system

Abstract

We provide the system. [Solution] A means by which the user enters a fashion style or the name of a celebrity, Means for sending the user's input data to the server, The server provides means for generating a coordinated image using an image generation model based on the input data, The server includes means for analyzing the generated coordinate image to identify each item, The server has means for searching for the corresponding item from the product database based on the identified item, The server provides means for transmitting the generated image and the searched item list to the user's terminal, A system in which the terminal includes means for displaying the generated image and item list to the user.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Conventional fashion style proposal systems rely on magazines and snapshots, making it difficult for users to easily visualize their specific preferences and the fashion styles of their favorite (such as models) famous people and obtain a shopping list based on that style. Therefore, there has been a problem that it is impossible to quickly and accurately propose a coordination or provide a purchase link according to the needs of users.

Means for Solving the Problems

[0005] The present invention provides a system that includes means for the user to input a fashion style or the name of a celebrity, means for transmitting the user's input data to a server, means for the server to generate a coordinated image using an image generation model based on the input data, means for analyzing the generated coordinated image to identify each item, means for searching for the corresponding item from a product database based on the identified item, means for transmitting the generated image and the searched item list to the user's terminal, and means for the terminal to display the generated image and item list to the user. With this system, the user can instantly visualize a specific fashion image, easily obtain purchase links based on the suggested style, and complete the coordinated outfit quickly and effectively.

[0006] A "user" is someone who uses the system to input fashion styles and celebrity outfits, and then receives the results.

[0007] "Input" refers to the act of a user specifying a fashion style or the name of a famous person to the system.

[0008] A "server" is a computing resource that receives user input data and performs processing such as generating coordinated images, identifying items, and searching for products.

[0009] An "image generation model" is a model that uses machine learning algorithms and other technologies to generate coordinated images based on a specified style.

[0010] A "coordinated image" is a visual representation of a generated fashion style, corresponding to user input.

[0011] "Analysis" is the process of identifying each item from the generated coordinated image.

[0012] An "item" refers to a fashion element, such as clothing or accessories, that is identified within a coordinated outfit image.

[0013] A "product database" is a database that stores product information to hold information about items and to suggest them to users.

[0014] "Searching" is the process of finding products that are similar to or match an item identified within a product database.

[0015] A "terminal" is a device (e.g., smartphone, computer, tablet) used by a user to input data or receive results.

[0016] "Display" refers to the act of a device visually providing the user with the generated coordinated image and the searched item list. [Brief explanation of the drawing]

[0017] [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]It 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] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Modes for Carrying Out the Invention

[0018] 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.

[0019] First, the language used in the following description will be explained.

[0020] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic device or a combination of a plurality of arithmetic devices. Also, the processor may be a single type of arithmetic device or a combination of a plurality of types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0021] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0022] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0023] 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).

[0024] 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."

[0025] [First Embodiment]

[0026] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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".

[0038] This invention is a system that generates specific outfit images based on the user's input of fashion styles and celebrity outfits, and then suggests product items based on those images.

[0039] 1. User input

[0040] When using this system, users are first required to enter a fashion style or the name of a celebrity. For example, specific requests such as "autumn casual outfit" or "celebrity style" are possible. This input is performed on the terminal's interface.

[0041] 2. Sending data

[0042] The terminal sends user input data to the server. HTTP requests are used for transmission, and the entered data is sent to a dedicated endpoint on the server.

[0043] 3. Generating the coordinated image

[0044] The server generates coordinated outfit images using an image generation model based on the user's input data. This image generation model employs machine learning algorithms to reproduce specific fashion styles based on user input, as well as typical styles of celebrities.

[0045] 4. Image analysis and item identification

[0046] The server analyzes the generated outfit images and identifies each fashion item (e.g., jacket, pants, shoes, etc.). Image recognition technology is used for this analysis.

[0047] 5. Search for items

[0048] The server searches its product database for items based on the identified item. This database contains a large amount of product information, such as from online marketplaces, and finds products that match or are similar to each item identified by its image.

[0049] 6. Submit search results

[0050] The server sends the generated outfit images and the searched item list to the user's device. This allows the user to receive visuals of the suggested fashion style and a specific product list based on that style.

[0051] 7. Displaying the results

[0052] The device displays the received generated images and item list to the user. Through this display, the user can see specific fashion styles they desire and can also use links to directly purchase the suggested products.

[0053] As a concrete example, when a user enters "autumn casual outfit," the server generates an outfit image using a generated image model based on the received data. This image includes items such as a casual jacket, sweatpants, and sneakers. The server analyzes these items and searches for related products in its database, listing them. The generated outfit image is then displayed on the terminal along with these products, allowing the user to directly purchase the suggested items.

[0054] The following describes the processing flow.

[0055] Step 1:

[0056] The user enters a fashion style or the name of a celebrity. For example, the user might enter "Autumn casual outfit."

[0057] Step 2:

[0058] The terminal sends the user's input data to the server. Specifically, it sends the input data to the server as an HTTP POST request.

[0059] Step 3:

[0060] The server receives user input data. The server analyzes the input data and prepares it to be passed to the image generation model.

[0061] Step 4:

[0062] The server generates coordinated images using an image generation model. The image generation model outputs images that reproduce a specific fashion style based on the input style.

[0063] Step 5:

[0064] The server analyzes the generated outfit image and identifies each fashion item. Specifically, it uses image recognition technology to detect items such as jackets, pants, and shoes within the image and extracts their information.

[0065] Step 6:

[0066] The server searches the product database for the corresponding item based on each identified item. The server sends a search query to the online marketplace's API and retrieves the relevant products.

[0067] Step 7:

[0068] The server combines the generated outfit images with the item list retrieved from the product database. The server then formats this information into a format suitable for sending to the user's terminal.

[0069] Step 8:

[0070] The server sends the generated image and item list to the user's device. Specifically, it returns this data as an HTTP response.

[0071] Step 9:

[0072] The device displays the generated image and item list received from the server to the user. The user can review the generated outfit image and suggested items and access purchase links for each item.

[0073] (Example 1)

[0074] 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."

[0075] Conventional fashion suggestion systems had problems such as making it difficult for users to visually imagine specific outfits, and failing to adequately suggest products based on those outfits. In particular, it was difficult to generate specific outfit images based on the fashion style desired by the user or the style of a celebrity, and to quickly and accurately suggest products related to those images.

[0076] 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.

[0077] In this invention, the server includes means for the user to input a fashion style or observations of a celebrity; means for transmitting the user's input data to a server facility; means for the server facility to generate a coordinated image using an image generation algorithm based on the input data; means for the server facility to analyze the generated coordinated image and identify each item; means for the server facility to search for the corresponding item from a product information database based on the identified item; means for the server facility to transmit the generated image and the searched item list to the user's terminal device; and means for the terminal device to display the generated image and item list to the user. As a result, the user can simply input their desired fashion style or celebrity coordinated outfit, generate a specific coordinated image based on it, analyze the image to identify each item, and quickly and accurately suggest related products.

[0078] A "user" refers to a person who uses this system to input observations about fashion styles or celebrities.

[0079] A "terminal device" refers to an electronic device used by a user to input information and receive display results. Examples include smartphones, personal computers, and tablets.

[0080] A "server facility" refers to a computer system that has the function of receiving data sent from users, generating and analyzing images, searching for corresponding product information, and sending it to the user's terminal device.

[0081] An "image generation algorithm" refers to a machine learning algorithm used to generate coordinated images based on user input data. Examples include Generative Adversarial Networks (GANs).

[0082] "Coordinate images" refer to images that visually represent generated fashion styles or the styles of celebrities.

[0083] "Image recognition technology" refers to techniques for analyzing images and identifying each fashion item contained within them. Examples include YOLO and ResNet.

[0084] A "product information database" refers to a database that provides information about searched items. It is related to online sales websites.

[0085] An "item list" refers to a list of product information searched based on the generated outfit images, organized in a list format.

[0086] This invention is a system that generates specific outfit images and suggests related product items based on the user's input of fashion styles and celebrity styles. This system primarily operates with a server, terminal devices, and users.

[0087] User input

[0088] Users access the system interface using a terminal device (e.g., smartphone, PC, tablet) and input fashion styles or celebrity styles. For example, they can enter specific prompts such as "autumn casual outfit" or "a certain celebrity's style."

[0089] Sending data

[0090] The terminal device transmits the data entered by the user to the server facility. This transmission uses an HTTP POST request, and the input data is sent to the server facility in JSON format.

[0091] Coordinate image generation

[0092] The server facility generates coordinated images based on the received data using a generative AI model (e.g., StyleGAN). This generative AI model utilizes machine learning algorithms to generate highly relevant images based on the prompt text received from the user.

[0093] Image analysis and item identification

[0094] The generated outfit images are analyzed by a server facility to identify each fashion item (e.g., jacket, pants, shoes, etc.). Image recognition technology (e.g., YOLO or ResNet) is used for this analysis.

[0095] Item Search

[0096] The server facility searches for the corresponding product in the product information database based on the identified item. This database includes product information obtained from online sales sites and other sources.

[0097] Submit search results

[0098] The server facility sends the generated coordinated images and the searched product list to the terminal device. The transmitted data is in JSON format, and the terminal device receives and processes it.

[0099] Displaying Results

[0100] The terminal device displays the received generated images and item list to the user. Based on the displayed content, the user can visualize their desired fashion style and directly purchase the suggested products.

[0101] Specific example

[0102] For example, if a user enters "casual autumn outfit," the server facility uses this data to generate an outfit image using an AI model. The generated image will include items such as a casual jacket, sweatpants, and sneakers. The server facility analyzes these items and searches for related products in its product information database, listing them. Subsequently, the item list is displayed on the terminal device along with the generated outfit image, allowing the user to directly purchase the suggested items.

[0103] In this way, the present invention provides a system that quickly and accurately suggests the fashion style desired by the user and facilitates the purchase of related products based on that style.

[0104] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0105] Step 1:

[0106] Users input their observations of fashion styles and celebrities using a terminal device. For example, they can enter a prompt such as "Autumn casual outfit." Input is entered directly into the text field, and clicking the "Submit" button proceeds to the next step.

[0107] Input: Observations of fashion styles and celebrities (text format)

[0108] Output: Data entered by the user

[0109] Step 2:

[0110] The terminal device sends the data entered by the user to the server facility using an HTTP POST request. The input data is converted to JSON format and sent to the specified API endpoint.

[0111] Specific operation: The terminal device sends the following JSON data to the server facility.

[0112] json

[0113] {

[0114] "prompt": "Autumn casual outfit"

[0115] }

[0116] Input: Data entered by the user (prompt text)

[0117] Output: JSON data sent to the server facility

[0118] Step 3:

[0119] The server facility passes the received data to the generating AI model, which then generates coordinated images. The generating AI model uses a machine learning algorithm (e.g., StyleGAN) to generate images based on the input prompt text.

[0120] Specific operation: The server facility calls the generated AI model and generates images based on "autumn casual outfits".

[0121] Input: JSON data received by the server facility

[0122] Output: Generated coordinated image

[0123] Step 4:

[0124] The server facility passes the generated coordinated image to image recognition technology to identify each item. Specifically, it uses image recognition algorithms (e.g., YOLO or ResNet) to detect items such as jackets, pants, and shoes within the image.

[0125] Specific operation: The server facility applies image recognition technology and labels each fashion item from the generated images.

[0126] Input: Generated coordinate image

[0127] Output: A list of identified items (e.g., "jacket", "pants", "shoes")

[0128] Step 5:

[0129] The server facility searches the product information database for the corresponding product based on the identified item. The search query includes the category and characteristics of each item (e.g., color, material, etc.).

[0130] Specific operation: The server facility generates a database search query and retrieves a list of matching products.

[0131] Input: List of identified items

[0132] Output: List of relevant products

[0133] Step 6:

[0134] The server facility reconstructs the generated coordinated images and searched product lists into JSON format and sends them to the user's terminal device. This data includes the URLs of the generated images and the product lists.

[0135] Specific operation: The server facility sends the following JSON data to the terminal device.

[0136] json

[0137] {

[0138] "image_url": "https: / / cdn.example.com / generated-image.jpg",

[0139] "items": [

[0140] {"name": "Casual Jacket", "link": "https: / / shop.example.com / item123"},

[0141] {"name": "Sweatpants", "link": "https: / / shop.example.com / item456"},

[0142] {"name": "Sneakers", "link": "https: / / shop.example.com / item789"}

[0143] ]

[0144] }

[0145] Input: Generated outfit images and searched product list

[0146] Output: JSON data sent to the user's terminal device.

[0147] Step 7:

[0148] The terminal device displays the received generated images and product list to the user. This allows the user to visualize their desired fashion style and access links to directly purchase suggested products.

[0149] Specific operation: The terminal device displays images and a product list on the user interface.

[0150] Input: JSON data received from the server facility

[0151] Output: Generated image and product list displayed on the terminal device.

[0152] Through these steps, users can view specific outfit images based on their entered fashion style and receive quick and accurate suggestions for related products.

[0153] (Application Example 1)

[0154] 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."

[0155] Conventional fashion coordination systems have problems such as difficulty in easily recreating the style preferred by the user or the fashion of a specific celebrity, and the need to manually search for each item, which is time-consuming for the user. In addition, the methods for displaying the generated coordination image and related items are limited, and there is insufficient support for users to make quick purchase decisions. The present invention aims to solve these problems and provide a system that automatically generates coordination images using a generation AI model based on the fashion style entered by the user or the style of a celebrity, and further allows the user to easily purchase the suggested items.

[0156] 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.

[0157] In this invention, the server includes means for the user to input a fashion style or the name of a celebrity, means for transmitting the user's input data to the server, and means for generating a coordinated image using a generative AI model. This makes it possible to search for the corresponding items from a product database based on the generated coordinated image and identified items, transmit them to the user's terminal, and provide a link to directly purchase the suggested items.

[0158] A "user" is someone who uses the system to input fashion styles and celebrity names, and then receives suggested outfits and products.

[0159] "Fashion style" refers to a combination of clothing and accessories that are suited to a specific theme, season, or occasion.

[0160] "Celebrity names" refer to the names of specific famous people or entertainers, and are information used to help the system recognize the typical clothing and style of that person.

[0161] "Input data" refers to information that users enter into the system, such as fashion styles and names of famous people.

[0162] A "server" refers to a computer system that receives user input data, generates coordinated images using a generation AI model, and is also responsible for analyzing the generated images and linking them with a product database.

[0163] A "generative AI model" is a model that uses machine learning algorithms to reproduce specific fashion styles or celebrity styles based on user input.

[0164] "Coordinate images" are images that visually represent fashion styles or celebrity styles created using generative AI models.

[0165] "Analysis" refers to the process of analyzing the generated outfit images and identifying each fashion item within those images.

[0166] "Items" refer to individual clothing items, accessories, and other products identified within a coordinated outfit image.

[0167] A "product database" refers to a database that holds a large amount of product information, such as that found on online marketplaces.

[0168] "Searching" refers to the process of finding products that match or are similar to a specific item within a product database.

[0169] The "item list" refers to the collection of all items that the server searches for based on the generated outfit image and provides to the user.

[0170] "Terminal" refers to a device such as a smartphone or computer used by the user, and is used to display the generated outfit images and item lists.

[0171] A "link" is a hyperlink that a user can click to directly purchase a suggested item.

[0172] This invention is a system that generates coordinated outfit images using a generative AI model based on fashion styles entered by the user and the styles of celebrities, and suggests related products. This system mainly consists of a server, a user terminal, and a program.

[0173] Overall system configuration

[0174] The system includes means for the user to input a fashion style or the name of a celebrity, means for sending the user's input data to a server, means for generating a coordinated image using a generative AI model, means for analyzing the generated coordinated image to identify each item, means for searching for the corresponding item from a product database based on the identified item, means for sending the generated image and the list of searched items to the user's terminal, and means for displaying the generated image and the list of items to the user and providing a link for the user to directly purchase the suggested items.

[0175] Program Configuration

[0176] The server uses the Flask web framework and PIL (Python Imaging Library). The main data processing in this system is as follows:

[0177] 1. User Input: Users use their devices to input fashion styles or the names of specific celebrities. For example, they can specify things like "autumn casual outfits" or "celebrity styles."

[0178] 2. Data transmission: User input data is sent from the terminal to the server as an HTTP request.

[0179] 3. Coordinate Image Generation: Based on the user's input data received, the server generates coordinate images using a generative AI model. This image generation model employs machine learning algorithms to reproduce specific fashion styles based on user input, as well as typical styles of celebrities.

[0180] 4. Image Analysis and Item Identification: The server analyzes the generated outfit images and identifies each fashion item (e.g., jacket, pants, shoes). Image recognition technology is used for this analysis.

[0181] 5. Item Search: The server searches for the corresponding item from the product database (e.g., online marketplace) based on the specified item.

[0182] 6. Sending search results: The server sends the generated outfit images and the list of searched items to the user's device.

[0183] 7. Display of Results: The user's device displays the received generated images and item list to the user. Through this display, the user can see the specific fashion style they desire and also use links to directly purchase the suggested products.

[0184] Specific example

[0185] When a user enters "autumn casual outfit," the server uses an AI model to generate an outfit image based on the received data. This image includes items such as a casual jacket, sweatpants, and sneakers. The server analyzes these items and searches its database for related products, listing them. The generated outfit image is then displayed on the user's device along with these products, allowing the user to directly purchase the suggested items.

[0186] Examples of prompts to input into a generative AI model are as follows:

[0187] "Create a casual autumn outfit. A style including a gray jacket, sweatpants, and white sneakers."

[0188] In this way, the present invention allows users to easily and quickly find their desired fashion style and purchase related products online.

[0189] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0190] Step 1:

[0191] The user uses their device to input fashion styles or celebrity names on the application interface. This input is in text format. For example, let's say the user inputs "Autumn casual outfit." The device then sends this input data to the next step.

[0192] Step 2:

[0193] The terminal sends the entered fashion style and celebrity name to the server as an HTTP request. The server parses the received HTTP request and extracts the user's input data (fashion style and celebrity name in text format). This data is used in the next step.

[0194] Step 3:

[0195] The server creates a prompt message for the generating AI model based on the received input data. For example, if the input data is "autumn casual outfit," the server will generate the prompt message, "Generate an autumn casual outfit. A style including a gray jacket, sweatpants, and white sneakers." This prompt message is then input into the generating AI model.

[0196] Step 4:

[0197] The server uses a generative AI model to generate a coordinated image based on the prompt text. The generative AI model uses a machine learning algorithm to generate the image according to the content described in the prompt text. The generated coordinated image is obtained as output. This image will proceed to the next step.

[0198] Step 5:

[0199] The server analyzes the generated outfit image and uses image recognition technology to identify each fashion item (e.g., jacket, pants, shoes). The analysis yields a list of identified items. For example, items such as "gray jacket, sweatpants, white sneakers" might be identified.

[0200] Step 6:

[0201] The server searches its product database for items based on the identified item. This database contains a large amount of product information, including online marketplaces, and searches for products that match or are similar to each identified item. The search results provide a list of products. For example, a list is generated that includes links such as "Gray Jacket - URL", "Sweatpants - URL", and "White Sneakers - URL".

[0202] Step 7:

[0203] The server sends the generated outfit image and the searched item list to the user's device. An HTTP response is used for this transmission. The device receives this response and uses it in the next step.

[0204] Step 8:

[0205] The device displays the received generated outfit images and item list to the user. The user can review the displayed images and access purchase links directly through the list of suggested items. This allows the user to easily visualize their desired fashion style and utilize links to purchase related products.

[0206] 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.

[0207] This invention is a system that generates specific outfit images based on the user's input of fashion styles and celebrity outfits, and then suggests product items based on those images. Furthermore, this invention combines an emotion engine to provide personalized suggestions based on the user's emotions.

[0208] User input and emotion recognition

[0209] When a user uses this system, they are first required to enter a fashion style or the name of a celebrity. For example, the user might enter "autumn casual outfit" or "celebrity style." This input is done through the terminal's interface.

[0210] Simultaneously, the emotion engine analyzes the user's facial recognition and input data to recognize the user's emotions. Based on the information obtained from the user's facial expressions and input content, the emotion engine identifies an emotional state such as positive, negative, or neutral.

[0211] Sending data

[0212] The device sends user input data and sentiment data to the server. HTTP requests are used for transmission, and the input data is sent to a dedicated endpoint on the server.

[0213] Coordinate image generation

[0214] The server generates coordinated outfit images using an image generation model based on the user's input data and emotional data. This image generation model uses machine learning algorithms to reproduce specific fashion styles based on user input and typical styles of celebrities. It also adjusts the parameters of the generated coordinated outfit images based on the user's emotional data. For example, if the user is in a positive emotional state, a fashion style with bright colors may be suggested.

[0215] Image analysis and item identification

[0216] The server analyzes the generated outfit images and identifies each fashion item (e.g., jacket, pants, shoes). This analysis uses image recognition technology to automatically detect items within the image and organize their information.

[0217] Item Search

[0218] The server searches its product database for items based on the identified item. This database contains a large amount of product information from online marketplaces and finds products that match or are similar to each item identified by its image.

[0219] Submit search results

[0220] The server combines the generated outfit images with the item list retrieved from the product database. The server then formats this information into a format suitable for sending to the user's terminal and returns the appropriate information to the user.

[0221] Displaying Results

[0222] The terminal displays the generated image and item list received from the server to the user. The user can visually review the generated outfit image and suggested items, and will have access to links to purchase each item directly.

[0223] Specific example

[0224] If a user enters "casual autumn outfit" and the emotion engine recognizes a positive emotional state, the server generates an outfit image using a generated image model based on the received data. This image includes a casual jacket, sweatpants, and sneakers. Furthermore, the server analyzes the image to search for and list related products. The generated outfit image is then displayed on the device along with suggested items, and the user can purchase each item directly. If the user is in a negative emotional state, an outfit with more subdued colors may be suggested.

[0225] The following describes the processing flow.

[0226] Step 1:

[0227] The user enters a fashion style or the name of a celebrity. For example, the user might enter "Autumn casual outfit."

[0228] Step 2:

[0229] The device sends user input data to the emotion engine. The emotion engine analyzes the user's input and facial expressions.

[0230] Step 3:

[0231] The emotion engine recognizes the user's emotions and identifies them as positive, negative, neutral, etc. For example, if the user is smiling while typing, it recognizes this as a positive emotion.

[0232] Step 4:

[0233] The device sends user input data and sentiment data to the server. HTTP requests are used for transmission.

[0234] Step 5:

[0235] The server receives user input data and sentiment data. The server analyzes the input data and prepares it to be passed to the image generation model.

[0236] Step 6:

[0237] The server generates coordinated outfit images using an image generation model. The image generation model uses machine learning algorithms to recreate fashion styles based on user input and emotions.

[0238] Step 7:

[0239] The server analyzes the generated outfit image and identifies each fashion item. Specifically, it uses image recognition technology to detect items such as jackets, pants, and shoes within the image.

[0240] Step 8:

[0241] The server searches the product database for items based on the identified item. For example, it might use an online marketplace API to retrieve similar products.

[0242] Step 9:

[0243] The server combines the generated outfit images with the item list retrieved from the product database. The server then formats this information for transmission to the user's terminal.

[0244] Step 10:

[0245] The server sends the generated image and item list to the user's device. Specifically, it returns this data as an HTTP response.

[0246] Step 11:

[0247] The terminal displays the generated image and item list received from the server to the user. The user can review the generated outfit image and suggested items and access purchase links for each item.

[0248] As a concrete example, if a user enters "autumn casual outfit" and shows a positive emotion with a smile, the server will generate an image including a brightly colored jacket, sweatpants, and sneakers. This image is then analyzed to retrieve relevant products from the product database and suggest them to the user. The user can then review and purchase these suggested items.

[0249] (Example 2)

[0250] 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".

[0251] Current fashion coordination systems offer only simple item suggestions without considering the user's emotions. Therefore, it is difficult to suggest outfits that suit the user's feelings or mood on any given day. Furthermore, the need for manual item selection and searching limits the user experience.

[0252] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for transmitting user input data and emotion data to the server, means for the server to generate a coordinated image using an image generation model based on the input data and emotion data, and means for the server to analyze the generated coordinated image and identify each item. This makes it possible to suggest personalized fashion coordinates according to the user's emotions.

[0253] A "user" is the entity that uses the system to input fashion styles and celebrity names, and generates coordinated outfit images.

[0254] "Input data" refers to information that users enter into the system, such as fashion styles and names of famous people.

[0255] "Emotional data" refers to information about a user's emotional state, identified by analyzing their facial expressions and text input.

[0256] A "server" is a computer system that processes input data and sentiment data received from users, and performs tasks such as generating and analyzing coordinated images and searching for items from a product database.

[0257] An "image generation model" is a technology that uses machine learning algorithms to generate coordinated images based on input data and sentiment data.

[0258] A "machine learning algorithm" is a technology that uses large amounts of data to learn and perform pattern recognition and data generation.

[0259] A "coordinate image" is an image generated by a generative AI model that visually represents a specific fashion style.

[0260] "Image recognition technology" is a technology that analyzes image data to identify specific objects or features.

[0261] A "product database" is a data storage system that contains a large amount of product information related to fashion items.

[0262] An "online marketplace" is a platform where multiple sellers and buyers can buy and sell goods over the internet.

[0263] The "item list" is a list of product items selected based on the analysis results of the coordinated outfit images.

[0264] A "terminal" is a device used by a user to interact with a system, and includes, for example, personal computers and smartphones.

[0265] This invention is a system that generates specific outfit images based on the user's input of fashion styles and celebrity outfits, and then suggests product items based on those images. Furthermore, this invention incorporates an emotion engine to provide personalized suggestions based on the user's emotions.

[0266] User input and emotion recognition

[0267] The user inputs fashion styles or celebrity names using the device's interface. For example, they might enter prompts such as "autumn casual outfits" or "celebrity styles." Simultaneously, an emotion engine is activated, analyzing the user's facial expressions and entered text to identify their emotional state, such as positive, negative, or neutral. Specifically, it uses the device's camera for facial recognition to read emotions.

[0268] Sending data

[0269] The device sends user input data and sentiment data to the server via HTTP requests. The input data and sentiment data are combined in JSON format and sent to a dedicated endpoint on the server.

[0270] Coordinate image generation

[0271] The server uses the received user input data and sentiment data to generate coordinated outfit images using an image generation model (e.g., GAN: Generative Adversarial Network). If the user has a positive sentiment, a fashion style with bright colors will be suggested. The generated images visually represent specific fashion items and are customized according to the user's needs.

[0272] Image analysis and item identification

[0273] The server analyzes the generated outfit images using image recognition technology (e.g., CNN: Convolutional Neural Networks) to automatically identify each fashion item (jacket, pants, shoes, etc.). The identified items are then organized as data for the next search step.

[0274] Item Search

[0275] The server searches its product database for items based on the identified fashion item. This product database utilizes the large data storage of the online marketplace to find products that match or are similar to the item identified by the image. The search results are listed for the user to see.

[0276] Submit search results

[0277] The server integrates the generated outfit images and the item list retrieved from the product database, and formats them into an appropriate format for transmission to the user's device. This information is compiled in JSON format and sent to the user's device.

[0278] Displaying Results

[0279] The terminal displays generated images and item lists received from the server to the user. The user can visually review these and click on links to purchase each item directly. For example, in response to a suggestion for "Autumn Casual Outfit," casual jackets, sweatpants, sneakers, and other items will be displayed.

[0280] Specific example

[0281] When a user enters "autumn casual outfit" and the emotion engine recognizes a positive emotional state, the server generates an outfit image based on this. The generated image includes a casual jacket, light-colored sweatpants, and white sneakers. The server searches the product database for these items and identifies the corresponding products. The generated outfit image and recommended product list are then sent to the terminal, where the user can review and purchase them. An example of a prompt message is, "Please enter an autumn casual outfit, generate an outfit image based on positive emotions, and suggest related products."

[0282] The flow of the specific process in Example 2 will be described with reference to FIG. 13.

[0283] Step 1: User Input

[0284] The user uses the terminal interface to input a fashion style or the name of a celebrity. For example, the user inputs a prompt sentence such as "Autumn casual coordination". As input data, the content entered by the user in the text field of the terminal is used. As a result, the user's coordination preference is obtained as specific text data.

[0285] Input: Text data input by the user to the terminal (e.g., "Autumn casual coordination")

[0286] Output: The user's input is obtained in the form of text data

[0287] Step 2: Emotion Recognition

[0288] The terminal captures the user's face using the camera mounted on the terminal when the user inputs, and analyzes it with an emotion engine. As an analysis result, emotion data such as positive, negative, and neutral is generated.

[0289] Input: User's face image, input text

[0290] Output: Emotion data (e.g., positive)

[0291] Step 3: Data Transmission

[0292] The terminal combines the user's input data and emotion data and sends them to the server through an HTTP request. This data is sent to the dedicated endpoint of the server in JSON format.

[0293] Input: User's input data, emotion data

[0294] Output: Data in JSON format, sent to the server.

[0295] Step 4: Generate the coordinated image

[0296] The server uses an image generation model (e.g., GAN) to generate specific outfit images based on the user's input data and sentiment data. The image parameters are adjusted according to the sentiment data. For example, if the sentiment data is positive, a fashion item with bright colors will be generated.

[0297] Input: User input data, sentiment data

[0298] Output: Coordinated image

[0299] Step 5: Image analysis and item identification

[0300] The server analyzes the generated outfit images and identifies each fashion item (e.g., jacket, pants, shoes). Using image recognition technology (e.g., CNN), it identifies items within the image and extracts information about each individual item.

[0301] Input: Coordinated image

[0302] Output: Identified item information

[0303] Step 6: Search for items

[0304] The server searches the product database for the corresponding item based on the identified item information. Specifically, it issues a query to the online marketplace database to find the corresponding product.

[0305] Input: Identified item information

[0306] Output: Product List

[0307] Step 7: Submit search results

[0308] The server combines the generated coordinate image and the product list, formats them into an appropriate format (JSON format) for transmission to the user's terminal. The generated data is transmitted to the user's terminal as an HTTP response.

[0309] Input: Coordinate image, product list

[0310] Output: Data to be transmitted to the user's terminal

[0311] Step 8: Display of results

[0312] The terminal displays the generated image and the item list received from the server to the user. The user can click on the provided link to purchase each item.

[0313] Input: Data received from the server

[0314] Output: Coordinate image and item list displayed to the user

[0315] As a specific example of operation, when the user inputs "Autumn casual coordination" and the emotion engine recognizes a positive emotional state, the server generates a coordinate image based on this, searches for an item list, and transmits and displays the generated information to the terminal. An example of a prompt sentence is "Input autumn casual coordination, generate a coordinate image based on positive emotions, and propose related products."

[0316] (Application Example 2)

[0317] Next, Application Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart device 14 is referred to as the "terminal".

[0318] Conventional fashion style suggestion systems only propose styles based on user input information, and do not provide personalized suggestions that take into account the user's emotional state. Furthermore, the lack of functionality to virtually try on and purchase suggested coordinated items prevented improvements in user satisfaction and the purchasing experience.

[0319] In Application Example 2, the identification processing by the identification processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for the user to input a fashion style or the name of a celebrity; means for transmitting the user's input data to the server; means for the server to generate a coordinated image using an image generation model based on the input data; means for the server to analyze the generated coordinated image and identify each item; means for the server to search for the corresponding item from a product database based on the identified item; means for the server to transmit the generated image and the searched item list to the user's terminal; means for the terminal to display the generated image and item list to the user; means for combining an emotion engine to recognize the user's emotional state and adjusting the content of the generated image and item suggestions based on the recognized emotional state; and means for displaying the generated coordinated image and suggested items in a virtual store, enabling the user to virtually try on and directly purchase the suggested items. This enables personalized fashion suggestions according to the user's emotional state, and further enables trying on and purchasing in a virtual space.

[0320] A "user" refers to an individual who uses this system to input their fashion style and the names of celebrities, and receives outfit suggestions.

[0321] "Fashion style" refers to the overall concept of coordination based on a specific theme or aesthetic sense, including clothing, accessories, and hairstyles.

[0322] A "celebrity" refers to a person who is well-known and whose style is widely recognized.

[0323] "Input data" refers to information about fashion styles and celebrity names entered by the user.

[0324] A "server" refers to a central processing unit that receives input data from users and performs tasks such as generating coordinated images and searching for product items.

[0325] An "image generation model" refers to an algorithm or software that uses machine learning algorithms to generate specific coordinated images based on user input.

[0326] A "coordinate image" refers to an image that shows a visual example of fashion generated based on the user's input data.

[0327] An "emotion engine" refers to software or hardware that recognizes a user's emotional state from their facial expressions and input, and reflects that in the system's operation.

[0328] A "product database" refers to a collection of data related to fashion items stored within an online marketplace.

[0329] A "virtual store" refers to a virtual shopping space that users can access on the internet.

[0330] An "item list" refers to a list of items retrieved from the product database that correspond to the fashion items identified within the generated outfit image.

[0331] "Virtual try-on" refers to a feature that allows users to virtually try on fashion items suggested within a virtual store and check how they look.

[0332] Explanation of program generation and processing

[0333] This invention implements a system in which a user inputs a fashion style or the name of a celebrity, and a server generates coordinated images based on that input data and suggests appropriate items.

[0334] Hardware and software configuration

[0335] Hardware: Smartphone or PC, server, camera for acquiring user facial images.

[0336] Software: Python, face_recognition library, TENSORFLOW®, Requests, Pillow

[0337] 1. User Input and Sentiment Recognition

[0338] The user uses their smartphone or computer to input a fashion style (e.g., "Spring casual outfit") or the name of a celebrity. Next, they provide a facial image using their smartphone's camera or an image file on their device. The emotion engine uses the face_recognition library and an emotion recognition model (built using TensorFlow) to identify emotions from the user's facial image.

[0339] 2. Server-side processing

[0340] The server receives user input data (fashion style or celebrity name) and sentiment data. The server then uses machine learning algorithms to generate outfit images. Furthermore, it analyzes the generated outfit images to identify specific fashion items. Based on the identified items, it searches for the corresponding items in its product database (related to the online marketplace).

[0341] 3. Sending and displaying results to the user

[0342] The server sends the generated outfit image and the searched item list to the user's device. The user's device receives this information and displays the generated image and item list. Within the virtual store, the user can visually confirm the generated outfit image and suggested items, virtually try on the suggested items, and purchase them directly.

[0343] Specific examples of usage

[0344] For example, if a user enters "spring casual outfit" and the emotion engine recognizes a positive emotional state, the server uses a machine learning algorithm to generate an outfit image based on the received data. This image would include a casual jacket, shirt, and pants in bright colors. Furthermore, the server analyzes the image and lists the corresponding items from the online marketplace's product database. The generated outfit image is then displayed on the terminal along with suggested items, and the user can purchase each item directly.

[0345] Example of a prompt

[0346] 1. "Please suggest a casual spring outfit. My current emotional state is positive."

[0347] 2. "Please enter the style of a famous person (e.g., a famous singer). Your current emotional state is neutral."

[0348] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0349] Step 1:

[0350] The user enters a fashion style or the name of a celebrity. Specifically, the user uses a smartphone or computer to enter keywords such as "spring casual outfit" or "famous singer" into the application's input form. The input data is saved on the device as string data.

[0351] Step 2:

[0352] The user provides a facial image. Specifically, the user either takes a picture of their face with their smartphone camera or uploads a facial image file stored on their device. The image data is saved in JPEG or PNG format and imported as input data for the application.

[0353] Step 3:

[0354] The emotion engine analyzes the user's facial image and recognizes their emotional state. Specifically, it uses the face_recognition library on the device to determine the position of the face, and then uses TensorFlow to estimate the emotional state using an emotion recognition model. The input is facial image data, and the output is the emotional state (positive, negative, neutral, etc.). For example, if the model detects a smile, it is recognized as a positive emotional state.

[0355] Step 4:

[0356] The device sends user input data and emotional data to the server. Specifically, it sends the entered fashion style, celebrity names, and recognized emotional states to a dedicated endpoint on the server via an HTTP request. The transmitted data is in JSON format and is received by the server.

[0357] Step 5:

[0358] The server generates coordinated outfit images based on the input data it receives. Specifically, it uses a machine learning algorithm (generative AI model) running on the server to generate fashion coordinated outfit images based on the user's input data and sentiment data. The input is user data and sentiment data, and the output is the generated coordinated outfit image.

[0359] Step 6:

[0360] The server analyzes the generated outfit image to identify each item. Specifically, it uses image recognition technology to analyze the generated image and identify each fashion item (jacket, shirt, pants, etc.). The input is the latest generated outfit image, and the output is item information. For example, it automatically identifies shirts, pants, shoes, etc., in an image.

[0361] Step 7:

[0362] The server searches the product database for items based on the identified item. Specifically, it queries the product database (online marketplace) to retrieve product information (name, price, purchase link, etc.) that matches the identified item. The input is the information of the identified item, and the output is a list of matching product information.

[0363] Step 8:

[0364] The server sends the generated image and the searched item list to the user's device. Specifically, it sends a list of product information matching the generated outfit image to the device as an HTTP response in JSON format. The transmitted data includes the URL of the generated image and the item list.

[0365] Step 9:

[0366] The device displays the generated image and item list to the user. Specifically, it displays the coordinated outfit image generated within the application, allowing for visual confirmation along with the suggested item list. Users can virtually try on the suggested items using the virtual try-on function and purchase them directly by clicking the displayed purchase link. The input is data received from the server, and the output is the displayed coordinated outfit image and item list.

[0367] 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.

[0368] 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.

[0369] 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.

[0370] [Second Embodiment]

[0371] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0372] 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.

[0373] 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).

[0374] 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.

[0375] 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.

[0376] 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).

[0377] 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.

[0378] 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.

[0379] 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.

[0380] 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.

[0381] 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.

[0382] 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".

[0383] This invention is a system that generates specific outfit images based on the user's input of fashion styles and celebrity outfits, and then suggests product items based on those images.

[0384] 1. User input

[0385] When using this system, users are first required to enter a fashion style or the name of a celebrity. For example, specific requests such as "autumn casual outfit" or "celebrity style" are possible. This input is performed on the terminal's interface.

[0386] 2. Sending data

[0387] The terminal sends user input data to the server. HTTP requests are used for transmission, and the entered data is sent to a dedicated endpoint on the server.

[0388] 3. Generating the coordinated image

[0389] The server generates coordinated outfit images using an image generation model based on the user's input data. This image generation model employs machine learning algorithms to reproduce specific fashion styles based on user input, as well as typical styles of celebrities.

[0390] 4. Image analysis and item identification

[0391] The server analyzes the generated outfit images and identifies each fashion item (e.g., jacket, pants, shoes, etc.). Image recognition technology is used for this analysis.

[0392] 5. Search for items

[0393] The server searches its product database for items based on the identified item. This database contains a large amount of product information, such as from online marketplaces, and finds products that match or are similar to each item identified by its image.

[0394] 6. Submit search results

[0395] The server sends the generated outfit images and the searched item list to the user's device. This allows the user to receive visuals of the suggested fashion style and a specific product list based on that style.

[0396] 7. Displaying the results

[0397] The device displays the received generated images and item list to the user. Through this display, the user can see specific fashion styles they desire and can also use links to directly purchase the suggested products.

[0398] As a concrete example, when a user enters "autumn casual outfit," the server generates an outfit image using a generated image model based on the received data. This image includes items such as a casual jacket, sweatpants, and sneakers. The server analyzes these items and searches for related products in its database, listing them. The generated outfit image is then displayed on the terminal along with these products, allowing the user to directly purchase the suggested items.

[0399] The following describes the processing flow.

[0400] Step 1:

[0401] The user enters a fashion style or the name of a celebrity. For example, the user might enter "Autumn casual outfit."

[0402] Step 2:

[0403] The terminal sends the user's input data to the server. Specifically, it sends the input data to the server as an HTTP POST request.

[0404] Step 3:

[0405] The server receives user input data. The server analyzes the input data and prepares it to be passed to the image generation model.

[0406] Step 4:

[0407] The server generates coordinated images using an image generation model. The image generation model outputs images that reproduce a specific fashion style based on the input style.

[0408] Step 5:

[0409] The server analyzes the generated outfit image and identifies each fashion item. Specifically, it uses image recognition technology to detect items such as jackets, pants, and shoes within the image and extracts their information.

[0410] Step 6:

[0411] The server searches the product database for the corresponding item based on each identified item. The server sends a search query to the online marketplace's API and retrieves the relevant products.

[0412] Step 7:

[0413] The server combines the generated outfit images with the item list retrieved from the product database. The server then formats this information into a format suitable for sending to the user's terminal.

[0414] Step 8:

[0415] The server sends the generated image and item list to the user's device. Specifically, it returns this data as an HTTP response.

[0416] Step 9:

[0417] The device displays the generated image and item list received from the server to the user. The user can review the generated outfit image and suggested items and access purchase links for each item.

[0418] (Example 1)

[0419] 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".

[0420] Conventional fashion suggestion systems had problems such as making it difficult for users to visually imagine specific outfits, and failing to adequately suggest products based on those outfits. In particular, it was difficult to generate specific outfit images based on the fashion style desired by the user or the style of a celebrity, and to quickly and accurately suggest products related to those images.

[0421] 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.

[0422] In this invention, the server includes means for the user to input a fashion style or observations of a celebrity; means for transmitting the user's input data to a server facility; means for the server facility to generate a coordinated image using an image generation algorithm based on the input data; means for the server facility to analyze the generated coordinated image and identify each item; means for the server facility to search for the corresponding item from a product information database based on the identified item; means for the server facility to transmit the generated image and the searched item list to the user's terminal device; and means for the terminal device to display the generated image and item list to the user. As a result, the user can simply input their desired fashion style or celebrity coordinated outfit, generate a specific coordinated image based on it, analyze the image to identify each item, and quickly and accurately suggest related products.

[0423] A "user" refers to a person who uses this system to input observations about fashion styles or celebrities.

[0424] A "terminal device" refers to an electronic device used by a user to input information and receive display results. Examples include smartphones, personal computers, and tablets.

[0425] A "server facility" refers to a computer system that has the function of receiving data sent from users, generating and analyzing images, searching for corresponding product information, and sending it to the user's terminal device.

[0426] An "image generation algorithm" refers to a machine learning algorithm used to generate coordinated images based on user input data. Examples include Generative Adversarial Networks (GANs).

[0427] "Coordinate images" refer to images that visually represent generated fashion styles or the styles of celebrities.

[0428] "Image recognition technology" refers to techniques for analyzing images and identifying each fashion item contained within them. Examples include YOLO and ResNet.

[0429] A "product information database" refers to a database that provides information about searched items. It is related to online sales websites.

[0430] An "item list" refers to a list of product information searched based on the generated outfit images, organized in a list format.

[0431] This invention is a system that generates specific outfit images and suggests related product items based on the user's input of fashion styles and celebrity styles. This system primarily operates with a server, terminal devices, and users.

[0432] User input

[0433] Users access the system interface using a terminal device (e.g., smartphone, PC, tablet) and input fashion styles or celebrity styles. For example, they can enter specific prompts such as "autumn casual outfit" or "a certain celebrity's style."

[0434] Sending data

[0435] The terminal device transmits the data entered by the user to the server facility. This transmission uses an HTTP POST request, and the input data is sent to the server facility in JSON format.

[0436] Coordinate image generation

[0437] The server facility generates coordinated images based on the received data using a generative AI model (e.g., StyleGAN). This generative AI model utilizes machine learning algorithms to generate highly relevant images based on the prompt text received from the user.

[0438] Image analysis and item identification

[0439] The generated outfit images are analyzed by a server facility to identify each fashion item (e.g., jacket, pants, shoes, etc.). Image recognition technology (e.g., YOLO or ResNet) is used for this analysis.

[0440] Item Search

[0441] The server facility searches for the corresponding product in the product information database based on the identified item. This database includes product information obtained from online sales sites and other sources.

[0442] Submit search results

[0443] The server facility sends the generated coordinated images and the searched product list to the terminal device. The transmitted data is in JSON format, and the terminal device receives and processes it.

[0444] Displaying Results

[0445] The terminal device displays the received generated images and item list to the user. Based on the displayed content, the user can visualize their desired fashion style and directly purchase the suggested products.

[0446] Specific example

[0447] For example, if a user enters "casual autumn outfit," the server facility uses this data to generate an outfit image using an AI model. The generated image will include items such as a casual jacket, sweatpants, and sneakers. The server facility analyzes these items and searches for related products in its product information database, listing them. Subsequently, the item list is displayed on the terminal device along with the generated outfit image, allowing the user to directly purchase the suggested items.

[0448] In this way, the present invention provides a system that quickly and accurately suggests the fashion style desired by the user and facilitates the purchase of related products based on that style.

[0449] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0450] Step 1:

[0451] Users input their observations of fashion styles and celebrities using a terminal device. For example, they can enter a prompt such as "Autumn casual outfit." Input is entered directly into the text field, and clicking the "Submit" button proceeds to the next step.

[0452] Input: Observations of fashion styles and celebrities (text format)

[0453] Output: Data entered by the user

[0454] Step 2:

[0455] The terminal device sends the data entered by the user to the server facility using an HTTP POST request. The input data is converted to JSON format and sent to the specified API endpoint.

[0456] Specific operation: The terminal device sends the following JSON data to the server facility.

[0457] json

[0458] {

[0459] "prompt": "Autumn casual outfit"

[0460] }

[0461] Input: Data entered by the user (prompt text)

[0462] Output: JSON data sent to the server facility

[0463] Step 3:

[0464] The server facility passes the received data to the generating AI model, which then generates coordinated images. The generating AI model uses a machine learning algorithm (e.g., StyleGAN) to generate images based on the input prompt text.

[0465] Specific operation: The server facility calls the generated AI model and generates images based on "autumn casual outfits".

[0466] Input: JSON data received by the server facility

[0467] Output: Generated coordinated image

[0468] Step 4:

[0469] The server facility passes the generated coordinated image to image recognition technology to identify each item. Specifically, it uses image recognition algorithms (e.g., YOLO or ResNet) to detect items such as jackets, pants, and shoes within the image.

[0470] Specific operation: The server facility applies image recognition technology and labels each fashion item from the generated images.

[0471] Input: Generated coordinate image

[0472] Output: A list of identified items (e.g., "jacket", "pants", "shoes")

[0473] Step 5:

[0474] The server facility searches the product information database for the corresponding product based on the identified item. The search query includes the category and characteristics of each item (e.g., color, material, etc.).

[0475] Specific operation: The server facility generates a database search query and retrieves a list of matching products.

[0476] Input: List of identified items

[0477] Output: List of relevant products

[0478] Step 6:

[0479] The server facility reconstructs the generated coordinated images and searched product lists into JSON format and sends them to the user's terminal device. This data includes the URLs of the generated images and the product lists.

[0480] Specific operation: The server facility sends the following JSON data to the terminal device.

[0481] json

[0482] {

[0483] "image_url": "https: / / cdn.example.com / generated-image.jpg",

[0484] "items": [

[0485] {"name": "Casual Jacket", "link": "https: / / shop.example.com / item123"},

[0486] {"name": "Sweatpants", "link": "https: / / shop.example.com / item456"},

[0487] {"name": "Sneakers", "link": "https: / / shop.example.com / item789"}

[0488] ]

[0489] }

[0490] Input: Generated outfit images and searched product list

[0491] Output: JSON data sent to the user's terminal device.

[0492] Step 7:

[0493] The terminal device displays the received generated images and product list to the user. This allows the user to visualize their desired fashion style and access links to directly purchase suggested products.

[0494] Specific operation: The terminal device displays images and a product list on the user interface.

[0495] Input: JSON data received from the server facility

[0496] Output: Generated image and product list displayed on the terminal device.

[0497] Through these steps, users can view specific outfit images based on their entered fashion style and receive quick and accurate suggestions for related products.

[0498] (Application Example 1)

[0499] 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."

[0500] Conventional fashion coordination systems have problems such as difficulty in easily recreating the style preferred by the user or the fashion of a specific celebrity, and the need to manually search for each item, which is time-consuming for the user. In addition, the methods for displaying the generated coordination image and related items are limited, and there is insufficient support for users to make quick purchase decisions. The present invention aims to solve these problems and provide a system that automatically generates coordination images using a generation AI model based on the fashion style entered by the user or the style of a celebrity, and further allows the user to easily purchase the suggested items.

[0501] 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.

[0502] In this invention, the server includes means for the user to input a fashion style or the name of a celebrity, means for transmitting the user's input data to the server, and means for generating a coordinated image using a generative AI model. This makes it possible to search for the corresponding items from a product database based on the generated coordinated image and identified items, transmit them to the user's terminal, and provide a link to directly purchase the suggested items.

[0503] A "user" is someone who uses the system to input fashion styles and celebrity names, and then receives suggested outfits and products.

[0504] "Fashion style" refers to a combination of clothing and accessories that are suited to a specific theme, season, or occasion.

[0505] "Celebrity names" refer to the names of specific famous people or entertainers, and are information used to help the system recognize the typical clothing and style of that person.

[0506] "Input data" refers to information that users enter into the system, such as fashion styles and names of famous people.

[0507] A "server" refers to a computer system that receives user input data, generates coordinated images using a generation AI model, and is also responsible for analyzing the generated images and linking them with a product database.

[0508] A "generative AI model" is a model that uses machine learning algorithms to reproduce specific fashion styles or celebrity styles based on user input.

[0509] "Coordinate images" are images that visually represent fashion styles or celebrity styles created using generative AI models.

[0510] "Analysis" refers to the process of analyzing the generated outfit images and identifying each fashion item within those images.

[0511] "Items" refer to individual clothing items, accessories, and other products identified within a coordinated outfit image.

[0512] A "product database" refers to a database that holds a large amount of product information, such as that found on online marketplaces.

[0513] "Searching" refers to the process of finding products that match or are similar to a specific item within a product database.

[0514] The "item list" refers to the collection of all items that the server searches for based on the generated outfit image and provides to the user.

[0515] "Terminal" refers to a device such as a smartphone or computer used by the user, and is used to display the generated outfit images and item lists.

[0516] A "link" is a hyperlink that a user can click to directly purchase a suggested item.

[0517] This invention is a system that generates coordinated outfit images using a generative AI model based on fashion styles entered by the user and the styles of celebrities, and suggests related products. This system mainly consists of a server, a user terminal, and a program.

[0518] Overall system configuration

[0519] The system includes means for the user to input a fashion style or the name of a celebrity, means for sending the user's input data to a server, means for generating a coordinated image using a generative AI model, means for analyzing the generated coordinated image to identify each item, means for searching for the corresponding item from a product database based on the identified item, means for sending the generated image and the list of searched items to the user's terminal, and means for displaying the generated image and the list of items to the user and providing a link for the user to directly purchase the suggested items.

[0520] Program Configuration

[0521] The server uses the Flask web framework and PIL (Python Imaging Library). The main data processing in this system is as follows:

[0522] 1. User Input: Users use their devices to input fashion styles or the names of specific celebrities. For example, they can specify things like "autumn casual outfits" or "celebrity styles."

[0523] 2. Data transmission: User input data is sent from the terminal to the server as an HTTP request.

[0524] 3. Coordinate Image Generation: Based on the user's input data received, the server generates coordinate images using a generative AI model. This image generation model employs machine learning algorithms to reproduce specific fashion styles based on user input, as well as typical styles of celebrities.

[0525] 4. Image Analysis and Item Identification: The server analyzes the generated outfit images and identifies each fashion item (e.g., jacket, pants, shoes). Image recognition technology is used for this analysis.

[0526] 5. Item Search: The server searches for the corresponding item from the product database (e.g., online marketplace) based on the specified item.

[0527] 6. Sending search results: The server sends the generated outfit images and the list of searched items to the user's device.

[0528] 7. Display of Results: The user's device displays the received generated images and item list to the user. Through this display, the user can see the specific fashion style they desire and also use links to directly purchase the suggested products.

[0529] Specific example

[0530] When a user enters "autumn casual outfit," the server uses an AI model to generate an outfit image based on the received data. This image includes items such as a casual jacket, sweatpants, and sneakers. The server analyzes these items and searches its database for related products, listing them. The generated outfit image is then displayed on the user's device along with these products, allowing the user to directly purchase the suggested items.

[0531] Examples of prompts to input into a generative AI model are as follows:

[0532] "Create a casual autumn outfit. A style including a gray jacket, sweatpants, and white sneakers."

[0533] In this way, the present invention allows users to easily and quickly find their desired fashion style and purchase related products online.

[0534] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0535] Step 1:

[0536] The user uses their device to input fashion styles or celebrity names on the application interface. This input is in text format. For example, let's say the user inputs "Autumn casual outfit." The device then sends this input data to the next step.

[0537] Step 2:

[0538] The terminal sends the entered fashion style and celebrity name to the server as an HTTP request. The server parses the received HTTP request and extracts the user's input data (fashion style and celebrity name in text format). This data is used in the next step.

[0539] Step 3:

[0540] The server creates a prompt message for the generating AI model based on the received input data. For example, if the input data is "autumn casual outfit," the server will generate the prompt message, "Generate an autumn casual outfit. A style including a gray jacket, sweatpants, and white sneakers." This prompt message is then input into the generating AI model.

[0541] Step 4:

[0542] The server uses a generative AI model to generate a coordinated image based on the prompt text. The generative AI model uses a machine learning algorithm to generate the image according to the content described in the prompt text. The generated coordinated image is obtained as output. This image will proceed to the next step.

[0543] Step 5:

[0544] The server analyzes the generated outfit image and uses image recognition technology to identify each fashion item (e.g., jacket, pants, shoes). The analysis yields a list of identified items. For example, items such as "gray jacket, sweatpants, white sneakers" might be identified.

[0545] Step 6:

[0546] The server searches its product database for items based on the identified item. This database contains a large amount of product information, including online marketplaces, and searches for products that match or are similar to each identified item. The search results provide a list of products. For example, a list is generated that includes links such as "Gray Jacket - URL", "Sweatpants - URL", and "White Sneakers - URL".

[0547] Step 7:

[0548] The server sends the generated outfit image and the searched item list to the user's device. An HTTP response is used for this transmission. The device receives this response and uses it in the next step.

[0549] Step 8:

[0550] The device displays the received generated outfit images and item list to the user. The user can review the displayed images and access purchase links directly through the list of suggested items. This allows the user to easily visualize their desired fashion style and utilize links to purchase related products.

[0551] 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.

[0552] This invention is a system that generates specific outfit images based on the user's input of fashion styles and celebrity outfits, and then suggests product items based on those images. Furthermore, this invention combines an emotion engine to provide personalized suggestions based on the user's emotions.

[0553] User input and emotion recognition

[0554] When a user uses this system, they are first required to enter a fashion style or the name of a celebrity. For example, the user might enter "autumn casual outfit" or "celebrity style." This input is done through the terminal's interface.

[0555] Simultaneously, the emotion engine analyzes the user's facial recognition and input data to recognize the user's emotions. Based on the information obtained from the user's facial expressions and input content, the emotion engine identifies an emotional state such as positive, negative, or neutral.

[0556] Sending data

[0557] The device sends user input data and sentiment data to the server. HTTP requests are used for transmission, and the input data is sent to a dedicated endpoint on the server.

[0558] Coordinate image generation

[0559] The server generates coordinated outfit images using an image generation model based on the user's input data and emotional data. This image generation model uses machine learning algorithms to reproduce specific fashion styles based on user input and typical styles of celebrities. It also adjusts the parameters of the generated coordinated outfit images based on the user's emotional data. For example, if the user is in a positive emotional state, a fashion style with bright colors may be suggested.

[0560] Image analysis and item identification

[0561] The server analyzes the generated outfit images and identifies each fashion item (e.g., jacket, pants, shoes). This analysis uses image recognition technology to automatically detect items within the image and organize their information.

[0562] Item Search

[0563] The server searches its product database for items based on the identified item. This database contains a large amount of product information from online marketplaces and finds products that match or are similar to each item identified by its image.

[0564] Submit search results

[0565] The server combines the generated outfit images with the item list retrieved from the product database. The server then formats this information into a format suitable for sending to the user's terminal and returns the appropriate information to the user.

[0566] Displaying Results

[0567] The terminal displays the generated image and item list received from the server to the user. The user can visually review the generated outfit image and suggested items, and will have access to links to purchase each item directly.

[0568] Specific example

[0569] If a user enters "casual autumn outfit" and the emotion engine recognizes a positive emotional state, the server generates an outfit image using a generated image model based on the received data. This image includes a casual jacket, sweatpants, and sneakers. Furthermore, the server analyzes the image to search for and list related products. The generated outfit image is then displayed on the device along with suggested items, and the user can purchase each item directly. If the user is in a negative emotional state, an outfit with more subdued colors may be suggested.

[0570] The following describes the processing flow.

[0571] Step 1:

[0572] The user enters a fashion style or the name of a celebrity. For example, the user might enter "Autumn casual outfit."

[0573] Step 2:

[0574] The device sends user input data to the emotion engine. The emotion engine analyzes the user's input and facial expressions.

[0575] Step 3:

[0576] The emotion engine recognizes the user's emotions and identifies them as positive, negative, neutral, etc. For example, if the user is smiling while typing, it recognizes this as a positive emotion.

[0577] Step 4:

[0578] The device sends user input data and sentiment data to the server. HTTP requests are used for transmission.

[0579] Step 5:

[0580] The server receives user input data and sentiment data. The server analyzes the input data and prepares it to be passed to the image generation model.

[0581] Step 6:

[0582] The server generates coordinated outfit images using an image generation model. The image generation model uses machine learning algorithms to recreate fashion styles based on user input and emotions.

[0583] Step 7:

[0584] The server analyzes the generated outfit image and identifies each fashion item. Specifically, it uses image recognition technology to detect items such as jackets, pants, and shoes within the image.

[0585] Step 8:

[0586] The server searches the product database for items based on the identified item. For example, it might use an online marketplace API to retrieve similar products.

[0587] Step 9:

[0588] The server combines the generated outfit images with the item list retrieved from the product database. The server then formats this information for transmission to the user's terminal.

[0589] Step 10:

[0590] The server sends the generated image and item list to the user's device. Specifically, it returns this data as an HTTP response.

[0591] Step 11:

[0592] The terminal displays the generated image and item list received from the server to the user. The user can review the generated outfit image and suggested items and access purchase links for each item.

[0593] As a concrete example, if a user enters "autumn casual outfit" and shows a positive emotion with a smile, the server will generate an image including a brightly colored jacket, sweatpants, and sneakers. This image is then analyzed to retrieve relevant products from the product database and suggest them to the user. The user can then review and purchase these suggested items.

[0594] (Example 2)

[0595] 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".

[0596] Current fashion coordination systems offer only simple item suggestions without considering the user's emotions. Therefore, it is difficult to suggest outfits that suit the user's feelings or mood on any given day. Furthermore, the need for manual item selection and searching limits the user experience.

[0597] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for transmitting user input data and emotion data to the server, means for the server to generate a coordinated image using an image generation model based on the input data and emotion data, and means for the server to analyze the generated coordinated image and identify each item. This makes it possible to suggest personalized fashion coordinates according to the user's emotions.

[0598] A "user" is the entity that uses the system to input fashion styles and celebrity names, and generates coordinated outfit images.

[0599] "Input data" refers to information that users enter into the system, such as fashion styles and names of famous people.

[0600] "Emotional data" refers to information about a user's emotional state, identified by analyzing their facial expressions and text input.

[0601] A "server" is a computer system that processes input data and sentiment data received from users, and performs tasks such as generating and analyzing coordinated images and searching for items from a product database.

[0602] An "image generation model" is a technology that uses machine learning algorithms to generate coordinated images based on input data and sentiment data.

[0603] A "machine learning algorithm" is a technology that uses large amounts of data to learn and perform pattern recognition and data generation.

[0604] A "coordinate image" is an image generated by a generative AI model that visually represents a specific fashion style.

[0605] "Image recognition technology" is a technology that analyzes image data to identify specific objects or features.

[0606] A "product database" is a data storage system that contains a large amount of product information related to fashion items.

[0607] An "online marketplace" is a platform where multiple sellers and buyers can buy and sell goods over the internet.

[0608] The "item list" is a list of product items selected based on the analysis results of the coordinated outfit images.

[0609] A "terminal" is a device used by a user to interact with a system, and includes, for example, personal computers and smartphones.

[0610] This invention is a system that generates specific outfit images based on the user's input of fashion styles and celebrity outfits, and then suggests product items based on those images. Furthermore, this invention incorporates an emotion engine to provide personalized suggestions based on the user's emotions.

[0611] User input and emotion recognition

[0612] The user inputs fashion styles or celebrity names using the device's interface. For example, they might enter prompts such as "autumn casual outfits" or "celebrity styles." Simultaneously, an emotion engine is activated, analyzing the user's facial expressions and entered text to identify their emotional state, such as positive, negative, or neutral. Specifically, it uses the device's camera for facial recognition to read emotions.

[0613] Sending data

[0614] The device sends user input data and sentiment data to the server via HTTP requests. The input data and sentiment data are combined in JSON format and sent to a dedicated endpoint on the server.

[0615] Coordinate image generation

[0616] The server uses the received user input data and sentiment data to generate coordinated outfit images using an image generation model (e.g., GAN: Generative Adversarial Network). If the user has a positive sentiment, a fashion style with bright colors will be suggested. The generated images visually represent specific fashion items and are customized according to the user's needs.

[0617] Image analysis and item identification

[0618] The server analyzes the generated outfit images using image recognition technology (e.g., CNN: Convolutional Neural Networks) to automatically identify each fashion item (jacket, pants, shoes, etc.). The identified items are then organized as data for the next search step.

[0619] Item Search

[0620] The server searches its product database for items based on the identified fashion item. This product database utilizes the large data storage of the online marketplace to find products that match or are similar to the item identified by the image. The search results are listed for the user to see.

[0621] Submit search results

[0622] The server integrates the generated outfit images and the item list retrieved from the product database, and formats them into an appropriate format for transmission to the user's device. This information is compiled in JSON format and sent to the user's device.

[0623] Displaying Results

[0624] The terminal displays generated images and item lists received from the server to the user. The user can visually review these and click on links to purchase each item directly. For example, in response to a suggestion for "Autumn Casual Outfit," casual jackets, sweatpants, sneakers, and other items will be displayed.

[0625] Specific example

[0626] When a user enters "autumn casual outfit" and the emotion engine recognizes a positive emotional state, the server generates an outfit image based on this. The generated image includes a casual jacket, light-colored sweatpants, and white sneakers. The server searches the product database for these items and identifies the corresponding products. The generated outfit image and recommended product list are then sent to the terminal, where the user can review and purchase them. An example of a prompt message is, "Please enter an autumn casual outfit, generate an outfit image based on positive emotions, and suggest related products."

[0627] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0628] Step 1: User input

[0629] The user uses the terminal's interface to input fashion styles or the names of celebrities. For example, they might enter a prompt like "Autumn casual outfit." The content entered by the user in the terminal's text field is used as input data. This allows the user's desired outfit to be obtained as specific text data.

[0630] Input: Text data entered by the user on the device (e.g., "Autumn casual outfit")

[0631] Output: User input is obtained in the form of text data.

[0632] Step 2: Emotion Recognition

[0633] The device uses its built-in camera to capture the user's face when they input data, and then analyzes it using an emotion engine. As a result of the analysis, emotion data such as positive, negative, and neutral is generated.

[0634] Input: User's face image, input text

[0635] Output: Sentiment data (e.g., positive)

[0636] Step 3: Data transmission

[0637] The device collects user input data and sentiment data and sends it to the server via an HTTP request. This data is sent in JSON format to a dedicated endpoint on the server.

[0638] Input: User input data, sentiment data

[0639] Output: Data in JSON format, sent to the server.

[0640] Step 4: Generate the coordinated image

[0641] The server uses an image generation model (e.g., GAN) to generate specific outfit images based on the user's input data and sentiment data. The image parameters are adjusted according to the sentiment data. For example, if the sentiment data is positive, a fashion item with bright colors will be generated.

[0642] Input: User input data, sentiment data

[0643] Output: Coordinated image

[0644] Step 5: Image analysis and item identification

[0645] The server analyzes the generated outfit images and identifies each fashion item (e.g., jacket, pants, shoes). Using image recognition technology (e.g., CNN), it identifies items within the image and extracts information about each individual item.

[0646] Input: Coordinated image

[0647] Output: Identified item information

[0648] Step 6: Search for items

[0649] The server searches the product database for the corresponding item based on the identified item information. Specifically, it issues a query to the online marketplace database to find the corresponding product.

[0650] Input: Identified item information

[0651] Output: Product List

[0652] Step 7: Submit search results

[0653] The server combines the generated outfit images and product list and formats them into an appropriate format (JSON) for transmission to the user's device. The generated data is sent to the user's device as an HTTP response.

[0654] Input: Coordination image, product list

[0655] Output: Data sent to the user's device

[0656] Step 8: Displaying the results

[0657] The terminal displays the generated image and item list received from the server to the user. The user can purchase each item by clicking on the provided links.

[0658] Input: Data received from the server

[0659] Output: Coordinated outfit images and item list displayed to the user

[0660] As a concrete example of its operation, if a user inputs "autumn casual outfit" and the emotion engine recognizes a positive emotional state, the server generates an outfit image based on this, searches the item list, and sends and displays the generated information on the terminal. An example of a prompt message would be, "Please input an autumn casual outfit, generate an outfit image based on positive emotions, and suggest related products."

[0661] (Application Example 2)

[0662] 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."

[0663] Conventional fashion style suggestion systems only propose styles based on user input information, and do not provide personalized suggestions that take into account the user's emotional state. Furthermore, the lack of functionality to virtually try on and purchase suggested coordinated items prevented improvements in user satisfaction and the purchasing experience.

[0664] In Application Example 2, the identification processing by the identification processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for the user to input a fashion style or the name of a celebrity; means for transmitting the user's input data to the server; means for the server to generate a coordinated image using an image generation model based on the input data; means for the server to analyze the generated coordinated image and identify each item; means for the server to search for the corresponding item from a product database based on the identified item; means for the server to transmit the generated image and the searched item list to the user's terminal; means for the terminal to display the generated image and item list to the user; means for combining an emotion engine to recognize the user's emotional state and adjusting the content of the generated image and item suggestions based on the recognized emotional state; and means for displaying the generated coordinated image and suggested items in a virtual store, enabling the user to virtually try on and directly purchase the suggested items. This enables personalized fashion suggestions according to the user's emotional state, and further enables trying on and purchasing in a virtual space.

[0665] A "user" refers to an individual who uses this system to input their fashion style and the names of celebrities, and receives outfit suggestions.

[0666] "Fashion style" refers to the overall concept of coordination based on a specific theme or aesthetic sense, including clothing, accessories, and hairstyles.

[0667] A "celebrity" refers to a person who is well-known and whose style is widely recognized.

[0668] "Input data" refers to information about fashion styles and celebrity names entered by the user.

[0669] A "server" refers to a central processing unit that receives input data from users and performs tasks such as generating coordinated images and searching for product items.

[0670] An "image generation model" refers to an algorithm or software that uses machine learning algorithms to generate specific coordinated images based on user input.

[0671] A "coordinate image" refers to an image that shows a visual example of fashion generated based on the user's input data.

[0672] An "emotion engine" refers to software or hardware that recognizes a user's emotional state from their facial expressions and input, and reflects that in the system's operation.

[0673] A "product database" refers to a collection of data related to fashion items stored within an online marketplace.

[0674] A "virtual store" refers to a virtual shopping space that users can access on the internet.

[0675] An "item list" refers to a list of items retrieved from the product database that correspond to the fashion items identified within the generated outfit image.

[0676] "Virtual try-on" refers to a feature that allows users to virtually try on fashion items suggested within a virtual store and check how they look.

[0677] Explanation of program generation and processing

[0678] This invention implements a system in which a user inputs a fashion style or the name of a celebrity, and a server generates coordinated images based on that input data and suggests appropriate items.

[0679] Hardware and software configuration

[0680] Hardware: Smartphone or PC, server, camera for acquiring user facial images.

[0681] Software: Python, face_recognition library, TensorFlow, Requests, Pillow

[0682] 1. User Input and Sentiment Recognition

[0683] The user uses their smartphone or computer to input a fashion style (e.g., "Spring casual outfit") or the name of a celebrity. Next, they provide a facial image using their smartphone's camera or an image file on their device. The emotion engine uses the face_recognition library and an emotion recognition model (built using TensorFlow) to identify emotions from the user's facial image.

[0684] 2. Server-side processing

[0685] The server receives user input data (fashion style or celebrity name) and sentiment data. The server then uses machine learning algorithms to generate outfit images. Furthermore, it analyzes the generated outfit images to identify specific fashion items. Based on the identified items, it searches for the corresponding items in its product database (related to the online marketplace).

[0686] 3. Sending and displaying results to the user

[0687] The server sends the generated outfit image and the searched item list to the user's device. The user's device receives this information and displays the generated image and item list. Within the virtual store, the user can visually confirm the generated outfit image and suggested items, virtually try on the suggested items, and purchase them directly.

[0688] Specific examples of usage

[0689] For example, if a user enters "spring casual outfit" and the emotion engine recognizes a positive emotional state, the server uses a machine learning algorithm to generate an outfit image based on the received data. This image would include a casual jacket, shirt, and pants in bright colors. Furthermore, the server analyzes the image and lists the corresponding items from the online marketplace's product database. The generated outfit image is then displayed on the terminal along with suggested items, and the user can purchase each item directly.

[0690] Example of a prompt

[0691] 1. "Please suggest a casual spring outfit. My current emotional state is positive."

[0692] 2. "Please enter the style of a famous person (e.g., a famous singer). Your current emotional state is neutral."

[0693] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0694] Step 1:

[0695] The user enters a fashion style or the name of a celebrity. Specifically, the user uses a smartphone or computer to enter keywords such as "spring casual outfit" or "famous singer" into the application's input form. The input data is saved on the device as string data.

[0696] Step 2:

[0697] The user provides a facial image. Specifically, the user either takes a picture of their face with their smartphone camera or uploads a facial image file stored on their device. The image data is saved in JPEG or PNG format and imported as input data for the application.

[0698] Step 3:

[0699] The emotion engine analyzes the user's facial image and recognizes their emotional state. Specifically, it uses the face_recognition library on the device to determine the position of the face, and then uses TensorFlow to estimate the emotional state using an emotion recognition model. The input is facial image data, and the output is the emotional state (positive, negative, neutral, etc.). For example, if the model detects a smile, it is recognized as a positive emotional state.

[0700] Step 4:

[0701] The device sends user input data and emotional data to the server. Specifically, it sends the entered fashion style, celebrity names, and recognized emotional states to a dedicated endpoint on the server via an HTTP request. The transmitted data is in JSON format and is received by the server.

[0702] Step 5:

[0703] The server generates coordinated outfit images based on the input data it receives. Specifically, it uses a machine learning algorithm (generative AI model) running on the server to generate fashion coordinated outfit images based on the user's input data and sentiment data. The input is user data and sentiment data, and the output is the generated coordinated outfit image.

[0704] Step 6:

[0705] The server analyzes the generated outfit image to identify each item. Specifically, it uses image recognition technology to analyze the generated image and identify each fashion item (jacket, shirt, pants, etc.). The input is the latest generated outfit image, and the output is item information. For example, it automatically identifies shirts, pants, shoes, etc., in an image.

[0706] Step 7:

[0707] The server searches the product database for items based on the identified item. Specifically, it queries the product database (online marketplace) to retrieve product information (name, price, purchase link, etc.) that matches the identified item. The input is the information of the identified item, and the output is a list of matching product information.

[0708] Step 8:

[0709] The server sends the generated image and the searched item list to the user's device. Specifically, it sends a list of product information matching the generated outfit image to the device as an HTTP response in JSON format. The transmitted data includes the URL of the generated image and the item list.

[0710] Step 9:

[0711] The device displays the generated image and item list to the user. Specifically, it displays the coordinated outfit image generated within the application, allowing for visual confirmation along with the suggested item list. Users can virtually try on the suggested items using the virtual try-on function and purchase them directly by clicking the displayed purchase link. The input is data received from the server, and the output is the displayed coordinated outfit image and item list.

[0712] 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.

[0713] 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.

[0714] 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.

[0715] [Third Embodiment]

[0716] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0717] 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.

[0718] 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).

[0719] 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.

[0720] 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.

[0721] 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).

[0722] 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.

[0723] 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.

[0724] 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.

[0725] 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.

[0726] 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.

[0727] 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".

[0728] This invention is a system that generates specific outfit images based on the user's input of fashion styles and celebrity outfits, and then suggests product items based on those images.

[0729] 1. User input

[0730] When using this system, users are first required to enter a fashion style or the name of a celebrity. For example, specific requests such as "autumn casual outfit" or "celebrity style" are possible. This input is performed on the terminal's interface.

[0731] 2. Sending data

[0732] The terminal sends user input data to the server. HTTP requests are used for transmission, and the entered data is sent to a dedicated endpoint on the server.

[0733] 3. Generating the coordinated image

[0734] The server generates coordinated outfit images using an image generation model based on the user's input data. This image generation model employs machine learning algorithms to reproduce specific fashion styles based on user input, as well as typical styles of celebrities.

[0735] 4. Image analysis and item identification

[0736] The server analyzes the generated outfit images and identifies each fashion item (e.g., jacket, pants, shoes, etc.). Image recognition technology is used for this analysis.

[0737] 5. Search for items

[0738] The server searches its product database for items based on the identified item. This database contains a large amount of product information, such as from online marketplaces, and finds products that match or are similar to each item identified by its image.

[0739] 6. Submit search results

[0740] The server sends the generated outfit images and the searched item list to the user's device. This allows the user to receive visuals of the suggested fashion style and a specific product list based on that style.

[0741] 7. Displaying the results

[0742] The device displays the received generated images and item list to the user. Through this display, the user can see specific fashion styles they desire and can also use links to directly purchase the suggested products.

[0743] As a concrete example, when a user enters "autumn casual outfit," the server generates an outfit image using a generated image model based on the received data. This image includes items such as a casual jacket, sweatpants, and sneakers. The server analyzes these items and searches for related products in its database, listing them. The generated outfit image is then displayed on the terminal along with these products, allowing the user to directly purchase the suggested items.

[0744] The following describes the processing flow.

[0745] Step 1:

[0746] The user enters a fashion style or the name of a celebrity. For example, the user might enter "Autumn casual outfit."

[0747] Step 2:

[0748] The terminal sends the user's input data to the server. Specifically, it sends the input data to the server as an HTTP POST request.

[0749] Step 3:

[0750] The server receives user input data. The server analyzes the input data and prepares it to be passed to the image generation model.

[0751] Step 4:

[0752] The server generates coordinated images using an image generation model. The image generation model outputs images that reproduce a specific fashion style based on the input style.

[0753] Step 5:

[0754] The server analyzes the generated outfit image and identifies each fashion item. Specifically, it uses image recognition technology to detect items such as jackets, pants, and shoes within the image and extracts their information.

[0755] Step 6:

[0756] The server searches the product database for the corresponding item based on each identified item. The server sends a search query to the online marketplace's API and retrieves the relevant products.

[0757] Step 7:

[0758] The server combines the generated outfit images with the item list retrieved from the product database. The server then formats this information into a format suitable for sending to the user's terminal.

[0759] Step 8:

[0760] The server sends the generated image and item list to the user's device. Specifically, it returns this data as an HTTP response.

[0761] Step 9:

[0762] The device displays the generated image and item list received from the server to the user. The user can review the generated outfit image and suggested items and access purchase links for each item.

[0763] (Example 1)

[0764] 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."

[0765] Conventional fashion suggestion systems had problems such as making it difficult for users to visually imagine specific outfits, and failing to adequately suggest products based on those outfits. In particular, it was difficult to generate specific outfit images based on the fashion style desired by the user or the style of a celebrity, and to quickly and accurately suggest products related to those images.

[0766] 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.

[0767] In this invention, the server includes means for the user to input a fashion style or observations of a celebrity; means for transmitting the user's input data to a server facility; means for the server facility to generate a coordinated image using an image generation algorithm based on the input data; means for the server facility to analyze the generated coordinated image and identify each item; means for the server facility to search for the corresponding item from a product information database based on the identified item; means for the server facility to transmit the generated image and the searched item list to the user's terminal device; and means for the terminal device to display the generated image and item list to the user. As a result, the user can simply input their desired fashion style or celebrity coordinated outfit, generate a specific coordinated image based on it, analyze the image to identify each item, and quickly and accurately suggest related products.

[0768] A "user" refers to a person who uses this system to input observations about fashion styles or celebrities.

[0769] A "terminal device" refers to an electronic device used by a user to input information and receive display results. Examples include smartphones, personal computers, and tablets.

[0770] A "server facility" refers to a computer system that has the function of receiving data sent from users, generating and analyzing images, searching for corresponding product information, and sending it to the user's terminal device.

[0771] An "image generation algorithm" refers to a machine learning algorithm used to generate coordinated images based on user input data. Examples include Generative Adversarial Networks (GANs).

[0772] "Coordinate images" refer to images that visually represent generated fashion styles or the styles of celebrities.

[0773] "Image recognition technology" refers to techniques for analyzing images and identifying each fashion item contained within them. Examples include YOLO and ResNet.

[0774] A "product information database" refers to a database that provides information about searched items. It is related to online sales websites.

[0775] An "item list" refers to a list of product information searched based on the generated outfit images, organized in a list format.

[0776] This invention is a system that generates specific outfit images and suggests related product items based on the user's input of fashion styles and celebrity styles. This system primarily operates with a server, terminal devices, and users.

[0777] User input

[0778] Users access the system interface using a terminal device (e.g., smartphone, PC, tablet) and input fashion styles or celebrity styles. For example, they can enter specific prompts such as "autumn casual outfit" or "a certain celebrity's style."

[0779] Sending data

[0780] The terminal device transmits the data entered by the user to the server facility. This transmission uses an HTTP POST request, and the input data is sent to the server facility in JSON format.

[0781] Coordinate image generation

[0782] The server facility generates coordinated images based on the received data using a generative AI model (e.g., StyleGAN). This generative AI model utilizes machine learning algorithms to generate highly relevant images based on the prompt text received from the user.

[0783] Image analysis and item identification

[0784] The generated outfit images are analyzed by a server facility to identify each fashion item (e.g., jacket, pants, shoes, etc.). Image recognition technology (e.g., YOLO or ResNet) is used for this analysis.

[0785] Item Search

[0786] The server facility searches for the corresponding product in the product information database based on the identified item. This database includes product information obtained from online sales sites and other sources.

[0787] Submit search results

[0788] The server facility sends the generated coordinated images and the searched product list to the terminal device. The transmitted data is in JSON format, and the terminal device receives and processes it.

[0789] Displaying Results

[0790] The terminal device displays the received generated images and item list to the user. Based on the displayed content, the user can visualize their desired fashion style and directly purchase the suggested products.

[0791] Specific example

[0792] For example, if a user enters "casual autumn outfit," the server facility uses this data to generate an outfit image using an AI model. The generated image will include items such as a casual jacket, sweatpants, and sneakers. The server facility analyzes these items and searches for related products in its product information database, listing them. Subsequently, the item list is displayed on the terminal device along with the generated outfit image, allowing the user to directly purchase the suggested items.

[0793] In this way, the present invention provides a system that quickly and accurately suggests the fashion style desired by the user and facilitates the purchase of related products based on that style.

[0794] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0795] Step 1:

[0796] Users input their observations of fashion styles and celebrities using a terminal device. For example, they can enter a prompt such as "Autumn casual outfit." Input is entered directly into the text field, and clicking the "Submit" button proceeds to the next step.

[0797] Input: Observations of fashion styles and celebrities (text format)

[0798] Output: Data entered by the user

[0799] Step 2:

[0800] The terminal device sends the data entered by the user to the server facility using an HTTP POST request. The input data is converted to JSON format and sent to the specified API endpoint.

[0801] Specific operation: The terminal device sends the following JSON data to the server facility.

[0802] json

[0803] {

[0804] "prompt": "Autumn casual outfit"

[0805] }

[0806] Input: Data entered by the user (prompt text)

[0807] Output: JSON data sent to the server facility

[0808] Step 3:

[0809] The server facility passes the received data to the generating AI model, which then generates coordinated images. The generating AI model uses a machine learning algorithm (e.g., StyleGAN) to generate images based on the input prompt text.

[0810] Specific operation: The server facility calls the generated AI model and generates images based on "autumn casual outfits".

[0811] Input: JSON data received by the server facility

[0812] Output: Generated coordinated image

[0813] Step 4:

[0814] The server facility passes the generated coordinated image to image recognition technology to identify each item. Specifically, it uses image recognition algorithms (e.g., YOLO or ResNet) to detect items such as jackets, pants, and shoes within the image.

[0815] Specific operation: The server facility applies image recognition technology and labels each fashion item from the generated images.

[0816] Input: Generated coordinate image

[0817] Output: A list of identified items (e.g., "jacket", "pants", "shoes")

[0818] Step 5:

[0819] The server facility searches the product information database for the corresponding product based on the identified item. The search query includes the category and characteristics of each item (e.g., color, material, etc.).

[0820] Specific operation: The server facility generates a database search query and retrieves a list of matching products.

[0821] Input: List of identified items

[0822] Output: List of relevant products

[0823] Step 6:

[0824] The server facility reconstructs the generated coordinated images and searched product lists into JSON format and sends them to the user's terminal device. This data includes the URLs of the generated images and the product lists.

[0825] Specific operation: The server facility sends the following JSON data to the terminal device.

[0826] json

[0827] {

[0828] "image_url": "https: / / cdn.example.com / generated-image.jpg",

[0829] "items": [

[0830] {"name": "Casual Jacket", "link": "https: / / shop.example.com / item123"},

[0831] {"name": "Sweatpants", "link": "https: / / shop.example.com / item456"},

[0832] {"name": "Sneakers", "link": "https: / / shop.example.com / item789"}

[0833] ]

[0834] }

[0835] Input: Generated outfit images and searched product list

[0836] Output: JSON data sent to the user's terminal device.

[0837] Step 7:

[0838] The terminal device displays the received generated images and product list to the user. This allows the user to visualize their desired fashion style and access links to directly purchase suggested products.

[0839] Specific operation: The terminal device displays images and a product list on the user interface.

[0840] Input: JSON data received from the server facility

[0841] Output: Generated image and product list displayed on the terminal device.

[0842] Through these steps, users can view specific outfit images based on their entered fashion style and receive quick and accurate suggestions for related products.

[0843] (Application Example 1)

[0844] 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."

[0845] Conventional fashion coordination systems have problems such as difficulty in easily recreating the style preferred by the user or the fashion of a specific celebrity, and the need to manually search for each item, which is time-consuming for the user. In addition, the methods for displaying the generated coordination image and related items are limited, and there is insufficient support for users to make quick purchase decisions. The present invention aims to solve these problems and provide a system that automatically generates coordination images using a generation AI model based on the fashion style entered by the user or the style of a celebrity, and further allows the user to easily purchase the suggested items.

[0846] 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.

[0847] In this invention, the server includes means for the user to input a fashion style or the name of a celebrity, means for transmitting the user's input data to the server, and means for generating a coordinated image using a generative AI model. This makes it possible to search for the corresponding items from a product database based on the generated coordinated image and identified items, transmit them to the user's terminal, and provide a link to directly purchase the suggested items.

[0848] A "user" is someone who uses the system to input fashion styles and celebrity names, and then receives suggested outfits and products.

[0849] "Fashion style" refers to a combination of clothing and accessories that are suited to a specific theme, season, or occasion.

[0850] "Celebrity names" refer to the names of specific famous people or entertainers, and are information used to help the system recognize the typical clothing and style of that person.

[0851] "Input data" refers to information that users enter into the system, such as fashion styles and names of famous people.

[0852] A "server" refers to a computer system that receives user input data, generates coordinated images using a generation AI model, and is also responsible for analyzing the generated images and linking them with a product database.

[0853] A "generative AI model" is a model that uses machine learning algorithms to reproduce specific fashion styles or celebrity styles based on user input.

[0854] "Coordinate images" are images that visually represent fashion styles or celebrity styles created using generative AI models.

[0855] "Analysis" refers to the process of analyzing the generated outfit images and identifying each fashion item within those images.

[0856] "Items" refer to individual clothing items, accessories, and other products identified within a coordinated outfit image.

[0857] A "product database" refers to a database that holds a large amount of product information, such as that found on online marketplaces.

[0858] "Searching" refers to the process of finding products that match or are similar to a specific item within a product database.

[0859] The "item list" refers to the collection of all items that the server searches for based on the generated outfit image and provides to the user.

[0860] "Terminal" refers to a device such as a smartphone or computer used by the user, and is used to display the generated outfit images and item lists.

[0861] A "link" is a hyperlink that a user can click to directly purchase a suggested item.

[0862] This invention is a system that generates coordinated outfit images using a generative AI model based on fashion styles entered by the user and the styles of celebrities, and suggests related products. This system mainly consists of a server, a user terminal, and a program.

[0863] Overall system configuration

[0864] The system includes means for the user to input a fashion style or the name of a celebrity, means for sending the user's input data to a server, means for generating a coordinated image using a generative AI model, means for analyzing the generated coordinated image to identify each item, means for searching for the corresponding item from a product database based on the identified item, means for sending the generated image and the list of searched items to the user's terminal, and means for displaying the generated image and the list of items to the user and providing a link for the user to directly purchase the suggested items.

[0865] Program Configuration

[0866] The server uses the Flask web framework and PIL (Python Imaging Library). The main data processing in this system is as follows:

[0867] 1. User Input: Users use their devices to input fashion styles or the names of specific celebrities. For example, they can specify things like "autumn casual outfits" or "celebrity styles."

[0868] 2. Data transmission: User input data is sent from the terminal to the server as an HTTP request.

[0869] 3. Coordinate Image Generation: Based on the user's input data received, the server generates coordinate images using a generative AI model. This image generation model employs machine learning algorithms to reproduce specific fashion styles based on user input, as well as typical styles of celebrities.

[0870] 4. Image Analysis and Item Identification: The server analyzes the generated outfit images and identifies each fashion item (e.g., jacket, pants, shoes). Image recognition technology is used for this analysis.

[0871] 5. Item Search: The server searches for the corresponding item from the product database (e.g., online marketplace) based on the specified item.

[0872] 6. Sending search results: The server sends the generated outfit images and the list of searched items to the user's device.

[0873] 7. Display of Results: The user's device displays the received generated images and item list to the user. Through this display, the user can see the specific fashion style they desire and also use links to directly purchase the suggested products.

[0874] Specific example

[0875] When a user enters "autumn casual outfit," the server uses an AI model to generate an outfit image based on the received data. This image includes items such as a casual jacket, sweatpants, and sneakers. The server analyzes these items and searches its database for related products, listing them. The generated outfit image is then displayed on the user's device along with these products, allowing the user to directly purchase the suggested items.

[0876] Examples of prompts to input into a generative AI model are as follows:

[0877] "Create a casual autumn outfit. A style including a gray jacket, sweatpants, and white sneakers."

[0878] In this way, the present invention allows users to easily and quickly find their desired fashion style and purchase related products online.

[0879] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0880] Step 1:

[0881] The user uses their device to input fashion styles or celebrity names on the application interface. This input is in text format. For example, let's say the user inputs "Autumn casual outfit." The device then sends this input data to the next step.

[0882] Step 2:

[0883] The terminal sends the entered fashion style and celebrity name to the server as an HTTP request. The server parses the received HTTP request and extracts the user's input data (fashion style and celebrity name in text format). This data is used in the next step.

[0884] Step 3:

[0885] The server creates a prompt message for the generating AI model based on the received input data. For example, if the input data is "autumn casual outfit," the server will generate the prompt message, "Generate an autumn casual outfit. A style including a gray jacket, sweatpants, and white sneakers." This prompt message is then input into the generating AI model.

[0886] Step 4:

[0887] The server uses a generative AI model to generate a coordinated image based on the prompt text. The generative AI model uses a machine learning algorithm to generate the image according to the content described in the prompt text. The generated coordinated image is obtained as output. This image will proceed to the next step.

[0888] Step 5:

[0889] The server analyzes the generated outfit image and uses image recognition technology to identify each fashion item (e.g., jacket, pants, shoes). The analysis yields a list of identified items. For example, items such as "gray jacket, sweatpants, white sneakers" might be identified.

[0890] Step 6:

[0891] The server searches its product database for items based on the identified item. This database contains a large amount of product information, including online marketplaces, and searches for products that match or are similar to each identified item. The search results provide a list of products. For example, a list is generated that includes links such as "Gray Jacket - URL", "Sweatpants - URL", and "White Sneakers - URL".

[0892] Step 7:

[0893] The server sends the generated outfit image and the searched item list to the user's device. An HTTP response is used for this transmission. The device receives this response and uses it in the next step.

[0894] Step 8:

[0895] The device displays the received generated outfit images and item list to the user. The user can review the displayed images and access purchase links directly through the list of suggested items. This allows the user to easily visualize their desired fashion style and utilize links to purchase related products.

[0896] 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.

[0897] This invention is a system that generates specific outfit images based on the user's input of fashion styles and celebrity outfits, and then suggests product items based on those images. Furthermore, this invention combines an emotion engine to provide personalized suggestions based on the user's emotions.

[0898] User input and emotion recognition

[0899] When a user uses this system, they are first required to enter a fashion style or the name of a celebrity. For example, the user might enter "autumn casual outfit" or "celebrity style." This input is done through the terminal's interface.

[0900] Simultaneously, the emotion engine analyzes the user's facial recognition and input data to recognize the user's emotions. Based on the information obtained from the user's facial expressions and input content, the emotion engine identifies an emotional state such as positive, negative, or neutral.

[0901] Sending data

[0902] The device sends user input data and sentiment data to the server. HTTP requests are used for transmission, and the input data is sent to a dedicated endpoint on the server.

[0903] Coordinate image generation

[0904] The server generates coordinated outfit images using an image generation model based on the user's input data and emotional data. This image generation model uses machine learning algorithms to reproduce specific fashion styles based on user input and typical styles of celebrities. It also adjusts the parameters of the generated coordinated outfit images based on the user's emotional data. For example, if the user is in a positive emotional state, a fashion style with bright colors may be suggested.

[0905] Image analysis and item identification

[0906] The server analyzes the generated outfit images and identifies each fashion item (e.g., jacket, pants, shoes). This analysis uses image recognition technology to automatically detect items within the image and organize their information.

[0907] Item Search

[0908] The server searches its product database for items based on the identified item. This database contains a large amount of product information from online marketplaces and finds products that match or are similar to each item identified by its image.

[0909] Submit search results

[0910] The server combines the generated outfit images with the item list retrieved from the product database. The server then formats this information into a format suitable for sending to the user's terminal and returns the appropriate information to the user.

[0911] Displaying Results

[0912] The terminal displays the generated image and item list received from the server to the user. The user can visually review the generated outfit image and suggested items, and will have access to links to purchase each item directly.

[0913] Specific example

[0914] If a user enters "casual autumn outfit" and the emotion engine recognizes a positive emotional state, the server generates an outfit image using a generated image model based on the received data. This image includes a casual jacket, sweatpants, and sneakers. Furthermore, the server analyzes the image to search for and list related products. The generated outfit image is then displayed on the device along with suggested items, and the user can purchase each item directly. If the user is in a negative emotional state, an outfit with more subdued colors may be suggested.

[0915] The following describes the processing flow.

[0916] Step 1:

[0917] The user enters a fashion style or the name of a celebrity. For example, the user might enter "Autumn casual outfit."

[0918] Step 2:

[0919] The device sends user input data to the emotion engine. The emotion engine analyzes the user's input and facial expressions.

[0920] Step 3:

[0921] The emotion engine recognizes the user's emotions and identifies them as positive, negative, neutral, etc. For example, if the user is smiling while typing, it recognizes this as a positive emotion.

[0922] Step 4:

[0923] The device sends user input data and sentiment data to the server. HTTP requests are used for transmission.

[0924] Step 5:

[0925] The server receives user input data and sentiment data. The server analyzes the input data and prepares it to be passed to the image generation model.

[0926] Step 6:

[0927] The server generates coordinated outfit images using an image generation model. The image generation model uses machine learning algorithms to recreate fashion styles based on user input and emotions.

[0928] Step 7:

[0929] The server analyzes the generated outfit image and identifies each fashion item. Specifically, it uses image recognition technology to detect items such as jackets, pants, and shoes within the image.

[0930] Step 8:

[0931] The server searches the product database for items based on the identified item. For example, it might use an online marketplace API to retrieve similar products.

[0932] Step 9:

[0933] The server combines the generated outfit images with the item list retrieved from the product database. The server then formats this information for transmission to the user's terminal.

[0934] Step 10:

[0935] The server sends the generated image and item list to the user's device. Specifically, it returns this data as an HTTP response.

[0936] Step 11:

[0937] The terminal displays the generated image and item list received from the server to the user. The user can review the generated outfit image and suggested items and access purchase links for each item.

[0938] As a concrete example, if a user enters "autumn casual outfit" and shows a positive emotion with a smile, the server will generate an image including a brightly colored jacket, sweatpants, and sneakers. This image is then analyzed to retrieve relevant products from the product database and suggest them to the user. The user can then review and purchase these suggested items.

[0939] (Example 2)

[0940] 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."

[0941] Current fashion coordination systems offer only simple item suggestions without considering the user's emotions. Therefore, it is difficult to suggest outfits that suit the user's feelings or mood on any given day. Furthermore, the need for manual item selection and searching limits the user experience.

[0942] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for transmitting user input data and emotion data to the server, means for the server to generate a coordinated image using an image generation model based on the input data and emotion data, and means for the server to analyze the generated coordinated image and identify each item. This makes it possible to suggest personalized fashion coordinates according to the user's emotions.

[0943] A "user" is the entity that uses the system to input fashion styles and celebrity names, and generates coordinated outfit images.

[0944] "Input data" refers to information that users enter into the system, such as fashion styles and names of famous people.

[0945] "Emotional data" refers to information about a user's emotional state, identified by analyzing their facial expressions and text input.

[0946] A "server" is a computer system that processes input data and sentiment data received from users, and performs tasks such as generating and analyzing coordinated images and searching for items from a product database.

[0947] An "image generation model" is a technology that uses machine learning algorithms to generate coordinated images based on input data and sentiment data.

[0948] A "machine learning algorithm" is a technology that uses large amounts of data to learn and perform pattern recognition and data generation.

[0949] A "coordinate image" is an image generated by a generative AI model that visually represents a specific fashion style.

[0950] "Image recognition technology" is a technology that analyzes image data to identify specific objects or features.

[0951] A "product database" is a data storage system that contains a large amount of product information related to fashion items.

[0952] An "online marketplace" is a platform where multiple sellers and buyers can buy and sell goods over the internet.

[0953] The "item list" is a list of product items selected based on the analysis results of the coordinated outfit images.

[0954] A "terminal" is a device used by a user to interact with a system, and includes, for example, personal computers and smartphones.

[0955] This invention is a system that generates specific outfit images based on the user's input of fashion styles and celebrity outfits, and then suggests product items based on those images. Furthermore, this invention incorporates an emotion engine to provide personalized suggestions based on the user's emotions.

[0956] User input and emotion recognition

[0957] The user inputs fashion styles or celebrity names using the device's interface. For example, they might enter prompts such as "autumn casual outfits" or "celebrity styles." Simultaneously, an emotion engine is activated, analyzing the user's facial expressions and entered text to identify their emotional state, such as positive, negative, or neutral. Specifically, it uses the device's camera for facial recognition to read emotions.

[0958] Sending data

[0959] The device sends user input data and sentiment data to the server via HTTP requests. The input data and sentiment data are combined in JSON format and sent to a dedicated endpoint on the server.

[0960] Coordinate image generation

[0961] The server uses the received user input data and sentiment data to generate coordinated outfit images using an image generation model (e.g., GAN: Generative Adversarial Network). If the user has a positive sentiment, a fashion style with bright colors will be suggested. The generated images visually represent specific fashion items and are customized according to the user's needs.

[0962] Image analysis and item identification

[0963] The server analyzes the generated outfit images using image recognition technology (e.g., CNN: Convolutional Neural Networks) to automatically identify each fashion item (jacket, pants, shoes, etc.). The identified items are then organized as data for the next search step.

[0964] Item Search

[0965] The server searches its product database for items based on the identified fashion item. This product database utilizes the large data storage of the online marketplace to find products that match or are similar to the item identified by the image. The search results are listed for the user to see.

[0966] Submit search results

[0967] The server integrates the generated outfit images and the item list retrieved from the product database, and formats them into an appropriate format for transmission to the user's device. This information is compiled in JSON format and sent to the user's device.

[0968] Displaying Results

[0969] The terminal displays generated images and item lists received from the server to the user. The user can visually review these and click on links to purchase each item directly. For example, in response to a suggestion for "Autumn Casual Outfit," casual jackets, sweatpants, sneakers, and other items will be displayed.

[0970] Specific example

[0971] When a user enters "autumn casual outfit" and the emotion engine recognizes a positive emotional state, the server generates an outfit image based on this. The generated image includes a casual jacket, light-colored sweatpants, and white sneakers. The server searches the product database for these items and identifies the corresponding products. The generated outfit image and recommended product list are then sent to the terminal, where the user can review and purchase them. An example of a prompt message is, "Please enter an autumn casual outfit, generate an outfit image based on positive emotions, and suggest related products."

[0972] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0973] Step 1: User input

[0974] The user uses the terminal's interface to input fashion styles or the names of celebrities. For example, they might enter a prompt like "Autumn casual outfit." The content entered by the user in the terminal's text field is used as input data. This allows the user's desired outfit to be obtained as specific text data.

[0975] Input: Text data entered by the user on the device (e.g., "Autumn casual outfit")

[0976] Output: User input is obtained in the form of text data.

[0977] Step 2: Emotion Recognition

[0978] The device uses its built-in camera to capture the user's face when they input data, and then analyzes it using an emotion engine. As a result of the analysis, emotion data such as positive, negative, and neutral is generated.

[0979] Input: User's face image, input text

[0980] Output: Sentiment data (e.g., positive)

[0981] Step 3: Data transmission

[0982] The device collects user input data and sentiment data and sends it to the server via an HTTP request. This data is sent in JSON format to a dedicated endpoint on the server.

[0983] Input: User input data, sentiment data

[0984] Output: Data in JSON format, sent to the server.

[0985] Step 4: Generate the coordinated image

[0986] The server uses an image generation model (e.g., GAN) to generate specific outfit images based on the user's input data and sentiment data. The image parameters are adjusted according to the sentiment data. For example, if the sentiment data is positive, a fashion item with bright colors will be generated.

[0987] Input: User input data, sentiment data

[0988] Output: Coordinated image

[0989] Step 5: Image analysis and item identification

[0990] The server analyzes the generated outfit images and identifies each fashion item (e.g., jacket, pants, shoes). Using image recognition technology (e.g., CNN), it identifies items within the image and extracts information about each individual item.

[0991] Input: Coordinated image

[0992] Output: Identified item information

[0993] Step 6: Search for items

[0994] The server searches the product database for the corresponding item based on the identified item information. Specifically, it issues a query to the online marketplace database to find the corresponding product.

[0995] Input: Identified item information

[0996] Output: Product List

[0997] Step 7: Submit search results

[0998] The server combines the generated outfit images and product list and formats them into an appropriate format (JSON) for transmission to the user's device. The generated data is sent to the user's device as an HTTP response.

[0999] Input: Coordination image, product list

[1000] Output: Data sent to the user's device

[1001] Step 8: Displaying the results

[1002] The terminal displays the generated image and item list received from the server to the user. The user can purchase each item by clicking on the provided links.

[1003] Input: Data received from the server

[1004] Output: Coordinated outfit images and item list displayed to the user

[1005] As a concrete example of its operation, if a user inputs "autumn casual outfit" and the emotion engine recognizes a positive emotional state, the server generates an outfit image based on this, searches the item list, and sends and displays the generated information on the terminal. An example of a prompt message would be, "Please input an autumn casual outfit, generate an outfit image based on positive emotions, and suggest related products."

[1006] (Application Example 2)

[1007] 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."

[1008] Conventional fashion style suggestion systems only propose styles based on user input information, and do not provide personalized suggestions that take into account the user's emotional state. Furthermore, the lack of functionality to virtually try on and purchase suggested coordinated items prevented improvements in user satisfaction and the purchasing experience.

[1009] In Application Example 2, the identification processing by the identification processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for the user to input a fashion style or the name of a celebrity; means for transmitting the user's input data to the server; means for the server to generate a coordinated image using an image generation model based on the input data; means for the server to analyze the generated coordinated image and identify each item; means for the server to search for the corresponding item from a product database based on the identified item; means for the server to transmit the generated image and the searched item list to the user's terminal; means for the terminal to display the generated image and item list to the user; means for combining an emotion engine to recognize the user's emotional state and adjusting the content of the generated image and item suggestions based on the recognized emotional state; and means for displaying the generated coordinated image and suggested items in a virtual store, enabling the user to virtually try on and directly purchase the suggested items. This enables personalized fashion suggestions according to the user's emotional state, and further enables trying on and purchasing in a virtual space.

[1010] A "user" refers to an individual who uses this system to input their fashion style and the names of celebrities, and receives outfit suggestions.

[1011] "Fashion style" refers to the overall concept of coordination based on a specific theme or aesthetic sense, including clothing, accessories, and hairstyles.

[1012] A "celebrity" refers to a person who is well-known and whose style is widely recognized.

[1013] "Input data" refers to information about fashion styles and celebrity names entered by the user.

[1014] A "server" refers to a central processing unit that receives input data from users and performs tasks such as generating coordinated images and searching for product items.

[1015] An "image generation model" refers to an algorithm or software that uses machine learning algorithms to generate specific coordinated images based on user input.

[1016] A "coordinate image" refers to an image that shows a visual example of fashion generated based on the user's input data.

[1017] An "emotion engine" refers to software or hardware that recognizes a user's emotional state from their facial expressions and input, and reflects that in the system's operation.

[1018] A "product database" refers to a collection of data related to fashion items stored within an online marketplace.

[1019] A "virtual store" refers to a virtual shopping space that users can access on the internet.

[1020] An "item list" refers to a list of items retrieved from the product database that correspond to the fashion items identified within the generated outfit image.

[1021] "Virtual try-on" refers to a feature that allows users to virtually try on fashion items suggested within a virtual store and check how they look.

[1022] Explanation of program generation and processing

[1023] This invention implements a system in which a user inputs a fashion style or the name of a celebrity, and a server generates coordinated images based on that input data and suggests appropriate items.

[1024] Hardware and software configuration

[1025] Hardware: Smartphone or PC, server, camera for acquiring user facial images.

[1026] Software: Python, face_recognition library, TensorFlow, Requests, Pillow

[1027] 1. User Input and Sentiment Recognition

[1028] The user uses their smartphone or computer to input a fashion style (e.g., "Spring casual outfit") or the name of a celebrity. Next, they provide a facial image using their smartphone's camera or an image file on their device. The emotion engine uses the face_recognition library and an emotion recognition model (built using TensorFlow) to identify emotions from the user's facial image.

[1029] 2. Server-side processing

[1030] The server receives user input data (fashion style or celebrity name) and sentiment data. The server then uses machine learning algorithms to generate outfit images. Furthermore, it analyzes the generated outfit images to identify specific fashion items. Based on the identified items, it searches for the corresponding items in its product database (related to the online marketplace).

[1031] 3. Sending and displaying results to the user

[1032] The server sends the generated outfit image and the searched item list to the user's device. The user's device receives this information and displays the generated image and item list. Within the virtual store, the user can visually confirm the generated outfit image and suggested items, virtually try on the suggested items, and purchase them directly.

[1033] Specific examples of usage

[1034] For example, if a user enters "spring casual outfit" and the emotion engine recognizes a positive emotional state, the server uses a machine learning algorithm to generate an outfit image based on the received data. This image would include a casual jacket, shirt, and pants in bright colors. Furthermore, the server analyzes the image and lists the corresponding items from the online marketplace's product database. The generated outfit image is then displayed on the terminal along with suggested items, and the user can purchase each item directly.

[1035] Example of a prompt

[1036] 1. "Please suggest a casual spring outfit. My current emotional state is positive."

[1037] 2. "Please enter the style of a famous person (e.g., a famous singer). Your current emotional state is neutral."

[1038] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1039] Step 1:

[1040] The user enters a fashion style or the name of a celebrity. Specifically, the user uses a smartphone or computer to enter keywords such as "spring casual outfit" or "famous singer" into the application's input form. The input data is saved on the device as string data.

[1041] Step 2:

[1042] The user provides a facial image. Specifically, the user either takes a picture of their face with their smartphone camera or uploads a facial image file stored on their device. The image data is saved in JPEG or PNG format and imported as input data for the application.

[1043] Step 3:

[1044] The emotion engine analyzes the user's facial image and recognizes their emotional state. Specifically, it uses the face_recognition library on the device to determine the position of the face, and then uses TensorFlow to estimate the emotional state using an emotion recognition model. The input is facial image data, and the output is the emotional state (positive, negative, neutral, etc.). For example, if the model detects a smile, it is recognized as a positive emotional state.

[1045] Step 4:

[1046] The device sends user input data and emotional data to the server. Specifically, it sends the entered fashion style, celebrity names, and recognized emotional states to a dedicated endpoint on the server via an HTTP request. The transmitted data is in JSON format and is received by the server.

[1047] Step 5:

[1048] The server generates coordinated outfit images based on the input data it receives. Specifically, it uses a machine learning algorithm (generative AI model) running on the server to generate fashion coordinated outfit images based on the user's input data and sentiment data. The input is user data and sentiment data, and the output is the generated coordinated outfit image.

[1049] Step 6:

[1050] The server analyzes the generated outfit image to identify each item. Specifically, it uses image recognition technology to analyze the generated image and identify each fashion item (jacket, shirt, pants, etc.). The input is the latest generated outfit image, and the output is item information. For example, it automatically identifies shirts, pants, shoes, etc., in an image.

[1051] Step 7:

[1052] The server searches the product database for items based on the identified item. Specifically, it queries the product database (online marketplace) to retrieve product information (name, price, purchase link, etc.) that matches the identified item. The input is the information of the identified item, and the output is a list of matching product information.

[1053] Step 8:

[1054] The server sends the generated image and the searched item list to the user's device. Specifically, it sends a list of product information matching the generated outfit image to the device as an HTTP response in JSON format. The transmitted data includes the URL of the generated image and the item list.

[1055] Step 9:

[1056] The device displays the generated image and item list to the user. Specifically, it displays the coordinated outfit image generated within the application, allowing for visual confirmation along with the suggested item list. Users can virtually try on the suggested items using the virtual try-on function and purchase them directly by clicking the displayed purchase link. The input is data received from the server, and the output is the displayed coordinated outfit image and item list.

[1057] 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.

[1058] 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.

[1059] 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.

[1060] [Fourth Embodiment]

[1061] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1062] 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.

[1063] 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).

[1064] 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.

[1065] 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.

[1066] 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).

[1067] 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.

[1068] 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.

[1069] 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.

[1070] 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.

[1071] 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.

[1072] 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.

[1073] 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".

[1074] This invention is a system that generates specific outfit images based on the user's input of fashion styles and celebrity outfits, and then suggests product items based on those images.

[1075] 1. User input

[1076] When using this system, users are first required to enter a fashion style or the name of a celebrity. For example, specific requests such as "autumn casual outfit" or "celebrity style" are possible. This input is performed on the terminal's interface.

[1077] 2. Sending data

[1078] The terminal sends user input data to the server. HTTP requests are used for transmission, and the entered data is sent to a dedicated endpoint on the server.

[1079] 3. Generating the coordinated image

[1080] The server generates coordinated outfit images using an image generation model based on the user's input data. This image generation model employs machine learning algorithms to reproduce specific fashion styles based on user input, as well as typical styles of celebrities.

[1081] 4. Image analysis and item identification

[1082] The server analyzes the generated outfit images and identifies each fashion item (e.g., jacket, pants, shoes, etc.). Image recognition technology is used for this analysis.

[1083] 5. Search for items

[1084] The server searches its product database for items based on the identified item. This database contains a large amount of product information, such as from online marketplaces, and finds products that match or are similar to each item identified by its image.

[1085] 6. Submit search results

[1086] The server sends the generated outfit images and the searched item list to the user's device. This allows the user to receive visuals of the suggested fashion style and a specific product list based on that style.

[1087] 7. Displaying the results

[1088] The device displays the received generated images and item list to the user. Through this display, the user can see specific fashion styles they desire and can also use links to directly purchase the suggested products.

[1089] As a concrete example, when a user enters "autumn casual outfit," the server generates an outfit image using a generated image model based on the received data. This image includes items such as a casual jacket, sweatpants, and sneakers. The server analyzes these items and searches for related products in its database, listing them. The generated outfit image is then displayed on the terminal along with these products, allowing the user to directly purchase the suggested items.

[1090] The following describes the processing flow.

[1091] Step 1:

[1092] The user enters a fashion style or the name of a celebrity. For example, the user might enter "Autumn casual outfit."

[1093] Step 2:

[1094] The terminal sends the user's input data to the server. Specifically, it sends the input data to the server as an HTTP POST request.

[1095] Step 3:

[1096] The server receives user input data. The server analyzes the input data and prepares it to be passed to the image generation model.

[1097] Step 4:

[1098] The server generates coordinated images using an image generation model. The image generation model outputs images that reproduce a specific fashion style based on the input style.

[1099] Step 5:

[1100] The server analyzes the generated outfit image and identifies each fashion item. Specifically, it uses image recognition technology to detect items such as jackets, pants, and shoes within the image and extracts their information.

[1101] Step 6:

[1102] The server searches the product database for the corresponding item based on each identified item. The server sends a search query to the online marketplace's API and retrieves the relevant products.

[1103] Step 7:

[1104] The server combines the generated outfit images with the item list retrieved from the product database. The server then formats this information into a format suitable for sending to the user's terminal.

[1105] Step 8:

[1106] The server sends the generated image and item list to the user's device. Specifically, it returns this data as an HTTP response.

[1107] Step 9:

[1108] The device displays the generated image and item list received from the server to the user. The user can review the generated outfit image and suggested items and access purchase links for each item.

[1109] (Example 1)

[1110] 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".

[1111] Conventional fashion suggestion systems had problems such as making it difficult for users to visually imagine specific outfits, and failing to adequately suggest products based on those outfits. In particular, it was difficult to generate specific outfit images based on the fashion style desired by the user or the style of a celebrity, and to quickly and accurately suggest products related to those images.

[1112] 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.

[1113] In this invention, the server includes means for the user to input a fashion style or observations of a celebrity; means for transmitting the user's input data to a server facility; means for the server facility to generate a coordinated image using an image generation algorithm based on the input data; means for the server facility to analyze the generated coordinated image and identify each item; means for the server facility to search for the corresponding item from a product information database based on the identified item; means for the server facility to transmit the generated image and the searched item list to the user's terminal device; and means for the terminal device to display the generated image and item list to the user. As a result, the user can simply input their desired fashion style or celebrity coordinated outfit, generate a specific coordinated image based on it, analyze the image to identify each item, and quickly and accurately suggest related products.

[1114] A "user" refers to a person who uses this system to input observations about fashion styles or celebrities.

[1115] A "terminal device" refers to an electronic device used by a user to input information and receive display results. Examples include smartphones, personal computers, and tablets.

[1116] A "server facility" refers to a computer system that has the function of receiving data sent from users, generating and analyzing images, searching for corresponding product information, and sending it to the user's terminal device.

[1117] An "image generation algorithm" refers to a machine learning algorithm used to generate coordinated images based on user input data. Examples include Generative Adversarial Networks (GANs).

[1118] "Coordinate images" refer to images that visually represent generated fashion styles or the styles of celebrities.

[1119] "Image recognition technology" refers to techniques for analyzing images and identifying each fashion item contained within them. Examples include YOLO and ResNet.

[1120] A "product information database" refers to a database that provides information about searched items. It is related to online sales websites.

[1121] An "item list" refers to a list of product information searched based on the generated outfit images, organized in a list format.

[1122] This invention is a system that generates specific outfit images and suggests related product items based on the user's input of fashion styles and celebrity styles. This system primarily operates with a server, terminal devices, and users.

[1123] User input

[1124] Users access the system interface using a terminal device (e.g., smartphone, PC, tablet) and input fashion styles or celebrity styles. For example, they can enter specific prompts such as "autumn casual outfit" or "a certain celebrity's style."

[1125] Sending data

[1126] The terminal device transmits the data entered by the user to the server facility. This transmission uses an HTTP POST request, and the input data is sent to the server facility in JSON format.

[1127] Coordinate image generation

[1128] The server facility generates coordinated images based on the received data using a generative AI model (e.g., StyleGAN). This generative AI model utilizes machine learning algorithms to generate highly relevant images based on the prompt text received from the user.

[1129] Image analysis and item identification

[1130] The generated outfit images are analyzed by a server facility to identify each fashion item (e.g., jacket, pants, shoes, etc.). Image recognition technology (e.g., YOLO or ResNet) is used for this analysis.

[1131] Item Search

[1132] The server facility searches for the corresponding product in the product information database based on the identified item. This database includes product information obtained from online sales sites and other sources.

[1133] Submit search results

[1134] The server facility sends the generated coordinated images and the searched product list to the terminal device. The transmitted data is in JSON format, and the terminal device receives and processes it.

[1135] Displaying Results

[1136] The terminal device displays the received generated images and item list to the user. Based on the displayed content, the user can visualize their desired fashion style and directly purchase the suggested products.

[1137] Specific example

[1138] For example, if a user enters "casual autumn outfit," the server facility uses this data to generate an outfit image using an AI model. The generated image will include items such as a casual jacket, sweatpants, and sneakers. The server facility analyzes these items and searches for related products in its product information database, listing them. Subsequently, the item list is displayed on the terminal device along with the generated outfit image, allowing the user to directly purchase the suggested items.

[1139] In this way, the present invention provides a system that quickly and accurately suggests the fashion style desired by the user and facilitates the purchase of related products based on that style.

[1140] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1141] Step 1:

[1142] Users input their observations of fashion styles and celebrities using a terminal device. For example, they can enter a prompt such as "Autumn casual outfit." Input is entered directly into the text field, and clicking the "Submit" button proceeds to the next step.

[1143] Input: Observations of fashion styles and celebrities (text format)

[1144] Output: Data entered by the user

[1145] Step 2:

[1146] The terminal device sends the data entered by the user to the server facility using an HTTP POST request. The input data is converted to JSON format and sent to the specified API endpoint.

[1147] Specific operation: The terminal device sends the following JSON data to the server facility.

[1148] json

[1149] {

[1150] "prompt": "Autumn casual outfit"

[1151] }

[1152] Input: Data entered by the user (prompt text)

[1153] Output: JSON data sent to the server facility

[1154] Step 3:

[1155] The server facility passes the received data to the generating AI model, which then generates coordinated images. The generating AI model uses a machine learning algorithm (e.g., StyleGAN) to generate images based on the input prompt text.

[1156] Specific operation: The server facility calls the generated AI model and generates images based on "autumn casual outfits".

[1157] Input: JSON data received by the server facility

[1158] Output: Generated coordinated image

[1159] Step 4:

[1160] The server facility passes the generated coordinated image to image recognition technology to identify each item. Specifically, it uses image recognition algorithms (e.g., YOLO or ResNet) to detect items such as jackets, pants, and shoes within the image.

[1161] Specific operation: The server facility applies image recognition technology and labels each fashion item from the generated images.

[1162] Input: Generated coordinate image

[1163] Output: A list of identified items (e.g., "jacket", "pants", "shoes")

[1164] Step 5:

[1165] The server facility searches the product information database for the corresponding product based on the identified item. The search query includes the category and characteristics of each item (e.g., color, material, etc.).

[1166] Specific operation: The server facility generates a database search query and retrieves a list of matching products.

[1167] Input: List of identified items

[1168] Output: List of relevant products

[1169] Step 6:

[1170] The server facility reconstructs the generated coordinated images and searched product lists into JSON format and sends them to the user's terminal device. This data includes the URLs of the generated images and the product lists.

[1171] Specific operation: The server facility sends the following JSON data to the terminal device.

[1172] json

[1173] {

[1174] "image_url": "https: / / cdn.example.com / generated-image.jpg",

[1175] "items": [

[1176] {"name": "Casual Jacket", "link": "https: / / shop.example.com / item123"},

[1177] {"name": "Sweatpants", "link": "https: / / shop.example.com / item456"},

[1178] {"name": "Sneakers", "link": "https: / / shop.example.com / item789"}

[1179] ]

[1180] }

[1181] Input: Generated outfit images and searched product list

[1182] Output: JSON data sent to the user's terminal device.

[1183] Step 7:

[1184] The terminal device displays the received generated images and product list to the user. This allows the user to visualize their desired fashion style and access links to directly purchase suggested products.

[1185] Specific operation: The terminal device displays images and a product list on the user interface.

[1186] Input: JSON data received from the server facility

[1187] Output: Generated image and product list displayed on the terminal device.

[1188] Through these steps, users can view specific outfit images based on their entered fashion style and receive quick and accurate suggestions for related products.

[1189] (Application Example 1)

[1190] 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".

[1191] Conventional fashion coordination systems have problems such as difficulty in easily recreating the style preferred by the user or the fashion of a specific celebrity, and the need to manually search for each item, which is time-consuming for the user. In addition, the methods for displaying the generated coordination image and related items are limited, and there is insufficient support for users to make quick purchase decisions. The present invention aims to solve these problems and provide a system that automatically generates coordination images using a generation AI model based on the fashion style entered by the user or the style of a celebrity, and further allows the user to easily purchase the suggested items.

[1192] 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.

[1193] In this invention, the server includes means for the user to input a fashion style or the name of a celebrity, means for transmitting the user's input data to the server, and means for generating a coordinated image using a generative AI model. This makes it possible to search for the corresponding items from a product database based on the generated coordinated image and identified items, transmit them to the user's terminal, and provide a link to directly purchase the suggested items.

[1194] A "user" is someone who uses the system to input fashion styles and celebrity names, and then receives suggested outfits and products.

[1195] "Fashion style" refers to a combination of clothing and accessories that are suited to a specific theme, season, or occasion.

[1196] "Celebrity names" refer to the names of specific famous people or entertainers, and are information used to help the system recognize the typical clothing and style of that person.

[1197] "Input data" refers to information that users enter into the system, such as fashion styles and names of famous people.

[1198] A "server" refers to a computer system that receives user input data, generates coordinated images using a generation AI model, and is also responsible for analyzing the generated images and linking them with a product database.

[1199] A "generative AI model" is a model that uses machine learning algorithms to reproduce specific fashion styles or celebrity styles based on user input.

[1200] "Coordinate images" are images that visually represent fashion styles or celebrity styles created using generative AI models.

[1201] "Analysis" refers to the process of analyzing the generated outfit images and identifying each fashion item within those images.

[1202] "Items" refer to individual clothing items, accessories, and other products identified within a coordinated outfit image.

[1203] A "product database" refers to a database that holds a large amount of product information, such as that found on online marketplaces.

[1204] "Searching" refers to the process of finding products that match or are similar to a specific item within a product database.

[1205] The "item list" refers to the collection of all items that the server searches for based on the generated outfit image and provides to the user.

[1206] "Terminal" refers to a device such as a smartphone or computer used by the user, and is used to display the generated outfit images and item lists.

[1207] A "link" is a hyperlink that a user can click to directly purchase a suggested item.

[1208] This invention is a system that generates coordinated outfit images using a generative AI model based on fashion styles entered by the user and the styles of celebrities, and suggests related products. This system mainly consists of a server, a user terminal, and a program.

[1209] Overall system configuration

[1210] The system includes means for the user to input a fashion style or the name of a celebrity, means for sending the user's input data to a server, means for generating a coordinated image using a generative AI model, means for analyzing the generated coordinated image to identify each item, means for searching for the corresponding item from a product database based on the identified item, means for sending the generated image and the list of searched items to the user's terminal, and means for displaying the generated image and the list of items to the user and providing a link for the user to directly purchase the suggested items.

[1211] Program Configuration

[1212] The server uses the Flask web framework and PIL (Python Imaging Library). The main data processing in this system is as follows:

[1213] 1. User Input: Users use their devices to input fashion styles or the names of specific celebrities. For example, they can specify things like "autumn casual outfits" or "celebrity styles."

[1214] 2. Data transmission: User input data is sent from the terminal to the server as an HTTP request.

[1215] 3. Coordinate Image Generation: Based on the user's input data received, the server generates coordinate images using a generative AI model. This image generation model employs machine learning algorithms to reproduce specific fashion styles based on user input, as well as typical styles of celebrities.

[1216] 4. Image Analysis and Item Identification: The server analyzes the generated outfit images and identifies each fashion item (e.g., jacket, pants, shoes). Image recognition technology is used for this analysis.

[1217] 5. Item Search: The server searches for the corresponding item from the product database (e.g., online marketplace) based on the specified item.

[1218] 6. Sending search results: The server sends the generated outfit images and the list of searched items to the user's device.

[1219] 7. Display of Results: The user's device displays the received generated images and item list to the user. Through this display, the user can see the specific fashion style they desire and also use links to directly purchase the suggested products.

[1220] Specific example

[1221] When a user enters "autumn casual outfit," the server uses an AI model to generate an outfit image based on the received data. This image includes items such as a casual jacket, sweatpants, and sneakers. The server analyzes these items and searches its database for related products, listing them. The generated outfit image is then displayed on the user's device along with these products, allowing the user to directly purchase the suggested items.

[1222] Examples of prompts to input into a generative AI model are as follows:

[1223] "Create a casual autumn outfit. A style including a gray jacket, sweatpants, and white sneakers."

[1224] In this way, the present invention allows users to easily and quickly find their desired fashion style and purchase related products online.

[1225] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1226] Step 1:

[1227] The user uses their device to input fashion styles or celebrity names on the application interface. This input is in text format. For example, let's say the user inputs "Autumn casual outfit." The device then sends this input data to the next step.

[1228] Step 2:

[1229] The terminal sends the entered fashion style and celebrity name to the server as an HTTP request. The server parses the received HTTP request and extracts the user's input data (fashion style and celebrity name in text format). This data is used in the next step.

[1230] Step 3:

[1231] The server creates a prompt message for the generating AI model based on the received input data. For example, if the input data is "autumn casual outfit," the server will generate the prompt message, "Generate an autumn casual outfit. A style including a gray jacket, sweatpants, and white sneakers." This prompt message is then input into the generating AI model.

[1232] Step 4:

[1233] The server uses a generative AI model to generate a coordinated image based on the prompt text. The generative AI model uses a machine learning algorithm to generate the image according to the content described in the prompt text. The generated coordinated image is obtained as output. This image will proceed to the next step.

[1234] Step 5:

[1235] The server analyzes the generated outfit image and uses image recognition technology to identify each fashion item (e.g., jacket, pants, shoes). The analysis yields a list of identified items. For example, items such as "gray jacket, sweatpants, white sneakers" might be identified.

[1236] Step 6:

[1237] The server searches its product database for items based on the identified item. This database contains a large amount of product information, including online marketplaces, and searches for products that match or are similar to each identified item. The search results provide a list of products. For example, a list is generated that includes links such as "Gray Jacket - URL", "Sweatpants - URL", and "White Sneakers - URL".

[1238] Step 7:

[1239] The server sends the generated outfit image and the searched item list to the user's device. An HTTP response is used for this transmission. The device receives this response and uses it in the next step.

[1240] Step 8:

[1241] The device displays the received generated outfit images and item list to the user. The user can review the displayed images and access purchase links directly through the list of suggested items. This allows the user to easily visualize their desired fashion style and utilize links to purchase related products.

[1242] 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.

[1243] This invention is a system that generates specific outfit images based on the user's input of fashion styles and celebrity outfits, and then suggests product items based on those images. Furthermore, this invention combines an emotion engine to provide personalized suggestions based on the user's emotions.

[1244] User input and emotion recognition

[1245] When a user uses this system, they are first required to enter a fashion style or the name of a celebrity. For example, the user might enter "autumn casual outfit" or "celebrity style." This input is done through the terminal's interface.

[1246] Simultaneously, the emotion engine analyzes the user's facial recognition and input data to recognize the user's emotions. Based on the information obtained from the user's facial expressions and input content, the emotion engine identifies an emotional state such as positive, negative, or neutral.

[1247] Sending data

[1248] The device sends user input data and sentiment data to the server. HTTP requests are used for transmission, and the input data is sent to a dedicated endpoint on the server.

[1249] Coordinate image generation

[1250] The server generates coordinated outfit images using an image generation model based on the user's input data and emotional data. This image generation model uses machine learning algorithms to reproduce specific fashion styles based on user input and typical styles of celebrities. It also adjusts the parameters of the generated coordinated outfit images based on the user's emotional data. For example, if the user is in a positive emotional state, a fashion style with bright colors may be suggested.

[1251] Image analysis and item identification

[1252] The server analyzes the generated outfit images and identifies each fashion item (e.g., jacket, pants, shoes). This analysis uses image recognition technology to automatically detect items within the image and organize their information.

[1253] Item Search

[1254] The server searches its product database for items based on the identified item. This database contains a large amount of product information from online marketplaces and finds products that match or are similar to each item identified by its image.

[1255] Submit search results

[1256] The server combines the generated outfit images with the item list retrieved from the product database. The server then formats this information into a format suitable for sending to the user's terminal and returns the appropriate information to the user.

[1257] Displaying Results

[1258] The terminal displays the generated image and item list received from the server to the user. The user can visually review the generated outfit image and suggested items, and will have access to links to purchase each item directly.

[1259] Specific example

[1260] If a user enters "casual autumn outfit" and the emotion engine recognizes a positive emotional state, the server generates an outfit image using a generated image model based on the received data. This image includes a casual jacket, sweatpants, and sneakers. Furthermore, the server analyzes the image to search for and list related products. The generated outfit image is then displayed on the device along with suggested items, and the user can purchase each item directly. If the user is in a negative emotional state, an outfit with more subdued colors may be suggested.

[1261] The following describes the processing flow.

[1262] Step 1:

[1263] The user enters a fashion style or the name of a celebrity. For example, the user might enter "Autumn casual outfit."

[1264] Step 2:

[1265] The device sends user input data to the emotion engine. The emotion engine analyzes the user's input and facial expressions.

[1266] Step 3:

[1267] The emotion engine recognizes the user's emotions and identifies them as positive, negative, neutral, etc. For example, if the user is smiling while typing, it recognizes this as a positive emotion.

[1268] Step 4:

[1269] The device sends user input data and sentiment data to the server. HTTP requests are used for transmission.

[1270] Step 5:

[1271] The server receives user input data and sentiment data. The server analyzes the input data and prepares it to be passed to the image generation model.

[1272] Step 6:

[1273] The server generates coordinated outfit images using an image generation model. The image generation model uses machine learning algorithms to recreate fashion styles based on user input and emotions.

[1274] Step 7:

[1275] The server analyzes the generated outfit image and identifies each fashion item. Specifically, it uses image recognition technology to detect items such as jackets, pants, and shoes within the image.

[1276] Step 8:

[1277] The server searches the product database for items based on the identified item. For example, it might use an online marketplace API to retrieve similar products.

[1278] Step 9:

[1279] The server combines the generated outfit images with the item list retrieved from the product database. The server then formats this information for transmission to the user's terminal.

[1280] Step 10:

[1281] The server sends the generated image and item list to the user's device. Specifically, it returns this data as an HTTP response.

[1282] Step 11:

[1283] The terminal displays the generated image and item list received from the server to the user. The user can review the generated outfit image and suggested items and access purchase links for each item.

[1284] As a concrete example, if a user enters "autumn casual outfit" and shows a positive emotion with a smile, the server will generate an image including a brightly colored jacket, sweatpants, and sneakers. This image is then analyzed to retrieve relevant products from the product database and suggest them to the user. The user can then review and purchase these suggested items.

[1285] (Example 2)

[1286] 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".

[1287] Current fashion coordination systems offer only simple item suggestions without considering the user's emotions. Therefore, it is difficult to suggest outfits that suit the user's feelings or mood on any given day. Furthermore, the need for manual item selection and searching limits the user experience.

[1288] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for transmitting user input data and emotion data to the server, means for the server to generate a coordinated image using an image generation model based on the input data and emotion data, and means for the server to analyze the generated coordinated image and identify each item. This makes it possible to suggest personalized fashion coordinates according to the user's emotions.

[1289] A "user" is the entity that uses the system to input fashion styles and celebrity names, and generates coordinated outfit images.

[1290] "Input data" refers to information that users enter into the system, such as fashion styles and names of famous people.

[1291] "Emotional data" refers to information about a user's emotional state, identified by analyzing their facial expressions and text input.

[1292] A "server" is a computer system that processes input data and sentiment data received from users, and performs tasks such as generating and analyzing coordinated images and searching for items from a product database.

[1293] An "image generation model" is a technology that uses machine learning algorithms to generate coordinated images based on input data and sentiment data.

[1294] A "machine learning algorithm" is a technology that uses large amounts of data to learn and perform pattern recognition and data generation.

[1295] A "coordinate image" is an image generated by a generative AI model that visually represents a specific fashion style.

[1296] "Image recognition technology" is a technology that analyzes image data to identify specific objects or features.

[1297] A "product database" is a data storage system that contains a large amount of product information related to fashion items.

[1298] An "online marketplace" is a platform where multiple sellers and buyers can buy and sell goods over the internet.

[1299] The "item list" is a list of product items selected based on the analysis results of the coordinated outfit images.

[1300] A "terminal" is a device used by a user to interact with a system, and includes, for example, personal computers and smartphones.

[1301] This invention is a system that generates specific outfit images based on the user's input of fashion styles and celebrity outfits, and then suggests product items based on those images. Furthermore, this invention incorporates an emotion engine to provide personalized suggestions based on the user's emotions.

[1302] User input and emotion recognition

[1303] The user inputs fashion styles or celebrity names using the device's interface. For example, they might enter prompts such as "autumn casual outfits" or "celebrity styles." Simultaneously, an emotion engine is activated, analyzing the user's facial expressions and entered text to identify their emotional state, such as positive, negative, or neutral. Specifically, it uses the device's camera for facial recognition to read emotions.

[1304] Sending data

[1305] The device sends user input data and sentiment data to the server via HTTP requests. The input data and sentiment data are combined in JSON format and sent to a dedicated endpoint on the server.

[1306] Coordinate image generation

[1307] The server uses the received user input data and sentiment data to generate coordinated outfit images using an image generation model (e.g., GAN: Generative Adversarial Network). If the user has a positive sentiment, a fashion style with bright colors will be suggested. The generated images visually represent specific fashion items and are customized according to the user's needs.

[1308] Image analysis and item identification

[1309] The server analyzes the generated outfit images using image recognition technology (e.g., CNN: Convolutional Neural Networks) to automatically identify each fashion item (jacket, pants, shoes, etc.). The identified items are then organized as data for the next search step.

[1310] Item Search

[1311] The server searches its product database for items based on the identified fashion item. This product database utilizes the large data storage of the online marketplace to find products that match or are similar to the item identified by the image. The search results are listed for the user to see.

[1312] Submit search results

[1313] The server integrates the generated outfit images and the item list retrieved from the product database, and formats them into an appropriate format for transmission to the user's device. This information is compiled in JSON format and sent to the user's device.

[1314] Displaying Results

[1315] The terminal displays generated images and item lists received from the server to the user. The user can visually review these and click on links to purchase each item directly. For example, in response to a suggestion for "Autumn Casual Outfit," casual jackets, sweatpants, sneakers, and other items will be displayed.

[1316] Specific example

[1317] When a user enters "autumn casual outfit" and the emotion engine recognizes a positive emotional state, the server generates an outfit image based on this. The generated image includes a casual jacket, light-colored sweatpants, and white sneakers. The server searches the product database for these items and identifies the corresponding products. The generated outfit image and recommended product list are then sent to the terminal, where the user can review and purchase them. An example of a prompt message is, "Please enter an autumn casual outfit, generate an outfit image based on positive emotions, and suggest related products."

[1318] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1319] Step 1: User input

[1320] The user uses the terminal's interface to input fashion styles or the names of celebrities. For example, they might enter a prompt like "Autumn casual outfit." The content entered by the user in the terminal's text field is used as input data. This allows the user's desired outfit to be obtained as specific text data.

[1321] Input: Text data entered by the user on the device (e.g., "Autumn casual outfit")

[1322] Output: User input is obtained in the form of text data.

[1323] Step 2: Emotion Recognition

[1324] The device uses its built-in camera to capture the user's face when they input data, and then analyzes it using an emotion engine. As a result of the analysis, emotion data such as positive, negative, and neutral is generated.

[1325] Input: User's face image, input text

[1326] Output: Sentiment data (e.g., positive)

[1327] Step 3: Data transmission

[1328] The device collects user input data and sentiment data and sends it to the server via an HTTP request. This data is sent in JSON format to a dedicated endpoint on the server.

[1329] Input: User input data, sentiment data

[1330] Output: Data in JSON format, sent to the server.

[1331] Step 4: Generate the coordinated image

[1332] The server uses an image generation model (e.g., GAN) to generate specific outfit images based on the user's input data and sentiment data. The image parameters are adjusted according to the sentiment data. For example, if the sentiment data is positive, a fashion item with bright colors will be generated.

[1333] Input: User input data, sentiment data

[1334] Output: Coordinated image

[1335] Step 5: Image analysis and item identification

[1336] The server analyzes the generated outfit images and identifies each fashion item (e.g., jacket, pants, shoes). Using image recognition technology (e.g., CNN), it identifies items within the image and extracts information about each individual item.

[1337] Input: Coordinated image

[1338] Output: Identified item information

[1339] Step 6: Search for items

[1340] The server searches the product database for the corresponding item based on the identified item information. Specifically, it issues a query to the online marketplace database to find the corresponding product.

[1341] Input: Identified item information

[1342] Output: Product List

[1343] Step 7: Submit search results

[1344] The server combines the generated outfit images and product list and formats them into an appropriate format (JSON) for transmission to the user's device. The generated data is sent to the user's device as an HTTP response.

[1345] Input: Coordination image, product list

[1346] Output: Data sent to the user's device

[1347] Step 8: Displaying the results

[1348] The terminal displays the generated image and item list received from the server to the user. The user can purchase each item by clicking on the provided links.

[1349] Input: Data received from the server

[1350] Output: Coordinated outfit images and item list displayed to the user

[1351] As a concrete example of its operation, if a user inputs "autumn casual outfit" and the emotion engine recognizes a positive emotional state, the server generates an outfit image based on this, searches the item list, and sends and displays the generated information on the terminal. An example of a prompt message would be, "Please input an autumn casual outfit, generate an outfit image based on positive emotions, and suggest related products."

[1352] (Application Example 2)

[1353] 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".

[1354] Conventional fashion style suggestion systems only propose styles based on user input information, and do not provide personalized suggestions that take into account the user's emotional state. Furthermore, the lack of functionality to virtually try on and purchase suggested coordinated items prevented improvements in user satisfaction and the purchasing experience.

[1355] In Application Example 2, the identification processing by the identification processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for the user to input a fashion style or the name of a celebrity; means for transmitting the user's input data to the server; means for the server to generate a coordinated image using an image generation model based on the input data; means for the server to analyze the generated coordinated image and identify each item; means for the server to search for the corresponding item from a product database based on the identified item; means for the server to transmit the generated image and the searched item list to the user's terminal; means for the terminal to display the generated image and item list to the user; means for combining an emotion engine to recognize the user's emotional state and adjusting the content of the generated image and item suggestions based on the recognized emotional state; and means for displaying the generated coordinated image and suggested items in a virtual store, enabling the user to virtually try on and directly purchase the suggested items. This enables personalized fashion suggestions according to the user's emotional state, and further enables trying on and purchasing in a virtual space.

[1356] A "user" refers to an individual who uses this system to input their fashion style and the names of celebrities, and receives outfit suggestions.

[1357] "Fashion style" refers to the overall concept of coordination based on a specific theme or aesthetic sense, including clothing, accessories, and hairstyles.

[1358] A "celebrity" refers to a person who is well-known and whose style is widely recognized.

[1359] "Input data" refers to information about fashion styles and celebrity names entered by the user.

[1360] A "server" refers to a central processing unit that receives input data from users and performs tasks such as generating coordinated images and searching for product items.

[1361] An "image generation model" refers to an algorithm or software that uses machine learning algorithms to generate specific coordinated images based on user input.

[1362] A "coordinate image" refers to an image that shows a visual example of fashion generated based on the user's input data.

[1363] An "emotion engine" refers to software or hardware that recognizes a user's emotional state from their facial expressions and input, and reflects that in the system's operation.

[1364] A "product database" refers to a collection of data related to fashion items stored within an online marketplace.

[1365] A "virtual store" refers to a virtual shopping space that users can access on the internet.

[1366] An "item list" refers to a list of items retrieved from the product database that correspond to the fashion items identified within the generated outfit image.

[1367] "Virtual try-on" refers to a feature that allows users to virtually try on fashion items suggested within a virtual store and check how they look.

[1368] Explanation of program generation and processing

[1369] This invention implements a system in which a user inputs a fashion style or the name of a celebrity, and a server generates coordinated images based on that input data and suggests appropriate items.

[1370] Hardware and software configuration

[1371] Hardware: Smartphone or PC, server, camera for acquiring user facial images.

[1372] Software: Python, face_recognition library, TensorFlow, Requests, Pillow

[1373] 1. User Input and Sentiment Recognition

[1374] The user uses their smartphone or computer to input a fashion style (e.g., "Spring casual outfit") or the name of a celebrity. Next, they provide a facial image using their smartphone's camera or an image file on their device. The emotion engine uses the face_recognition library and an emotion recognition model (built using TensorFlow) to identify emotions from the user's facial image.

[1375] 2. Server-side processing

[1376] The server receives user input data (fashion style or celebrity name) and sentiment data. The server then uses machine learning algorithms to generate outfit images. Furthermore, it analyzes the generated outfit images to identify specific fashion items. Based on the identified items, it searches for the corresponding items in its product database (related to the online marketplace).

[1377] 3. Sending and displaying results to the user

[1378] The server sends the generated outfit image and the searched item list to the user's device. The user's device receives this information and displays the generated image and item list. Within the virtual store, the user can visually confirm the generated outfit image and suggested items, virtually try on the suggested items, and purchase them directly.

[1379] Specific examples of usage

[1380] For example, if a user enters "spring casual outfit" and the emotion engine recognizes a positive emotional state, the server uses a machine learning algorithm to generate an outfit image based on the received data. This image would include a casual jacket, shirt, and pants in bright colors. Furthermore, the server analyzes the image and lists the corresponding items from the online marketplace's product database. The generated outfit image is then displayed on the terminal along with suggested items, and the user can purchase each item directly.

[1381] Example of a prompt

[1382] 1. "Please suggest a casual spring outfit. My current emotional state is positive."

[1383] 2. "Please enter the style of a famous person (e.g., a famous singer). Your current emotional state is neutral."

[1384] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1385] Step 1:

[1386] The user enters a fashion style or the name of a celebrity. Specifically, the user uses a smartphone or computer to enter keywords such as "spring casual outfit" or "famous singer" into the application's input form. The input data is saved on the device as string data.

[1387] Step 2:

[1388] The user provides a facial image. Specifically, the user either takes a picture of their face with their smartphone camera or uploads a facial image file stored on their device. The image data is saved in JPEG or PNG format and imported as input data for the application.

[1389] Step 3:

[1390] The emotion engine analyzes the user's facial image and recognizes their emotional state. Specifically, it uses the face_recognition library on the device to determine the position of the face, and then uses TensorFlow to estimate the emotional state using an emotion recognition model. The input is facial image data, and the output is the emotional state (positive, negative, neutral, etc.). For example, if the model detects a smile, it is recognized as a positive emotional state.

[1391] Step 4:

[1392] The device sends user input data and emotional data to the server. Specifically, it sends the entered fashion style, celebrity names, and recognized emotional states to a dedicated endpoint on the server via an HTTP request. The transmitted data is in JSON format and is received by the server.

[1393] Step 5:

[1394] The server generates coordinated outfit images based on the input data it receives. Specifically, it uses a machine learning algorithm (generative AI model) running on the server to generate fashion coordinated outfit images based on the user's input data and sentiment data. The input is user data and sentiment data, and the output is the generated coordinated outfit image.

[1395] Step 6:

[1396] The server analyzes the generated outfit image to identify each item. Specifically, it uses image recognition technology to analyze the generated image and identify each fashion item (jacket, shirt, pants, etc.). The input is the latest generated outfit image, and the output is item information. For example, it automatically identifies shirts, pants, shoes, etc., in an image.

[1397] Step 7:

[1398] The server searches the product database for items based on the identified item. Specifically, it queries the product database (online marketplace) to retrieve product information (name, price, purchase link, etc.) that matches the identified item. The input is the information of the identified item, and the output is a list of matching product information.

[1399] Step 8:

[1400] The server sends the generated image and the searched item list to the user's device. Specifically, it sends a list of product information matching the generated outfit image to the device as an HTTP response in JSON format. The transmitted data includes the URL of the generated image and the item list.

[1401] Step 9:

[1402] The device displays the generated image and item list to the user. Specifically, it displays the coordinated outfit image generated within the application, allowing for visual confirmation along with the suggested item list. Users can virtually try on the suggested items using the virtual try-on function and purchase them directly by clicking the displayed purchase link. The input is data received from the server, and the output is the displayed coordinated outfit image and item list.

[1403] 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.

[1404] 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.

[1405] 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.

[1406] 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.

[1407] 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.

[1408] 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.

[1409] 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.

[1410] 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.

[1411] 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."

[1412] 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.

[1413] 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.

[1414] 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.

[1415] 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.

[1416] 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.

[1417] 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.

[1418] 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.

[1419] 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.

[1420] 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.

[1421] 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.

[1422] 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.

[1423] 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.

[1424] The following is further disclosed regarding the embodiments described above.

[1425] (Claim 1)

[1426] A means for the user to enter a fashion style or the name of a celebrity,

[1427] Means for sending the user's input data to the server,

[1428] The server provides means for generating a coordinated image using an image generation model based on the input data,

[1429] The server includes means for analyzing the generated coordinate image to identify each item,

[1430] The server has means for searching for the corresponding item from the product database based on the identified item,

[1431] The server provides means for transmitting the generated image and the searched item list to the user's terminal,

[1432] A system in which the terminal includes means for displaying the generated image and item list to the user.

[1433] (Claim 2)

[1434] The system according to claim 1, wherein the image generation model uses a machine learning algorithm.

[1435] (Claim 3)

[1436] The system according to claim 1, wherein the product database is related to an online marketplace.

[1437] "Example 1"

[1438] (Claim 1)

[1439] A means by which users input their observations of fashion styles or celebrities,

[1440] Means for transmitting the user's input data to a server facility,

[1441] The server facility includes means for generating a coordinated image using an image generation algorithm based on the input data,

[1442] The server facility includes means for analyzing the generated coordinated image and identifying each item,

[1443] The server facility includes means for searching for the corresponding item from a product information database based on the identified item,

[1444] The server facility provides means for transmitting the generated image and the searched item list to the user's terminal device,

[1445] A system in which the terminal device includes means for displaying the generated image and item list to the user.

[1446] (Claim 2)

[1447] The system according to claim 1, wherein the image generation algorithm uses a machine learning algorithm.

[1448] (Claim 3)

[1449] The system according to claim 1, wherein the product information database is related to an online sales site.

[1450] "Application Example 1"

[1451] (Claim 1)

[1452] A means for the user to enter a fashion style or the name of a celebrity,

[1453] Means for sending the user's input data to the server,

[1454] The server provides means for generating coordinated images using a generation AI model based on the input data,

[1455] The server includes means for analyzing the generated coordinate image to identify each item,

[1456] The server has means for searching for the corresponding item from the product database based on the identified item,

[1457] The server provides means for transmitting the generated image and the searched item list to the user's terminal,

[1458] A system including means for the terminal to display the generated image and item list to the user and to provide the user with a link to directly purchase the suggested items.

[1459] (Claim 2)

[1460] The system according to claim 1, wherein the image generation model uses a machine learning algorithm.

[1461] (Claim 3)

[1462] The system according to claim 1, wherein the product database is related to an online marketplace.

[1463] "Example 2 of combining an emotion engine"

[1464] (Claim 1)

[1465] A means for the user to enter a fashion style or the name of a celebrity,

[1466] Means for transmitting the user's input data and emotional data to a server,

[1467] The server includes means for generating coordinated images using an image generation model based on the input data and emotion data,

[1468] The server includes means for analyzing the generated coordinate image to identify each item,

[1469] The server has means for searching for the corresponding item from the product database based on the identified item,

[1470] The server provides means for transmitting the generated image and the searched item list to the user's terminal,

[1471] A system in which the terminal includes means for displaying the generated image and item list to the user.

[1472] (Claim 2)

[1473] The system according to claim 1, wherein the image generation model uses a machine learning algorithm to adjust the parameters of the image based on sentiment data.

[1474] (Claim 3)

[1475] The system according to claim 1, wherein the product database is related to an online marketplace.

[1476] "Application example 2 when combining with an emotional engine"

[1477] (Claim 1)

[1478] A means for the user to enter a fashion style or the name of a celebrity,

[1479] Means for sending the user's input data to the server,

[1480] The server provides means for generating a coordinated image using an image generation model based on the input data,

[1481] The server includes means for analyzing the generated coordinate image to identify each item,

[1482] The server has means for searching for the corresponding item from the product database based on the identified item,

[1483] The server provides means for transmitting the generated image and the searched item list to the user's terminal,

[1484] The terminal includes means for displaying the generated image and item list to the user,

[1485] A means for combining emotion engines to recognize the user's emotional state and adjusting the content of generated images and item suggestions based on the recognized emotional state,

[1486] A system that displays generated outfit images and suggested items in a virtual store, and includes means to allow users to virtually try on and directly purchase the suggested items.

[1487] (Claim 2)

[1488] The system according to claim 1, wherein the image generation model uses a machine learning algorithm.

[1489] (Claim 3)

[1490] The system according to claim 1, wherein the product database is related to an online marketplace. [Explanation of Symbols]

[1491] 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 for the user to enter a fashion style or the name of a celebrity, Means for sending the user's input data to the server, The server provides means for generating a coordinated image using an image generation model based on the input data, The server includes means for analyzing the generated coordinate image to identify each item, The server has means for searching for the corresponding item from the product database based on the identified item, The server provides means for transmitting the generated image and the searched item list to the user's terminal, A system in which the terminal includes means for displaying the generated image and item list to the user.

2. The system according to claim 1, wherein the image generation model uses a machine learning algorithm.

3. The system according to claim 1, wherein the product database is related to an online marketplace.

Images