the product page; means for the user to confirm the suggested clothing item and proceed with the purchase; processing means for the terminal to analyze user input using natural language processing technology and image analysis technology; transmission means for sending the prompt generated by the terminal to the server via an API request; means for the server to search the database based on the generated image and create a suggestion list; transmission means for the server to generate an API response and return it to the user's terminal; and display means for the terminal to display the results to the user. As a result, users can easily find the optimal item based on their desired image of clothing, and sellers can easily create and provide professional product images.

[0621] "User input" refers to text or images that a user provides to the system.

[0622] "Clothing image" refers to text or images that specifically describe the type of clothing the user desires.

[0623] An "image generation prompt" is a set of instructions used to request an AI model to generate an image based on the user's input data.

[0624] A "server" is a central processing unit that analyzes user input, creates image generation prompts, performs database searches based on the generated images, and suggests the most suitable clothing items.

[0625] "Generation means" refers to a function that generates images based on user requests using a generation AI model.

[0626] A "database" is a storage device that systematically stores and allows retrieval of information about clothing items.

[0627] The "suggestion method" refers to a function that selects the most suitable clothing items from a database based on the generated image and suggests them to the user.

[0628] "Artificial intelligence" refers to the technology that enables computers to learn, reason, and improve themselves by mimicking human intelligence.

[0629] "Natural language processing technology" refers to the technology of analyzing and understanding human language, and is used to analyze the meaning of text data.

[0630] "Image analysis technology" refers to techniques for extracting specific information from image data.

[0631] An "API request" is a request from one software program to another program to perform a specific function.

[0632] An "API response" is the response that another software program returns to an API request.

[0633] "Display means" refers to a function that presents results in an easy-to-understand manner on the user's terminal.

[0634] This invention is a system designed to simplify the user's clothing selection process and assist sellers in creating attractive product pages. This system achieves improved user satisfaction and seller convenience through multiple processing steps involving the user, terminal, and server.

[0635] Overall system configuration

[0636] user:

[0637] Users input their desired clothing image using a smartphone or computer application. Specifically, they can enter their request in text or upload reference images.

[0638] Specific example:

[0639] Enter "A casual style consisting of a denim jacket, black leggings, and sneakers" into the text box.

[0640] Alternatively, upload an image of your favorite outfit.

[0641] Terminal:

[0642] The terminal analyzes the input data received from the user and creates an appropriate image generation prompt. This prompt is sent to the server, requesting AI-generated image generation. Furthermore, the suggested results and generated image returned from the server are displayed to the user.

[0643] Example of technology used:

[0644] For natural language processing techniques, we use Python's NLTK library and spaCy.

[0645] For image analysis techniques, we use OpenCV and TensorFlow.

[0646] server:

[0647] Based on prompts received from the terminal, the server uses image generation AI to generate an image that replicates the specified clothing style. Based on this generated image, it searches a database of clothing items for similar products and makes optimal suggestions. If necessary, it generates model images of the clothing items being sold and displays them on the product page.

[0648] Example of technology used:

[0649] For image generation, we use OpenAI's DALL-E or Stability AI's Stable Diffusion as generative AI models.

[0650] SQL or NoSQL database technologies are used for searching the database.

[0651] Specific processing details of the system

[0652] Receiving and analyzing user input:

[0653] The user inputs an image of the clothing they are looking for as text or an image. The device analyzes the received input data using natural language processing and image analysis technologies to form a specific image generation prompt. For example, if the user inputs "casual denim jacket, black leggings, and sneakers," the prompt "generate image: casual denim jacket with black leggings and sneakers" will be generated.

[0654] Example of a prompt:

[0655] "generate image: casual denim jacket with black leggings and sneakers"

[0656] Sending the prompt to the server:

[0657] The system generates an API request to send the prompt generated by the terminal to the server, and then sends it to the server using an HTTP POST request or similar method.

[0658] Image generation:

[0659] Based on the received prompt, the server uses an image generation AI to generate an image of the specified clothing. The generated image is temporarily stored.

[0660] Product proposal generation:

[0661] Based on the generated image, the server searches the database and suggests similar clothing items. These suggestions are tailored to the user's needs.

[0662] Returning and displaying results to the user:

[0663] The server sends the generated image and suggested clothing items together in an API response to the user's device. The device then displays the received results to the user.

[0664] Generating model images and updating product pages as needed:

[0665] The server uses AI to generate images of models wearing clothing items as needed, and displays them on the product page. This allows sellers to easily create and provide professional product images.

[0666] This system makes it easy for users to find the perfect outfit to match their image, and also allows sellers to create more appealing product pages.

[0667] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0668] Step 1:

[0669] The user enters an image of the clothing they want to wear.

[0670] Input: Text or reference image

[0671] Specific actions: The user uses a smartphone or computer application and enters "a casual style with a denim jacket, black leggings, and sneakers" into a text box. Alternatively, they can upload an image of their favorite outfit.

[0672] Output: Text or image data entered by the user.

[0673] Step 2:

[0674] The terminal analyzes user input.

[0675] Input: Text or image data entered by the user.

[0676] Specific operation: The device analyzes text using natural language processing techniques (e.g., Python's NLTK library or spaCy). It also analyzes image data using image analysis techniques (e.g., OpenCV or TensorFlow).

[0677] Output: Information based on the clothing image obtained from the analysis (e.g., "casual denim jacket with black leggings and sneakers")

[0678] Step 3:

[0679] The terminal generates the prompt.

[0680] Input: Information based on clothing images obtained from the analysis results.

[0681] Specific operation: The device creates a prompt suitable for the generated AI model. For example, the prompt "generate image: casual denim jacket with black leggings and sneakers" is generated.

[0682] Output: Generated prompt message

[0683] Step 4:

[0684] The terminal sends a prompt to the server.

[0685] Input: Generated prompt message

[0686] Specific operation: The terminal generates an HTTP POST request and sends the generated prompt message to the server as an API request.

[0687] Output: Prompt message sent to the server

[0688] Step 5:

[0689] The server receives the prompt and generates the image.

[0690] Input: Prompt message sent from the terminal

[0691] Specific operation: The server uses an image generation AI (e.g., OpenAI's DALL-E or Stability AI's Stable Diffusion) to generate an image of the specified clothing. The generated image is temporarily stored.

[0692] Output: Image of the generated clothing

[0693] Step 6:

[0694] The server searches the database and generates product suggestions.

[0695] Input: Image of the generated clothing

[0696] Specific operation: The server searches a database of clothing items based on the generated image. This search uses SQL or NoSQL database technology. The most suitable clothing item is selected from the search results.

[0697] Output: List of suggested optimal clothing items

[0698] Step 7:

[0699] The server returns the results to the user.

[0700] Input: A list of generated images and suggested clothing items.

[0701] Specific operation: The server generates an API response and sends the generated image and a list of suggested clothing items to the user's device.

[0702] Output: A list of images and clothing items returned to the user's device.

[0703] Step 8:

[0704] The device displays the results to the user.

[0705] Input: List of images and clothing items returned from the server.

[0706] Specific operation: The device displays the received results on the user's screen. The UI allows the user to easily review the suggested items.

[0707] Output: A list of images and clothing items displayed on the user's screen.

[0708] Step 9:

[0709] The server generates model images as needed and displays them on the product page.

[0710] Input: Settings for generating data and model images of clothing items to be sold.

[0711] Specific operation: The server uses AI to generate images of models wearing clothing items and displays them on the product page.

[0712] Output: Model image reflected on the product page

[0713] (Application Example 1)

[0714] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0715] Traditional online shopping sites have presented challenges, such as users spending a lot of time and effort finding clothing items that match their desired fashion style. Furthermore, the sheer number of product options often overwhelms users, making it difficult to choose the right items. Additionally, product images alone are often insufficient to convey how the items will look when worn, potentially diminishing purchasing intent. This invention aims to solve these problems and provide a system that improves the user's purchasing experience.

[0716] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0717] This invention includes a server that generates specific prompt text based on the fashion style entered by the user and sends it to an image generation AI model; a server that displays a list of related clothing items based on the generated model image; a server that allows the user to click on a clothing item to go to a details page and complete the purchase process; and a server that collects post-purchase feedback. This makes it possible for the user to easily find appropriate clothing items that match their desired fashion style, visually confirm them with model images, and purchase them on the spot.

[0718] "User input" refers to the user specifying their desired clothing image to the system using text or images.

[0719] An "image generation prompt" is a text message that generates specific instructions based on user input and sends to an image generation AI model.

[0720] An "image generation AI model" is an artificial intelligence that generates images of specified clothing based on the input prompt text.

[0721] "Clothing items" is a term that refers to fashion-related products and accessories, and includes a range of products included in the database.

[0722] A "database" is an information management system that systematically stores information about clothing items.

[0723] A "model image" is an image of a model wearing the generated clothing image, and is generated to present it visually to the user.

[0724] A "prompt message" is text generated by analyzing user input and contains specific instructions for the image generation AI model.

[0725] The "product list" is a list of related clothing items suggested based on the generated model image.

[0726] A "details page" is a webpage or screen that displays detailed information about a suggested clothing item.

[0727] "Feedback" refers to the opinions and impressions that users provide after a purchase, and is used to improve the system and enhance the user experience.

[0728] This invention relates to a system that suggests clothing items that accurately reflect the user's desired fashion style and allows them to purchase those items. This system optimizes the user experience and purchase process through the coordinated operation of user input, terminals, and servers.

[0729] System Overview

[0730] 1. User input

[0731] Users access the system using smartphones or personal computers.

[0732] Users can enter a text description of their desired outfit or upload a reference image.

[0733] 2. Terminal processing

[0734] The terminal will be equipped with an interface for receiving user input.

[0735] Text input is analyzed using a natural language processing library (e.g., spaCy).

[0736] For image input, an image analysis library (e.g., OpenCV) is used.

[0737] The input data is analyzed, and specific prompt messages are generated.

[0738] Specific example: If the user enters "a casual summer dress to wear on the beach in summer," the prompt "generate image: casual summer dress for beach" will be generated.

[0739] 3. Server processing

[0740] Receives prompt messages sent from the terminal.

[0741] Using an image generation AI model (e.g., OpenAI's DALL-E), images of clothing based on prompt text are generated.

[0742] Based on the generated image, the system searches for related products in a database of clothing items (e.g., MySQL).

[0743] Send the search results and generated images to the device.

[0744] 4. Display and Purchase Process

[0745] The device displays a list of suggested clothing items and generated images to the user.

[0746] Users can click on suggested items to go to the details page and proceed with the purchase.

[0747] An interface is provided for collecting post-purchase feedback.

[0748] Examples of specific cases and prompt statements

[0749] Specific example:

[0750] 1. The user enters the text, "A casual dress perfect for spring cherry blossom viewing."

[0751] 2. The terminal generates the prompt message "generate image: casual spring dress for cherry blossom viewing".

[0752] 3. The server sends the generated prompt message to the image generation AI model and generates the corresponding image.

[0753] 4. Search the database of clothing items for related products and display them to the user along with a list of suggestions.

[0754] 5. The user navigates to the product details page and makes a purchase.

[0755] Hardware and software to be used

[0756] Hardware: Smartphones, PCs, servers, GPUs (as needed)

[0757] Software: Mobile app development frameworks (e.g., React Native), natural language processing libraries (e.g., spaCy), image analysis libraries (e.g., OpenCV), AI image generation models (e.g., OpenAI's DALL-E), API request libraries (e.g., Axios), database management systems (e.g., MySQL), frontend libraries (e.g., React.js)

[0758] In this way, a system is created that suggests clothing items that best suit the image entered by the user, allowing them to easily purchase them after visual confirmation.

[0759] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0760] Step 1:

[0761] Users access the system using their smartphones or computers. They then enter an image of their desired clothing style into a text box, or upload a reference image. This allows the system to retrieve the user's fashion preferences. The input is in text or image format, and this information is then analyzed.

[0762] Step 2:

[0763] The terminal receives user input and calls natural language processing libraries (e.g., spaCy) or image analysis libraries (e.g., OpenCV) to analyze its content. For text input, natural language processing converts the content into structured data (such as key-value pairs). For image input, image analysis techniques are used to extract image features. Based on these analysis results, a specific prompt message (e.g., "generate image: casual summer dress for beach") is generated. The input is user text or images, and the output is a specific prompt message.

[0764] Step 3:

[0765] The generated prompt message is sent from the terminal to the server. An API request library (e.g., Axios) and a communication protocol (e.g., HTTP) are used in this process. The terminal formats the prompt message into an API request format and sends it to the server. The input is the generated prompt message, and the output is the request sent to the server.

[0766] Step 4:

[0767] The server passes the received prompt message to an image generation AI model (e.g., OpenAI's DALL-E), and generates an image based on that prompt. The AI ​​model analyzes the generation prompt and generates an image with the specified clothing. The input is the prompt message, and the output is the generated image.

[0768] Step 5:

[0769] The server uses a database management system (e.g., MySQL) to search for clothing items based on the generated image. This search extracts the most suitable specific clothing item using the image analysis results and relevant metadata. The input is the generated image, and the output is a list of related clothing items.

[0770] Step 6:

[0771] The server returns the generated image and a list of searched clothing items to the terminal. The input is the search results and the generated image, and the output is the data sent to the terminal.

[0772] Step 7:

[0773] The terminal displays the received data to the user. Specifically, it provides a user interface that can beautifully display a list of suggested clothing items and generated images. Input is data from the server, and output is the display on the user interface.

[0774] Step 8:

[0775] The user clicks on a suggested item to go to its details page. This details page displays detailed information, price, and a purchase button for each item. The user can then proceed with the purchase. The input is a list of clothing items, and the output is a transition to the details page.

[0776] Step 9:

[0777] After completing a purchase, the user accesses an interface to provide feedback. The device receives the user's feedback and sends it to the server. This feedback is used to improve the system and enhance the user experience. The input is the user's feedback, and the output is the data sent to the server.

[0778] Through these steps, a system is created that allows users to easily find, visually confirm, and purchase their desired fashion style on the spot.

[0779] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0780] This invention is a system in which a user inputs an image of the clothing they desire, and based on that, AI suggests appropriate clothing items. Furthermore, by using an emotion engine, it realizes coordinate suggestions that take into account the user's emotional state. This system improves user satisfaction and enhances convenience for sellers through multiple processing steps between the user, terminal, and server.

[0781] System Configuration

[0782] user:

[0783] Users use their devices to input images of the clothing they want. Specifically, they can enter their requests in text or upload reference images.

[0784] Furthermore, the emotion engine detects and analyzes the user's facial expressions, voice, and biometric information to understand the user's current emotional state.

[0785] Example: Launch the app on your smartphone or computer and type "a casual style with a denim jacket, black leggings, and sneakers" into the text box. Alternatively, upload an image of your favorite outfit, and the emotion engine will analyze your facial expressions and voice using the camera and microphone.

[0786] Terminal:

[0787] The device analyzes input data and sentiment data received from the user and creates appropriate image generation prompts.

[0788] This prompt is sent to the server to request image generation by AI.

[0789] Furthermore, the suggested results and generated images returned from the server are displayed to the user.

[0790] server:

[0791] Based on prompts received from the terminal, the server uses image generation AI to generate an image that reproduces the specified clothing style.

[0792] Based on the generated image, the system searches for similar items in a database of clothing items and provides optimal suggestions.

[0793] The suggested items are adjusted based on the emotional state analyzed by the emotion engine.

[0794] If necessary, AI will generate model images of the clothing items being sold and display them on the product page.

[0795] Program processing details

[0796] User input and emotion recognition

[0797] User inputs clothing image: Users send requests to the system by entering text or images on their device.

[0798] The emotion engine recognizes emotions: It analyzes the user's facial expressions, voice, and biometric information to understand their current emotional state. For example, if the user is smiling, it detects an emotional state of "joy."

[0799] Creating a prompt and sending it to the server

[0800] The device analyzes input and emotions: it generates appropriate prompts based on text, images, and emotional states. For example, if the user wants to wear casual clothing and is in an emotional state of "joy," it will create a prompt that is appropriate for that.

[0801] The terminal sends a prompt to the server: It sends a prompt to the server via the API, requesting the necessary action.

[0802] Image generation and product suggestions

[0803] The server receives a prompt and generates an image: The server uses an image generation AI to generate an image of the specified clothing style.

[0804] The server searches the database: Based on the generated image, it searches the database of clothing items for the most suitable item.

[0805] The server adjusts suggestions based on the user's emotional state: It selects items from the search results that are appropriate for the user's emotional state and adjusts the suggestions accordingly.

[0806] Displaying results to the user and generating model images.

[0807] The server returns results to the user: it sends a list of suggested clothing items and generated images back to the user's device. The suggestions take the user's emotional state into consideration.

[0808] The device displays the results to the user: The returned results are displayed to the user in an easy-to-read format. This allows the user to review the suggested items and consider purchasing them.

[0809] The server generates model images and displays them on the product page: If necessary, it generates model images of the clothing being sold and displays them on the product page.

[0810] This system will allow users to easily find the perfect outfit to match their emotional state, and sellers will be able to easily display their products in a professional way.

[0811] The following describes the processing flow.

[0812] Step 1:

[0813] user:

[0814] Enter the image of the clothing you're looking for.

[0815] Example: The user enters "a casual denim jacket, black leggings, and sneakers" into a text box and uploads reference images as needed. They also send facial expressions and voice information using a camera and microphone that support the emotion engine.

[0816] Step 2:

[0817] Terminal:

[0818] Receives and analyzes user input.

[0819] Example: Analyze text and images to extract keywords such as "casual," "denim jacket," "black leggings," and "sneakers."

[0820] Step 3:

[0821] Terminal:

[0822] Use an emotion engine to recognize the user's emotions.

[0823] For example, a camera captures the user's facial expressions, and a voice recognition system analyzes the tone of their voice to determine their emotional state, such as whether they are happy or depressed.

[0824] Step 4:

[0825] Terminal:

[0826] Create an appropriate image generation prompt.

[0827] Example: Based on the extracted keywords and recognized emotional state, create a prompt that says, "generate image: casual denim jacket with black leggings and sneakers for a happy mood."

[0828] Step 5:

[0829] Terminal:

[0830] Send the created prompt to the server.

[0831] Example: Use an API request to send the prompt "generate image: casual denim jacket with black leggings and sneakers for a happy mood" to the server.

[0832] Step 6:

[0833] server:

[0834] Receive the prompt and pass it to the image generation AI.

[0835] Example: Analyze the received prompt and input it into an AI image generation model (e.g., GAN or Diffusion model).

[0836] Step 7:

[0837] server:

[0838] The image generation AI generates images of the specified clothing style.

[0839] Example: Generate an image of a "casual denim jacket, black leggings, and sneakers."

[0840] Step 8:

[0841] server:

[0842] The generated image is used to search a database of clothing items.

[0843] Example: Using visual recognition technology based on the generated image, search a database for related items such as a denim jacket, black leggings, and sneakers.

[0844] Step 9:

[0845] server:

[0846] Adjust product suggestions based on the results of the emotion engine.

[0847] Example: Select the most suitable product from the search results based on the user's emotional state and adjust the suggestion list accordingly.

[0848] Step 10:

[0849] server:

[0850] The search results and generated images are sent back to the device.

[0851] Example: A list of suggested products (product ID, name, price, detail link) and generated coordinated images are returned to the device in JSON format.

[0852] Step 11:

[0853] Terminal:

[0854] The suggested clothing items and generated images are displayed to the user.

[0855] Example: Display the generated image and a list of products on the app screen, and provide a link to each product.

[0856] Step 12:

[0857] user:

[0858] Review the suggested clothing items and add the ones you like to your cart.

[0859] Example: Click the "Add to Cart" button for a denim jacket you like.

[0860] Step 13:

[0861] user:

[0862] Proceed with the purchase process.

[0863] Example: Enter your payment information on the purchase screen and click the "Confirm Order" button.

[0864] Step 14:

[0865] Terminal:

[0866] The purchase information is sent to the server and the transaction is processed.

[0867] Example: Purchase information is sent to the server, which then checks inventory and processes payment.

[0868] Step 15:

[0869] server:

[0870] If necessary, generate model images wearing the clothing that will be sold.

[0871] Example: The server uses AI to generate images of a model wearing a denim jacket.

[0872] Step 16:

[0873] server:

[0874] The generated model image is reflected on the product page.

[0875] Example: Save a new model image to the database and display it on the product page.

[0876] These steps make it easy for users to find and purchase clothing that matches their image and emotional state. It also allows sellers to easily display their products in a professional manner.

[0877] (Example 2)

[0878] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0879] Conventional clothing coordination suggestion systems often fail to adequately satisfy users because they suggest clothing items without considering the user's emotional state. Furthermore, they struggle to accurately meet user needs by failing to provide suggestions based on specific images the user desires. Additionally, the professional presentation of products was not sufficiently automated, leading to cumbersome and inconvenient product selection processes.

[0880] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0881] In this invention, the server includes means for receiving user input and inputting an image of clothing as text or an image; means for detecting the user's facial expressions, voice, and biometric information and analyzing their emotional state; means for analyzing the user input and emotional state, creating an appropriate image generation prompt and sending it to the server; means for generating an image based on the prompt; means for searching for the optimal clothing item from a database of clothing items based on the generated image; means for adjusting the suggested clothing item considering the emotional state; means for returning the suggested clothing item and the generated image to the user; means for the user to confirm the suggested clothing item and proceed with the purchase; means for generating a model image wearing the clothing to be sold based on the generated image; and means for reflecting the generated model image on the product page. This makes it possible to suggest the optimal clothing that matches the user's emotional state, and allows sellers to easily present their products in a professional way.

[0882] "User input" refers to information that users provide to the system in the form of text or images describing their clothing preferences.

[0883] "Emotional state" refers to the user's current emotional state, analyzed based on factors such as facial expressions, voice, and biometric information.

[0884] An "image generation prompt" is text information created based on user input and emotional state, used to instruct the image generation AI.

[0885] "Generation means" refers to a method or apparatus for generating an image based on an image generation prompt.

[0886] A "database" is a collection of data that stores information about clothing items.

[0887] "Adjustment means" refers to methods or devices for appropriately modifying the suggested content, taking into account the generated image and the user's emotional state.

[0888] "Return method" refers to a method or device for sending back the proposed clothing items and generated images to the user.

[0889] The "purchase process" refers to the series of steps a user takes to review suggested clothing items and actually purchase them.

[0890] "Model images" are images of people wearing the clothing that will be sold, and they are generated by AI.

[0891] A "product page" is a webpage on an online shopping site that displays product information.

[0892] This invention is a system in which a user inputs an image of the clothing they desire, and based on that, artificial intelligence (AI) suggests appropriate clothing items. Furthermore, by using an emotion engine, it realizes coordinate suggestions that take into account the user's emotional state. This system improves user satisfaction and enhances convenience for sellers through multiple processing steps between the user, terminal, and server.

[0893] Users input clothing ideas using devices such as smartphones and computers. Specifically, users can enter their requests in text or upload reference images. In addition, the user's facial expressions, voice, and biometric information are analyzed by an emotion engine via the device's camera and microphone to understand their current emotional state. For example, a user might launch the app and enter "a casual denim jacket, black leggings, and sneakers" into the text box. Alternatively, they could upload an image of their favorite outfit, and the emotion engine would analyze their facial expressions and voice using the camera and microphone.

[0894] The device analyzes input and sentiment data received from the user and creates an appropriate image generation prompt. This prompt is sent to the server to request image generation by AI. The software used includes RESTful APIs and HTTP communication libraries (e.g., Axios or Fetch API). An example of a prompt might be "a denim jacket, black leggings, and sneakers that give a casual and fun impression."

[0895] The server generates an image that reproduces the specified clothing style using image generation AI (e.g., OpenAI's DALL-E or Stable Diffusion) based on prompts received from the terminal. Based on the generated image, it searches for similar items in a database of clothing items (e.g., MySQL or MongoDB) and makes optimal suggestions. It also adjusts the suggestions based on the emotional state analyzed by the emotion engine. For example, if the user is in an "enjoyable" emotional state, it will prioritize suggesting items with bright colors and positive designs.

[0896] The server returns the generated image and a list of suggested clothing items to the terminal. The terminal displays these results to the user, who then reviews the suggested items and consider purchasing them. Additionally, if necessary, the server uses AI to generate model images of the clothing being sold and displays them on the product page. For example, GANs technology can be used to generate an image of a model wearing a denim jacket, which is then displayed on the product page of the e-commerce site.

[0897] This system allows users to easily find the perfect outfit to match their emotional state, and enables sellers to easily display their products in a professional manner.

[0898] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0899] System program processing details

[0900] Flow of processing steps and specific actions

[0901] Step 1:

[0902] The user enters an image of the clothing they want to wear.

[0903] Input: The user enters an image of the clothing they want to wear into the terminal using text or images.

[0904] Specific actions: The user uses a smartphone or computer to type "a casual style consisting of a denim jacket, black leggings, and sneakers" into a text box. Alternatively, they can upload an image of an outfit they would like to use as a reference.

[0905] Output: The input text or image file.

[0906] Step 2:

[0907] The device recognizes the user's emotions.

[0908] Input: The device collects the user's facial expressions, voice, and biometric information using its camera and microphone.

[0909] Specific operation: The device captures and analyzes the user's real-time facial expressions and voice through its built-in camera and microphone. For example, the camera detects the user's smile, and the microphone analyzes their voice tone.

[0910] Output: The user's emotional state (e.g., "joy" or "sadness").

[0911] Step 3:

[0912] The terminal creates the prompt.

[0913] Input: User input data (text or image) and emotional state.

[0914] Specific operation: The terminal analyzes input text with its text analysis engine and analyzes uploaded images with its image analysis engine. It integrates emotional state data to generate appropriate image generation prompts.

[0915] Output: Generated image generation prompt (example prompt: "A denim jacket, black leggings, and sneakers for a casual and fun look").

[0916] Step 4:

[0917] The terminal sends a prompt to the server.

[0918] Input: The generated prompt.

[0919] Specific operation: The generated prompt is sent to the server via the API in JSON format. Libraries used include, for example, Axios and the Fetch API.

[0920] Output: Prompt data sent to the server.

[0921] Step 5:

[0922] The server generates the image.

[0923] Input: Prompt data.

[0924] Specific operation: The server uses image generation AI (e.g., OpenAI's DALL-E or Stable Diffusion) to generate images based on prompts.

[0925] Output: Images of the generated clothing styles.

[0926] Step 6:

[0927] The server searches the product database.

[0928] Input: The generated image.

[0929] Specific operation: Analyze images generated using image recognition technology and search for similar items in a database of clothing items (e.g., MySQL or MongoDB).

[0930] Output: A list of suggested clothing items.

[0931] Step 7:

[0932] The server adjusts the suggestion, taking emotions into consideration.

[0933] Input: User's emotional state and a list of suggested clothing items.

[0934] Specific operation: Based on emotional state data, select the most suitable items from the suggested items and adjust the list.

[0935] Output: A list of optimal clothing items adjusted based on emotional state.

[0936] Step 8:

[0937] The server sends the results back to the terminal.

[0938] Input: A list of optimal clothing items and the generated images.

[0939] Specific action: The suggestion list and images are sent back to the device in JSON format.

[0940] Output: Result data sent to the terminal.

[0941] Step 9:

[0942] The device displays the results to the user.

[0943] Input: Result data sent from the server.

[0944] Specific actions: The app screen displays a list of suggested clothing items and generated images, allowing the user to view detailed information.

[0945] Output: Suggested images and a list of clothing items displayed to the user.

[0946] Step 10:

[0947] The server generates model images as needed and displays them on the product page.

[0948] Input: Information about the suggested clothing items.

[0949] Specific operation: Using GANs technology, model images wearing the proposed clothing items are generated and posted on the product page of the e-commerce site.

[0950] Output: Model image reflected on the product page.

[0951] (Application Example 2)

[0952] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0953] Traditional online shopping systems have struggled to appropriately suggest clothing styles that users desire. In particular, the lack of consideration for the user's emotional state often leads to low user satisfaction. Furthermore, if the suggested clothing is not visually appealing, purchasing intent decreases. This results in problems such as low repeat purchase rates and limited sales.

[0954] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for analyzing user input and the user's emotional state, creating an appropriate image generation prompt and sending it to the server, means for searching for the optimal clothing item from a database of clothing items based on the generated image, adjusting the suggested content considering the user's emotional state, and means for generating model images of the clothing being sold using artificial intelligence. This makes it possible to provide optimal clothing suggestions tailored to the user's emotional state while also creating visually appealing suggestions, thereby improving user satisfaction and increasing purchasing intent.

[0955] "User input" refers to users providing information about their desired clothing in the form of text or images.

[0956] "Emotional state" refers to the psychological state of a user, as analyzed from their facial expressions, voice, and other factors.

[0957] An "image generation prompt" refers to a set of instructions that generate an image of a specified clothing style based on user input and emotional state.

[0958] A "server" refers to a computer system that receives user input and emotional states, and performs analysis, image generation, and database searches.

[0959] "Generation method" refers to the process of generating images of a specified clothing style using image generation AI.

[0960] A "database" refers to a storage system where information about clothing items is accumulated.

[0961] "Search method" refers to the process of finding the most suitable clothing items from a database based on the generated images.

[0962] "Suggested content" refers to information that provides the user with the most suitable clothing items based on user input and emotional state.

[0963] "Artificial intelligence" refers to computer systems that perform intelligent tasks by utilizing machine learning and data analysis technologies.

[0964] A "model image" refers to an image that makes it appear as if the suggested clothing items are actually being worn.

[0965] A "product page" refers to a webpage on an online shopping site that showcases a product.

[0966] "Purchase process" refers to the series of steps a user takes to actually buy the suggested clothing items.

[0967] This invention is a system that allows a user to input an image of the clothing they desire, and based on that, an AI suggests appropriate clothing items. Furthermore, by using an emotion engine, it enables coordinated outfit suggestions that take into account the user's emotional state. This system includes three main components: the user, the terminal, and the server.

[0968] System Configuration

[0969] user

[0970] Users input their desired clothing image using their smartphone or computer. Specifically, they can enter their request in text or upload reference images. Furthermore, the emotion engine detects and analyzes the user's facial expressions, voice, and biometric information to understand the user's current emotional state.

[0971] Specific example:

[0972] Launch the app on your smartphone or computer and type "a casual style consisting of a denim jacket, black leggings, and sneakers" into the text box.

[0973] Upload an image of your favorite outfit.

[0974] The camera and microphone are used to analyze facial expressions and voice, which are then processed by an emotion engine.

[0975] terminal

[0976] The terminal analyzes input data and sentiment data received from the user and creates an appropriate image generation prompt. This is the process of generating prompt sentences to instruct the generation AI model (e.g., DALL-E2 or MidJourney). This prompt is sent to the server to request image generation by the AI.

[0977] server

[0978] The server uses image generation AI to generate an image that replicates the specified clothing style based on prompts received from the terminal. Based on this generated image, it searches for similar products in a database of clothing items (e.g., MySQL or Elasticsearch) and makes optimal suggestions. The suggested items are adjusted based on the emotional state analyzed by the emotion engine. If necessary, the AI ​​generates model images of the clothing items being sold and displays them on the product page.

[0979] Specific example:

[0980] Example of prompt format: "Female model with a casual denim jacket, black leggings, sneakers, and a smile"

[0981] The server generates images using DALL-E2 or MidJourney.

[0982] Search for the most suitable clothing items from databases such as MySQL and Elasticsearch.

[0983] Program processing details

[0984] 1. User Input Reception and Emotion Recognition: Users input text and images on their devices, and their emotions are analyzed using the camera and microphone. This allows the system to capture the user's desired clothing and emotional state.

[0985] 2. Creating and sending image generation prompts: Based on the received input data and sentiment data, the terminal generates prompt sentences that instruct the image generation AI model and sends them to the server.

[0986] 3. Image generation and database search: The server generates an image based on the received prompt message and searches the database for the most suitable clothing item based on the generated image.

[0987] 4. Suggestion adjustment based on emotional state: Select items from the searched items that are appropriate for the user's emotional state and adjust the suggested content accordingly.

[0988] 5. Display to the user and model image generation: The server returns a list of suggested clothing items and generated images to the user, which the device displays. If necessary, the AI-generated model images are reflected on the product page.

[0989] This allows users to easily find the perfect outfit to match their emotional state and receive visually convincing suggestions. Salespeople can display products with a professional look, potentially improving sales and customer satisfaction.

[0990] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0991] Step 1:

[0992] The system receives user input. Users input images of their desired clothing style using their smartphones or computers, either as text or images. For example, they might type "a casual denim jacket, black leggings, and sneakers" into a text box, or upload a reference image. The input data is then transferred to the device.

[0993] Step 2:

[0994] The device acquires emotional data. It uses its camera and microphone to capture the user's facial expressions and voice, which are then analyzed by an emotion engine. For example, if the user is smiling, the device detects an emotional state of "joy." This emotional data is also stored on the device.

[0995] Step 3:

[0996] Creating an image generation prompt. The terminal analyzes the received user input and sentiment data and creates a prompt message to pass to the generation AI model based on that analysis. The prompt message reflects the user's desired clothing and emotional state. The generated prompt message might look like this: "A smiling female model wearing a casual denim jacket, black leggings, and sneakers." This prompt message is then sent to the server.

[0997] Step 4:

[0998] Image generation. Based on the prompt message received from the terminal, the server uses a generation AI model (e.g., DALL-E2 or MidJourney) to generate an image of the specified clothing style. The generated image is temporarily stored on the server.

[0999] Step 5:

[1000] Database search. The server searches a database of clothing items (e.g., MySQL or Elasticsearch) for the most suitable clothing item based on the generated image. The input is the generated image, and the output is a list of clothing items as search results.

[1001] Step 6:

[1002] Adjusting the suggested items. The server takes emotional data into consideration and selects the most suitable items from the list of clothing items obtained in the previous step, based on the user's emotional state. For example, it prioritizes brightly colored items that match the emotion of "joy." This adjusted list is stored on the server.

[1003] Step 7:

[1004] Return of results. The server returns a list of adjusted clothing items and the generated images to the terminal. The terminal receives this and displays it to the user.

[1005] Step 8:

[1006] Model image generation. If necessary, the server uses artificial intelligence to generate model images of the clothing being sold. These generated model images are reflected on the product page, allowing users to visually confirm the product.

[1007] Step 9:

[1008] Purchase procedure. The user reviews the clothing items suggested on their device, selects the items they like, and proceeds with the purchase. Finally, purchase completion information for the selected items is sent to the server.

[1009] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1010] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1011] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[1012] [Third Embodiment]

[1013] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[1014] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1015] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1016] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[1017] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1018] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1019] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1020] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1021] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1022] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1023] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1024] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[1025] This invention is a system that begins with the user inputting an image of the clothing they desire. Based on that image, AI suggests appropriate clothing items, and further generates and presents images of a model wearing those outfits. This system goes through multiple processing steps between the user, the terminal, and the server to improve user satisfaction and seller convenience.

[1026] System Configuration

[1027] user:

[1028] Users use their devices to input an image of the clothing they want. Specifically, they can enter their request in text or upload a reference image.

[1029] Example: Launch the app on your smartphone or computer and type "a casual style with a denim jacket, black leggings, and sneakers" into the text box. Alternatively, upload an image of your favorite outfit.

[1030] Terminal:

[1031] The terminal analyzes the input data received from the user and creates an appropriate image generation prompt.

[1032] This prompt is sent to the server to request image generation by AI.

[1033] Furthermore, the suggested results and generated images returned from the server are displayed to the user.

[1034] server:

[1035] Based on prompts received from the terminal, the server uses image generation AI to generate an image that reproduces the specified clothing style.

[1036] Based on the generated image, the system searches for similar items in its clothing item database and provides optimal suggestions.

[1037] Additionally, if necessary, model images of customers wearing the clothing items being sold will be generated and displayed on the product pages.

[1038] Program processing details

[1039] Receiving and analyzing user input

[1040] User inputs clothing image: Users send requests to the system by entering text or images on their device.

[1041] The terminal analyzes the input: The terminal processes the input data using natural language processing and image analysis techniques to create specific image generation prompts.

[1042] Creating a prompt and sending it to the server

[1043] The terminal generates the prompt: Based on the analysis results, it forms the appropriate prompt. For example, if the user enters "casual denim jacket, black leggings, and sneakers," the terminal will generate the prompt "generate image: casual denim jacket with black leggings and sneakers."

[1044] The terminal sends a prompt to the server: It generates and sends an API request to send a prompt to the server.

[1045] Image generation and product suggestions

[1046] The server receives a prompt and generates an image: The server uses an image generation AI to generate an image of the specified clothing.

[1047] The server searches the database: Based on the generated image, it searches the database of clothing items for the best suggestions. These suggestions are then sent back to the user.

[1048] Displaying results to the user and generating model images.

[1049] The server returns the results to the user: it sends a list of suggested clothing items and the generated images back to the user's device.

[1050] The device displays the results to the user: The returned results are displayed to the user in an easy-to-read format. This allows the user to review the suggested items and consider purchasing them.

[1051] The server generates model images and displays them on the product page: If necessary, AI generates model images of the clothing being sold and displays them on the product page. This allows sellers to easily provide professional-looking images.

[1052] This system allows users to easily find clothing that best suits their image, and enables sellers to create more appealing product pages.

[1053] The following describes the processing flow.

[1054] Step 1:

[1055] user:

[1056] Enter the image of the clothing you're looking for.

[1057] Example: The user enters "a casual denim jacket, black leggings, and sneakers" into the text box and uploads reference images as needed.

[1058] Step 2:

[1059] Terminal:

[1060] Receives and analyzes user input.

[1061] Example: Analyze text and images to extract keywords such as "casual," "denim jacket," "black leggings," and "sneakers."

[1062] Step 3:

[1063] Terminal:

[1064] Create an appropriate image generation prompt.

[1065] Example: Based on the extracted keywords, create a prompt that says "generate image: casual denim jacket with black leggings and sneakers".

[1066] Step 4:

[1067] Terminal:

[1068] Send the created prompt to the server.

[1069] Example: Use an API request to send the prompt "generate image: casual denim jacket with black leggings and sneakers" to the server.

[1070] Step 5:

[1071] server:

[1072] Receive the prompt and pass it to the image generation AI.

[1073] Example: Analyze the received prompt and input it into an AI image generation model (e.g., GAN or Diffusion model).

[1074] Step 6:

[1075] server:

[1076] The image generation AI generates images of the specified clothing style.

[1077] Example: Generate an image of a "casual denim jacket, black leggings, and sneakers."

[1078] Step 7:

[1079] server:

[1080] The generated image is used to search a database of clothing items.

[1081] Example: Using visual recognition technology based on the generated image, search a database for related items such as a denim jacket, black leggings, and sneakers.

[1082] Step 8:

[1083] server:

[1084] The search results and generated images are sent back to the device.

[1085] Example: A list of suggested products (product ID, name, price, detail link) and generated coordinated images are returned to the device in JSON format.

[1086] Step 9:

[1087] Terminal:

[1088] The suggested clothing items and generated images are displayed to the user.

[1089] Example: Display the generated image and a list of products on the app screen, and provide a link to each product.

[1090] Step 10:

[1091] user:

[1092] Review the suggested clothing items and add the ones you like to your cart.

[1093] Example: Click the "Add to Cart" button for a denim jacket you like.

[1094] Step 11:

[1095] user:

[1096] Proceed with the purchase process.

[1097] Example: Enter your payment information on the purchase screen and click the "Confirm Order" button.

[1098] Step 12:

[1099] Terminal:

[1100] The purchase information is sent to the server and the transaction is processed.

[1101] Example: Purchase information is sent to the server, which then checks inventory and processes payment.

[1102] Step 13:

[1103] server:

[1104] If necessary, generate model images wearing the clothing that will be sold.

[1105] Example: The server uses AI to generate images of a model wearing a denim jacket.

[1106] Step 14:

[1107] server:

[1108] The generated model image is reflected on the product page.

[1109] Example: Save a new model image to the database and display it on the product page.

[1110] These steps make it easy for users to find and purchase clothing that matches their image. Additionally, sellers can easily display their products in a professional manner.

[1111] (Example 1)

[1112] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1113] Traditional online shopping systems lacked the means to support users in visualizing the specific clothing they wanted, forcing them to choose their outfits themselves based on a lot of information. This was time-consuming and laborious, sometimes resulting in a decrease in purchase intent. Furthermore, sellers lacked the means to easily generate professional images to showcase their products attractively. To meet the needs of both users and sellers, there is a need for more efficient and accurate clothing item suggestions and the provision of visual information.

[1114] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1115] In this invention, the server includes means for receiving user input and inputting an image of clothing as text or an image; means for analyzing the user input and creating an appropriate image generation prompt and sending it to the server; means for generating an image based on the prompt; means for searching for the optimal clothing item from a database of clothing items based on the generated image; means for returning the suggested clothing item and the generated image to the user; means for generating a model image of the clothing being sold using artificial intelligence; means for reflecting the generated model image on the product page; means for the user to confirm the suggested clothing item and proceed with the purchase; processing means for the terminal to analyze user input using natural language processing technology and image analysis technology; transmission means for sending the prompt generated by the terminal to the server via an API request; means for the server to search the database based on the generated image and create a suggestion list; transmission means for the server to generate an API response and return it to the user's terminal; and display means for the terminal to display the results to the user. As a result, users can easily find the optimal item based on their desired image of clothing, and sellers can easily create and provide professional product images.

[1116] "User input" refers to text or images that a user provides to the system.

[1117] "Clothing image" refers to text or images that specifically describe the type of clothing the user desires.

[1118] An "image generation prompt" is a set of instructions used to request an AI model to generate an image based on the user's input data.

[1119] A "server" is a central processing unit that analyzes user input, creates image generation prompts, performs database searches based on the generated images, and suggests the most suitable clothing items.

[1120] "Generation means" refers to a function that generates images based on user requests using a generation AI model.

[1121] A "database" is a storage device that systematically stores and allows retrieval of information about clothing items.

[1122] The "suggestion method" refers to a function that selects the most suitable clothing items from a database based on the generated image and suggests them to the user.

[1123] "Artificial intelligence" refers to the technology that enables computers to learn, reason, and improve themselves by mimicking human intelligence.

[1124] "Natural language processing technology" refers to the technology of analyzing and understanding human language, and is used to analyze the meaning of text data.

[1125] "Image analysis technology" refers to techniques for extracting specific information from image data.

[1126] An "API request" is a request from one software program to another program to perform a specific function.

[1127] An "API response" is the response that another software program returns to an API request.

[1128] "Display means" refers to a function that presents results in an easy-to-understand manner on the user's terminal.

[1129] This invention is a system designed to simplify the user's clothing selection process and assist sellers in creating attractive product pages. This system achieves improved user satisfaction and seller convenience through multiple processing steps involving the user, terminal, and server.

[1130] Overall system configuration

[1131] user:

[1132] Users input their desired clothing image using a smartphone or computer application. Specifically, they can enter their request in text or upload reference images.

[1133] Specific example:

[1134] Enter "A casual style consisting of a denim jacket, black leggings, and sneakers" into the text box.

[1135] Alternatively, upload an image of your favorite outfit.

[1136] Terminal:

[1137] The terminal analyzes the input data received from the user and creates an appropriate image generation prompt. This prompt is sent to the server, requesting AI-generated image generation. Furthermore, the suggested results and generated image returned from the server are displayed to the user.

[1138] Example of technology used:

[1139] For natural language processing techniques, we use Python's NLTK library and spaCy.

[1140] For image analysis techniques, we use OpenCV and TensorFlow.

[1141] server:

[1142] Based on prompts received from the terminal, the server uses image generation AI to generate an image that replicates the specified clothing style. Based on this generated image, it searches a database of clothing items for similar products and makes optimal suggestions. If necessary, it generates model images of the clothing items being sold and displays them on the product page.

[1143] Example of technology used:

[1144] For image generation, we use OpenAI's DALL-E or Stability AI's Stable Diffusion as generative AI models.

[1145] SQL or NoSQL database technologies are used for searching the database.

[1146] Specific processing details of the system

[1147] Receiving and analyzing user input:

[1148] The user inputs an image of the clothing they are looking for as text or an image. The device analyzes the received input data using natural language processing and image analysis technologies to form a specific image generation prompt. For example, if the user inputs "casual denim jacket, black leggings, and sneakers," the prompt "generate image: casual denim jacket with black leggings and sneakers" will be generated.

[1149] Example of a prompt:

[1150] "generate image: casual denim jacket with black leggings and sneakers"

[1151] Sending the prompt to the server:

[1152] The system generates an API request to send the prompt generated by the terminal to the server, and then sends it to the server using an HTTP POST request or similar method.

[1153] Image generation:

[1154] Based on the received prompt, the server uses an image generation AI to generate an image of the specified clothing. The generated image is temporarily stored.

[1155] Product proposal generation:

[1156] Based on the generated image, the server searches the database and suggests similar clothing items. These suggestions are tailored to the user's needs.

[1157] Returning and displaying results to the user:

[1158] The server sends the generated image and suggested clothing items together in an API response to the user's device. The device then displays the received results to the user.

[1159] Generating model images and updating product pages as needed:

[1160] The server uses AI to generate images of models wearing clothing items as needed, and displays them on the product page. This allows sellers to easily create and provide professional product images.

[1161] This system makes it easy for users to find the perfect outfit to match their image, and also allows sellers to create more appealing product pages.

[1162] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1163] Step 1:

[1164] The user enters an image of the clothing they want to wear.

[1165] Input: Text or reference image

[1166] Specific actions: The user uses a smartphone or computer application and enters "a casual style with a denim jacket, black leggings, and sneakers" into a text box. Alternatively, they can upload an image of their favorite outfit.

[1167] Output: Text or image data entered by the user.

[1168] Step 2:

[1169] The terminal analyzes user input.

[1170] Input: Text or image data entered by the user.

[1171] Specific operation: The device analyzes text using natural language processing techniques (e.g., Python's NLTK library or spaCy). It also analyzes image data using image analysis techniques (e.g., OpenCV or TensorFlow).

[1172] Output: Information based on the clothing image obtained from the analysis (e.g., "casual denim jacket with black leggings and sneakers")

[1173] Step 3:

[1174] The terminal generates the prompt.

[1175] Input: Information based on clothing images obtained from the analysis results.

[1176] Specific operation: The device creates a prompt suitable for the generated AI model. For example, the prompt "generate image: casual denim jacket with black leggings and sneakers" is generated.

[1177] Output: Generated prompt message

[1178] Step 4:

[1179] The terminal sends a prompt to the server.

[1180] Input: Generated prompt message

[1181] Specific operation: The terminal generates an HTTP POST request and sends the generated prompt message to the server as an API request.

[1182] Output: Prompt message sent to the server

[1183] Step 5:

[1184] The server receives the prompt and generates the image.

[1185] Input: Prompt message sent from the terminal

[1186] Specific operation: The server uses an image generation AI (e.g., OpenAI's DALL-E or Stability AI's Stable Diffusion) to generate an image of the specified clothing. The generated image is temporarily stored.

[1187] Output: Image of the generated clothing

[1188] Step 6:

[1189] The server searches the database and generates product suggestions.

[1190] Input: Image of the generated clothing

[1191] Specific operation: The server searches a database of clothing items based on the generated image. This search uses SQL or NoSQL database technology. The most suitable clothing item is selected from the search results.

[1192] Output: List of suggested optimal clothing items

[1193] Step 7:

[1194] The server returns the results to the user.

[1195] Input: A list of generated images and suggested clothing items.

[1196] Specific operation: The server generates an API response and sends the generated image and a list of suggested clothing items to the user's device.

[1197] Output: A list of images and clothing items returned to the user's device.

[1198] Step 8:

[1199] The device displays the results to the user.

[1200] Input: List of images and clothing items returned from the server.

[1201] Specific operation: The device displays the received results on the user's screen. The UI allows the user to easily review the suggested items.

[1202] Output: A list of images and clothing items displayed on the user's screen.

[1203] Step 9:

[1204] The server generates model images as needed and displays them on the product page.

[1205] Input: Settings for generating data and model images of clothing items to be sold.

[1206] Specific operation: The server uses AI to generate images of models wearing clothing items and displays them on the product page.

[1207] Output: Model image reflected on the product page

[1208] (Application Example 1)

[1209] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1210] Traditional online shopping sites have presented challenges, such as users spending a lot of time and effort finding clothing items that match their desired fashion style. Furthermore, the sheer number of product options often overwhelms users, making it difficult to choose the right items. Additionally, product images alone are often insufficient to convey how the items will look when worn, potentially diminishing purchasing intent. This invention aims to solve these problems and provide a system that improves the user's purchasing experience.

[1211] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1212] This invention includes a server that generates specific prompt text based on the fashion style entered by the user and sends it to an image generation AI model; a server that displays a list of related clothing items based on the generated model image; a server that allows the user to click on a clothing item to go to a details page and complete the purchase process; and a server that collects post-purchase feedback. This makes it possible for the user to easily find appropriate clothing items that match their desired fashion style, visually confirm them with model images, and purchase them on the spot.

[1213] "User input" refers to the user specifying their desired clothing image to the system using text or images.

[1214] An "image generation prompt" is a text message that generates specific instructions based on user input and sends to an image generation AI model.

[1215] An "image generation AI model" is an artificial intelligence that generates images of specified clothing based on the input prompt text.

[1216] "Clothing items" is a term that refers to fashion-related products and accessories, and includes a range of products included in the database.

[1217] A "database" is an information management system that systematically stores information about clothing items.

[1218] A "model image" is an image of a model wearing the generated clothing image, and is generated to present it visually to the user.

[1219] A "prompt message" is text generated by analyzing user input and contains specific instructions for the image generation AI model.

[1220] The "product list" is a list of related clothing items suggested based on the generated model image.

[1221] A "details page" is a webpage or screen that displays detailed information about a suggested clothing item.

[1222] "Feedback" refers to the opinions and impressions that users provide after a purchase, and is used to improve the system and enhance the user experience.

[1223] This invention relates to a system that suggests clothing items that accurately reflect the user's desired fashion style and allows them to purchase those items. This system optimizes the user experience and purchase process through the coordinated operation of user input, terminals, and servers.

[1224] System Overview

[1225] 1. User input

[1226] Users access the system using smartphones or personal computers.

[1227] Users can enter a text description of their desired outfit or upload a reference image.

[1228] 2. Terminal processing

[1229] The terminal will be equipped with an interface for receiving user input.

[1230] Text input is analyzed using a natural language processing library (e.g., spaCy).

[1231] For image input, an image analysis library (e.g., OpenCV) is used.

[1232] The input data is analyzed, and specific prompt messages are generated.

[1233] Specific example: If the user enters "a casual summer dress to wear on the beach in summer," the prompt "generate image: casual summer dress for beach" will be generated.

[1234] 3. Server processing

[1235] Receives prompt messages sent from the terminal.

[1236] Using an image generation AI model (e.g., OpenAI's DALL-E), images of clothing based on prompt text are generated.

[1237] Based on the generated image, the system searches for related products in a database of clothing items (e.g., MySQL).

[1238] Send the search results and generated images to the device.

[1239] 4. Display and Purchase Process

[1240] The device displays a list of suggested clothing items and generated images to the user.

[1241] Users can click on suggested items to go to the details page and proceed with the purchase.

[1242] An interface is provided for collecting post-purchase feedback.

[1243] Examples of specific cases and prompt statements

[1244] Specific example:

[1245] 1. The user enters the text, "A casual dress perfect for spring cherry blossom viewing."

[1246] 2. The terminal generates the prompt message "generate image: casual spring dress for cherry blossom viewing".

[1247] 3. The server sends the generated prompt message to the image generation AI model and generates the corresponding image.

[1248] 4. Search the database of clothing items for related products and display them to the user along with a list of suggestions.

[1249] 5. The user navigates to the product details page and makes a purchase.

[1250] Hardware and software to be used

[1251] Hardware: Smartphones, PCs, servers, GPUs (as needed)

[1252] Software: Mobile app development frameworks (e.g., React Native), natural language processing libraries (e.g., spaCy), image analysis libraries (e.g., OpenCV), AI image generation models (e.g., OpenAI's DALL-E), API request libraries (e.g., Axios), database management systems (e.g., MySQL), frontend libraries (e.g., React.js)

[1253] In this way, a system is created that suggests clothing items that best suit the image entered by the user, allowing them to easily purchase them after visual confirmation.

[1254] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1255] Step 1:

[1256] Users access the system using their smartphones or computers. They then enter an image of their desired clothing style into a text box, or upload a reference image. This allows the system to retrieve the user's fashion preferences. The input is in text or image format, and this information is then analyzed.

[1257] Step 2:

[1258] The terminal receives user input and calls natural language processing libraries (e.g., spaCy) or image analysis libraries (e.g., OpenCV) to analyze its content. For text input, natural language processing converts the content into structured data (such as key-value pairs). For image input, image analysis techniques are used to extract image features. Based on these analysis results, a specific prompt message (e.g., "generate image: casual summer dress for beach") is generated. The input is user text or images, and the output is a specific prompt message.

[1259] Step 3:

[1260] The generated prompt message is sent from the terminal to the server. An API request library (e.g., Axios) and a communication protocol (e.g., HTTP) are used in this process. The terminal formats the prompt message into an API request format and sends it to the server. The input is the generated prompt message, and the output is the request sent to the server.

[1261] Step 4:

[1262] The server passes the received prompt message to an image generation AI model (e.g., OpenAI's DALL-E), and generates an image based on that prompt. The AI ​​model analyzes the generation prompt and generates an image with the specified clothing. The input is the prompt message, and the output is the generated image.

[1263] Step 5:

[1264] The server uses a database management system (e.g., MySQL) to search for clothing items based on the generated image. This search extracts the most suitable specific clothing item using the image analysis results and relevant metadata. The input is the generated image, and the output is a list of related clothing items.

[1265] Step 6:

[1266] The server returns the generated image and a list of searched clothing items to the terminal. The input is the search results and the generated image, and the output is the data sent to the terminal.

[1267] Step 7:

[1268] The terminal displays the received data to the user. Specifically, it provides a user interface that can beautifully display a list of suggested clothing items and generated images. Input is data from the server, and output is the display on the user interface.

[1269] Step 8:

[1270] The user clicks on a suggested item to go to its details page. This details page displays detailed information, price, and a purchase button for each item. The user can then proceed with the purchase. The input is a list of clothing items, and the output is a transition to the details page.

[1271] Step 9:

[1272] After completing a purchase, the user accesses an interface to provide feedback. The device receives the user's feedback and sends it to the server. This feedback is used to improve the system and enhance the user experience. The input is the user's feedback, and the output is the data sent to the server.

[1273] Through these steps, a system is created that allows users to easily find, visually confirm, and purchase their desired fashion style on the spot.

[1274] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1275] This invention is a system in which a user inputs an image of the clothing they desire, and based on that, AI suggests appropriate clothing items. Furthermore, by using an emotion engine, it realizes coordinate suggestions that take into account the user's emotional state. This system improves user satisfaction and enhances convenience for sellers through multiple processing steps between the user, terminal, and server.

[1276] System Configuration

[1277] user:

[1278] Users use their devices to input images of the clothing they want. Specifically, they can enter their requests in text or upload reference images.

[1279] Furthermore, the emotion engine detects and analyzes the user's facial expressions, voice, and biometric information to understand the user's current emotional state.

[1280] Example: Launch the app on your smartphone or computer and type "a casual style with a denim jacket, black leggings, and sneakers" into the text box. Alternatively, upload an image of your favorite outfit, and the emotion engine will analyze your facial expressions and voice using the camera and microphone.

[1281] Terminal:

[1282] The device analyzes input data and sentiment data received from the user and creates appropriate image generation prompts.

[1283] This prompt is sent to the server to request image generation by AI.

[1284] Furthermore, the suggested results and generated images returned from the server are displayed to the user.

[1285] server:

[1286] Based on prompts received from the terminal, the server uses image generation AI to generate an image that reproduces the specified clothing style.

[1287] Based on the generated image, the system searches for similar items in a database of clothing items and provides optimal suggestions.

[1288] The suggested items are adjusted based on the emotional state analyzed by the emotion engine.

[1289] If necessary, AI will generate model images of the clothing items being sold and display them on the product page.

[1290] Program processing details

[1291] User input and emotion recognition

[1292] User inputs clothing image: Users send requests to the system by entering text or images on their device.

[1293] The emotion engine recognizes emotions: It analyzes the user's facial expressions, voice, and biometric information to understand their current emotional state. For example, if the user is smiling, it detects an emotional state of "joy."

[1294] Creating a prompt and sending it to the server

[1295] The device analyzes input and emotions: it generates appropriate prompts based on text, images, and emotional states. For example, if the user wants to wear casual clothing and is in an emotional state of "joy," it will create a prompt that is appropriate for that.

[1296] The terminal sends a prompt to the server: It sends a prompt to the server via the API, requesting the necessary action.

[1297] Image generation and product suggestions

[1298] The server receives a prompt and generates an image: The server uses an image generation AI to generate an image of the specified clothing style.

[1299] The server searches the database: Based on the generated image, it searches the database of clothing items for the most suitable item.

[1300] The server adjusts suggestions based on the user's emotional state: It selects items from the search results that are appropriate for the user's emotional state and adjusts the suggestions accordingly.

[1301] Displaying results to the user and generating model images.

[1302] The server returns results to the user: it sends a list of suggested clothing items and generated images back to the user's device. The suggestions take the user's emotional state into consideration.

[1303] The device displays the results to the user: The returned results are displayed to the user in an easy-to-read format. This allows the user to review the suggested items and consider purchasing them.

[1304] The server generates model images and displays them on the product page: If necessary, it generates model images of the clothing being sold and displays them on the product page.

[1305] This system will allow users to easily find the perfect outfit to match their emotional state, and sellers will be able to easily display their products in a professional way.

[1306] The following describes the processing flow.

[1307] Step 1:

[1308] user:

[1309] Enter the image of the clothing you're looking for.

[1310] Example: The user enters "a casual denim jacket, black leggings, and sneakers" into a text box and uploads reference images as needed. They also send facial expressions and voice information using a camera and microphone that support the emotion engine.

[1311] Step 2:

[1312] Terminal:

[1313] Receives and analyzes user input.

[1314] Example: Analyze text and images to extract keywords such as "casual," "denim jacket," "black leggings," and "sneakers."

[1315] Step 3:

[1316] Terminal:

[1317] Use an emotion engine to recognize the user's emotions.

[1318] For example, a camera captures the user's facial expressions, and a voice recognition system analyzes the tone of their voice to determine their emotional state, such as whether they are happy or depressed.

[1319] Step 4:

[1320] Terminal:

[1321] Create an appropriate image generation prompt.

[1322] Example: Based on the extracted keywords and recognized emotional state, create a prompt that says, "generate image: casual denim jacket with black leggings and sneakers for a happy mood."

[1323] Step 5:

[1324] Terminal:

[1325] Send the created prompt to the server.

[1326] Example: Use an API request to send the prompt "generate image: casual denim jacket with black leggings and sneakers for a happy mood" to the server.

[1327] Step 6:

[1328] server:

[1329] Receive the prompt and pass it to the image generation AI.

[1330] Example: Analyze the received prompt and input it into an AI image generation model (e.g., GAN or Diffusion model).

[1331] Step 7:

[1332] server:

[1333] The image generation AI generates images of the specified clothing style.

[1334] Example: Generate an image of a "casual denim jacket, black leggings, and sneakers."

[1335] Step 8:

[1336] server:

[1337] The generated image is used to search a database of clothing items.

[1338] Example: Using visual recognition technology based on the generated image, search a database for related items such as a denim jacket, black leggings, and sneakers.

[1339] Step 9:

[1340] server:

[1341] Adjust product suggestions based on the results of the emotion engine.

[1342] Example: Select the most suitable product from the search results based on the user's emotional state and adjust the suggestion list accordingly.

[1343] Step 10:

[1344] server:

[1345] The search results and generated images are sent back to the device.

[1346] Example: A list of suggested products (product ID, name, price, detail link) and generated coordinated images are returned to the device in JSON format.

[1347] Step 11:

[1348] Terminal:

[1349] The suggested clothing items and generated images are displayed to the user.

[1350] Example: Display the generated image and a list of products on the app screen, and provide a link to each product.

[1351] Step 12:

[1352] user:

[1353] Review the suggested clothing items and add the ones you like to your cart.

[1354] Example: Click the "Add to Cart" button for a denim jacket you like.

[1355] Step 13:

[1356] user:

[1357] Proceed with the purchase process.

[1358] Example: Enter your payment information on the purchase screen and click the "Confirm Order" button.

[1359] Step 14:

[1360] Terminal:

[1361] The purchase information is sent to the server and the transaction is processed.

[1362] Example: Purchase information is sent to the server, which then checks inventory and processes payment.

[1363] Step 15:

[1364] server:

[1365] If necessary, generate model images wearing the clothing that will be sold.

[1366] Example: The server uses AI to generate images of a model wearing a denim jacket.

[1367] Step 16:

[1368] server:

[1369] The generated model image is reflected on the product page.

[1370] Example: Save a new model image to the database and display it on the product page.

[1371] These steps make it easy for users to find and purchase clothing that matches their image and emotional state. It also allows sellers to easily display their products in a professional manner.

[1372] (Example 2)

[1373] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1374] Conventional clothing coordination suggestion systems often fail to adequately satisfy users because they suggest clothing items without considering the user's emotional state. Furthermore, they struggle to accurately meet user needs by failing to provide suggestions based on specific images the user desires. Additionally, the professional presentation of products was not sufficiently automated, leading to cumbersome and inconvenient product selection processes.

[1375] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1376] In this invention, the server includes means for receiving user input and inputting an image of clothing as text or an image; means for detecting the user's facial expressions, voice, and biometric information and analyzing their emotional state; means for analyzing the user input and emotional state, creating an appropriate image generation prompt and sending it to the server; means for generating an image based on the prompt; means for searching for the optimal clothing item from a database of clothing items based on the generated image; means for adjusting the suggested clothing item considering the emotional state; means for returning the suggested clothing item and the generated image to the user; means for the user to confirm the suggested clothing item and proceed with the purchase; means for generating a model image wearing the clothing to be sold based on the generated image; and means for reflecting the generated model image on the product page. This makes it possible to suggest the optimal clothing that matches the user's emotional state, and allows sellers to easily present their products in a professional way.

[1377] "User input" refers to information that users provide to the system in the form of text or images describing their clothing preferences.

[1378] "Emotional state" refers to the user's current emotional state, analyzed based on factors such as facial expressions, voice, and biometric information.

[1379] An "image generation prompt" is text information created based on user input and emotional state, used to instruct the image generation AI.

[1380] "Generation means" refers to a method or apparatus for generating an image based on an image generation prompt.

[1381] A "database" is a collection of data that stores information about clothing items.

[1382] "Adjustment means" refers to methods or devices for appropriately modifying the suggested content, taking into account the generated image and the user's emotional state.

[1383] "Return method" refers to a method or device for sending back the proposed clothing items and generated images to the user.

[1384] The "purchase process" refers to the series of steps a user takes to review suggested clothing items and actually purchase them.

[1385] "Model images" are images of people wearing the clothing that will be sold, and they are generated by AI.

[1386] A "product page" is a webpage on an online shopping site that displays product information.

[1387] This invention is a system in which a user inputs an image of the clothing they desire, and based on that, artificial intelligence (AI) suggests appropriate clothing items. Furthermore, by using an emotion engine, it realizes coordinate suggestions that take into account the user's emotional state. This system improves user satisfaction and enhances convenience for sellers through multiple processing steps between the user, terminal, and server.

[1388] Users input clothing ideas using devices such as smartphones and computers. Specifically, users can enter their requests in text or upload reference images. In addition, the user's facial expressions, voice, and biometric information are analyzed by an emotion engine via the device's camera and microphone to understand their current emotional state. For example, a user might launch the app and enter "a casual denim jacket, black leggings, and sneakers" into the text box. Alternatively, they could upload an image of their favorite outfit, and the emotion engine would analyze their facial expressions and voice using the camera and microphone.

[1389] The device analyzes input and sentiment data received from the user and creates an appropriate image generation prompt. This prompt is sent to the server to request image generation by AI. The software used includes RESTful APIs and HTTP communication libraries (e.g., Axios or Fetch API). An example of a prompt might be "a denim jacket, black leggings, and sneakers that give a casual and fun impression."

[1390] The server generates an image that reproduces the specified clothing style using image generation AI (e.g., OpenAI's DALL-E or Stable Diffusion) based on prompts received from the terminal. Based on the generated image, it searches for similar items in a database of clothing items (e.g., MySQL or MongoDB) and makes optimal suggestions. It also adjusts the suggestions based on the emotional state analyzed by the emotion engine. For example, if the user is in an "enjoyable" emotional state, it will prioritize suggesting items with bright colors and positive designs.

[1391] The server returns the generated image and a list of suggested clothing items to the terminal. The terminal displays these results to the user, who then reviews the suggested items and consider purchasing them. Additionally, if necessary, the server uses AI to generate model images of the clothing being sold and displays them on the product page. For example, GANs technology can be used to generate an image of a model wearing a denim jacket, which is then displayed on the product page of the e-commerce site.

[1392] This system allows users to easily find the perfect outfit to match their emotional state, and enables sellers to easily display their products in a professional manner.

[1393] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1394] System program processing details

[1395] Flow of processing steps and specific actions

[1396] Step 1:

[1397] The user enters an image of the clothing they want to wear.

[1398] Input: The user enters an image of the clothing they want to wear into the terminal using text or images.

[1399] Specific actions: The user uses a smartphone or computer to type "a casual style consisting of a denim jacket, black leggings, and sneakers" into a text box. Alternatively, they can upload an image of an outfit they would like to use as a reference.

[1400] Output: The input text or image file.

[1401] Step 2:

[1402] The device recognizes the user's emotions.

[1403] Input: The device collects the user's facial expressions, voice, and biometric information using its camera and microphone.

[1404] Specific operation: The device captures and analyzes the user's real-time facial expressions and voice through its built-in camera and microphone. For example, the camera detects the user's smile, and the microphone analyzes their voice tone.

[1405] Output: The user's emotional state (e.g., "joy" or "sadness").

[1406] Step 3:

[1407] The terminal creates the prompt.

[1408] Input: User input data (text or image) and emotional state.

[1409] Specific operation: The terminal analyzes input text with its text analysis engine and analyzes uploaded images with its image analysis engine. It integrates emotional state data to generate appropriate image generation prompts.

[1410] Output: Generated image generation prompt (example prompt: "A denim jacket, black leggings, and sneakers for a casual and fun look").

[1411] Step 4:

[1412] The terminal sends a prompt to the server.

[1413] Input: The generated prompt.

[1414] Specific operation: The generated prompt is sent to the server via the API in JSON format. Libraries used include, for example, Axios and the Fetch API.

[1415] Output: Prompt data sent to the server.

[1416] Step 5:

[1417] The server generates the image.

[1418] Input: Prompt data.

[1419] Specific operation: The server uses image generation AI (e.g., OpenAI's DALL-E or Stable Diffusion) to generate images based on prompts.

[1420] Output: Images of the generated clothing styles.

[1421] Step 6:

[1422] The server searches the product database.

[1423] Input: The generated image.

[1424] Specific operation: Analyze images generated using image recognition technology and search for similar items in a database of clothing items (e.g., MySQL or MongoDB).

[1425] Output: A list of suggested clothing items.

[1426] Step 7:

[1427] The server adjusts the suggestion, taking emotions into consideration.

[1428] Input: User's emotional state and a list of suggested clothing items.

[1429] Specific operation: Based on emotional state data, select the most suitable items from the suggested items and adjust the list.

[1430] Output: A list of optimal clothing items adjusted based on emotional state.

[1431] Step 8:

[1432] The server sends the results back to the terminal.

[1433] Input: A list of optimal clothing items and the generated images.

[1434] Specific action: The suggestion list and images are sent back to the device in JSON format.

[1435] Output: Result data sent to the terminal.

[1436] Step 9:

[1437] The device displays the results to the user.

[1438] Input: Result data sent from the server.

[1439] Specific actions: The app screen displays a list of suggested clothing items and generated images, allowing the user to view detailed information.

[1440] Output: Suggested images and a list of clothing items displayed to the user.

[1441] Step 10:

[1442] The server generates model images as needed and displays them on the product page.

[1443] Input: Information about the suggested clothing items.

[1444] Specific operation: Using GANs technology, model images wearing the proposed clothing items are generated and posted on the product page of the e-commerce site.

[1445] Output: Model image reflected on the product page.

[1446] (Application Example 2)

[1447] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1448] Traditional online shopping systems have struggled to appropriately suggest clothing styles that users desire. In particular, the lack of consideration for the user's emotional state often leads to low user satisfaction. Furthermore, if the suggested clothing is not visually appealing, purchasing intent decreases. This results in problems such as low repeat purchase rates and limited sales.

[1449] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for analyzing user input and the user's emotional state, creating an appropriate image generation prompt and sending it to the server, means for searching for the optimal clothing item from a database of clothing items based on the generated image, adjusting the suggested content considering the user's emotional state, and means for generating model images of the clothing being sold using artificial intelligence. This makes it possible to provide optimal clothing suggestions tailored to the user's emotional state while also creating visually appealing suggestions, thereby improving user satisfaction and increasing purchasing intent.

[1450] "User input" refers to users providing information about their desired clothing in the form of text or images.

[1451] "Emotional state" refers to the psychological state of a user, as analyzed from their facial expressions, voice, and other factors.

[1452] An "image generation prompt" refers to a set of instructions that generate an image of a specified clothing style based on user input and emotional state.

[1453] A "server" refers to a computer system that receives user input and emotional states, and performs analysis, image generation, and database searches.

[1454] "Generation method" refers to the process of generating images of a specified clothing style using image generation AI.

[1455] A "database" refers to a storage system where information about clothing items is accumulated.

[1456] "Search method" refers to the process of finding the most suitable clothing items from a database based on the generated images.

[1457] "Suggested content" refers to information that provides the user with the most suitable clothing items based on user input and emotional state.

[1458] "Artificial intelligence" refers to computer systems that perform intelligent tasks by utilizing machine learning and data analysis technologies.

[1459] A "model image" refers to an image that makes it appear as if the suggested clothing items are actually being worn.

[1460] A "product page" refers to a webpage on an online shopping site that showcases a product.

[1461] "Purchase process" refers to the series of steps a user takes to actually buy the suggested clothing items.

[1462] This invention is a system that allows a user to input an image of the clothing they desire, and based on that, an AI suggests appropriate clothing items. Furthermore, by using an emotion engine, it enables coordinated outfit suggestions that take into account the user's emotional state. This system includes three main components: the user, the terminal, and the server.

[1463] System Configuration

[1464] user

[1465] Users input their desired clothing image using their smartphone or computer. Specifically, they can enter their request in text or upload reference images. Furthermore, the emotion engine detects and analyzes the user's facial expressions, voice, and biometric information to understand the user's current emotional state.

[1466] Specific example:

[1467] Launch the app on your smartphone or computer and type "a casual style consisting of a denim jacket, black leggings, and sneakers" into the text box.

[1468] Upload an image of your favorite outfit.

[1469] The camera and microphone are used to analyze facial expressions and voice, which are then processed by an emotion engine.

[1470] terminal

[1471] The terminal analyzes input data and sentiment data received from the user and creates an appropriate image generation prompt. This is the process of generating prompt sentences to instruct the generation AI model (e.g., DALL-E2 or MidJourney). This prompt is sent to the server to request image generation by the AI.

[1472] server

[1473] The server uses image generation AI to generate an image that replicates the specified clothing style based on prompts received from the terminal. Based on this generated image, it searches for similar products in a database of clothing items (e.g., MySQL or Elasticsearch) and makes optimal suggestions. The suggested items are adjusted based on the emotional state analyzed by the emotion engine. If necessary, the AI ​​generates model images of the clothing items being sold and displays them on the product page.

[1474] Specific example:

[1475] Example of prompt format: "Female model with a casual denim jacket, black leggings, sneakers, and a smile"

[1476] The server generates images using DALL-E2 or MidJourney.

[1477] Search for the most suitable clothing items from databases such as MySQL and Elasticsearch.

[1478] Program processing details

[1479] 1. User Input Reception and Emotion Recognition: Users input text and images on their devices, and their emotions are analyzed using the camera and microphone. This allows the system to capture the user's desired clothing and emotional state.

[1480] 2. Creating and sending image generation prompts: Based on the received input data and sentiment data, the terminal generates prompt sentences that instruct the image generation AI model and sends them to the server.

[1481] 3. Image generation and database search: The server generates an image based on the received prompt message and searches the database for the most suitable clothing item based on the generated image.

[1482] 4. Suggestion adjustment based on emotional state: Select items from the searched items that are appropriate for the user's emotional state and adjust the suggested content accordingly.

[1483] 5. Display to the user and model image generation: The server returns a list of suggested clothing items and generated images to the user, which the device displays. If necessary, the AI-generated model images are reflected on the product page.

[1484] This allows users to easily find the perfect outfit to match their emotional state and receive visually convincing suggestions. Salespeople can display products with a professional look, potentially improving sales and customer satisfaction.

[1485] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1486] Step 1:

[1487] The system receives user input. Users input images of their desired clothing style using their smartphones or computers, either as text or images. For example, they might type "a casual denim jacket, black leggings, and sneakers" into a text box, or upload a reference image. The input data is then transferred to the device.

[1488] Step 2:

[1489] The device acquires emotional data. It uses its camera and microphone to capture the user's facial expressions and voice, which are then analyzed by an emotion engine. For example, if the user is smiling, the device detects an emotional state of "joy." This emotional data is also stored on the device.

[1490] Step 3:

[1491] Creating an image generation prompt. The terminal analyzes the received user input and sentiment data and creates a prompt message to pass to the generation AI model based on that analysis. The prompt message reflects the user's desired clothing and emotional state. The generated prompt message might look like this: "A smiling female model wearing a casual denim jacket, black leggings, and sneakers." This prompt message is then sent to the server.

[1492] Step 4:

[1493] Image generation. Based on the prompt message received from the terminal, the server uses a generation AI model (e.g., DALL-E2 or MidJourney) to generate an image of the specified clothing style. The generated image is temporarily stored on the server.

[1494] Step 5:

[1495] Database search. The server searches a database of clothing items (e.g., MySQL or Elasticsearch) for the most suitable clothing item based on the generated image. The input is the generated image, and the output is a list of clothing items as search results.

[1496] Step 6:

[1497] Adjusting the suggested items. The server takes emotional data into consideration and selects the most suitable items from the list of clothing items obtained in the previous step, based on the user's emotional state. For example, it prioritizes brightly colored items that match the emotion of "joy." This adjusted list is stored on the server.

[1498] Step 7:

[1499] Return of results. The server returns a list of adjusted clothing items and the generated images to the terminal. The terminal receives this and displays it to the user.

[1500] Step 8:

[1501] Model image generation. If necessary, the server uses artificial intelligence to generate model images of the clothing being sold. These generated model images are reflected on the product page, allowing users to visually confirm the product.

[1502] Step 9:

[1503] Purchase procedure. The user reviews the clothing items suggested on their device, selects the items they like, and proceeds with the purchase. Finally, purchase completion information for the selected items is sent to the server.

[1504] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1505] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1506] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1507] [Fourth Embodiment]

[1508] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1509] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1510] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1511] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1512] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1513] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1514] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1515] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1516] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1517] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1518] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1519] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1520] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1521] This invention is a system that begins with the user inputting an image of the clothing they desire. Based on that image, AI suggests appropriate clothing items, and further generates and presents images of a model wearing those outfits. This system goes through multiple processing steps between the user, the terminal, and the server to improve user satisfaction and seller convenience.

[1522] System Configuration

[1523] user:

[1524] Users use their devices to input an image of the clothing they want. Specifically, they can enter their request in text or upload a reference image.

[1525] Example: Launch the app on your smartphone or computer and type "a casual style with a denim jacket, black leggings, and sneakers" into the text box. Alternatively, upload an image of your favorite outfit.

[1526] Terminal:

[1527] The terminal analyzes the input data received from the user and creates an appropriate image generation prompt.

[1528] This prompt is sent to the server to request image generation by AI.

[1529] Furthermore, the suggested results and generated images returned from the server are displayed to the user.

[1530] server:

[1531] Based on prompts received from the terminal, the server uses image generation AI to generate an image that reproduces the specified clothing style.

[1532] Based on the generated image, the system searches for similar items in its clothing item database and provides optimal suggestions.

[1533] Additionally, if necessary, model images of customers wearing the clothing items being sold will be generated and displayed on the product pages.

[1534] Program processing details

[1535] Receiving and analyzing user input

[1536] User inputs clothing image: Users send requests to the system by entering text or images on their device.

[1537] The terminal analyzes the input: The terminal processes the input data using natural language processing and image analysis techniques to create specific image generation prompts.

[1538] Creating a prompt and sending it to the server

[1539] The terminal generates the prompt: Based on the analysis results, it forms the appropriate prompt. For example, if the user enters "casual denim jacket, black leggings, and sneakers," the terminal will generate the prompt "generate image: casual denim jacket with black leggings and sneakers."

[1540] The terminal sends a prompt to the server: It generates and sends an API request to send a prompt to the server.

[1541] Image generation and product suggestions

[1542] The server receives a prompt and generates an image: The server uses an image generation AI to generate an image of the specified clothing.

[1543] The server searches the database: Based on the generated image, it searches the database of clothing items for the best suggestions. These suggestions are then sent back to the user.

[1544] Displaying results to the user and generating model images.

[1545] The server returns the results to the user: it sends a list of suggested clothing items and the generated images back to the user's device.

[1546] The device displays the results to the user: The returned results are displayed to the user in an easy-to-read format. This allows the user to review the suggested items and consider purchasing them.

[1547] The server generates model images and displays them on the product page: If necessary, AI generates model images of the clothing being sold and displays them on the product page. This allows sellers to easily provide professional-looking images.

[1548] This system allows users to easily find clothing that best suits their image, and enables sellers to create more appealing product pages.

[1549] The following describes the processing flow.

[1550] Step 1:

[1551] user:

[1552] Enter the image of the clothing you're looking for.

[1553] Example: The user enters "a casual denim jacket, black leggings, and sneakers" into the text box and uploads reference images as needed.

[1554] Step 2:

[1555] Terminal:

[1556] Receives and analyzes user input.

[1557] Example: Analyze text and images to extract keywords such as "casual," "denim jacket," "black leggings," and "sneakers."

[1558] Step 3:

[1559] Terminal:

[1560] Create an appropriate image generation prompt.

[1561] Example: Based on the extracted keywords, create a prompt that says "generate image: casual denim jacket with black leggings and sneakers".

[1562] Step 4:

[1563] Terminal:

[1564] Send the created prompt to the server.

[1565] Example: Use an API request to send the prompt "generate image: casual denim jacket with black leggings and sneakers" to the server.

[1566] Step 5:

[1567] server:

[1568] Receive the prompt and pass it to the image generation AI.

[1569] Example: Analyze the received prompt and input it into an AI image generation model (e.g., GAN or Diffusion model).

[1570] Step 6:

[1571] server:

[1572] The image generation AI generates images of the specified clothing style.

[1573] Example: Generate an image of a "casual denim jacket, black leggings, and sneakers."

[1574] Step 7:

[1575] server:

[1576] The generated image is used to search a database of clothing items.

[1577] Example: Using visual recognition technology based on the generated image, search a database for related items such as a denim jacket, black leggings, and sneakers.

[1578] Step 8:

[1579] server:

[1580] The search results and generated images are sent back to the device.

[1581] Example: A list of suggested products (product ID, name, price, detail link) and generated coordinated images are returned to the device in JSON format.

[1582] Step 9:

[1583] Terminal:

[1584] The suggested clothing items and generated images are displayed to the user.

[1585] Example: Display the generated image and a list of products on the app screen, and provide a link to each product.

[1586] Step 10:

[1587] user:

[1588] Review the suggested clothing items and add the ones you like to your cart.

[1589] Example: Click the "Add to Cart" button for a denim jacket you like.

[1590] Step 11:

[1591] user:

[1592] Proceed with the purchase process.

[1593] Example: Enter your payment information on the purchase screen and click the "Confirm Order" button.

[1594] Step 12:

[1595] Terminal:

[1596] The purchase information is sent to the server and the transaction is processed.

[1597] Example: Purchase information is sent to the server, which then checks inventory and processes payment.

[1598] Step 13:

[1599] server:

[1600] If necessary, generate model images wearing the clothing that will be sold.

[1601] Example: The server uses AI to generate images of a model wearing a denim jacket.

[1602] Step 14:

[1603] server:

[1604] The generated model image is reflected on the product page.

[1605] Example: Save a new model image to the database and display it on the product page.

[1606] These steps make it easy for users to find and purchase clothing that matches their image. Additionally, sellers can easily display their products in a professional manner.

[1607] (Example 1)

[1608] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1609] Traditional online shopping systems lacked the means to support users in visualizing the specific clothing they wanted, forcing them to choose their outfits themselves based on a lot of information. This was time-consuming and laborious, sometimes resulting in a decrease in purchase intent. Furthermore, sellers lacked the means to easily generate professional images to showcase their products attractively. To meet the needs of both users and sellers, there is a need for more efficient and accurate clothing item suggestions and the provision of visual information.

[1610] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1611] In this invention, the server includes means for receiving user input and inputting an image of clothing as text or an image; means for analyzing the user input and creating an appropriate image generation prompt and sending it to the server; means for generating an image based on the prompt; means for searching for the optimal clothing item from a database of clothing items based on the generated image; means for returning the suggested clothing item and the generated image to the user; means for generating a model image of the clothing being sold using artificial intelligence; means for reflecting the generated model image on the product page; means for the user to confirm the suggested clothing item and proceed with the purchase; processing means for the terminal to analyze user input using natural language processing technology and image analysis technology; transmission means for sending the prompt generated by the terminal to the server via an API request; means for the server to search the database based on the generated image and create a suggestion list; transmission means for the server to generate an API response and return it to the user's terminal; and display means for the terminal to display the results to the user. As a result, users can easily find the optimal item based on their desired image of clothing, and sellers can easily create and provide professional product images.

[1612] "User input" refers to text or images that a user provides to the system.

[1613] "Clothing image" refers to text or images that specifically describe the type of clothing the user desires.

[1614] An "image generation prompt" is a set of instructions used to request an AI model to generate an image based on the user's input data.

[1615] A "server" is a central processing unit that analyzes user input, creates image generation prompts, performs database searches based on the generated images, and suggests the most suitable clothing items.

[1616] "Generation means" refers to a function that generates images based on user requests using a generation AI model.

[1617] A "database" is a storage device that systematically stores and allows retrieval of information about clothing items.

[1618] The "suggestion method" refers to a function that selects the most suitable clothing items from a database based on the generated image and suggests them to the user.

[1619] "Artificial intelligence" refers to the technology that enables computers to learn, reason, and improve themselves by mimicking human intelligence.

[1620] "Natural language processing technology" refers to the technology of analyzing and understanding human language, and is used to analyze the meaning of text data.

[1621] "Image analysis technology" refers to techniques for extracting specific information from image data.

[1622] An "API request" is a request from one software program to another program to perform a specific function.

[1623] An "API response" is the response that another software program returns to an API request.

[1624] "Display means" refers to a function that presents results in an easy-to-understand manner on the user's terminal.

[1625] This invention is a system designed to simplify the user's clothing selection process and assist sellers in creating attractive product pages. This system achieves improved user satisfaction and seller convenience through multiple processing steps involving the user, terminal, and server.

[1626] Overall system configuration

[1627] user:

[1628] Users input their desired clothing image using a smartphone or computer application. Specifically, they can enter their request in text or upload reference images.

[1629] Specific example:

[1630] Enter "A casual style consisting of a denim jacket, black leggings, and sneakers" into the text box.

[1631] Alternatively, upload an image of your favorite outfit.

[1632] Terminal:

[1633] The terminal analyzes the input data received from the user and creates an appropriate image generation prompt. This prompt is sent to the server, requesting AI-generated image generation. Furthermore, the suggested results and generated image returned from the server are displayed to the user.

[1634] Example of technology used:

[1635] For natural language processing techniques, we use Python's NLTK library and spaCy.

[1636] For image analysis techniques, we use OpenCV and TensorFlow.

[1637] server:

[1638] Based on prompts received from the terminal, the server uses image generation AI to generate an image that replicates the specified clothing style. Based on this generated image, it searches a database of clothing items for similar products and makes optimal suggestions. If necessary, it generates model images of the clothing items being sold and displays them on the product page.

[1639] Example of technology used:

[1640] For image generation, we use OpenAI's DALL-E or Stability AI's Stable Diffusion as generative AI models.

[1641] SQL or NoSQL database technologies are used for searching the database.

[1642] Specific processing details of the system

[1643] Receiving and analyzing user input:

[1644] The user inputs an image of the clothing they are looking for as text or an image. The device analyzes the received input data using natural language processing and image analysis technologies to form a specific image generation prompt. For example, if the user inputs "casual denim jacket, black leggings, and sneakers," the prompt "generate image: casual denim jacket with black leggings and sneakers" will be generated.

[1645] Example of a prompt:

[1646] "generate image: casual denim jacket with black leggings and sneakers"

[1647] Sending the prompt to the server:

[1648] The system generates an API request to send the prompt generated by the terminal to the server, and then sends it to the server using an HTTP POST request or similar method.

[1649] Image generation:

[1650] Based on the received prompt, the server uses an image generation AI to generate an image of the specified clothing. The generated image is temporarily stored.

[1651] Product proposal generation:

[1652] Based on the generated image, the server searches the database and suggests similar clothing items. These suggestions are tailored to the user's needs.

[1653] Returning and displaying results to the user:

[1654] The server sends the generated image and suggested clothing items together in an API response to the user's device. The device then displays the received results to the user.

[1655] Generating model images and updating product pages as needed:

[1656] The server uses AI to generate images of models wearing clothing items as needed, and displays them on the product page. This allows sellers to easily create and provide professional product images.

[1657] This system makes it easy for users to find the perfect outfit to match their image, and also allows sellers to create more appealing product pages.

[1658] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1659] Step 1:

[1660] The user enters an image of the clothing they want to wear.

[1661] Input: Text or reference image

[1662] Specific actions: The user uses a smartphone or computer application and enters "a casual style with a denim jacket, black leggings, and sneakers" into a text box. Alternatively, they can upload an image of their favorite outfit.

[1663] Output: Text or image data entered by the user.

[1664] Step 2:

[1665] The terminal analyzes user input.

[1666] Input: Text or image data entered by the user.

[1667] Specific operation: The device analyzes text using natural language processing techniques (e.g., Python's NLTK library or spaCy). It also analyzes image data using image analysis techniques (e.g., OpenCV or TensorFlow).

[1668] Output: Information based on the clothing image obtained from the analysis (e.g., "casual denim jacket with black leggings and sneakers")

[1669] Step 3:

[1670] The terminal generates the prompt.

[1671] Input: Information based on clothing images obtained from the analysis results.

[1672] Specific operation: The device creates a prompt suitable for the generated AI model. For example, the prompt "generate image: casual denim jacket with black leggings and sneakers" is generated.

[1673] Output: Generated prompt message

[1674] Step 4:

[1675] The terminal sends a prompt to the server.

[1676] Input: Generated prompt message

[1677] Specific operation: The terminal generates an HTTP POST request and sends the generated prompt message to the server as an API request.

[1678] Output: Prompt message sent to the server

[1679] Step 5:

[1680] The server receives the prompt and generates the image.

[1681] Input: Prompt message sent from the terminal

[1682] Specific operation: The server uses an image generation AI (e.g., OpenAI's DALL-E or Stability AI's Stable Diffusion) to generate an image of the specified clothing. The generated image is temporarily stored.

[1683] Output: Image of the generated clothing

[1684] Step 6:

[1685] The server searches the database and generates product suggestions.

[1686] Input: Image of the generated clothing

[1687] Specific operation: The server searches a database of clothing items based on the generated image. This search uses SQL or NoSQL database technology. The most suitable clothing item is selected from the search results.

[1688] Output: List of suggested optimal clothing items

[1689] Step 7:

[1690] The server returns the results to the user.

[1691] Input: A list of generated images and suggested clothing items.

[1692] Specific operation: The server generates an API response and sends the generated image and a list of suggested clothing items to the user's device.

[1693] Output: A list of images and clothing items returned to the user's device.

[1694] Step 8:

[1695] The device displays the results to the user.

[1696] Input: List of images and clothing items returned from the server.

[1697] Specific operation: The device displays the received results on the user's screen. The UI allows the user to easily review the suggested items.

[1698] Output: A list of images and clothing items displayed on the user's screen.

[1699] Step 9:

[1700] The server generates model images as needed and displays them on the product page.

[1701] Input: Settings for generating data and model images of clothing items to be sold.

[1702] Specific operation: The server uses AI to generate images of models wearing clothing items and displays them on the product page.

[1703] Output: Model image reflected on the product page

[1704] (Application Example 1)

[1705] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1706] Traditional online shopping sites have presented challenges, such as users spending a lot of time and effort finding clothing items that match their desired fashion style. Furthermore, the sheer number of product options often overwhelms users, making it difficult to choose the right items. Additionally, product images alone are often insufficient to convey how the items will look when worn, potentially diminishing purchasing intent. This invention aims to solve these problems and provide a system that improves the user's purchasing experience.

[1707] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1708] This invention includes a server that generates specific prompt text based on the fashion style entered by the user and sends it to an image generation AI model; a server that displays a list of related clothing items based on the generated model image; a server that allows the user to click on a clothing item to go to a details page and complete the purchase process; and a server that collects post-purchase feedback. This makes it possible for the user to easily find appropriate clothing items that match their desired fashion style, visually confirm them with model images, and purchase them on the spot.

[1709] "User input" refers to the user specifying their desired clothing image to the system using text or images.

[1710] An "image generation prompt" is a text message that generates specific instructions based on user input and sends to an image generation AI model.

[1711] An "image generation AI model" is an artificial intelligence that generates images of specified clothing based on the input prompt text.

[1712] "Clothing items" is a term that refers to fashion-related products and accessories, and includes a range of products included in the database.

[1713] A "database" is an information management system that systematically stores information about clothing items.

[1714] A "model image" is an image of a model wearing the generated clothing image, and is generated to present it visually to the user.

[1715] A "prompt message" is text generated by analyzing user input and contains specific instructions for the image generation AI model.

[1716] The "product list" is a list of related clothing items suggested based on the generated model image.

[1717] A "details page" is a webpage or screen that displays detailed information about a suggested clothing item.

[1718] "Feedback" refers to the opinions and impressions that users provide after a purchase, and is used to improve the system and enhance the user experience.

[1719] This invention relates to a system that suggests clothing items that accurately reflect the user's desired fashion style and allows them to purchase those items. This system optimizes the user experience and purchase process through the coordinated operation of user input, terminals, and servers.

[1720] System Overview

[1721] 1. User input

[1722] Users access the system using smartphones or personal computers.

[1723] Users can enter a text description of their desired outfit or upload a reference image.

[1724] 2. Terminal processing

[1725] The terminal will be equipped with an interface for receiving user input.

[1726] Text input is analyzed using a natural language processing library (e.g., spaCy).

[1727] For image input, an image analysis library (e.g., OpenCV) is used.

[1728] The input data is analyzed, and specific prompt messages are generated.

[1729] Specific example: If the user enters "a casual summer dress to wear on the beach in summer," the prompt "generate image: casual summer dress for beach" will be generated.

[1730] 3. Server processing

[1731] Receives prompt messages sent from the terminal.

[1732] Using an image generation AI model (e.g., OpenAI's DALL-E), images of clothing based on prompt text are generated.

[1733] Based on the generated image, the system searches for related products in a database of clothing items (e.g., MySQL).

[1734] Send the search results and generated images to the device.

[1735] 4. Display and Purchase Process

[1736] The device displays a list of suggested clothing items and generated images to the user.

[1737] Users can click on suggested items to go to the details page and proceed with the purchase.

[1738] An interface is provided for collecting post-purchase feedback.

[1739] Examples of specific cases and prompt statements

[1740] Specific example:

[1741] 1. The user enters the text, "A casual dress perfect for spring cherry blossom viewing."

[1742] 2. The terminal generates the prompt message "generate image: casual spring dress for cherry blossom viewing".

[1743] 3. The server sends the generated prompt message to the image generation AI model and generates the corresponding image.

[1744] 4. Search the database of clothing items for related products and display them to the user along with a list of suggestions.

[1745] 5. The user navigates to the product details page and makes a purchase.

[1746] Hardware and software to be used

[1747] Hardware: Smartphones, PCs, servers, GPUs (as needed)

[1748] Software: Mobile app development frameworks (e.g., React Native), natural language processing libraries (e.g., spaCy), image analysis libraries (e.g., OpenCV), AI image generation models (e.g., OpenAI's DALL-E), API request libraries (e.g., Axios), database management systems (e.g., MySQL), frontend libraries (e.g., React.js)

[1749] In this way, a system is created that suggests clothing items that best suit the image entered by the user, allowing them to easily purchase them after visual confirmation.

[1750] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1751] Step 1:

[1752] Users access the system using their smartphones or computers. They then enter an image of their desired clothing style into a text box, or upload a reference image. This allows the system to retrieve the user's fashion preferences. The input is in text or image format, and this information is then analyzed.

[1753] Step 2:

[1754] The terminal receives user input and calls natural language processing libraries (e.g., spaCy) or image analysis libraries (e.g., OpenCV) to analyze its content. For text input, natural language processing converts the content into structured data (such as key-value pairs). For image input, image analysis techniques are used to extract image features. Based on these analysis results, a specific prompt message (e.g., "generate image: casual summer dress for beach") is generated. The input is user text or images, and the output is a specific prompt message.

[1755] Step 3:

[1756] The generated prompt message is sent from the terminal to the server. An API request library (e.g., Axios) and a communication protocol (e.g., HTTP) are used in this process. The terminal formats the prompt message into an API request format and sends it to the server. The input is the generated prompt message, and the output is the request sent to the server.

[1757] Step 4:

[1758] The server passes the received prompt message to an image generation AI model (e.g., OpenAI's DALL-E), and generates an image based on that prompt. The AI ​​model analyzes the generation prompt and generates an image with the specified clothing. The input is the prompt message, and the output is the generated image.

[1759] Step 5:

[1760] The server uses a database management system (e.g., MySQL) to search for clothing items based on the generated image. This search extracts the most suitable specific clothing item using the image analysis results and relevant metadata. The input is the generated image, and the output is a list of related clothing items.

[1761] Step 6:

[1762] The server returns the generated image and a list of searched clothing items to the terminal. The input is the search results and the generated image, and the output is the data sent to the terminal.

[1763] Step 7:

[1764] The terminal displays the received data to the user. Specifically, it provides a user interface that can beautifully display a list of suggested clothing items and generated images. Input is data from the server, and output is the display on the user interface.

[1765] Step 8:

[1766] The user clicks on a suggested item to go to its details page. This details page displays detailed information, price, and a purchase button for each item. The user can then proceed with the purchase. The input is a list of clothing items, and the output is a transition to the details page.

[1767] Step 9:

[1768] After completing a purchase, the user accesses an interface to provide feedback. The device receives the user's feedback and sends it to the server. This feedback is used to improve the system and enhance the user experience. The input is the user's feedback, and the output is the data sent to the server.

[1769] Through these steps, a system is created that allows users to easily find, visually confirm, and purchase their desired fashion style on the spot.

[1770] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1771] This invention is a system in which a user inputs an image of the clothing they desire, and based on that, AI suggests appropriate clothing items. Furthermore, by using an emotion engine, it realizes coordinate suggestions that take into account the user's emotional state. This system improves user satisfaction and enhances convenience for sellers through multiple processing steps between the user, terminal, and server.

[1772] System Configuration

[1773] user:

[1774] Users use their devices to input images of the clothing they want. Specifically, they can enter their requests in text or upload reference images.

[1775] Furthermore, the emotion engine detects and analyzes the user's facial expressions, voice, and biometric information to understand the user's current emotional state.

[1776] Example: Launch the app on your smartphone or computer and type "a casual style with a denim jacket, black leggings, and sneakers" into the text box. Alternatively, upload an image of your favorite outfit, and the emotion engine will analyze your facial expressions and voice using the camera and microphone.

[1777] Terminal:

[1778] The device analyzes input data and sentiment data received from the user and creates appropriate image generation prompts.

[1779] This prompt is sent to the server to request image generation by AI.

[1780] Furthermore, the suggested results and generated images returned from the server are displayed to the user.

[1781] server:

[1782] Based on prompts received from the terminal, the server uses image generation AI to generate an image that reproduces the specified clothing style.

[1783] Based on the generated image, the system searches for similar items in a database of clothing items and provides optimal suggestions.

[1784] The suggested items are adjusted based on the emotional state analyzed by the emotion engine.

[1785] If necessary, AI will generate model images of the clothing items being sold and display them on the product page.

[1786] Program processing details

[1787] User input and emotion recognition

[1788] User inputs clothing image: Users send requests to the system by entering text or images on their device.

[1789] The emotion engine recognizes emotions: It analyzes the user's facial expressions, voice, and biometric information to understand their current emotional state. For example, if the user is smiling, it detects an emotional state of "joy."

[1790] Creating a prompt and sending it to the server

[1791] The device analyzes input and emotions: it generates appropriate prompts based on text, images, and emotional states. For example, if the user wants to wear casual clothing and is in an emotional state of "joy," it will create a prompt that is appropriate for that.

[1792] The terminal sends a prompt to the server: It sends a prompt to the server via the API, requesting the necessary action.

[1793] Image generation and product suggestions

[1794] The server receives a prompt and generates an image: The server uses an image generation AI to generate an image of the specified clothing style.

[1795] The server searches the database: Based on the generated image, it searches the database of clothing items for the most suitable item.

[1796] The server adjusts suggestions based on the user's emotional state: It selects items from the search results that are appropriate for the user's emotional state and adjusts the suggestions accordingly.

[1797] Displaying results to the user and generating model images.

[1798] The server returns results to the user: it sends a list of suggested clothing items and generated images back to the user's device. The suggestions take the user's emotional state into consideration.

[1799] The device displays the results to the user: The returned results are displayed to the user in an easy-to-read format. This allows the user to review the suggested items and consider purchasing them.

[1800] The server generates model images and displays them on the product page: If necessary, it generates model images of the clothing being sold and displays them on the product page.

[1801] This system will allow users to easily find the perfect outfit to match their emotional state, and sellers will be able to easily display their products in a professional way.

[1802] The following describes the processing flow.

[1803] Step 1:

[1804] user:

[1805] Enter the image of the clothing you're looking for.

[1806] Example: The user enters "a casual denim jacket, black leggings, and sneakers" into a text box and uploads reference images as needed. They also send facial expressions and voice information using a camera and microphone that support the emotion engine.

[1807] Step 2:

[1808] Terminal:

[1809] Receives and analyzes user input.

[1810] Example: Analyze text and images to extract keywords such as "casual," "denim jacket," "black leggings," and "sneakers."

[1811] Step 3:

[1812] Terminal:

[1813] Use an emotion engine to recognize the user's emotions.

[1814] For example, a camera captures the user's facial expressions, and a voice recognition system analyzes the tone of their voice to determine their emotional state, such as whether they are happy or depressed.

[1815] Step 4:

[1816] Terminal:

[1817] Create an appropriate image generation prompt.

[1818] Example: Based on the extracted keywords and recognized emotional state, create a prompt that says, "generate image: casual denim jacket with black leggings and sneakers for a happy mood."

[1819] Step 5:

[1820] Terminal:

[1821] Send the created prompt to the server.

[1822] Example: Use an API request to send the prompt "generate image: casual denim jacket with black leggings and sneakers for a happy mood" to the server.

[1823] Step 6:

[1824] server:

[1825] Receive the prompt and pass it to the image generation AI.

[1826] Example: Analyze the received prompt and input it into an AI image generation model (e.g., GAN or Diffusion model).

[1827] Step 7:

[1828] server:

[1829] The image generation AI generates images of the specified clothing style.

[1830] Example: Generate an image of a "casual denim jacket, black leggings, and sneakers."

[1831] Step 8:

[1832] server:

[1833] The generated image is used to search a database of clothing items.

[1834] Example: Using visual recognition technology based on the generated image, search a database for related items such as a denim jacket, black leggings, and sneakers.

[1835] Step 9:

[1836] server:

[1837] Adjust product suggestions based on the results of the emotion engine.

[1838] Example: Select the most suitable product from the search results based on the user's emotional state and adjust the suggestion list accordingly.

[1839] Step 10:

[1840] server:

[1841] The search results and generated images are sent back to the device.

[1842] Example: A list of suggested products (product ID, name, price, detail link) and generated coordinated images are returned to the device in JSON format.

[1843] Step 11:

[1844] Terminal:

[1845] The suggested clothing items and generated images are displayed to the user.

[1846] Example: Display the generated image and a list of products on the app screen, and provide a link to each product.

[1847] Step 12:

[1848] user:

[1849] Review the suggested clothing items and add the ones you like to your cart.

[1850] Example: Click the "Add to Cart" button for a denim jacket you like.

[1851] Step 13:

[1852] user:

[1853] Proceed with the purchase process.

[1854] Example: Enter your payment information on the purchase screen and click the "Confirm Order" button.

[1855] Step 14:

[1856] Terminal:

[1857] The purchase information is sent to the server and the transaction is processed.

[1858] Example: Purchase information is sent to the server, which then checks inventory and processes payment.

[1859] Step 15:

[1860] server:

[1861] If necessary, generate model images wearing the clothing that will be sold.

[1862] Example: The server uses AI to generate images of a model wearing a denim jacket.

[1863] Step 16:

[1864] server:

[1865] The generated model image is reflected on the product page.

[1866] Example: Save a new model image to the database and display it on the product page.

[1867] These steps make it easy for users to find and purchase clothing that matches their image and emotional state. It also allows sellers to easily display their products in a professional manner.

[1868] (Example 2)

[1869] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1870] Conventional clothing coordination suggestion systems often fail to adequately satisfy users because they suggest clothing items without considering the user's emotional state. Furthermore, they struggle to accurately meet user needs by failing to provide suggestions based on specific images the user desires. Additionally, the professional presentation of products was not sufficiently automated, leading to cumbersome and inconvenient product selection processes.

[1871] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1872] In this invention, the server includes means for receiving user input and inputting an image of clothing as text or an image; means for detecting the user's facial expressions, voice, and biometric information and analyzing their emotional state; means for analyzing the user input and emotional state, creating an appropriate image generation prompt and sending it to the server; means for generating an image based on the prompt; means for searching for the optimal clothing item from a database of clothing items based on the generated image; means for adjusting the suggested clothing item considering the emotional state; means for returning the suggested clothing item and the generated image to the user; means for the user to confirm the suggested clothing item and proceed with the purchase; means for generating a model image wearing the clothing to be sold based on the generated image; and means for reflecting the generated model image on the product page. This makes it possible to suggest the optimal clothing that matches the user's emotional state, and allows sellers to easily present their products in a professional way.

[1873] "User input" refers to information that users provide to the system in the form of text or images describing their clothing preferences.

[1874] "Emotional state" refers to the user's current emotional state, analyzed based on factors such as facial expressions, voice, and biometric information.

[1875] An "image generation prompt" is text information created based on user input and emotional state, used to instruct the image generation AI.

[1876] "Generation means" refers to a method or apparatus for generating an image based on an image generation prompt.

[1877] A "database" is a collection of data that stores information about clothing items.

[1878] "Adjustment means" refers to methods or devices for appropriately modifying the suggested content, taking into account the generated image and the user's emotional state.

[1879] "Return method" refers to a method or device for sending back the proposed clothing items and generated images to the user.

[1880] The "purchase process" refers to the series of steps a user takes to review suggested clothing items and actually purchase them.

[1881] "Model images" are images of people wearing the clothing that will be sold, and they are generated by AI.

[1882] A "product page" is a webpage on an online shopping site that displays product information.

[1883] This invention is a system in which a user inputs an image of the clothing they desire, and based on that, artificial intelligence (AI) suggests appropriate clothing items. Furthermore, by using an emotion engine, it realizes coordinate suggestions that take into account the user's emotional state. This system improves user satisfaction and enhances convenience for sellers through multiple processing steps between the user, terminal, and server.

[1884] Users input clothing ideas using devices such as smartphones and computers. Specifically, users can enter their requests in text or upload reference images. In addition, the user's facial expressions, voice, and biometric information are analyzed by an emotion engine via the device's camera and microphone to understand their current emotional state. For example, a user might launch the app and enter "a casual denim jacket, black leggings, and sneakers" into the text box. Alternatively, they could upload an image of their favorite outfit, and the emotion engine would analyze their facial expressions and voice using the camera and microphone.

[1885] The device analyzes input and sentiment data received from the user and creates an appropriate image generation prompt. This prompt is sent to the server to request image generation by AI. The software used includes RESTful APIs and HTTP communication libraries (e.g., Axios or Fetch API). An example of a prompt might be "a denim jacket, black leggings, and sneakers that give a casual and fun impression."

[1886] The server generates an image that reproduces the specified clothing style using image generation AI (e.g., OpenAI's DALL-E or Stable Diffusion) based on prompts received from the terminal. Based on the generated image, it searches for similar items in a database of clothing items (e.g., MySQL or MongoDB) and makes optimal suggestions. It also adjusts the suggestions based on the emotional state analyzed by the emotion engine. For example, if the user is in an "enjoyable" emotional state, it will prioritize suggesting items with bright colors and positive designs.

[1887] The server returns the generated image and a list of suggested clothing items to the terminal. The terminal displays these results to the user, who then reviews the suggested items and consider purchasing them. Additionally, if necessary, the server uses AI to generate model images of the clothing being sold and displays them on the product page. For example, GANs technology can be used to generate an image of a model wearing a denim jacket, which is then displayed on the product page of the e-commerce site.

[1888] This system allows users to easily find the perfect outfit to match their emotional state, and enables sellers to easily display their products in a professional manner.

[1889] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1890] System program processing details

[1891] Flow of processing steps and specific actions

[1892] Step 1:

[1893] The user enters an image of the clothing they want to wear.

[1894] Input: The user enters an image of the clothing they want to wear into the terminal using text or images.

[1895] Specific actions: The user uses a smartphone or computer to type "a casual style consisting of a denim jacket, black leggings, and sneakers" into a text box. Alternatively, they can upload an image of an outfit they would like to use as a reference.

[1896] Output: The input text or image file.

[1897] Step 2:

[1898] The device recognizes the user's emotions.

[1899] Input: The device collects the user's facial expressions, voice, and biometric information using its camera and microphone.

[1900] Specific operation: The device captures and analyzes the user's real-time facial expressions and voice through its built-in camera and microphone. For example, the camera detects the user's smile, and the microphone analyzes their voice tone.

[1901] Output: The user's emotional state (e.g., "joy" or "sadness").

[1902] Step 3:

[1903] The terminal creates the prompt.

[1904] Input: User input data (text or image) and emotional state.

[1905] Specific operation: The terminal analyzes input text with its text analysis engine and analyzes uploaded images with its image analysis engine. It integrates emotional state data to generate appropriate image generation prompts.

[1906] Output: Generated image generation prompt (example prompt: "A denim jacket, black leggings, and sneakers for a casual and fun look").

[1907] Step 4:

[1908] The terminal sends a prompt to the server.

[1909] Input: The generated prompt.

[1910] Specific operation: The generated prompt is sent to the server via the API in JSON format. Libraries used include, for example, Axios and the Fetch API.

[1911] Output: Prompt data sent to the server.

[1912] Step 5:

[1913] The server generates the image.

[1914] Input: Prompt data.

[1915] Specific operation: The server uses image generation AI (e.g., OpenAI's DALL-E or Stable Diffusion) to generate images based on prompts.

[1916] Output: Images of the generated clothing styles.

[1917] Step 6:

[1918] The server searches the product database.

[1919] Input: The generated image.

[1920] Specific operation: Analyze images generated using image recognition technology and search for similar items in a database of clothing items (e.g., MySQL or MongoDB).

[1921] Output: A list of suggested clothing items.

[1922] Step 7:

[1923] The server adjusts the suggestion, taking emotions into consideration.

[1924] Input: User's emotional state and a list of suggested clothing items.

[1925] Specific operation: Based on emotional state data, select the most suitable items from the suggested items and adjust the list.

[1926] Output: A list of optimal clothing items adjusted based on emotional state.

[1927] Step 8:

[1928] The server sends the results back to the terminal.

[1929] Input: A list of optimal clothing items and the generated images.

[1930] Specific action: The suggestion list and images are sent back to the device in JSON format.

[1931] Output: Result data sent to the terminal.

[1932] Step 9:

[1933] The device displays the results to the user.

[1934] Input: Result data sent from the server.

[1935] Specific actions: The app screen displays a list of suggested clothing items and generated images, allowing the user to view detailed information.

[1936] Output: Suggested images and a list of clothing items displayed to the user.

[1937] Step 10:

[1938] The server generates model images as needed and displays them on the product page.

[1939] Input: Information about the suggested clothing items.

[1940] Specific operation: Using GANs technology, model images wearing the proposed clothing items are generated and posted on the product page of the e-commerce site.

[1941] Output: Model image reflected on the product page.

[1942] (Application Example 2)

[1943] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1944] Traditional online shopping systems have struggled to appropriately suggest clothing styles that users desire. In particular, the lack of consideration for the user's emotional state often leads to low user satisfaction. Furthermore, if the suggested clothing is not visually appealing, purchasing intent decreases. This results in problems such as low repeat purchase rates and limited sales.

[1945] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for analyzing user input and the user's emotional state, creating an appropriate image generation prompt and sending it to the server, means for searching for the optimal clothing item from a database of clothing items based on the generated image, adjusting the suggested content considering the user's emotional state, and means for generating model images of the clothing being sold using artificial intelligence. This makes it possible to provide optimal clothing suggestions tailored to the user's emotional state while also creating visually appealing suggestions, thereby improving user satisfaction and increasing purchasing intent.

[1946] "User input" refers to users providing information about their desired clothing in the form of text or images.

[1947] "Emotional state" refers to the psychological state of a user, as analyzed from their facial expressions, voice, and other factors.

[1948] An "image generation prompt" refers to a set of instructions that generate an image of a specified clothing style based on user input and emotional state.

[1949] A "server" refers to a computer system that receives user input and emotional states, and performs analysis, image generation, and database searches.

[1950] "Generation method" refers to the process of generating images of a specified clothing style using image generation AI.

[1951] A "database" refers to a storage system where information about clothing items is accumulated.

[1952] "Search method" refers to the process of finding the most suitable clothing items from a database based on the generated images.

[1953] "Suggested content" refers to information that provides the user with the most suitable clothing items based on user input and emotional state.

[1954] "Artificial intelligence" refers to computer systems that perform intelligent tasks by utilizing machine learning and data analysis technologies.

[1955] A "model image" refers to an image that makes it appear as if the suggested clothing items are actually being worn.

[1956] A "product page" refers to a webpage on an online shopping site that showcases a product.

[1957] "Purchase process" refers to the series of steps a user takes to actually buy the suggested clothing items.

[1958] This invention is a system that allows a user to input an image of the clothing they desire, and based on that, an AI suggests appropriate clothing items. Furthermore, by using an emotion engine, it enables coordinated outfit suggestions that take into account the user's emotional state. This system includes three main components: the user, the terminal, and the server.

[1959] System Configuration

[1960] user

[1961] Users input their desired clothing image using their smartphone or computer. Specifically, they can enter their request in text or upload reference images. Furthermore, the emotion engine detects and analyzes the user's facial expressions, voice, and biometric information to understand the user's current emotional state.

[1962] Specific example:

[1963] Launch the app on your smartphone or computer and type "a casual style consisting of a denim jacket, black leggings, and sneakers" into the text box.

[1964] Upload an image of your favorite outfit.

[1965] The camera and microphone are used to analyze facial expressions and voice, which are then processed by an emotion engine.

[1966] terminal

[1967] The terminal analyzes input data and sentiment data received from the user and creates an appropriate image generation prompt. This is the process of generating prompt sentences to instruct the generation AI model (e.g., DALL-E2 or MidJourney). This prompt is sent to the server to request image generation by the AI.

[1968] server

[1969] The server uses image generation AI to generate an image that replicates the specified clothing style based on prompts received from the terminal. Based on this generated image, it searches for similar products in a database of clothing items (e.g., MySQL or Elasticsearch) and makes optimal suggestions. The suggested items are adjusted based on the emotional state analyzed by the emotion engine. If necessary, the AI ​​generates model images of the clothing items being sold and displays them on the product page.

[1970] Specific example:

[1971] Example of prompt format: "Female model with a casual denim jacket, black leggings, sneakers, and a smile"

[1972] The server generates images using DALL-E2 or MidJourney.

[1973] Search for the most suitable clothing items from databases such as MySQL and Elasticsearch.

[1974] Program processing details

[1975] 1. User Input Reception and Emotion Recognition: Users input text and images on their devices, and their emotions are analyzed using the camera and microphone. This allows the system to capture the user's desired clothing and emotional state.

[1976] 2. Creating and sending image generation prompts: Based on the received input data and sentiment data, the terminal generates prompt sentences that instruct the image generation AI model and sends them to the server.

[1977] 3. Image generation and database search: The server generates an image based on the received prompt message and searches the database for the most suitable clothing item based on the generated image.

[1978] 4. Suggestion adjustment based on emotional state: Select items from the searched items that are appropriate for the user's emotional state and adjust the suggested content accordingly.

[1979] 5. Display to the user and model image generation: The server returns a list of suggested clothing items and generated images to the user, which the device displays. If necessary, the AI-generated model images are reflected on the product page.

[1980] This allows users to easily find the perfect outfit to match their emotional state and receive visually convincing suggestions. Salespeople can display products with a professional look, potentially improving sales and customer satisfaction.

[1981] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1982] Step 1:

[1983] The system receives user input. Users input images of their desired clothing style using their smartphones or computers, either as text or images. For example, they might type "a casual denim jacket, black leggings, and sneakers" into a text box, or upload a reference image. The input data is then transferred to the device.

[1984] Step 2:

[1985] The device acquires emotional data. It uses its camera and microphone to capture the user's facial expressions and voice, which are then analyzed by an emotion engine. For example, if the user is smiling, the device detects an emotional state of "joy." This emotional data is also stored on the device.

[1986] Step 3:

[1987] Creating an image generation prompt. The terminal analyzes the received user input and sentiment data and creates a prompt message to pass to the generation AI model based on that analysis. The prompt message reflects the user's desired clothing and emotional state. The generated prompt message might look like this: "A smiling female model wearing a casual denim jacket, black leggings, and sneakers." This prompt message is then sent to the server.

[1988] Step 4:

[1989] Image generation. Based on the prompt message received from the terminal, the server uses a generation AI model (e.g., DALL-E2 or MidJourney) to generate an image of the specified clothing style. The generated image is temporarily stored on the server.

[1990] Step 5:

[1991] Database search. The server searches a database of clothing items (e.g., MySQL or Elasticsearch) for the most suitable clothing item based on the generated image. The input is the generated image, and the output is a list of clothing items as search results.

[1992] Step 6:

[1993] Adjusting the suggested items. The server takes emotional data into consideration and selects the most suitable items from the list of clothing items obtained in the previous step, based on the user's emotional state. For example, it prioritizes brightly colored items that match the emotion of "joy." This adjusted list is stored on the server.

[1994] Step 7:

[1995] Return of results. The server returns a list of adjusted clothing items and the generated images to the terminal. The terminal receives this and displays it to the user.

[1996] Step 8:

[1997] Model image generation. If necessary, the server uses artificial intelligence to generate model images of the clothing being sold. These generated model images are reflected on the product page, allowing users to visually confirm the product.

[1998] Step 9:

[1999] Purchase procedure. The user reviews the clothing items suggested on their device, selects the items they like, and proceeds with the purchase. Finally, purchase completion information for the selected items is sent to the server.

[2000] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[2001] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2002] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[2003] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2004] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[2005] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[2006] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[2007] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[2008] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[2009] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[2010] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[2011] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[2012] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[2013] 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.

[2014] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[2015] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[2016] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[2017] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[2018] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[2019] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[2020] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[2021] The following is further disclosed regarding the embodiments described above.

[2022] (Claim 1)

[2023] A means of receiving user input and inputting an image of clothing as text or an image,

[2024] A means for analyzing the user input, creating an appropriate image generation prompt, and sending it to the server,

[2025] A generation means for generating an image based on the prompt,

[2026] A means for searching for the most suitable clothing item from a database of clothing items based on the generated image,

[2027] A means for returning the proposed clothing items and generated images to the user,

[2028] A method for generating model images wearing clothes to be sold using AI,

[2029] A means for reflecting the generated model image on the product page,

[2030] A system including a means for the user to confirm and purchase the proposed clothing items.

[2031] (Claim 2)

[2032] The system according to claim 1, comprising means for receiving user input in both text and image form, and processing for analyzing the text and image to generate an appropriate prompt.

[2033] (Claim 3)

[2034] The system according to claim 1, wherein the image generation means includes means for extracting the characteristics of clothing items based on the generated image using visual recognition technology and suggesting the most suitable clothing items.

[2035] "Example 1"

[2036] (Claim 1)

[2037] A means of receiving user input and inputting an image of clothing as text or an image,

[2038] A means for analyzing the user input, creating an appropriate image generation prompt, and sending it to the server,

[2039] A generation means for generating an image based on the prompt,

[2040] A means for searching for the most suitable clothing item from a database of clothing items based on the generated image,

[2041] A means for returning the proposed clothing items and generated images to the user,

[2042] A method for generating model images wearing clothes to be sold using artificial intelligence,

[2043] A means for reflecting the generated model image on the product page,

[2044] A means by which the user can view and purchase the aforementioned proposed clothing items,

[2045] The terminal uses natural language processing technology and image analysis technology to analyze user input, and

[2046] A means of sending a prompt generated by the terminal to the server via an API request,

[2047] A method for the server to search a database based on the generated images and create a suggestion list,

[2048] A transmission means by which the server generates an API response and sends it back to the user's terminal,

[2049] A system that includes a means of displaying results to the user.

[2050] (Claim 2)

[2051] The system according to claim 1, comprising means for receiving user input in both text and image form, and processing for analyzing the text and image to generate an appropriate prompt.

[2052] (Claim 3)

[2053] The system according to claim 1, wherein the image generation means includes means for extracting the characteristics of clothing items based on the generated image using visual recognition technology and suggesting the most suitable clothing items.

[2054] "Application Example 1"

[2055] (Claim 1)

[2056] A means of receiving user input and inputting an image of clothing as text or an image,

[2057] A means for analyzing the user input, creating an appropriate image generation prompt, and sending it to the server,

[2058] A generation means for generating an image based on the prompt,

[2059] A means for searching for the most suitable clothing item from a database of clothing items based on the generated image,

[2060] A means for returning the proposed clothing items and generated images to the user,

[2061] A method for generating model images wearing clothes to be sold using AI,

[2062] A means for reflecting the generated model image on the product page,

[2063] A means by which the user can view and purchase the aforementioned proposed clothing items,

[2064] A means of generating specific prompt text based on the fashion style entered by the user and sending it to an image generation AI model,

[2065] A means for displaying a list of related clothing items based on the aforementioned model image,

[2066] One method is to click on the aforementioned clothing item to go to the details page and proceed with the purchase.

[2067] A system including means for collecting feedback after the aforementioned purchase.

[2068] (Claim 2)

[2069] The system according to claim 1, comprising means for receiving user input in both text and image form, and processing for analyzing the text and image to generate an appropriate prompt sentence.

[2070] (Claim 3)

[2071] The system according to claim 1, wherein the image generation means includes means for extracting the characteristics of clothing items based on the generated image using visual recognition technology and suggesting the most suitable clothing items.

[2072] "Example 2 of combining an emotion engine"

[2073] (Claim 1)

[2074] A means of receiving user input and inputting an image of clothing as text or an image,

[2075] A means for detecting the user's facial expressions, voice, and biometric information and analyzing their emotional state,

[2076] A means for analyzing the user input and emotional state, creating an appropriate image generation prompt, and sending it to the server,

[2077] A generation means for generating an image based on the prompt,

[2078] A means for searching for the most suitable clothing item from a database of clothing items based on the generated image,

[2079] A means of adjusting the proposed clothing items in consideration of the aforementioned emotional state,

[2080] A means for returning the proposed clothing items and generated images to the user,

[2081] A means by which the user can view and purchase the aforementioned proposed clothing items,

[2082] A means for generating a model image wearing the clothing to be sold based on the generated image,

[2083] A means for reflecting the generated model image on the product page,

[2084] A system that includes this.

[2085] (Claim 2)

[2086] The system according to claim 1, which accepts user input in both text and image formats, and processes the text, image, and emotional state to generate an appropriate prompt.

[2087] (Claim 3)

[2088] The system according to claim 1, wherein the image generation means includes means for extracting the characteristics of clothing items based on the generated image using visual recognition technology and suggesting the most suitable clothing items.

[2089] "Application example 2 when combining with an emotional engine"

[2090] (Claim 1)

[2091] A means of receiving user input and inputting an image of clothing as text or an image,

[2092] A means for analyzing the user input and the user's emotional state, creating an appropriate image generation prompt, and sending it to the server,

[2093] A generation means for generating an image based on the prompt,

[2094] A means for searching for the most suitable clothing item from a database of clothing items based on the generated image, and adjusting the suggested content while considering the user's emotional state,

[2095] A means for returning the proposed clothing items and generated images to the user,

[2096] A method for generating model images wearing clothes to be sold using artificial intelligence,

[2097] A means for reflecting the generated model image on the product page,

[2098] A system including a means for the user to confirm and purchase the proposed clothing items.

[2099] (Claim 2)

[2100] The system according to claim 1, comprising means for receiving user input in both text and image form, and processing for analyzing the text and image to generate an appropriate prompt.

[2101] (Claim 3)

[2102] The system according to claim 1, wherein the image generation means includes means for extracting the characteristics of clothing items based on the generated image using visual recognition technology and suggesting the most suitable clothing items. [Explanation of Symbols]

[2103] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of receiving user input and inputting an image of clothing as text or an image, A means for analyzing the user input, creating an appropriate image generation prompt, and sending it to the server, A generation means for generating an image based on the prompt, A means for searching for the most suitable clothing item from a database of clothing items based on the generated image, A means for returning the proposed clothing items and generated images to the user, A method for generating model images wearing clothes to be sold using AI, A means for reflecting the generated model image on the product page, A system including a means for the user to confirm and purchase the proposed clothing items.

2. The system according to claim 1, comprising means for receiving user input in both text and image form, and processing for analyzing the text and image to generate an appropriate prompt.

3. The system according to claim 1, wherein the image generation means includes means for extracting the characteristics of clothing items using visual recognition technology based on the generated image and suggesting the most suitable clothing items.

Images