system

Abstract

This system provides accurate fashion coordination suggestions tailored to individual body types and preferences, thereby increasing user satisfaction. [Solution] A system comprising means for the user to input height, weight, gender, and a full-body photograph; means for the user to specify coordination requirements; means for the server to analyze the user's body shape based on the full-body photograph; means for the server to generate coordination ideas according to the user's specified requirements based on the analysis results; means for the server to generate image representations of coordinations that the server deems suitable for the user; means for the server to transmit the generated coordination ideas and image representations to a terminal; means for the terminal to display a list of suggested coordinations and image representations to the user; means for the user to provide feedback; and means for the server to analyze the user's feedback and optimize the suggestion algorithm.

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] In modern times, it is an issue to efficiently and accurately propose fashion coordinations that suit individual body shapes and preferences. In conventional systems, it is difficult to propose coordinations that fully consider the specific body shapes and preferences of users, and users need to spend time finding clothes that suit them. In such a situation, it is particularly difficult for users who are not familiar with fashion to find the most suitable clothes, which becomes a factor reducing the satisfaction of online shopping.

Means for Solving the Problems

[0005] To solve the above problems, the present invention provides a system that includes means for the user to input height, weight, gender, and a full-body photograph, and means for the user to specify coordination requirements. The server analyzes the user's body shape based on the full-body photograph and generates coordination ideas according to the user's specified requirements based on the analysis results. Furthermore, the server also generates image representations of the coordination judged to suit the user and sends the generated coordination ideas and image representations to the terminal. The terminal also includes means for displaying the suggested coordination list and image representations to the user and for the user to provide feedback. The server also includes means for analyzing the user's feedback and optimizing the suggestion algorithm to improve the accuracy of the suggestions. This makes it possible to suggest appropriate fashion coordinations according to individual body shapes and preferences, thereby increasing user satisfaction.

[0006] A "user" is an individual who uses the system to receive fashion coordination suggestions.

[0007] A "terminal" is a device operated by a user that transmits entered information to a server and displays the results to the user. Examples include smartphones and tablets.

[0008] A "server" is a computer system that processes information sent by a user, generates coordination ideas and image files, and sends them to the terminal.

[0009] "Height" is a numerical value that indicates the user's body length and is one of the pieces of information used to suggest fashion coordinates.

[0010] "Weight" is a numerical value that represents the user's mass and is one of the pieces of information used to suggest fashion coordinates.

[0011] "Gender" refers to information indicating the user's gender and is one of the factors that influence fashion coordination suggestions.

[0012] A "full-body photo" is an image showing the user's entire body, and the information is used for body shape analysis and outfit suggestions.

[0013] "Coordination requirements" refer to the user's desired conditions, such as the situation and genre of clothing, as well as the items they wish to use.

[0014] "Body shape analysis" is a process that analyzes the shape and dimensions of a user's body based on a full-body photograph, and is a means of providing important information that forms the basis for suggesting outfit combinations.

[0015] "Outfit ideas" are suggestions for multiple outfits suitable for the user, generated by an AI model.

[0016] An "image representation" is a generated image that makes it appear as if the user is actually wearing the outfit idea.

[0017] "Feedback" refers to the evaluations and opinions that users provide regarding the outfit suggestions they receive.

[0018] The "proposal algorithm" is a computational method used by the server to generate the optimal fashion coordination based on the user's body shape and requirements. [Brief explanation of the drawing]

[0019] [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]It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It 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

[0020] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described according to the accompanying drawings.

[0021] First, the terms used in the following description will be explained.

[0022] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0023] 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.

[0024] 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.

[0025] 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).

[0026] 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."

[0027] [First Embodiment]

[0028] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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".

[0040] This invention relates to a system for users to receive fashion coordination suggestions that suit their body shape and preferences. Specific embodiments thereof are described below.

[0041] The user first installs the system's application on their device and creates an account. The user then enters their height, weight, gender, and a full-body photograph into the application. The device sends this information to the server. At this point, the device checks the format of the entered information and only sends it to the server if the format is correct.

[0042] The server preprocesses the received full-body photos and analyzes the user's body shape. Specifically, it uses image processing technology to extract the user's body shape information (height, shoulder width, waist size, etc.). Then, based on the user's specified outfit requirements (e.g., date, casual, want to wear a jacket), the server uses an AI model to generate dozens of outfit ideas.

[0043] For example, a casual outfit for a date might be generated, such as a white T-shirt, blue jeans, and sneakers. This generated outfit idea is then further adapted to the user's body shape, creating an image of what it would look like to actually wear those clothes.

[0044] The server sends the generated outfit ideas and image files to the terminal. The terminal displays this information to the user. The user browses the suggested outfits and selects their favorite. Furthermore, the user can provide feedback on the suggestions (e.g., "Good," "Bad," "Points to improve," etc.).

[0045] The terminal sends user feedback to the server. The server analyzes this feedback and optimizes the suggestion algorithm. This improves the accuracy of future coordination suggestions.

[0046] As a concrete example, consider a male user who is 170cm tall and weighs 60kg and wants a casual outfit for a date. The user first uploads a full-body photo to the application and specifies the requirements. The server analyzes this information and makes suggestions such as "white T-shirt, blue jeans, sneakers" that are best suited for the user, and also generates image files of the user wearing those clothes. The user reviews these suggestions and provides feedback, which helps to make future suggestions even more accurate.

[0047] As described above, the present invention aims to provide a system that proposes the optimal fashion coordination based on the user's body shape and requirements, thereby increasing user satisfaction.

[0048] The following describes the processing flow.

[0049] Step 1:

[0050] The user installs the application on their device and creates an account. The user enters their height, weight, gender, and a full-body photo.

[0051] Step 2:

[0052] The terminal checks the information entered by the user and verifies whether the input format is correct. If the format is correct, it sends the information to the server.

[0053] Step 3:

[0054] The server preprocesses the received full-body images. This preprocessing includes adjusting the image resolution and removing noise.

[0055] Step 4:

[0056] The server analyzes the user's body shape information (e.g., height, weight, shoulder width, waist size) based on pre-processed full-body photographs. This is done using an image recognition algorithm.

[0057] Step 5:

[0058] Users specify their outfit requirements within the application. This includes the situation (e.g., date, work), genre (e.g., casual, formal), and items they want to use (e.g., jacket, jeans).

[0059] Step 6:

[0060] The terminal sends the user's specified coordination requirements to the server.

[0061] Step 7:

[0062] The server uses an AI model to generate multiple outfit ideas based on the user's body shape information and specified requirements. For example, based on "date" and "casual" criteria, it might select "white T-shirt, blue jeans, and sneakers."

[0063] Step 8:

[0064] The server generates image renderings of what the user would look like wearing the generated outfit ideas. This image generation uses deep learning-based image synthesis technology.

[0065] Step 9:

[0066] The server sends the generated outfit ideas and image files to the terminal.

[0067] Step 10:

[0068] The device displays a list of suggested outfits and image files to the user.

[0069] Step 11:

[0070] Users review the suggested outfits and select their favorites. They can also optionally provide feedback (e.g., "Good," "Bad," "Suggestions for Improvement").

[0071] Step 12:

[0072] The device sends user feedback to the server.

[0073] Step 13:

[0074] The server analyzes user feedback and optimizes the proposed algorithm. This process includes retraining the machine learning model using the feedback data.

[0075] This will improve the accuracy of future outfit suggestions and increase user satisfaction.

[0076] (Example 1)

[0077] 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."

[0078] Conventional fashion coordination support systems lacked sufficient mechanisms to provide optimal coordination tailored to the user's body shape and preferences, making it difficult to offer highly accurate suggestions. Furthermore, the optimization of suggestion algorithms based on user feedback was not adequately implemented, posing a challenge in improving user satisfaction.

[0079] 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.

[0080] In this invention, the server includes means for pre-processing a full-body photograph of the user and analyzing the user's body shape, means for generating outfit ideas according to the user's specified requirements based on the analysis results, and means for generating outfit ideas using a generation AI model. This enables highly accurate outfit suggestions tailored to the user's body shape and preferences. Furthermore, it allows for optimization of the suggestion algorithm based on user feedback, thereby improving user satisfaction.

[0081] "User" refers to a person who uses this system, and specifically to a person who inputs personal information such as height, weight, gender, and full-body photos to receive outfit suggestions.

[0082] "Means for inputting height, weight, gender, and full-body photos" refers to technology that provides an interface for users to input their own physical data and images.

[0083] "Means for specifying coordination requirements" refers to an interface that allows users to input and specify their coordination needs (for example, "for a date," "casual," etc.).

[0084] "Means of verifying format" refers to a function that allows the terminal to verify that the information entered by the user is in the correct format and check for errors.

[0085] "Methods for pre-processing full-body images" refers to processes such as resizing and noise reduction performed to prepare the received images for easier analysis by the server.

[0086] "Means for analyzing a user's body shape" refers to technology in which a server uses image processing techniques to extract and analyze body shape information based on a full-body photograph of the user.

[0087] "Methods for generating coordination ideas" refers to technology in which a server generates multiple fashion coordination suggestions using AI models or similar tools, based on analysis results and user-specified requirements.

[0088] A "generative AI model" refers to an algorithm or technology that uses artificial intelligence to generate outfit ideas tailored to the user's preferences and body type.

[0089] "Methods for generating image data" refers to technology that creates images simulating how a user would look wearing an outfit based on outfit ideas generated by a server.

[0090] "Means for displaying suggested outfit lists and image files" refers to technology that visually displays outfit suggestions and image files received by the terminal from the server to the user.

[0091] "Means of providing feedback" refers to a function that allows users to input their opinions and requests for improvements regarding the suggested outfits through the application.

[0092] "Methods for optimizing the suggestion algorithm" refers to the technology in which the server analyzes user feedback and adjusts the algorithm to improve the accuracy and quality of future coordination suggestions.

[0093] This invention relates to a system for users to receive fashion coordination suggestions that suit their body shape and preferences. Specific embodiments thereof are described below.

[0094] Users first install the system's application on their device and create an account. During this process, users enter their height, weight, gender, and a full-body photograph into the application. This information is checked by the device for formatting, and only sent to the server if it is in the correct format.

[0095] The server preprocesses the received full-body photograph and analyzes the user's body shape. Specifically, it uses image processing technology to extract the user's body shape information (height, shoulder width, waist size, etc.). Specific image processing technologies used here include OpenCV and TENSORFLOW®. Based on this information, the server uses a generative AI model to generate dozens of outfit ideas according to the user's specified outfit requirements (e.g., "date," "casual," "want to wear a jacket").

[0096] For example, a "casual" outfit for a "date" might be generated, such as "white T-shirt, blue jeans, and sneakers." This generated outfit idea is then further processed to produce an image tailored to the user's body shape. The generative AI model used here could be, for example, a GAN (Generative Opposing Network) model.

[0097] The server sends the generated outfit ideas and image files to the terminal. The terminal displays this information to the user, allowing the user to browse the suggested outfits. Furthermore, the user can select their favorite outfit.

[0098] Users can provide feedback on the suggested outfits (e.g., "Good," "Bad," "Points to improve," etc.). The device sends the user's feedback to the server. The server analyzes this feedback and optimizes the suggestion algorithm. This improves the accuracy of outfit suggestions in the future.

[0099] As a concrete example, consider a male user who is 170cm tall and weighs 60kg and wants a casual outfit for a date. The user first uploads a full-body photo to the application and specifies the requirements. The server analyzes this information and makes suggestions such as "white T-shirt, blue jeans, sneakers" that are best suited to the user, and also generates image renderings of the user wearing those clothes. The user reviews these suggestions and provides feedback, which helps to make future suggestions even more accurate.

[0100] Examples of prompt statements are as follows:

[0101] 1. "Please suggest a casual outfit for a date. I am male, 170cm tall, 60kg."

[0102] 2. "I'd like some office-appropriate outfit ideas using a casual jacket. I'm 160cm tall, weigh 50kg, and am female."

[0103] 3. "Please suggest a fashion outfit suitable for a weekend outing. I am a male, 180cm tall and weigh 70kg."

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

[0105] Step 1:

[0106] The user installs the system's application on their device and creates an account.

[0107] Input: Application installation, user information (name, email address, password)

[0108] Output: User account creation complete message

[0109] Specific actions: The user downloads the application, enters the required information, and creates an account.

[0110] Step 2:

[0111] The user enters their height, weight, gender, and a full-body photo into the application.

[0112] Input: Height, weight, gender, full-body photo

[0113] Output: Confirmation message for input information

[0114] Specific operation: Following the application's instructions, the user enters the requested information. Photos can be taken using the device's camera or existing photos can be uploaded.

[0115] Step 3:

[0116] The terminal checks the format of the entered information and sends the information to the server if the format is correct.

[0117] Input: User's height, weight, gender, and full-body photo.

[0118] Output: Data transmission result to the server (success / failure)

[0119] Specific operation: The terminal validates the input information to check if it is in the correct format. If correct, it sends the information to the server. If incorrect, it displays an error message.

[0120] Step 4:

[0121] The server preprocesses the received full-body photos and analyzes the user's body shape.

[0122] Input: Full body photo

[0123] Output: Body shape analysis data (height, shoulder width, waist size, etc.)

[0124] Specific operation: The server processes images using OpenCV and TensorFlow, performing preprocessing such as noise reduction and resizing. Then, it extracts the user's body shape information using an image analysis algorithm.

[0125] Step 5:

[0126] The server generates coordination ideas based on the analysis results, according to the user's specified requirements.

[0127] Input: Body shape analysis data, outfit requirements (e.g., "date," "casual")

[0128] Output: Coordination Ideas

[0129] Specific operation: The server generates the most suitable fashion combination for the user's body type and requirements based on predefined coordination rules and style guides.

[0130] Step 6:

[0131] The server uses a generative AI model to generate outfit ideas and create image files tailored to the user's body shape.

[0132] Input: Outfit ideas, body shape analysis data

[0133] Output: Image

[0134] Specific operation: The server uses a generative AI model (e.g., a GAN model) to convert the generated outfit ideas into image files tailored to the user's body shape.

[0135] Step 7:

[0136] The server sends the generated outfit ideas and image files to the terminal.

[0137] Input: Outfit ideas, image

[0138] Output: Data transmission result to the terminal (success / failure)

[0139] Specific operation: The server sends the generated coordination idea and image to the terminal. If the transmission is successful, proceed to the next step.

[0140] Step 8:

[0141] The device displays a list of suggested outfits and image files to the user.

[0142] Input: Outfit ideas, image

[0143] Output: Content displayed to the user

[0144] Specific operation: The terminal displays suggested outfits and image files to the user based on data received from the server. The user is then made able to view them.

[0145] Step 9:

[0146] Users view the suggested outfits and provide feedback.

[0147] Input: Outfit suggestions, image

[0148] Output: Feedback (e.g., "Good," "Bad," "Areas for Improvement")

[0149] Specific actions: The user reviews the suggestion and selects / enters appropriate feedback on the screen. This feedback will be used in the next step.

[0150] Step 10:

[0151] The device sends user feedback to the server.

[0152] Input: Feedback

[0153] Output: Data transmission result to the server (success / failure)

[0154] Specific operation: The device collects user feedback information and sends it to the server. If the transmission is successful, it proceeds to the next step.

[0155] Step 11:

[0156] The server analyzes the feedback and optimizes the proposed algorithm.

[0157] Input: Feedback

[0158] Output: Optimized proposed algorithm

[0159] Specific operation: The server analyzes the feedback and adjusts specific parameters and models to improve the accuracy of future coordination suggestions.

[0160] (Application Example 1)

[0161] 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."

[0162] Traditional fashion coordination systems made it difficult for users to visually confirm clothing that suited their body type and preferences. Furthermore, they did not adequately optimize coordination based on user feedback. Therefore, there was a need for a means to improve user satisfaction.

[0163] 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.

[0164] In this invention, the server includes means for the user to input height, weight, gender, and a full-body photograph; means for the user to specify coordination requirements; means for the server to analyze the user's body shape based on the full-body photograph; means for the server to generate coordination ideas according to the user's specified requirements based on the analysis results; means for the server to generate image representations of coordinations that the server deems suitable for the user; means for the server to transmit the generated coordination ideas and image representations to a terminal; means for the terminal to display a list of suggested coordinations and image representations to the user; means for the user to provide feedback; means for the server to analyze the user's feedback and optimize the suggestion algorithm; means for displaying the coordination selected by the user in the virtual store in real time; and means for the user to explore the virtual store using smart glasses and reflect the selected coordination on an avatar. This allows the user to visually confirm coordinations that suit their body shape and preferences and to have a real-time try-on experience in the virtual store.

[0165] A "user" is someone who uses the system to receive fashion coordination suggestions tailored to their body type and preferences.

[0166] "Height" refers to a physical measurement that indicates the vertical length from the user's head to their feet.

[0167] "Weight" refers to the user's body weight, which is generally measured in kilograms.

[0168] "Gender" refers to information that indicates which gender a user identifies with.

[0169] A "full-body photo" is an image that captures the user from head to toe in a single photograph.

[0170] "Coordination requirements" refer to the specific situation and clothing preferences specified by the user.

[0171] A "server" is a computer system that analyzes data sent by a user and performs the necessary processing.

[0172] "Body shape analysis" is the process of extracting the shape and dimensions of a user's body from a full-body photograph.

[0173] A "coordinate idea" is a combination of clothing items generated based on the user's requirements.

[0174] An "image" is a visual representation of an outfit optimized for the user's body shape.

[0175] A "device" refers to a computing device used by a user, such as a smartphone or smart glasses.

[0176] "Feedback" refers to the evaluations and opinions that users give regarding the suggested outfits.

[0177] A "suggestion algorithm" is an algorithm that generates coordinates based on user feedback.

[0178] A "virtual store" is a virtual space where users can virtually try on clothes through a computer screen or smart device.

[0179] "Smart glasses" are glasses-type devices that use augmented reality technology to display information to the user.

[0180] An "avatar" is a virtual representation of the user that acts on their behalf within a virtual store.

[0181] This invention relates to a system that suggests fashion coordinates tailored to a user's body shape and preferences. Specific embodiments thereof are described below.

[0182] Users explore virtual stores while wearing smart glasses. The main hardware used in this system is smart glasses, specifically a glasses-type device that utilizes augmented reality technology. Cloud servers are used for backend processing.

[0183] The user installs the application on smart glasses and enters their height, weight, gender, and a full-body photo. This information is sent from the smart glasses to a cloud server. The cloud server uses Python and OpenCV to analyze the full-body photo and extract the user's body shape information. This body shape information includes height, shoulder width, waist size, etc.

[0184] The server uses a generative AI model to generate multiple outfit ideas based on the extracted body shape information and the outfit requirements specified by the user. For example, for a "casual outfit for a date," a combination of "white T-shirt, blue jeans, and sneakers" is generated. These outfit ideas are further generated as image files tailored to the user's body shape.

[0185] The generated outfit ideas and image files are saved to cloud storage and sent back to the user's smart glasses. The smart glasses receive this information and display the outfits the user has selected in real time within the virtual store, so that they are reflected on the avatar in real time. The user can try on various outfits while exploring the virtual store.

[0186] When a user provides feedback on a suggested outfit, this feedback information is sent back to the cloud server. The server analyzes this feedback and optimizes the suggestion algorithm. This results in more accurate suggestions in the future.

[0187] As a concrete example, consider a male user who is 170cm tall and weighs 60kg and wants a casual outfit for a date. This user first uploads a full-body photo to the application and specifies the requirements. The server analyzes this information and generates suggestions for the most suitable outfit for the user, such as "white T-shirt, blue jeans, sneakers," and also generates image previews. The user can review these suggestions in a virtual store and try on the selected outfit. Furthermore, the user can provide feedback, which will help improve the accuracy of future suggestions.

[0188] An example of a prompt message is as follows:

[0189] "A male user, 170cm tall and weighing 60kg, is looking for a casual outfit for a date. Please generate an outfit including a white t-shirt, blue jeans, and sneakers that is ideal for him to try on in a virtual store. Based on the user's full-body photo, generate a real-time image that fits his body shape and display it on smart glasses."

[0190] This allows users to visually check outfits that suit their body type and preferences, and to try them on in real time within a virtual store.

[0191] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0192] Step 1:

[0193] The user launches an application installed on the smart glasses and enters their height, weight, gender, and a full-body photograph. The entered data is sent from the smart glasses to a cloud server. The input here is height, weight, gender, and a full-body photograph, and the output is the transmission of this data to the server.

[0194] Step 2:

[0195] The server preprocesses the received full-body images using image processing software (OpenCV). This preprocessing includes adjusting the resolution, removing the background, and reducing noise. The preprocessed full-body images become the input data for body shape analysis. The output is the preprocessed full-body image.

[0196] Step 3:

[0197] The server uses image analysis technology to extract the user's body shape information based on a pre-processed full-body photograph. Specifically, it obtains data such as height, shoulder width, and waist size. This analysis employs machine learning algorithms to perform calculations to obtain accurate body shape information. The input is a pre-processed full-body photograph, and the output is the extracted body shape information.

[0198] Step 4:

[0199] The server receives the user's specified outfit requirements (e.g., a casual outfit for a date) and processes them along with body shape information. A generative AI model (e.g., TensorFlow) is used to generate multiple outfit ideas. The input is the user's body shape information and outfit requirements, and the output is the generated outfit ideas.

[0200] Step 5:

[0201] The server generates an image tailored to the user's body shape based on the generated outfit idea. This uses computer graphics technology. The input is the outfit idea and body shape information, and the output is the generated image.

[0202] Step 6:

[0203] The server saves the generated outfit ideas and image files to cloud storage and sends them to the user's smart glasses. The input is the image files and outfit ideas, and the output is the transmission of this data to the user's smart glasses.

[0204] Step 7:

[0205] Smart glasses display received outfit images and ideas in real time. Users can explore a virtual store and have their selected outfits reflected on their avatar. In this process, the input is the user's clothing selection, and the output is the selected outfit displayed on the avatar.

[0206] Step 8:

[0207] The user provides feedback on the suggested outfit. This feedback is sent to the server via smart glasses. The input is the user's feedback, and the output is this feedback being sent to the server.

[0208] Step 9:

[0209] The server analyzes the feedback it receives and optimizes the proposal algorithm of the generated AI model. This improves the accuracy of future coordination suggestions. The input is user feedback, and the output is the optimized proposal algorithm.

[0210] 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.

[0211] This invention combines a system for users to receive fashion coordination suggestions tailored to their body shape and preferences with an emotion engine that recognizes the user's emotions. A specific embodiment of this system is described below.

[0212] The user first installs the system's application on their device and creates an account. The user then enters their height, weight, gender, and a full-body photograph. The device sends this information to the server. At this point, the device checks the format of the entered information and only sends it to the server if the format is correct.

[0213] The server preprocesses the received full-body photos and analyzes the user's body shape. Specifically, it uses image processing technology to extract the user's body shape information (height, shoulder width, waist size, etc.). Then, based on the user's specified outfit requirements (e.g., date, casual, want to wear a jacket), the server uses an AI model to generate dozens of outfit ideas.

[0214] This system also includes an emotion engine that can recognize the user's emotions from a full-body photo and feedback submitted by the user. The emotion engine analyzes the user's facial expressions and text-based feedback to determine their current emotional state. For example, it recognizes "joy" if the user is smiling and "dissatisfaction" if they are frowning.

[0215] The server adjusts outfit ideas based on the user's emotional data recognized by the emotion engine. For example, if a user wants a "date" and "casual" outfit, but the emotion engine detects "dissatisfaction" from the user's feedback, the server can consider the reasons why the user previously rejected an outfit and generate a different outfit idea.

[0216] The server generates image renderings of what the user would look like wearing the generated outfit ideas. This image generation uses deep learning-based image synthesis technology.

[0217] The server sends the generated outfit ideas and image files to the terminal. The terminal displays this information to the user. The user browses the suggested outfits and selects their favorite. Furthermore, the user can provide feedback on the suggestions (e.g., "Good," "Bad," "Points to improve").

[0218] The device sends user feedback to the server. The server analyzes the user feedback and sentiment data to optimize the proposed algorithm. This process includes retraining the machine learning model using the feedback and sentiment data.

[0219] As a concrete example, consider a male user who is 170cm tall and weighs 60kg, who wants a casual outfit for a date and provided "dissatisfied" feedback on the previous suggestion. The user first uploads a full-body photo to the application and specifies the requirements. The server analyzes this information and makes suggestions such as "white T-shirt, blue jeans, sneakers" that are best suited to the user, and also generates an image of the user wearing those clothes. If the emotion engine detects "dissatisfaction" with the user, the server re-evaluates the user's preferences and makes a different suggestion.

[0220] As described above, the present invention aims to provide a system that proposes the optimal fashion coordination based on the user's body shape and emotional state, thereby increasing user satisfaction.

[0221] The following describes the processing flow.

[0222] Step 1:

[0223] The user installs the application on their device and creates an account. The user enters their height, weight, gender, and a full-body photo.

[0224] Step 2:

[0225] The terminal checks the information entered by the user and verifies whether the input format is correct. If the format is correct, it sends the information to the server.

[0226] Step 3:

[0227] The server preprocesses the received full-body images. Preprocessing includes adjusting the image resolution and denoising.

[0228] Step 4:

[0229] The server analyzes the user's body shape information (e.g., height, weight, shoulder width, waist size) based on pre-processed full-body photographs. This is done using an image recognition algorithm.

[0230] Step 5:

[0231] Within the application, users specify their outfit requirements. Specifically, they select the situation (e.g., date, office), genre (e.g., casual, formal), and items they want to use (e.g., jacket, jeans).

[0232] Step 6:

[0233] The terminal sends the user's specified coordination requirements to the server.

[0234] Step 7:

[0235] Based on the received requirements and body shape information, the server uses an appropriate AI model to generate multiple outfit ideas. For example, based on "date" and "casual" preferences, it might select a combination of "white T-shirt, blue jeans, and sneakers."

[0236] Step 8:

[0237] Based on the generated outfit ideas, the server creates image renderings of what it would look like if the user were wearing these items. This image generation uses deep learning-based image synthesis technology.

[0238] Step 9:

[0239] The server sends the generated coordination ideas and image files to the terminal.

[0240] Step 10:

[0241] The device displays a list of suggested outfits and image files to the user.

[0242] Step 11:

[0243] Users review the suggested outfits and select their favorites. They can also optionally provide feedback (e.g., "Good," "Bad," "Suggests revision").

[0244] Step 12:

[0245] The device sends user feedback to the server.

[0246] Step 13:

[0247] The server uses an emotion engine to recognize the user's emotions from the feedback it receives. This is a process that analyzes the user's facial expressions and text-based feedback to identify their current emotional state. For example, it recognizes "joy" in response to "good" feedback and "dissatisfaction" in response to feedback requesting correction.

[0248] Step 14:

[0249] The server optimizes the suggestion algorithm based on the user's emotion data recognized by the emotion engine. This optimization includes adjusting the outfit suggestions to match the user's emotions. For example, if the user is "dissatisfied," a different outfit idea will be generated.

[0250] Step 15:

[0251] The server accumulates user emotional data and uses it as reference when suggesting outfits in the future. This makes it possible to provide more personalized outfit suggestions based on each user's individual preferences and emotions.

[0252] This allows the system to suggest the most suitable fashion coordinates based on the user's body shape and emotional state, thereby increasing user satisfaction.

[0253] (Example 2)

[0254] 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".

[0255] Conventional fashion coordination systems often failed to provide optimal suggestions based on the user's body shape and emotions, resulting in low user satisfaction. Furthermore, it was difficult to determine whether the generated coordination ideas were actually suitable for the user, making it difficult to incorporate user feedback into the system. This invention aims to solve these problems.

[0256] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0257] In this invention, the server includes means for pre-processing a full-body photograph to analyze the user's body shape, means for generating coordination ideas according to the user's specified requirements, and means for an emotion engine to analyze the user's facial expressions and feedback to identify their emotional state. This makes it possible to suggest the optimal fashion coordination based on the user's body shape and emotions.

[0258] A "user" is an individual who uses the system to receive fashion coordination suggestions based on their own body shape and preferences.

[0259] A "terminal" is a device used by a user to operate a system, and includes smartphones, tablets, and personal computers.

[0260] A "server" is a computer system that processes data sent from users or terminals and generates coordination ideas and image files.

[0261] A "full-body photograph" is a photograph that includes the user's entire appearance and is used for image analysis.

[0262] "Body shape" refers to data that indicates the user's physical characteristics, such as height, shoulder width, and waist size.

[0263] "Coordination requirements" refer to input information about the fashion style and situation the user desires, such as a casual style for a date.

[0264] "Coordination ideas" are fashion suggestions generated by the server based on the user's body shape and coordination requirements.

[0265] An "emotion engine" is software or an algorithm that analyzes a user's facial expressions and text-based feedback to identify their emotional state.

[0266] An "image rendering" is a simulated image showing how a user would look wearing the suggested outfit.

[0267] "Feedback" refers to the opinions and impressions that users provide regarding the suggested outfits, including "good," "bad," and "points for improvement."

[0268] A "suggestion algorithm" is an algorithm that generates optimal outfit ideas based on the user's body shape information and feedback.

[0269] This invention relates to a system that suggests the optimal fashion coordination based on the user's body shape and emotions. Specific embodiments are described below.

[0270] Hardware and software to be used

[0271] 1. Hardware

[0272] Terminal: A device used by a user to operate a system. Specific examples include smartphones, tablets, and personal computers.

[0273] 2. Software

[0274] Image processing libraries: Use OpenCV and TensorFlow to preprocess and analyze the user's full-body images.

[0275] AI Models: Uses GPT-4 (registered trademark) and StyleGAN to generate outfit ideas.

[0276] Emotion Engine: Uses DeepFace and EmotionAPI to analyze user facial expressions and feedback to identify emotional states.

[0277] Image synthesis techniques: Generate images using GANs (e.g., StyleGAN and Pix2Pix).

[0278] System Operation

[0279] 1. The user installs the system application on the terminal and creates their account. This involves entering information such as email address and password.

[0280] 2. The user enters information such as their height, weight, gender, and full-body photo into the application. Then, they specify the coordination requirements (e.g., date, casual).

[0281] 3. The terminal checks the format of the input information and sends the information to the server only if the format is correct.

[0282] 4. The server preprocesses the received full-body photo using OpenCV or TensorFlow, performs noise removal and resolution adjustment on the image. Then, it analyzes the body shape information (height, shoulder width, waist size, etc.) and saves it in the database.

[0283] 5. Based on the user's body shape information and coordination requirements, the server uses GPT-4 or StyleGAN to generate dozens of coordination ideas.

[0284] 6. The emotion engines (such as DeepFace or EmotionAPI) included in the server recognize emotions from the user's full-body photo and feedback. Specifically, it performs facial expression analysis and text analysis to identify emotional states such as joy and dissatisfaction.

[0285] 7. Based on the emotion data recognized by the emotion engine, the server adjusts the generated coordination ideas. For example, if the user is recognized as "dissatisfied", new proposals are generated based on the previous feedback.

[0286] 8. The server uses image synthesis technology based on deep learning (such as StyleGAN and Pix2Pix) to generate an image of the user wearing the item proposed by the user.

[0287] 9. The server sends the generated coordinate ideas and image to the terminal. The terminal displays these to the user, enabling the user to easily view the proposals.

[0288] As a specific example, consider a male user who is 170 cm tall and weighs 60 kg and desires a casual coordination for a date, and who provided "dissatisfaction" feedback on the previous proposal. The user uploads a full-body photo and specifies the requirements. The server analyzes this information, makes proposals such as a white T-shirt, blue jeans, and sneakers, and also generates an image of the user wearing that clothing. If the emotion engine detects "dissatisfaction", the server re-evaluates the user's preferences and makes another proposal.

[0289] Example prompt sentence:

[0290] "A male user who is 170 cm tall and weighs 60 kg desires a casual coordination for a date. The feedback on the previous proposal was 'dissatisfaction'. Please generate a new proposal and its image."

[0291] This system enables the proposal of optimal fashion coordination based on the user's body shape and emotions, enhancing the user's satisfaction.

[0292] The flow of the specific process in Example 2 will be described using FIG. 13.

[0293] The flow of the program processing of this system

[0294] Step 1:

[0295] The user installs the system application on their device and creates an account. The user enters the required information (e.g., email address, password, etc.). The input in this step is the information entered by the user, and the output is a notification that the account has been created.

[0296] Step 2:

[0297] The user enters information such as their height, weight, gender, and a full-body photo into the application. They then specify their outfit requirements (e.g., date, casual). The input for this step consists of the user's physical information and outfit requirements, while the output is a confirmation screen of the entered information.

[0298] Step 3:

[0299] The terminal checks the format of the information entered by the user and sends the information to the server only if the format is correct. Specifically, it uses a format verification algorithm to check the integrity of the data. The input for this step is the information entered by the user, and the output is the result of the verification of whether the format is correct.

[0300] Step 4:

[0301] The server preprocesses the received full-body image using OpenCV or TensorFlow to remove noise and adjust the resolution. Next, it analyzes the user's body shape information (height, shoulder width, waist size, etc.) and stores it in a database. The input for this step is the user's full-body image, and the output is the analyzed body shape information.

[0302] Step 5:

[0303] The server uses GPT-4, StyleGAN, etc. to generate dozens of coordination idea based on the user's body shape information and coordination requirements. Based on the requirements specified by the user, the AI model performs data processing. The input for this step is the analyzed body shape information and coordination requirements, and the output is the generated coordination ideas.

[0304] Step 6:

[0305] The emotion engine (such as DeepFace or EmotionAPI) included in the server recognizes emotions from the user's full-body photo and feedback. Specifically, it performs facial expression analysis and text analysis to identify the user's emotional state. The input for this step is the user's full-body photo and feedback, and the output is the recognized emotion data.

[0306] Step 7:

[0307] The server adjusts the generated coordination ideas based on the emotion data recognized by the emotion engine. For example, if the user is recognized as "dissatisfied", new proposals are generated based on the previous feedback. The input for this step is the emotion data and the previous feedback, and the output is the adjusted coordination ideas.

[0308] Step 8:

[0309] Based on the generated coordination ideas, the server uses deep learning-based image synthesis technologies such as StyleGAN or Pix2Pix to generate an image of the user wearing the proposed items. The input for this step is the adjusted coordination ideas, and the output is the generated image.

[0310] Step 9:

[0311] The server sends generated outfit ideas and image files to the terminal. The terminal displays this information to the user, allowing them to easily view the suggested outfits. The input for this step is the data sent from the server, and the output is the outfit suggestions displayed to the user.

[0312] Step 10:

[0313] The user enters feedback on the suggested outfit (e.g., "Good," "Bad," "Points to improve"). The terminal sends the entered feedback data to the server. The input for this step is the user's feedback, and the output is the feedback data sent to the server.

[0314] Step 11:

[0315] The server analyzes the received feedback and sentiment data to optimize the proposed algorithm. Specifically, a machine learning model (e.g., retraining) is used to improve the accuracy of the next proposal. The input to this step is the feedback and sentiment data, and the output is the optimized proposed algorithm.

[0316] The above outlines the specific processing steps of this system.

[0317] (Application Example 2)

[0318] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0319] Traditional fashion coordination suggestion systems only generated outfits based on the user's body shape data, failing to consider the user's feelings. As a result, users were often dissatisfied with the suggestions, leading to a decline in overall satisfaction with the outfits. Furthermore, the lack of technology to simulate the user actually trying on the outfits made it difficult to grasp a concrete image of the suggested outfits.

[0320] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for recognizing the user's emotions using an emotion engine and analyzing the feedback, means for the server to adjust coordination ideas based on emotion data, and means for generating a virtual image of the user trying on the coordination using deep learning-based image synthesis technology. This makes it possible to propose coordinations that take the user's emotions into consideration and to provide concrete images through virtual try-on.

[0321] An "emotion engine" is a technology that analyzes a user's facial expressions and text-based feedback to recognize their current emotional state.

[0322] A "server" is a computer system that analyzes information sent by users and processes the data.

[0323] A "full-body photo" is image data that captures the user's entire body.

[0324] "Body shape data" refers to information about the user's physical dimensions, such as height, shoulder width, and waist size.

[0325] "Coordination ideas" are fashion combinations suggested based on the user's body shape and specified requirements.

[0326] "Deep learning-based image synthesis technology" is a technology that uses artificial intelligence to combine multiple images and generate new images.

[0327] "Feedback" refers to data that shows evaluations and opinions on suggestions provided by users.

[0328] A "virtual image" is a simulated image of how a user would look trying on a suggested outfit.

[0329] The "proposal algorithm" is a computational method that generates the optimal fashion coordination based on user data.

[0330] The system program that implements the example application is implemented as follows: First, the user inputs their height, weight, gender, and a full-body photo into the application using their smartphone. This information is first checked on the device for formatting, and only sent to the server if it is correct.

[0331] The server preprocesses the received full-body photographs and analyzes the user's body shape using image processing techniques. Image processing libraries such as OpenCV are used for this process. The data obtained from the body shape analysis includes specific dimensional information such as the user's height, shoulder width, and waist size.

[0332] Next, the server uses an AI model to generate dozens of outfit ideas based on the user's specified outfit requirements. This process utilizes machine learning libraries such as TensorFlow.

[0333] Furthermore, the server incorporates an emotion engine that recognizes the user's emotional state from full-body photos and feedback. It analyzes the user's facial expressions and text-based feedback to obtain emotional data such as "joy" and "dissatisfaction." Based on this emotional data, the server adjusts the outfit ideas.

[0334] Image synthesis technology based on deep learning is also used, generating virtual images of the user trying on the suggested outfits. TensorFlow is also used for this process.

[0335] The server generates outfit ideas and virtual images, which are then sent to the terminal, where the terminal displays this information to the user. The user can view the suggested outfits and provide feedback. The feedback is sent back to the server, which analyzes the feedback and sentiment data to optimize the suggestion algorithm.

[0336] As a concrete example, consider a male user who is 170cm tall and weighs 60kg and wants a casual outfit for a date, and who provided "dissatisfied" feedback on the previous suggestion. In this case, the user first uploads a full-body photo to the application and specifies the requirements. The server analyzes this information and makes suggestions such as "white T-shirt, blue jeans, sneakers," and also generates an image of the user wearing those clothes. If the emotion engine detects "dissatisfaction" with the user, the server re-evaluates the user's preferences and makes a different suggestion.

[0337] Examples of prompt statements to input into the generative AI model are as follows:

[0338] "A man who is 170cm tall and weighs 60kg is looking for a casual outfit for a date. Please generate images of a white T-shirt, blue jeans, and sneakers. The user is dissatisfied with the previous suggestions, so please consider more stylish suggestions."

[0339] As described above, this invention is a system that proposes the optimal fashion coordination based on the user's body shape and emotional state, thereby increasing user satisfaction.

[0340] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0341] Step 1:

[0342] The user launches the application using their smartphone and enters their height, weight, gender, and a full-body photo. After entering this information, the user specifies the outfit requirements (e.g., date, casual). The input data is formatted by the device, and only if it is in the correct format is the data sent to the server. The input includes height, weight, gender, full-body photo, and outfit requirements, and the output is the formatted user data.

[0343] Step 2:

[0344] The server preprocesses the received full-body photographs. Specifically, it uses image processing libraries such as OpenCV to perform denoising and resizing. The preprocessed images are then formatted to a format suitable for the next analysis step. The input is a full-body photograph of the user, and the output is the preprocessed image data.

[0345] Step 3:

[0346] The server analyzes the user's body shape using pre-processed full-body photographs. The server utilizes image processing techniques to extract body shape data such as height, shoulder width, and waist size. The OpenCV library is used for this analysis. The input is pre-processed image data, and the output is the user's body shape data.

[0347] Step 4:

[0348] The server uses an AI model to generate outfit ideas based on the user's specified outfit requirements. A machine learning model using TensorFlow is employed here. The input is body shape data and outfit requirements, and the output is multiple outfit ideas.

[0349] Step 5:

[0350] The emotion engine on the server analyzes emotional data from user-provided feedback and facial expression images. The emotion engine uses a specific algorithm to detect emotional states such as "joy" or "dissatisfaction." Input is the user's facial expression image and feedback text, and output is emotional data.

[0351] Step 6:

[0352] The server adjusts the generated coordination ideas based on emotional data. This is a process that modifies the priority and content of suggestions based on the user's emotional state. The input is coordination ideas and emotional data, and the output is the adjusted coordination ideas.

[0353] Step 7:

[0354] The server uses deep learning-based image synthesis technology to generate virtual images of the user trying on outfits. TensorFlow is used for this image generation. The input is a refined outfit idea and a pre-processed full-body photo of the user, and the output is a virtual try-on image.

[0355] Step 8:

[0356] The server sends the generated outfit ideas and virtual images to the terminal. The input is the virtual try-on image and outfit ideas, and the output is the data sent to the terminal.

[0357] Step 9:

[0358] The terminal displays the received coordinate list and virtual image to the user. The user can review these, make selections, or provide feedback. The input is data sent from the server, and the output is the user's display screen.

[0359] Step 10:

[0360] The user's feedback is sent back to the server. The server analyzes this feedback and sentiment data to retrain the model and optimize the proposed algorithm. The input is the user's feedback data, and the output is the optimized proposed algorithm.

[0361] 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.

[0362] 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.

[0363] 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.

[0364] [Second Embodiment]

[0365] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0366] 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.

[0367] 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).

[0368] 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.

[0369] 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.

[0370] 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).

[0371] 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.

[0372] 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.

[0373] 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.

[0374] 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.

[0375] 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.

[0376] 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".

[0377] This invention relates to a system for users to receive fashion coordination suggestions that suit their body shape and preferences. Specific embodiments thereof are described below.

[0378] The user first installs the system's application on their device and creates an account. The user then enters their height, weight, gender, and a full-body photograph into the application. The device sends this information to the server. At this point, the device checks the format of the entered information and only sends it to the server if the format is correct.

[0379] The server preprocesses the received full-body photos and analyzes the user's body shape. Specifically, it uses image processing technology to extract the user's body shape information (height, shoulder width, waist size, etc.). Then, based on the user's specified outfit requirements (e.g., date, casual, want to wear a jacket), the server uses an AI model to generate dozens of outfit ideas.

[0380] For example, a casual outfit for a date might be generated, such as a white T-shirt, blue jeans, and sneakers. This generated outfit idea is then further adapted to the user's body shape, creating an image of what it would look like to actually wear those clothes.

[0381] The server sends the generated outfit ideas and image files to the terminal. The terminal displays this information to the user. The user browses the suggested outfits and selects their favorite. Furthermore, the user can provide feedback on the suggestions (e.g., "Good," "Bad," "Points to improve," etc.).

[0382] The terminal sends user feedback to the server. The server analyzes this feedback and optimizes the suggestion algorithm. This improves the accuracy of future coordination suggestions.

[0383] As a concrete example, consider a male user who is 170cm tall and weighs 60kg and wants a casual outfit for a date. The user first uploads a full-body photo to the application and specifies the requirements. The server analyzes this information and makes suggestions such as "white T-shirt, blue jeans, sneakers" that are best suited for the user, and also generates image files of the user wearing those clothes. The user reviews these suggestions and provides feedback, which helps to make future suggestions even more accurate.

[0384] As described above, the present invention aims to provide a system that proposes the optimal fashion coordination based on the user's body shape and requirements, thereby increasing user satisfaction.

[0385] The following describes the processing flow.

[0386] Step 1:

[0387] The user installs the application on their device and creates an account. The user enters their height, weight, gender, and a full-body photo.

[0388] Step 2:

[0389] The terminal checks the information entered by the user and verifies whether the input format is correct. If the format is correct, it sends the information to the server.

[0390] Step 3:

[0391] The server preprocesses the received full-body images. This preprocessing includes adjusting the image resolution and removing noise.

[0392] Step 4:

[0393] The server analyzes the user's body shape information (e.g., height, weight, shoulder width, waist size) based on pre-processed full-body photographs. This is done using an image recognition algorithm.

[0394] Step 5:

[0395] Users specify their outfit requirements within the application. This includes the situation (e.g., date, work), genre (e.g., casual, formal), and items they want to use (e.g., jacket, jeans).

[0396] Step 6:

[0397] The terminal sends the user's specified coordination requirements to the server.

[0398] Step 7:

[0399] The server uses an AI model to generate multiple outfit ideas based on the user's body shape information and specified requirements. For example, based on "date" and "casual" criteria, it might select "white T-shirt, blue jeans, and sneakers."

[0400] Step 8:

[0401] The server generates image renderings of what the user would look like wearing the generated outfit ideas. This image generation uses deep learning-based image synthesis technology.

[0402] Step 9:

[0403] The server sends the generated outfit ideas and image files to the terminal.

[0404] Step 10:

[0405] The device displays a list of suggested outfits and image files to the user.

[0406] Step 11:

[0407] Users review the suggested outfits and select their favorites. They can also optionally provide feedback (e.g., "Good," "Bad," "Suggestions for Improvement").

[0408] Step 12:

[0409] The device sends user feedback to the server.

[0410] Step 13:

[0411] The server analyzes user feedback and optimizes the proposed algorithm. This process includes retraining the machine learning model using the feedback data.

[0412] This will improve the accuracy of future outfit suggestions and increase user satisfaction.

[0413] (Example 1)

[0414] 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."

[0415] Conventional fashion coordination support systems lacked sufficient mechanisms to provide optimal coordination tailored to the user's body shape and preferences, making it difficult to offer highly accurate suggestions. Furthermore, the optimization of suggestion algorithms based on user feedback was not adequately implemented, posing a challenge in improving user satisfaction.

[0416] 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.

[0417] In this invention, the server includes means for pre-processing a full-body photograph of the user and analyzing the user's body shape, means for generating outfit ideas according to the user's specified requirements based on the analysis results, and means for generating outfit ideas using a generation AI model. This enables highly accurate outfit suggestions tailored to the user's body shape and preferences. Furthermore, it allows for optimization of the suggestion algorithm based on user feedback, thereby improving user satisfaction.

[0418] "User" refers to a person who uses this system, and specifically to a person who inputs personal information such as height, weight, gender, and full-body photos to receive outfit suggestions.

[0419] "Means for inputting height, weight, gender, and full-body photos" refers to technology that provides an interface for users to input their own physical data and images.

[0420] "Means for specifying coordination requirements" refers to an interface that allows users to input and specify their coordination needs (for example, "for a date," "casual," etc.).

[0421] "Means of verifying format" refers to a function that allows the terminal to verify that the information entered by the user is in the correct format and check for errors.

[0422] "Methods for pre-processing full-body images" refers to processes such as resizing and noise reduction performed to prepare the received images for easier analysis by the server.

[0423] "Means for analyzing a user's body shape" refers to technology in which a server uses image processing techniques to extract and analyze body shape information based on a full-body photograph of the user.

[0424] "Methods for generating coordination ideas" refers to technology in which a server generates multiple fashion coordination suggestions using AI models or similar tools, based on analysis results and user-specified requirements.

[0425] A "generative AI model" refers to an algorithm or technology that uses artificial intelligence to generate outfit ideas tailored to the user's preferences and body type.

[0426] "Methods for generating image data" refers to technology that creates images simulating how a user would look wearing an outfit based on outfit ideas generated by a server.

[0427] "Means for displaying suggested outfit lists and image files" refers to technology that visually displays outfit suggestions and image files received by the terminal from the server to the user.

[0428] "Means of providing feedback" refers to a function that allows users to input their opinions and requests for improvements regarding the suggested outfits through the application.

[0429] "Methods for optimizing the suggestion algorithm" refers to the technology in which the server analyzes user feedback and adjusts the algorithm to improve the accuracy and quality of future coordination suggestions.

[0430] This invention relates to a system for users to receive fashion coordination suggestions that suit their body shape and preferences. Specific embodiments thereof are described below.

[0431] Users first install the system's application on their device and create an account. During this process, users enter their height, weight, gender, and a full-body photograph into the application. This information is checked by the device for formatting, and only sent to the server if it is in the correct format.

[0432] The server preprocesses the received full-body photograph and analyzes the user's body shape. Specifically, it uses image processing techniques to extract the user's body shape information (height, shoulder width, waist size, etc.). Specific image processing techniques used here include OpenCV and TensorFlow. Based on this information, the server uses a generative AI model to generate dozens of outfit ideas according to the user's specified outfit requirements (e.g., "date," "casual," "want to wear a jacket").

[0433] For example, a "casual" outfit for a "date" might be generated, such as "white T-shirt, blue jeans, and sneakers." This generated outfit idea is then further processed to produce an image tailored to the user's body shape. The generative AI model used here could be, for example, a GAN (Generative Opposing Network) model.

[0434] The server sends the generated outfit ideas and image files to the terminal. The terminal displays this information to the user, allowing the user to browse the suggested outfits. Furthermore, the user can select their favorite outfit.

[0435] Users can provide feedback on the suggested outfits (e.g., "Good," "Bad," "Points to improve," etc.). The device sends the user's feedback to the server. The server analyzes this feedback and optimizes the suggestion algorithm. This improves the accuracy of outfit suggestions in the future.

[0436] As a concrete example, consider a male user who is 170cm tall and weighs 60kg and wants a casual outfit for a date. The user first uploads a full-body photo to the application and specifies the requirements. The server analyzes this information and makes suggestions such as "white T-shirt, blue jeans, sneakers" that are best suited to the user, and also generates image renderings of the user wearing those clothes. The user reviews these suggestions and provides feedback, which helps to make future suggestions even more accurate.

[0437] Examples of prompt statements are as follows:

[0438] 1. "Please suggest a casual outfit for a date. I am male, 170cm tall, 60kg."

[0439] 2. "I'd like some office-appropriate outfit ideas using a casual jacket. I'm 160cm tall, weigh 50kg, and am female."

[0440] 3. "Please suggest a fashion outfit suitable for a weekend outing. I am a male, 180cm tall and weigh 70kg."

[0441] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0442] Step 1:

[0443] The user installs the system's application on their device and creates an account.

[0444] Input: Application installation, user information (name, email address, password)

[0445] Output: User account creation complete message

[0446] Specific actions: The user downloads the application, enters the required information, and creates an account.

[0447] Step 2:

[0448] The user enters their height, weight, gender, and a full-body photo into the application.

[0449] Input: Height, weight, gender, full-body photo

[0450] Output: Confirmation message for input information

[0451] Specific operation: Following the application's instructions, the user enters the requested information. Photos can be taken using the device's camera or existing photos can be uploaded.

[0452] Step 3:

[0453] The terminal checks the format of the entered information and sends the information to the server if the format is correct.

[0454] Input: User's height, weight, gender, and full-body photo.

[0455] Output: Data transmission result to the server (success / failure)

[0456] Specific operation: The terminal validates the input information to check if it is in the correct format. If correct, it sends the information to the server. If incorrect, it displays an error message.

[0457] Step 4:

[0458] The server preprocesses the received full-body photos and analyzes the user's body shape.

[0459] Input: Full body photo

[0460] Output: Body shape analysis data (height, shoulder width, waist size, etc.)

[0461] Specific operation: The server processes images using OpenCV and TensorFlow, performing preprocessing such as noise reduction and resizing. Then, it extracts the user's body shape information using an image analysis algorithm.

[0462] Step 5:

[0463] The server generates coordination ideas based on the analysis results, according to the user's specified requirements.

[0464] Input: Body shape analysis data, outfit requirements (e.g., "date," "casual")

[0465] Output: Coordination Ideas

[0466] Specific operation: The server generates the most suitable fashion combination for the user's body type and requirements based on predefined coordination rules and style guides.

[0467] Step 6:

[0468] The server uses a generative AI model to generate outfit ideas and create image files tailored to the user's body shape.

[0469] Input: Outfit ideas, body shape analysis data

[0470] Output: Image

[0471] Specific operation: The server uses a generative AI model (e.g., a GAN model) to convert the generated outfit ideas into image files tailored to the user's body shape.

[0472] Step 7:

[0473] The server sends the generated outfit ideas and image files to the terminal.

[0474] Input: Outfit ideas, image

[0475] Output: Data transmission result to the terminal (success / failure)

[0476] Specific operation: The server sends the generated coordination idea and image to the terminal. If the transmission is successful, proceed to the next step.

[0477] Step 8:

[0478] The device displays a list of suggested outfits and image files to the user.

[0479] Input: Outfit ideas, image

[0480] Output: Content displayed to the user

[0481] Specific operation: The terminal displays suggested outfits and image files to the user based on data received from the server. The user is then made able to view them.

[0482] Step 9:

[0483] Users view the suggested outfits and provide feedback.

[0484] Input: Outfit suggestions, image

[0485] Output: Feedback (e.g., "Good," "Bad," "Areas for Improvement")

[0486] Specific actions: The user reviews the suggestion and selects / enters appropriate feedback on the screen. This feedback will be used in the next step.

[0487] Step 10:

[0488] The device sends user feedback to the server.

[0489] Input: Feedback

[0490] Output: Data transmission result to the server (success / failure)

[0491] Specific operation: The device collects user feedback information and sends it to the server. If the transmission is successful, it proceeds to the next step.

[0492] Step 11:

[0493] The server analyzes the feedback and optimizes the proposed algorithm.

[0494] Input: Feedback

[0495] Output: Optimized proposed algorithm

[0496] Specific operation: The server analyzes the feedback and adjusts specific parameters and models to improve the accuracy of future coordination suggestions.

[0497] (Application Example 1)

[0498] 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."

[0499] Traditional fashion coordination systems made it difficult for users to visually confirm clothing that suited their body type and preferences. Furthermore, they did not adequately optimize coordination based on user feedback. Therefore, there was a need for a means to improve user satisfaction.

[0500] 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.

[0501] In this invention, the server includes means for the user to input height, weight, gender, and a full-body photograph; means for the user to specify coordination requirements; means for the server to analyze the user's body shape based on the full-body photograph; means for the server to generate coordination ideas according to the user's specified requirements based on the analysis results; means for the server to generate image representations of coordinations that the server deems suitable for the user; means for the server to transmit the generated coordination ideas and image representations to a terminal; means for the terminal to display a list of suggested coordinations and image representations to the user; means for the user to provide feedback; means for the server to analyze the user's feedback and optimize the suggestion algorithm; means for displaying the coordination selected by the user in the virtual store in real time; and means for the user to explore the virtual store using smart glasses and reflect the selected coordination on an avatar. This allows the user to visually confirm coordinations that suit their body shape and preferences and to have a real-time try-on experience in the virtual store.

[0502] A "user" is someone who uses the system to receive fashion coordination suggestions tailored to their body type and preferences.

[0503] "Height" refers to a physical measurement that indicates the vertical length from the user's head to their feet.

[0504] "Weight" refers to the user's body weight, which is generally measured in kilograms.

[0505] "Gender" refers to information that indicates which gender a user identifies with.

[0506] A "full-body photo" is an image that captures the user from head to toe in a single photograph.

[0507] "Coordination requirements" refer to the specific situation and clothing preferences specified by the user.

[0508] A "server" is a computer system that analyzes data sent by a user and performs the necessary processing.

[0509] "Body shape analysis" is the process of extracting the shape and dimensions of a user's body from a full-body photograph.

[0510] A "coordinate idea" is a combination of clothing items generated based on the user's requirements.

[0511] An "image" is a visual representation of an outfit optimized for the user's body shape.

[0512] A "device" refers to a computing device used by a user, such as a smartphone or smart glasses.

[0513] "Feedback" refers to the evaluations and opinions that users give regarding the suggested outfits.

[0514] A "suggestion algorithm" is an algorithm that generates coordinates based on user feedback.

[0515] A "virtual store" is a virtual space where users can virtually try on clothes through a computer screen or smart device.

[0516] "Smart glasses" are glasses-type devices that use augmented reality technology to display information to the user.

[0517] An "avatar" is a virtual representation of the user that acts on their behalf within a virtual store.

[0518] This invention relates to a system that suggests fashion coordinates tailored to a user's body shape and preferences. Specific embodiments thereof are described below.

[0519] Users explore virtual stores while wearing smart glasses. The main hardware used in this system is smart glasses, specifically a glasses-type device that utilizes augmented reality technology. Cloud servers are used for backend processing.

[0520] The user installs the application on smart glasses and enters their height, weight, gender, and a full-body photo. This information is sent from the smart glasses to a cloud server. The cloud server uses Python and OpenCV to analyze the full-body photo and extract the user's body shape information. This body shape information includes height, shoulder width, waist size, etc.

[0521] The server uses a generative AI model to generate multiple outfit ideas based on the extracted body shape information and the outfit requirements specified by the user. For example, for a "casual outfit for a date," a combination of "white T-shirt, blue jeans, and sneakers" is generated. These outfit ideas are further generated as image files tailored to the user's body shape.

[0522] The generated outfit ideas and image files are saved to cloud storage and sent back to the user's smart glasses. The smart glasses receive this information and display the outfits the user has selected in real time within the virtual store, so that they are reflected on the avatar in real time. The user can try on various outfits while exploring the virtual store.

[0523] When a user provides feedback on a suggested outfit, this feedback information is sent back to the cloud server. The server analyzes this feedback and optimizes the suggestion algorithm. This results in more accurate suggestions in the future.

[0524] As a concrete example, consider a male user who is 170cm tall and weighs 60kg and wants a casual outfit for a date. This user first uploads a full-body photo to the application and specifies the requirements. The server analyzes this information and generates suggestions for the most suitable outfit for the user, such as "white T-shirt, blue jeans, sneakers," and also generates image previews. The user can review these suggestions in a virtual store and try on the selected outfit. Furthermore, the user can provide feedback, which will help improve the accuracy of future suggestions.

[0525] An example of a prompt message is as follows:

[0526] "A male user, 170cm tall and weighing 60kg, is looking for a casual outfit for a date. Please generate an outfit including a white t-shirt, blue jeans, and sneakers that is ideal for him to try on in a virtual store. Based on the user's full-body photo, generate a real-time image that fits his body shape and display it on smart glasses."

[0527] This allows users to visually check outfits that suit their body type and preferences, and to try them on in real time within a virtual store.

[0528] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0529] Step 1:

[0530] The user launches an application installed on the smart glasses and enters their height, weight, gender, and a full-body photograph. The entered data is sent from the smart glasses to a cloud server. The input here is height, weight, gender, and a full-body photograph, and the output is the transmission of this data to the server.

[0531] Step 2:

[0532] The server preprocesses the received full-body images using image processing software (OpenCV). This preprocessing includes adjusting the resolution, removing the background, and reducing noise. The preprocessed full-body images become the input data for body shape analysis. The output is the preprocessed full-body image.

[0533] Step 3:

[0534] The server uses image analysis technology to extract the user's body shape information based on a pre-processed full-body photograph. Specifically, it obtains data such as height, shoulder width, and waist size. This analysis employs machine learning algorithms to perform calculations to obtain accurate body shape information. The input is a pre-processed full-body photograph, and the output is the extracted body shape information.

[0535] Step 4:

[0536] The server receives the user's specified outfit requirements (e.g., a casual outfit for a date) and processes them along with body shape information. A generative AI model (e.g., TensorFlow) is used to generate multiple outfit ideas. The input is the user's body shape information and outfit requirements, and the output is the generated outfit ideas.

[0537] Step 5:

[0538] The server generates an image tailored to the user's body shape based on the generated outfit idea. This uses computer graphics technology. The input is the outfit idea and body shape information, and the output is the generated image.

[0539] Step 6:

[0540] The server saves the generated outfit ideas and image files to cloud storage and sends them to the user's smart glasses. The input is the image files and outfit ideas, and the output is the transmission of this data to the user's smart glasses.

[0541] Step 7:

[0542] Smart glasses display received outfit images and ideas in real time. Users can explore a virtual store and have their selected outfits reflected on their avatar. In this process, the input is the user's clothing selection, and the output is the selected outfit displayed on the avatar.

[0543] Step 8:

[0544] The user provides feedback on the suggested outfit. This feedback is sent to the server via smart glasses. The input is the user's feedback, and the output is this feedback being sent to the server.

[0545] Step 9:

[0546] The server analyzes the feedback it receives and optimizes the proposal algorithm of the generated AI model. This improves the accuracy of future coordination suggestions. The input is user feedback, and the output is the optimized proposal algorithm.

[0547] 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.

[0548] This invention combines a system for users to receive fashion coordination suggestions tailored to their body shape and preferences with an emotion engine that recognizes the user's emotions. A specific embodiment of this system is described below.

[0549] The user first installs the system's application on their device and creates an account. The user then enters their height, weight, gender, and a full-body photograph. The device sends this information to the server. At this point, the device checks the format of the entered information and only sends it to the server if the format is correct.

[0550] The server preprocesses the received full-body photos and analyzes the user's body shape. Specifically, it uses image processing technology to extract the user's body shape information (height, shoulder width, waist size, etc.). Then, based on the user's specified outfit requirements (e.g., date, casual, want to wear a jacket), the server uses an AI model to generate dozens of outfit ideas.

[0551] This system also includes an emotion engine that can recognize the user's emotions from a full-body photo and feedback submitted by the user. The emotion engine analyzes the user's facial expressions and text-based feedback to determine their current emotional state. For example, it recognizes "joy" if the user is smiling and "dissatisfaction" if they are frowning.

[0552] The server adjusts outfit ideas based on the user's emotional data recognized by the emotion engine. For example, if a user wants a "date" and "casual" outfit, but the emotion engine detects "dissatisfaction" from the user's feedback, the server can consider the reasons why the user previously rejected an outfit and generate a different outfit idea.

[0553] The server generates image renderings of what the user would look like wearing the generated outfit ideas. This image generation uses deep learning-based image synthesis technology.

[0554] The server sends the generated outfit ideas and image files to the terminal. The terminal displays this information to the user. The user browses the suggested outfits and selects their favorite. Furthermore, the user can provide feedback on the suggestions (e.g., "Good," "Bad," "Points to improve").

[0555] The device sends user feedback to the server. The server analyzes the user feedback and sentiment data to optimize the proposed algorithm. This process includes retraining the machine learning model using the feedback and sentiment data.

[0556] As a concrete example, consider a male user who is 170cm tall and weighs 60kg, who wants a casual outfit for a date and provided "dissatisfied" feedback on the previous suggestion. The user first uploads a full-body photo to the application and specifies the requirements. The server analyzes this information and makes suggestions such as "white T-shirt, blue jeans, sneakers" that are best suited to the user, and also generates an image of the user wearing those clothes. If the emotion engine detects "dissatisfaction" with the user, the server re-evaluates the user's preferences and makes a different suggestion.

[0557] As described above, the present invention aims to provide a system that proposes the optimal fashion coordination based on the user's body shape and emotional state, thereby increasing user satisfaction.

[0558] The following describes the processing flow.

[0559] Step 1:

[0560] The user installs the application on their device and creates an account. The user enters their height, weight, gender, and a full-body photo.

[0561] Step 2:

[0562] The terminal checks the information entered by the user and verifies whether the input format is correct. If the format is correct, it sends the information to the server.

[0563] Step 3:

[0564] The server preprocesses the received full-body images. Preprocessing includes adjusting the image resolution and denoising.

[0565] Step 4:

[0566] The server analyzes the user's body shape information (e.g., height, weight, shoulder width, waist size) based on pre-processed full-body photographs. This is done using an image recognition algorithm.

[0567] Step 5:

[0568] Within the application, users specify their outfit requirements. Specifically, they select the situation (e.g., date, office), genre (e.g., casual, formal), and items they want to use (e.g., jacket, jeans).

[0569] Step 6:

[0570] The terminal sends the user's specified coordination requirements to the server.

[0571] Step 7:

[0572] Based on the received requirements and body shape information, the server uses an appropriate AI model to generate multiple outfit ideas. For example, based on "date" and "casual" preferences, it might select a combination of "white T-shirt, blue jeans, and sneakers."

[0573] Step 8:

[0574] Based on the generated outfit ideas, the server creates image renderings of what it would look like if the user were wearing these items. This image generation uses deep learning-based image synthesis technology.

[0575] Step 9:

[0576] The server sends the generated coordination ideas and image files to the terminal.

[0577] Step 10:

[0578] The device displays a list of suggested outfits and image files to the user.

[0579] Step 11:

[0580] Users review the suggested outfits and select their favorites. They can also optionally provide feedback (e.g., "Good," "Bad," "Suggests revision").

[0581] Step 12:

[0582] The device sends user feedback to the server.

[0583] Step 13:

[0584] The server uses an emotion engine to recognize the user's emotions from the feedback it receives. This is a process that analyzes the user's facial expressions and text-based feedback to identify their current emotional state. For example, it recognizes "joy" in response to "good" feedback and "dissatisfaction" in response to feedback requesting correction.

[0585] Step 14:

[0586] The server optimizes the suggestion algorithm based on the user's emotion data recognized by the emotion engine. This optimization includes adjusting the outfit suggestions to match the user's emotions. For example, if the user is "dissatisfied," a different outfit idea will be generated.

[0587] Step 15:

[0588] The server accumulates user emotional data and uses it as reference when suggesting outfits in the future. This makes it possible to provide more personalized outfit suggestions based on each user's individual preferences and emotions.

[0589] This allows the system to suggest the most suitable fashion coordinates based on the user's body shape and emotional state, thereby increasing user satisfaction.

[0590] (Example 2)

[0591] 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".

[0592] Conventional fashion coordination systems often failed to provide optimal suggestions based on the user's body shape and emotions, resulting in low user satisfaction. Furthermore, it was difficult to determine whether the generated coordination ideas were actually suitable for the user, making it difficult to incorporate user feedback into the system. This invention aims to solve these problems.

[0593] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0594] In this invention, the server includes means for pre-processing a full-body photograph to analyze the user's body shape, means for generating coordination ideas according to the user's specified requirements, and means for an emotion engine to analyze the user's facial expressions and feedback to identify their emotional state. This makes it possible to suggest the optimal fashion coordination based on the user's body shape and emotions.

[0595] A "user" is an individual who uses the system to receive fashion coordination suggestions based on their own body shape and preferences.

[0596] A "terminal" is a device used by a user to operate a system, and includes smartphones, tablets, and personal computers.

[0597] A "server" is a computer system that processes data sent from users or terminals and generates coordination ideas and image files.

[0598] A "full-body photograph" is a photograph that includes the user's entire appearance and is used for image analysis.

[0599] "Body shape" refers to data that indicates the user's physical characteristics, such as height, shoulder width, and waist size.

[0600] "Coordination requirements" refer to input information about the fashion style and situation the user desires, such as a casual style for a date.

[0601] "Coordination ideas" are fashion suggestions generated by the server based on the user's body shape and coordination requirements.

[0602] An "emotion engine" is software or an algorithm that analyzes a user's facial expressions and text-based feedback to identify their emotional state.

[0603] An "image rendering" is a simulated image showing how a user would look wearing the suggested outfit.

[0604] "Feedback" refers to the opinions and impressions that users provide regarding the suggested outfits, including "good," "bad," and "points for improvement."

[0605] A "suggestion algorithm" is an algorithm that generates optimal outfit ideas based on the user's body shape information and feedback.

[0606] This invention relates to a system that suggests the optimal fashion coordination based on the user's body shape and emotions. Specific embodiments are described below.

[0607] Hardware and software to be used

[0608] 1. Hardware

[0609] Terminal: A device used by a user to operate a system. Specific examples include smartphones, tablets, and personal computers.

[0610] 2. Software

[0611] Image processing libraries: Use OpenCV and TensorFlow to preprocess and analyze the user's full-body images.

[0612] AI Model: Generates outfit ideas using GPT-4 and StyleGAN.

[0613] Emotion Engine: Uses DeepFace and EmotionAPI to analyze user facial expressions and feedback to identify emotional states.

[0614] Image synthesis techniques: Generate images using GANs (e.g., StyleGAN and Pix2Pix).

[0615] System operation

[0616] 1. The user installs the system application on their device and creates their account. This involves entering information such as an email address and password.

[0617] 2. The user enters information such as their height, weight, gender, and a full-body photo into the application. They then specify the outfit requirements (e.g., date, casual).

[0618] 3. The terminal checks the format of the entered information and sends the information to the server only if the format is correct.

[0619] 4. The server preprocesses the received full-body images using OpenCV or TensorFlow to remove noise and adjust the resolution. Then, it analyzes body shape information (height, shoulder width, waist size, etc.) and stores it in a database.

[0620] 5. Based on the user's body shape information and coordination requirements, the server generates dozens of coordination ideas using GPT-4 or StyleGAN.

[0621] 6. The emotion engine included in the server (such as DeepFace or EmotionAPI) recognizes emotions from the user's full-body photo and feedback. Specifically, it performs facial expression analysis and text analysis to identify emotional states such as joy and dissatisfaction.

[0622] 7. The server adjusts the generated coordination ideas based on the emotional data recognized by the emotion engine. For example, if the user is perceived as "dissatisfied," a new suggestion will be generated based on the previous feedback.

[0623] 8. The server uses deep learning-based image synthesis techniques (such as StyleGAN or Pix2Pix) to generate image files of the user wearing the suggested items.

[0624] 9. The server sends the generated coordination ideas and image files to the terminal. The terminal displays these to the user, allowing the user to easily view the suggestions.

[0625] As a concrete example, consider a male user who is 170cm tall and weighs 60kg, who wants a casual outfit for a date and provided "dissatisfied" feedback on the previous suggestion. The user uploads a full-body photo and specifies the requirements. The server analyzes this information and makes suggestions such as a white T-shirt, blue jeans, and sneakers, and also generates an image of the user wearing those clothes. If the emotion engine detects "dissatisfaction," the server re-evaluates the user's preferences and makes a different suggestion.

[0626] Example of a prompt:

[0627] "A male user, 170cm tall and weighing 60kg, is requesting a casual outfit for a date. He gave negative feedback on the previous suggestion. Please generate a new suggestion and its image."

[0628] This system enables the suggestion of optimal fashion coordinates based on the user's body shape and emotions, thereby increasing user satisfaction.

[0629] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0630] The processing flow of this system's program

[0631] Step 1:

[0632] The user installs the system application on their device and creates an account. The user enters the required information (e.g., email address, password, etc.). The input in this step is the information entered by the user, and the output is a notification that the account has been created.

[0633] Step 2:

[0634] The user enters information such as their height, weight, gender, and a full-body photo into the application. They then specify their outfit requirements (e.g., date, casual). The input for this step consists of the user's physical information and outfit requirements, while the output is a confirmation screen of the entered information.

[0635] Step 3:

[0636] The terminal checks the format of the information entered by the user and sends the information to the server only if the format is correct. Specifically, it uses a format verification algorithm to check the integrity of the data. The input for this step is the information entered by the user, and the output is the result of the verification of whether the format is correct.

[0637] Step 4:

[0638] The server preprocesses the received full-body image using OpenCV or TensorFlow to remove noise and adjust the resolution. Next, it analyzes the user's body shape information (height, shoulder width, waist size, etc.) and stores it in a database. The input for this step is the user's full-body image, and the output is the analyzed body shape information.

[0639] Step 5:

[0640] The server generates dozens of outfit ideas using GPT-4 or StyleGAN based on the user's body shape information and outfit requirements. The AI ​​model processes the data based on the requirements specified by the user. The input for this step is the analyzed body shape information and outfit requirements, and the output is the generated outfit ideas.

[0641] Step 6:

[0642] The emotion engine (such as DeepFace or EmotionAPI) included in the server recognizes emotions from the user's full-body photo and feedback. Specifically, it performs facial expression analysis and text analysis to identify the user's emotional state. The input for this step is the user's full-body photo and feedback, and the output is the recognized emotion data.

[0643] Step 7:

[0644] The server adjusts the generated coordination ideas based on the emotion data recognized by the emotion engine. For example, if the user is identified as "dissatisfied," a new suggestion is generated based on the previous feedback. The input for this step is the emotion data and the previous feedback, and the output is the adjusted coordination idea.

[0645] Step 8:

[0646] Based on the generated outfit ideas, the server uses deep learning-based image synthesis techniques such as StyleGAN or Pix2Pix to generate image files of the user wearing the suggested items. The input for this step is the adjusted outfit idea, and the output is the generated image file.

[0647] Step 9:

[0648] The server sends generated outfit ideas and image files to the terminal. The terminal displays this information to the user, allowing them to easily view the suggested outfits. The input for this step is the data sent from the server, and the output is the outfit suggestions displayed to the user.

[0649] Step 10:

[0650] The user enters feedback on the suggested outfit (e.g., "Good," "Bad," "Points to improve"). The terminal sends the entered feedback data to the server. The input for this step is the user's feedback, and the output is the feedback data sent to the server.

[0651] Step 11:

[0652] The server analyzes the received feedback and sentiment data to optimize the proposed algorithm. Specifically, a machine learning model (e.g., retraining) is used to improve the accuracy of the next proposal. The input to this step is the feedback and sentiment data, and the output is the optimized proposed algorithm.

[0653] The above outlines the specific processing steps of this system.

[0654] (Application Example 2)

[0655] 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."

[0656] Traditional fashion coordination suggestion systems only generated outfits based on the user's body shape data, failing to consider the user's feelings. As a result, users were often dissatisfied with the suggestions, leading to a decline in overall satisfaction with the outfits. Furthermore, the lack of technology to simulate the user actually trying on the outfits made it difficult to grasp a concrete image of the suggested outfits.

[0657] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for recognizing the user's emotions using an emotion engine and analyzing the feedback, means for the server to adjust coordination ideas based on emotion data, and means for generating a virtual image of the user trying on the coordination using deep learning-based image synthesis technology. This makes it possible to propose coordinations that take the user's emotions into consideration and to provide concrete images through virtual try-on.

[0658] An "emotion engine" is a technology that analyzes a user's facial expressions and text-based feedback to recognize their current emotional state.

[0659] A "server" is a computer system that analyzes information sent by users and processes the data.

[0660] A "full-body photo" is image data that captures the user's entire body.

[0661] "Body shape data" refers to information about the user's physical dimensions, such as height, shoulder width, and waist size.

[0662] "Coordination ideas" are fashion combinations suggested based on the user's body shape and specified requirements.

[0663] "Deep learning-based image synthesis technology" is a technology that uses artificial intelligence to combine multiple images and generate new images.

[0664] "Feedback" refers to data that shows evaluations and opinions on suggestions provided by users.

[0665] A "virtual image" is a simulated image of how a user would look trying on a suggested outfit.

[0666] The "proposal algorithm" is a computational method that generates the optimal fashion coordination based on user data.

[0667] The system program that implements the example application is implemented as follows: First, the user inputs their height, weight, gender, and a full-body photo into the application using their smartphone. This information is first checked on the device for formatting, and only sent to the server if it is correct.

[0668] The server preprocesses the received full-body photographs and analyzes the user's body shape using image processing techniques. Image processing libraries such as OpenCV are used for this process. The data obtained from the body shape analysis includes specific dimensional information such as the user's height, shoulder width, and waist size.

[0669] Next, the server uses an AI model to generate dozens of outfit ideas based on the user's specified outfit requirements. This process utilizes machine learning libraries such as TensorFlow.

[0670] Furthermore, the server incorporates an emotion engine that recognizes the user's emotional state from full-body photos and feedback. It analyzes the user's facial expressions and text-based feedback to obtain emotional data such as "joy" and "dissatisfaction." Based on this emotional data, the server adjusts the outfit ideas.

[0671] Image synthesis technology based on deep learning is also used, generating virtual images of the user trying on the suggested outfits. TensorFlow is also used for this process.

[0672] The server generates outfit ideas and virtual images, which are then sent to the terminal, where the terminal displays this information to the user. The user can view the suggested outfits and provide feedback. The feedback is sent back to the server, which analyzes the feedback and sentiment data to optimize the suggestion algorithm.

[0673] As a concrete example, consider a male user who is 170cm tall and weighs 60kg and wants a casual outfit for a date, and who provided "dissatisfied" feedback on the previous suggestion. In this case, the user first uploads a full-body photo to the application and specifies the requirements. The server analyzes this information and makes suggestions such as "white T-shirt, blue jeans, sneakers," and also generates an image of the user wearing those clothes. If the emotion engine detects "dissatisfaction" with the user, the server re-evaluates the user's preferences and makes a different suggestion.

[0674] Examples of prompt statements to input into the generative AI model are as follows:

[0675] "A man who is 170cm tall and weighs 60kg is looking for a casual outfit for a date. Please generate images of a white T-shirt, blue jeans, and sneakers. The user is dissatisfied with the previous suggestions, so please consider more stylish suggestions."

[0676] As described above, this invention is a system that proposes the optimal fashion coordination based on the user's body shape and emotional state, thereby increasing user satisfaction.

[0677] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0678] Step 1:

[0679] The user launches the application using their smartphone and enters their height, weight, gender, and a full-body photo. After entering this information, the user specifies the outfit requirements (e.g., date, casual). The input data is formatted by the device, and only if it is in the correct format is the data sent to the server. The input includes height, weight, gender, full-body photo, and outfit requirements, and the output is the formatted user data.

[0680] Step 2:

[0681] The server preprocesses the received full-body photographs. Specifically, it uses image processing libraries such as OpenCV to perform denoising and resizing. The preprocessed images are then formatted to a format suitable for the next analysis step. The input is a full-body photograph of the user, and the output is the preprocessed image data.

[0682] Step 3:

[0683] The server analyzes the user's body shape using pre-processed full-body photographs. The server utilizes image processing techniques to extract body shape data such as height, shoulder width, and waist size. The OpenCV library is used for this analysis. The input is pre-processed image data, and the output is the user's body shape data.

[0684] Step 4:

[0685] The server uses an AI model to generate outfit ideas based on the user's specified outfit requirements. A machine learning model using TensorFlow is employed here. The input is body shape data and outfit requirements, and the output is multiple outfit ideas.

[0686] Step 5:

[0687] The emotion engine on the server analyzes emotional data from user-provided feedback and facial expression images. The emotion engine uses a specific algorithm to detect emotional states such as "joy" or "dissatisfaction." Input is the user's facial expression image and feedback text, and output is emotional data.

[0688] Step 6:

[0689] The server adjusts the generated coordination ideas based on emotional data. This is a process that modifies the priority and content of suggestions based on the user's emotional state. The input is coordination ideas and emotional data, and the output is the adjusted coordination ideas.

[0690] Step 7:

[0691] The server uses deep learning-based image synthesis technology to generate virtual images of the user trying on outfits. TensorFlow is used for this image generation. The input is a refined outfit idea and a pre-processed full-body photo of the user, and the output is a virtual try-on image.

[0692] Step 8:

[0693] The server sends the generated outfit ideas and virtual images to the terminal. The input is the virtual try-on image and outfit ideas, and the output is the data sent to the terminal.

[0694] Step 9:

[0695] The terminal displays the received coordinate list and virtual image to the user. The user can review these, make selections, or provide feedback. The input is data sent from the server, and the output is the user's display screen.

[0696] Step 10:

[0697] The user's feedback is sent back to the server. The server analyzes this feedback and sentiment data to retrain the model and optimize the proposed algorithm. The input is the user's feedback data, and the output is the optimized proposed algorithm.

[0698] 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.

[0699] The data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of the data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">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.

[0700] 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.

[0701] [Third Embodiment]

[0702] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0703] 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.

[0704] 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).

[0705] 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.

[0706] 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.

[0707] 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).

[0708] 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.

[0709] 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.

[0710] 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.

[0711] 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.

[0712] 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.

[0713] 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".

[0714] This invention relates to a system for users to receive fashion coordination suggestions that suit their body shape and preferences. Specific embodiments thereof are described below.

[0715] The user first installs the system's application on their device and creates an account. The user then enters their height, weight, gender, and a full-body photograph into the application. The device sends this information to the server. At this point, the device checks the format of the entered information and only sends it to the server if the format is correct.

[0716] The server preprocesses the received full-body photos and analyzes the user's body shape. Specifically, it uses image processing technology to extract the user's body shape information (height, shoulder width, waist size, etc.). Then, based on the user's specified outfit requirements (e.g., date, casual, want to wear a jacket), the server uses an AI model to generate dozens of outfit ideas.

[0717] For example, a casual outfit for a date might be generated, such as a white T-shirt, blue jeans, and sneakers. This generated outfit idea is then further adapted to the user's body shape, creating an image of what it would look like to actually wear those clothes.

[0718] The server sends the generated outfit ideas and image files to the terminal. The terminal displays this information to the user. The user browses the suggested outfits and selects their favorite. Furthermore, the user can provide feedback on the suggestions (e.g., "Good," "Bad," "Points to improve," etc.).

[0719] The terminal sends user feedback to the server. The server analyzes this feedback and optimizes the suggestion algorithm. This improves the accuracy of future coordination suggestions.

[0720] As a concrete example, consider a male user who is 170cm tall and weighs 60kg and wants a casual outfit for a date. The user first uploads a full-body photo to the application and specifies the requirements. The server analyzes this information and makes suggestions such as "white T-shirt, blue jeans, sneakers" that are best suited for the user, and also generates image files of the user wearing those clothes. The user reviews these suggestions and provides feedback, which helps to make future suggestions even more accurate.

[0721] As described above, the present invention aims to provide a system that proposes the optimal fashion coordination based on the user's body shape and requirements, thereby increasing user satisfaction.

[0722] The following describes the processing flow.

[0723] Step 1:

[0724] The user installs the application on their device and creates an account. The user enters their height, weight, gender, and a full-body photo.

[0725] Step 2:

[0726] The terminal checks the information entered by the user and verifies whether the input format is correct. If the format is correct, it sends the information to the server.

[0727] Step 3:

[0728] The server preprocesses the received full-body images. This preprocessing includes adjusting the image resolution and removing noise.

[0729] Step 4:

[0730] The server analyzes the user's body shape information (e.g., height, weight, shoulder width, waist size) based on pre-processed full-body photographs. This is done using an image recognition algorithm.

[0731] Step 5:

[0732] Users specify their outfit requirements within the application. This includes the situation (e.g., date, work), genre (e.g., casual, formal), and items they want to use (e.g., jacket, jeans).

[0733] Step 6:

[0734] The terminal sends the user's specified coordination requirements to the server.

[0735] Step 7:

[0736] The server uses an AI model to generate multiple outfit ideas based on the user's body shape information and specified requirements. For example, based on "date" and "casual" criteria, it might select "white T-shirt, blue jeans, and sneakers."

[0737] Step 8:

[0738] The server generates image renderings of what the user would look like wearing the generated outfit ideas. This image generation uses deep learning-based image synthesis technology.

[0739] Step 9:

[0740] The server sends the generated outfit ideas and image files to the terminal.

[0741] Step 10:

[0742] The device displays a list of suggested outfits and image files to the user.

[0743] Step 11:

[0744] Users review the suggested outfits and select their favorites. They can also optionally provide feedback (e.g., "Good," "Bad," "Suggestions for Improvement").

[0745] Step 12:

[0746] The device sends user feedback to the server.

[0747] Step 13:

[0748] The server analyzes user feedback and optimizes the proposed algorithm. This process includes retraining the machine learning model using the feedback data.

[0749] This will improve the accuracy of future outfit suggestions and increase user satisfaction.

[0750] (Example 1)

[0751] 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."

[0752] Conventional fashion coordination support systems lacked sufficient mechanisms to provide optimal coordination tailored to the user's body shape and preferences, making it difficult to offer highly accurate suggestions. Furthermore, the optimization of suggestion algorithms based on user feedback was not adequately implemented, posing a challenge in improving user satisfaction.

[0753] 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.

[0754] In this invention, the server includes means for pre-processing a full-body photograph of the user and analyzing the user's body shape, means for generating outfit ideas according to the user's specified requirements based on the analysis results, and means for generating outfit ideas using a generation AI model. This enables highly accurate outfit suggestions tailored to the user's body shape and preferences. Furthermore, it allows for optimization of the suggestion algorithm based on user feedback, thereby improving user satisfaction.

[0755] "User" refers to a person who uses this system, and specifically to a person who inputs personal information such as height, weight, gender, and full-body photos to receive outfit suggestions.

[0756] "Means for inputting height, weight, gender, and full-body photos" refers to technology that provides an interface for users to input their own physical data and images.

[0757] "Means for specifying coordination requirements" refers to an interface that allows users to input and specify their coordination needs (for example, "for a date," "casual," etc.).

[0758] "Means of verifying format" refers to a function that allows the terminal to verify that the information entered by the user is in the correct format and check for errors.

[0759] "Methods for pre-processing full-body images" refers to processes such as resizing and noise reduction performed to prepare the received images for easier analysis by the server.

[0760] "Means for analyzing a user's body shape" refers to technology in which a server uses image processing techniques to extract and analyze body shape information based on a full-body photograph of the user.

[0761] "Methods for generating coordination ideas" refers to technology in which a server generates multiple fashion coordination suggestions using AI models or similar tools, based on analysis results and user-specified requirements.

[0762] A "generative AI model" refers to an algorithm or technology that uses artificial intelligence to generate outfit ideas tailored to the user's preferences and body type.

[0763] "Methods for generating image data" refers to technology that creates images simulating how a user would look wearing an outfit based on outfit ideas generated by a server.

[0764] "Means for displaying suggested outfit lists and image files" refers to technology that visually displays outfit suggestions and image files received by the terminal from the server to the user.

[0765] "Means of providing feedback" refers to a function that allows users to input their opinions and requests for improvements regarding the suggested outfits through the application.

[0766] "Methods for optimizing the suggestion algorithm" refers to the technology in which the server analyzes user feedback and adjusts the algorithm to improve the accuracy and quality of future coordination suggestions.

[0767] This invention relates to a system for users to receive fashion coordination suggestions that suit their body shape and preferences. Specific embodiments thereof are described below.

[0768] Users first install the system's application on their device and create an account. During this process, users enter their height, weight, gender, and a full-body photograph into the application. This information is checked by the device for formatting, and only sent to the server if it is in the correct format.

[0769] The server preprocesses the received full-body photograph and analyzes the user's body shape. Specifically, it uses image processing techniques to extract the user's body shape information (height, shoulder width, waist size, etc.). Specific image processing techniques used here include OpenCV and TensorFlow. Based on this information, the server uses a generative AI model to generate dozens of outfit ideas according to the user's specified outfit requirements (e.g., "date," "casual," "want to wear a jacket").

[0770] For example, a "casual" outfit for a "date" might be generated, such as "white T-shirt, blue jeans, and sneakers." This generated outfit idea is then further processed to produce an image tailored to the user's body shape. The generative AI model used here could be, for example, a GAN (Generative Opposing Network) model.

[0771] The server sends the generated outfit ideas and image files to the terminal. The terminal displays this information to the user, allowing the user to browse the suggested outfits. Furthermore, the user can select their favorite outfit.

[0772] Users can provide feedback on the suggested outfits (e.g., "Good," "Bad," "Points to improve," etc.). The device sends the user's feedback to the server. The server analyzes this feedback and optimizes the suggestion algorithm. This improves the accuracy of outfit suggestions in the future.

[0773] As a concrete example, consider a male user who is 170cm tall and weighs 60kg and wants a casual outfit for a date. The user first uploads a full-body photo to the application and specifies the requirements. The server analyzes this information and makes suggestions such as "white T-shirt, blue jeans, sneakers" that are best suited to the user, and also generates image renderings of the user wearing those clothes. The user reviews these suggestions and provides feedback, which helps to make future suggestions even more accurate.

[0774] Examples of prompt statements are as follows:

[0775] 1. "Please suggest a casual outfit for a date. I am male, 170cm tall, 60kg."

[0776] 2. "I'd like some office-appropriate outfit ideas using a casual jacket. I'm 160cm tall, weigh 50kg, and am female."

[0777] 3. "Please suggest a fashion outfit suitable for a weekend outing. I am a male, 180cm tall and weigh 70kg."

[0778] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0779] Step 1:

[0780] The user installs the system's application on their device and creates an account.

[0781] Input: Application installation, user information (name, email address, password)

[0782] Output: User account creation complete message

[0783] Specific actions: The user downloads the application, enters the required information, and creates an account.

[0784] Step 2:

[0785] The user enters their height, weight, gender, and a full-body photo into the application.

[0786] Input: Height, weight, gender, full-body photo

[0787] Output: Confirmation message for input information

[0788] Specific operation: Following the application's instructions, the user enters the requested information. Photos can be taken using the device's camera or existing photos can be uploaded.

[0789] Step 3:

[0790] The terminal checks the format of the entered information and sends the information to the server if the format is correct.

[0791] Input: User's height, weight, gender, and full-body photo.

[0792] Output: Data transmission result to the server (success / failure)

[0793] Specific operation: The terminal validates the input information to check if it is in the correct format. If correct, it sends the information to the server. If incorrect, it displays an error message.

[0794] Step 4:

[0795] The server preprocesses the received full-body photos and analyzes the user's body shape.

[0796] Input: Full body photo

[0797] Output: Body shape analysis data (height, shoulder width, waist size, etc.)

[0798] Specific operation: The server processes images using OpenCV and TensorFlow, performing preprocessing such as noise reduction and resizing. Then, it extracts the user's body shape information using an image analysis algorithm.

[0799] Step 5:

[0800] The server generates coordination ideas based on the analysis results, according to the user's specified requirements.

[0801] Input: Body shape analysis data, outfit requirements (e.g., "date," "casual")

[0802] Output: Coordination Ideas

[0803] Specific operation: The server generates the most suitable fashion combination for the user's body type and requirements based on predefined coordination rules and style guides.

[0804] Step 6:

[0805] The server uses a generative AI model to generate outfit ideas and create image files tailored to the user's body shape.

[0806] Input: Outfit ideas, body shape analysis data

[0807] Output: Image

[0808] Specific operation: The server uses a generative AI model (e.g., a GAN model) to convert the generated outfit ideas into image files tailored to the user's body shape.

[0809] Step 7:

[0810] The server sends the generated outfit ideas and image files to the terminal.

[0811] Input: Outfit ideas, image

[0812] Output: Data transmission result to the terminal (success / failure)

[0813] Specific operation: The server sends the generated coordination idea and image to the terminal. If the transmission is successful, proceed to the next step.

[0814] Step 8:

[0815] The device displays a list of suggested outfits and image files to the user.

[0816] Input: Outfit ideas, image

[0817] Output: Content displayed to the user

[0818] Specific operation: The terminal displays suggested outfits and image files to the user based on data received from the server. The user is then made able to view them.

[0819] Step 9:

[0820] Users view the suggested outfits and provide feedback.

[0821] Input: Outfit suggestions, image

[0822] Output: Feedback (e.g., "Good," "Bad," "Areas for Improvement")

[0823] Specific actions: The user reviews the suggestion and selects / enters appropriate feedback on the screen. This feedback will be used in the next step.

[0824] Step 10:

[0825] The device sends user feedback to the server.

[0826] Input: Feedback

[0827] Output: Data transmission result to the server (success / failure)

[0828] Specific operation: The device collects user feedback information and sends it to the server. If the transmission is successful, it proceeds to the next step.

[0829] Step 11:

[0830] The server analyzes the feedback and optimizes the proposed algorithm.

[0831] Input: Feedback

[0832] Output: Optimized proposed algorithm

[0833] Specific operation: The server analyzes the feedback and adjusts specific parameters and models to improve the accuracy of future coordination suggestions.

[0834] (Application Example 1)

[0835] 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."

[0836] Traditional fashion coordination systems made it difficult for users to visually confirm clothing that suited their body type and preferences. Furthermore, they did not adequately optimize coordination based on user feedback. Therefore, there was a need for a means to improve user satisfaction.

[0837] 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.

[0838] In this invention, the server includes means for the user to input height, weight, gender, and a full-body photograph; means for the user to specify coordination requirements; means for the server to analyze the user's body shape based on the full-body photograph; means for the server to generate coordination ideas according to the user's specified requirements based on the analysis results; means for the server to generate image representations of coordinations that the server deems suitable for the user; means for the server to transmit the generated coordination ideas and image representations to a terminal; means for the terminal to display a list of suggested coordinations and image representations to the user; means for the user to provide feedback; means for the server to analyze the user's feedback and optimize the suggestion algorithm; means for displaying the coordination selected by the user in the virtual store in real time; and means for the user to explore the virtual store using smart glasses and reflect the selected coordination on an avatar. This allows the user to visually confirm coordinations that suit their body shape and preferences and to have a real-time try-on experience in the virtual store.

[0839] A "user" is someone who uses the system to receive fashion coordination suggestions tailored to their body type and preferences.

[0840] "Height" refers to a physical measurement that indicates the vertical length from the user's head to their feet.

[0841] "Weight" refers to the user's body weight, which is generally measured in kilograms.

[0842] "Gender" refers to information that indicates which gender a user identifies with.

[0843] A "full-body photo" is an image that captures the user from head to toe in a single photograph.

[0844] "Coordination requirements" refer to the specific situation and clothing preferences specified by the user.

[0845] A "server" is a computer system that analyzes data sent by a user and performs the necessary processing.

[0846] "Body shape analysis" is the process of extracting the shape and dimensions of a user's body from a full-body photograph.

[0847] A "coordinate idea" is a combination of clothing items generated based on the user's requirements.

[0848] An "image" is a visual representation of an outfit optimized for the user's body shape.

[0849] A "device" refers to a computing device used by a user, such as a smartphone or smart glasses.

[0850] "Feedback" refers to the evaluations and opinions that users give regarding the suggested outfits.

[0851] A "suggestion algorithm" is an algorithm that generates coordinates based on user feedback.

[0852] A "virtual store" is a virtual space where users can virtually try on clothes through a computer screen or smart device.

[0853] "Smart glasses" are glasses-type devices that use augmented reality technology to display information to the user.

[0854] An "avatar" is a virtual representation of the user that acts on their behalf within a virtual store.

[0855] This invention relates to a system that suggests fashion coordinates tailored to a user's body shape and preferences. Specific embodiments thereof are described below.

[0856] Users explore virtual stores while wearing smart glasses. The main hardware used in this system is smart glasses, specifically a glasses-type device that utilizes augmented reality technology. Cloud servers are used for backend processing.

[0857] The user installs the application on smart glasses and enters their height, weight, gender, and a full-body photo. This information is sent from the smart glasses to a cloud server. The cloud server uses Python and OpenCV to analyze the full-body photo and extract the user's body shape information. This body shape information includes height, shoulder width, waist size, etc.

[0858] The server uses a generative AI model to generate multiple outfit ideas based on the extracted body shape information and the outfit requirements specified by the user. For example, for a "casual outfit for a date," a combination of "white T-shirt, blue jeans, and sneakers" is generated. These outfit ideas are further generated as image files tailored to the user's body shape.

[0859] The generated outfit ideas and image files are saved to cloud storage and sent back to the user's smart glasses. The smart glasses receive this information and display the outfits the user has selected in real time within the virtual store, so that they are reflected on the avatar in real time. The user can try on various outfits while exploring the virtual store.

[0860] When a user provides feedback on a suggested outfit, this feedback information is sent back to the cloud server. The server analyzes this feedback and optimizes the suggestion algorithm. This results in more accurate suggestions in the future.

[0861] As a concrete example, consider a male user who is 170cm tall and weighs 60kg and wants a casual outfit for a date. This user first uploads a full-body photo to the application and specifies the requirements. The server analyzes this information and generates suggestions for the most suitable outfit for the user, such as "white T-shirt, blue jeans, sneakers," and also generates image previews. The user can review these suggestions in a virtual store and try on the selected outfit. Furthermore, the user can provide feedback, which will help improve the accuracy of future suggestions.

[0862] An example of a prompt message is as follows:

[0863] "A male user, 170cm tall and weighing 60kg, is looking for a casual outfit for a date. Please generate an outfit including a white t-shirt, blue jeans, and sneakers that is ideal for him to try on in a virtual store. Based on the user's full-body photo, generate a real-time image that fits his body shape and display it on smart glasses."

[0864] This allows users to visually check outfits that suit their body type and preferences, and to try them on in real time within a virtual store.

[0865] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0866] Step 1:

[0867] The user launches an application installed on the smart glasses and enters their height, weight, gender, and a full-body photograph. The entered data is sent from the smart glasses to a cloud server. The input here is height, weight, gender, and a full-body photograph, and the output is the transmission of this data to the server.

[0868] Step 2:

[0869] The server preprocesses the received full-body images using image processing software (OpenCV). This preprocessing includes adjusting the resolution, removing the background, and reducing noise. The preprocessed full-body images become the input data for body shape analysis. The output is the preprocessed full-body image.

[0870] Step 3:

[0871] The server uses image analysis technology to extract the user's body shape information based on a pre-processed full-body photograph. Specifically, it obtains data such as height, shoulder width, and waist size. This analysis employs machine learning algorithms to perform calculations to obtain accurate body shape information. The input is a pre-processed full-body photograph, and the output is the extracted body shape information.

[0872] Step 4:

[0873] The server receives the user's specified outfit requirements (e.g., a casual outfit for a date) and processes them along with body shape information. A generative AI model (e.g., TensorFlow) is used to generate multiple outfit ideas. The input is the user's body shape information and outfit requirements, and the output is the generated outfit ideas.

[0874] Step 5:

[0875] The server generates an image tailored to the user's body shape based on the generated outfit idea. This uses computer graphics technology. The input is the outfit idea and body shape information, and the output is the generated image.

[0876] Step 6:

[0877] The server saves the generated outfit ideas and image files to cloud storage and sends them to the user's smart glasses. The input is the image files and outfit ideas, and the output is the transmission of this data to the user's smart glasses.

[0878] Step 7:

[0879] Smart glasses display received outfit images and ideas in real time. Users can explore a virtual store and have their selected outfits reflected on their avatar. In this process, the input is the user's clothing selection, and the output is the selected outfit displayed on the avatar.

[0880] Step 8:

[0881] The user provides feedback on the suggested outfit. This feedback is sent to the server via smart glasses. The input is the user's feedback, and the output is this feedback being sent to the server.

[0882] Step 9:

[0883] The server analyzes the feedback it receives and optimizes the proposal algorithm of the generated AI model. This improves the accuracy of future coordination suggestions. The input is user feedback, and the output is the optimized proposal algorithm.

[0884] 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.

[0885] This invention combines a system for users to receive fashion coordination suggestions tailored to their body shape and preferences with an emotion engine that recognizes the user's emotions. A specific embodiment of this system is described below.

[0886] The user first installs the system's application on their device and creates an account. The user then enters their height, weight, gender, and a full-body photograph. The device sends this information to the server. At this point, the device checks the format of the entered information and only sends it to the server if the format is correct.

[0887] The server preprocesses the received full-body photos and analyzes the user's body shape. Specifically, it uses image processing technology to extract the user's body shape information (height, shoulder width, waist size, etc.). Then, based on the user's specified outfit requirements (e.g., date, casual, want to wear a jacket), the server uses an AI model to generate dozens of outfit ideas.

[0888] This system also includes an emotion engine that can recognize the user's emotions from a full-body photo and feedback submitted by the user. The emotion engine analyzes the user's facial expressions and text-based feedback to determine their current emotional state. For example, it recognizes "joy" if the user is smiling and "dissatisfaction" if they are frowning.

[0889] The server adjusts outfit ideas based on the user's emotional data recognized by the emotion engine. For example, if a user wants a "date" and "casual" outfit, but the emotion engine detects "dissatisfaction" from the user's feedback, the server can consider the reasons why the user previously rejected an outfit and generate a different outfit idea.

[0890] The server generates image renderings of what the user would look like wearing the generated outfit ideas. This image generation uses deep learning-based image synthesis technology.

[0891] The server sends the generated outfit ideas and image files to the terminal. The terminal displays this information to the user. The user browses the suggested outfits and selects their favorite. Furthermore, the user can provide feedback on the suggestions (e.g., "Good," "Bad," "Points to improve").

[0892] The device sends user feedback to the server. The server analyzes the user feedback and sentiment data to optimize the proposed algorithm. This process includes retraining the machine learning model using the feedback and sentiment data.

[0893] As a concrete example, consider a male user who is 170cm tall and weighs 60kg, who wants a casual outfit for a date and provided "dissatisfied" feedback on the previous suggestion. The user first uploads a full-body photo to the application and specifies the requirements. The server analyzes this information and makes suggestions such as "white T-shirt, blue jeans, sneakers" that are best suited to the user, and also generates an image of the user wearing those clothes. If the emotion engine detects "dissatisfaction" with the user, the server re-evaluates the user's preferences and makes a different suggestion.

[0894] As described above, the present invention aims to provide a system that proposes the optimal fashion coordination based on the user's body shape and emotional state, thereby increasing user satisfaction.

[0895] The following describes the processing flow.

[0896] Step 1:

[0897] The user installs the application on their device and creates an account. The user enters their height, weight, gender, and a full-body photo.

[0898] Step 2:

[0899] The terminal checks the information entered by the user and verifies whether the input format is correct. If the format is correct, it sends the information to the server.

[0900] Step 3:

[0901] The server preprocesses the received full-body images. Preprocessing includes adjusting the image resolution and denoising.

[0902] Step 4:

[0903] The server analyzes the user's body shape information (e.g., height, weight, shoulder width, waist size) based on pre-processed full-body photographs. This is done using an image recognition algorithm.

[0904] Step 5:

[0905] Within the application, users specify their outfit requirements. Specifically, they select the situation (e.g., date, office), genre (e.g., casual, formal), and items they want to use (e.g., jacket, jeans).

[0906] Step 6:

[0907] The terminal sends the user's specified coordination requirements to the server.

[0908] Step 7:

[0909] Based on the received requirements and body shape information, the server uses an appropriate AI model to generate multiple outfit ideas. For example, based on "date" and "casual" preferences, it might select a combination of "white T-shirt, blue jeans, and sneakers."

[0910] Step 8:

[0911] Based on the generated outfit ideas, the server creates image renderings of what it would look like if the user were wearing these items. This image generation uses deep learning-based image synthesis technology.

[0912] Step 9:

[0913] The server sends the generated coordination ideas and image files to the terminal.

[0914] Step 10:

[0915] The device displays a list of suggested outfits and image files to the user.

[0916] Step 11:

[0917] Users review the suggested outfits and select their favorites. They can also optionally provide feedback (e.g., "Good," "Bad," "Suggests revision").

[0918] Step 12:

[0919] The device sends user feedback to the server.

[0920] Step 13:

[0921] The server uses an emotion engine to recognize the user's emotions from the feedback it receives. This is a process that analyzes the user's facial expressions and text-based feedback to identify their current emotional state. For example, it recognizes "joy" in response to "good" feedback and "dissatisfaction" in response to feedback requesting correction.

[0922] Step 14:

[0923] The server optimizes the suggestion algorithm based on the user's emotion data recognized by the emotion engine. This optimization includes adjusting the outfit suggestions to match the user's emotions. For example, if the user is "dissatisfied," a different outfit idea will be generated.

[0924] Step 15:

[0925] The server accumulates user emotional data and uses it as reference when suggesting outfits in the future. This makes it possible to provide more personalized outfit suggestions based on each user's individual preferences and emotions.

[0926] This allows the system to suggest the most suitable fashion coordinates based on the user's body shape and emotional state, thereby increasing user satisfaction.

[0927] (Example 2)

[0928] 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."

[0929] Conventional fashion coordination systems often failed to provide optimal suggestions based on the user's body shape and emotions, resulting in low user satisfaction. Furthermore, it was difficult to determine whether the generated coordination ideas were actually suitable for the user, making it difficult to incorporate user feedback into the system. This invention aims to solve these problems.

[0930] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0931] In this invention, the server includes means for pre-processing a full-body photograph to analyze the user's body shape, means for generating coordination ideas according to the user's specified requirements, and means for an emotion engine to analyze the user's facial expressions and feedback to identify their emotional state. This makes it possible to suggest the optimal fashion coordination based on the user's body shape and emotions.

[0932] A "user" is an individual who uses the system to receive fashion coordination suggestions based on their own body shape and preferences.

[0933] A "terminal" is a device used by a user to operate a system, and includes smartphones, tablets, and personal computers.

[0934] A "server" is a computer system that processes data sent from users or terminals and generates coordination ideas and image files.

[0935] A "full-body photograph" is a photograph that includes the user's entire appearance and is used for image analysis.

[0936] "Body shape" refers to data that indicates the user's physical characteristics, such as height, shoulder width, and waist size.

[0937] "Coordination requirements" refer to input information about the fashion style and situation the user desires, such as a casual style for a date.

[0938] "Coordination ideas" are fashion suggestions generated by the server based on the user's body shape and coordination requirements.

[0939] An "emotion engine" is software or an algorithm that analyzes a user's facial expressions and text-based feedback to identify their emotional state.

[0940] An "image rendering" is a simulated image showing how a user would look wearing the suggested outfit.

[0941] "Feedback" refers to the opinions and impressions that users provide regarding the suggested outfits, including "good," "bad," and "points for improvement."

[0942] A "suggestion algorithm" is an algorithm that generates optimal outfit ideas based on the user's body shape information and feedback.

[0943] This invention relates to a system that suggests the optimal fashion coordination based on the user's body shape and emotions. Specific embodiments are described below.

[0944] Hardware and software to be used

[0945] 1. Hardware

[0946] Terminal: A device used by a user to operate a system. Specific examples include smartphones, tablets, and personal computers.

[0947] 2. Software

[0948] Image processing libraries: Use OpenCV and TensorFlow to preprocess and analyze the user's full-body images.

[0949] AI Model: Generates outfit ideas using GPT-4 and StyleGAN.

[0950] Emotion Engine: Uses DeepFace and EmotionAPI to analyze user facial expressions and feedback to identify emotional states.

[0951] Image synthesis techniques: Generate images using GANs (e.g., StyleGAN and Pix2Pix).

[0952] System operation

[0953] 1. The user installs the system application on their device and creates their account. This involves entering information such as an email address and password.

[0954] 2. The user enters information such as their height, weight, gender, and a full-body photo into the application. They then specify the outfit requirements (e.g., date, casual).

[0955] 3. The terminal checks the format of the entered information and sends the information to the server only if the format is correct.

[0956] 4. The server preprocesses the received full-body images using OpenCV or TensorFlow to remove noise and adjust the resolution. Then, it analyzes body shape information (height, shoulder width, waist size, etc.) and stores it in a database.

[0957] 5. Based on the user's body shape information and coordination requirements, the server generates dozens of coordination ideas using GPT-4 or StyleGAN.

[0958] 6. The emotion engine included in the server (such as DeepFace or EmotionAPI) recognizes emotions from the user's full-body photo and feedback. Specifically, it performs facial expression analysis and text analysis to identify emotional states such as joy and dissatisfaction.

[0959] 7. The server adjusts the generated coordination ideas based on the emotional data recognized by the emotion engine. For example, if the user is perceived as "dissatisfied," a new suggestion will be generated based on the previous feedback.

[0960] 8. The server uses deep learning-based image synthesis techniques (such as StyleGAN or Pix2Pix) to generate image files of the user wearing the suggested items.

[0961] 9. The server sends the generated coordination ideas and image files to the terminal. The terminal displays these to the user, allowing the user to easily view the suggestions.

[0962] As a concrete example, consider a male user who is 170cm tall and weighs 60kg, who wants a casual outfit for a date and provided "dissatisfied" feedback on the previous suggestion. The user uploads a full-body photo and specifies the requirements. The server analyzes this information and makes suggestions such as a white T-shirt, blue jeans, and sneakers, and also generates an image of the user wearing those clothes. If the emotion engine detects "dissatisfaction," the server re-evaluates the user's preferences and makes a different suggestion.

[0963] Example of a prompt:

[0964] "A male user, 170cm tall and weighing 60kg, is requesting a casual outfit for a date. He gave negative feedback on the previous suggestion. Please generate a new suggestion and its image."

[0965] This system enables the suggestion of optimal fashion coordinates based on the user's body shape and emotions, thereby increasing user satisfaction.

[0966] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0967] The processing flow of this system's program

[0968] Step 1:

[0969] The user installs the system application on their device and creates an account. The user enters the required information (e.g., email address, password, etc.). The input in this step is the information entered by the user, and the output is a notification that the account has been created.

[0970] Step 2:

[0971] The user enters information such as their height, weight, gender, and a full-body photo into the application. They then specify their outfit requirements (e.g., date, casual). The input for this step consists of the user's physical information and outfit requirements, while the output is a confirmation screen of the entered information.

[0972] Step 3:

[0973] The terminal checks the format of the information entered by the user and sends the information to the server only if the format is correct. Specifically, it uses a format verification algorithm to check the integrity of the data. The input for this step is the information entered by the user, and the output is the result of the verification of whether the format is correct.

[0974] Step 4:

[0975] The server preprocesses the received full-body image using OpenCV or TensorFlow to remove noise and adjust the resolution. Next, it analyzes the user's body shape information (height, shoulder width, waist size, etc.) and stores it in a database. The input for this step is the user's full-body image, and the output is the analyzed body shape information.

[0976] Step 5:

[0977] The server generates dozens of outfit ideas using GPT-4 or StyleGAN based on the user's body shape information and outfit requirements. The AI ​​model processes the data based on the requirements specified by the user. The input for this step is the analyzed body shape information and outfit requirements, and the output is the generated outfit ideas.

[0978] Step 6:

[0979] The emotion engine (such as DeepFace or EmotionAPI) included in the server recognizes emotions from the user's full-body photo and feedback. Specifically, it performs facial expression analysis and text analysis to identify the user's emotional state. The input for this step is the user's full-body photo and feedback, and the output is the recognized emotion data.

[0980] Step 7:

[0981] The server adjusts the generated coordination ideas based on the emotion data recognized by the emotion engine. For example, if the user is identified as "dissatisfied," a new suggestion is generated based on the previous feedback. The input for this step is the emotion data and the previous feedback, and the output is the adjusted coordination idea.

[0982] Step 8:

[0983] Based on the generated outfit ideas, the server uses deep learning-based image synthesis techniques such as StyleGAN or Pix2Pix to generate image files of the user wearing the suggested items. The input for this step is the adjusted outfit idea, and the output is the generated image file.

[0984] Step 9:

[0985] The server sends generated outfit ideas and image files to the terminal. The terminal displays this information to the user, allowing them to easily view the suggested outfits. The input for this step is the data sent from the server, and the output is the outfit suggestions displayed to the user.

[0986] Step 10:

[0987] The user enters feedback on the suggested outfit (e.g., "Good," "Bad," "Points to improve"). The terminal sends the entered feedback data to the server. The input for this step is the user's feedback, and the output is the feedback data sent to the server.

[0988] Step 11:

[0989] The server analyzes the received feedback and sentiment data to optimize the proposed algorithm. Specifically, a machine learning model (e.g., retraining) is used to improve the accuracy of the next proposal. The input to this step is the feedback and sentiment data, and the output is the optimized proposed algorithm.

[0990] The above outlines the specific processing steps of this system.

[0991] (Application Example 2)

[0992] 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."

[0993] Traditional fashion coordination suggestion systems only generated outfits based on the user's body shape data, failing to consider the user's feelings. As a result, users were often dissatisfied with the suggestions, leading to a decline in overall satisfaction with the outfits. Furthermore, the lack of technology to simulate the user actually trying on the outfits made it difficult to grasp a concrete image of the suggested outfits.

[0994] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for recognizing the user's emotions using an emotion engine and analyzing the feedback, means for the server to adjust coordination ideas based on emotion data, and means for generating a virtual image of the user trying on the coordination using deep learning-based image synthesis technology. This makes it possible to propose coordinations that take the user's emotions into consideration and to provide concrete images through virtual try-on.

[0995] An "emotion engine" is a technology that analyzes a user's facial expressions and text-based feedback to recognize their current emotional state.

[0996] A "server" is a computer system that analyzes information sent by users and processes the data.

[0997] A "full-body photo" is image data that captures the user's entire body.

[0998] "Body shape data" refers to information about the user's physical dimensions, such as height, shoulder width, and waist size.

[0999] "Coordination ideas" are fashion combinations suggested based on the user's body shape and specified requirements.

[1000] "Deep learning-based image synthesis technology" is a technology that uses artificial intelligence to combine multiple images and generate new images.

[1001] "Feedback" refers to data that shows evaluations and opinions on suggestions provided by users.

[1002] A "virtual image" is a simulated image of how a user would look trying on a suggested outfit.

[1003] The "proposal algorithm" is a computational method that generates the optimal fashion coordination based on user data.

[1004] The system program that implements the example application is implemented as follows: First, the user inputs their height, weight, gender, and a full-body photo into the application using their smartphone. This information is first checked on the device for formatting, and only sent to the server if it is correct.

[1005] The server preprocesses the received full-body photographs and analyzes the user's body shape using image processing techniques. Image processing libraries such as OpenCV are used for this process. The data obtained from the body shape analysis includes specific dimensional information such as the user's height, shoulder width, and waist size.

[1006] Next, the server uses an AI model to generate dozens of outfit ideas based on the user's specified outfit requirements. This process utilizes machine learning libraries such as TensorFlow.

[1007] Furthermore, the server incorporates an emotion engine that recognizes the user's emotional state from full-body photos and feedback. It analyzes the user's facial expressions and text-based feedback to obtain emotional data such as "joy" and "dissatisfaction." Based on this emotional data, the server adjusts the outfit ideas.

[1008] Image synthesis technology based on deep learning is also used, generating virtual images of the user trying on the suggested outfits. TensorFlow is also used for this process.

[1009] The server generates outfit ideas and virtual images, which are then sent to the terminal, where the terminal displays this information to the user. The user can view the suggested outfits and provide feedback. The feedback is sent back to the server, which analyzes the feedback and sentiment data to optimize the suggestion algorithm.

[1010] As a concrete example, consider a male user who is 170cm tall and weighs 60kg and wants a casual outfit for a date, and who provided "dissatisfied" feedback on the previous suggestion. In this case, the user first uploads a full-body photo to the application and specifies the requirements. The server analyzes this information and makes suggestions such as "white T-shirt, blue jeans, sneakers," and also generates an image of the user wearing those clothes. If the emotion engine detects "dissatisfaction" with the user, the server re-evaluates the user's preferences and makes a different suggestion.

[1011] Examples of prompt statements to input into the generative AI model are as follows:

[1012] "A man who is 170cm tall and weighs 60kg is looking for a casual outfit for a date. Please generate images of a white T-shirt, blue jeans, and sneakers. The user is dissatisfied with the previous suggestions, so please consider more stylish suggestions."

[1013] As described above, this invention is a system that proposes the optimal fashion coordination based on the user's body shape and emotional state, thereby increasing user satisfaction.

[1014] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1015] Step 1:

[1016] The user launches the application using their smartphone and enters their height, weight, gender, and a full-body photo. After entering this information, the user specifies the outfit requirements (e.g., date, casual). The input data is formatted by the device, and only if it is in the correct format is the data sent to the server. The input includes height, weight, gender, full-body photo, and outfit requirements, and the output is the formatted user data.

[1017] Step 2:

[1018] The server preprocesses the received full-body photographs. Specifically, it uses image processing libraries such as OpenCV to perform denoising and resizing. The preprocessed images are then formatted to a format suitable for the next analysis step. The input is a full-body photograph of the user, and the output is the preprocessed image data.

[1019] Step 3:

[1020] The server analyzes the user's body shape using pre-processed full-body photographs. The server utilizes image processing techniques to extract body shape data such as height, shoulder width, and waist size. The OpenCV library is used for this analysis. The input is pre-processed image data, and the output is the user's body shape data.

[1021] Step 4:

[1022] The server uses an AI model to generate outfit ideas based on the user's specified outfit requirements. A machine learning model using TensorFlow is employed here. The input is body shape data and outfit requirements, and the output is multiple outfit ideas.

[1023] Step 5:

[1024] The emotion engine on the server analyzes emotional data from user-provided feedback and facial expression images. The emotion engine uses a specific algorithm to detect emotional states such as "joy" or "dissatisfaction." Input is the user's facial expression image and feedback text, and output is emotional data.

[1025] Step 6:

[1026] The server adjusts the generated coordination ideas based on emotional data. This is a process that modifies the priority and content of suggestions based on the user's emotional state. The input is coordination ideas and emotional data, and the output is the adjusted coordination ideas.

[1027] Step 7:

[1028] The server uses deep learning-based image synthesis technology to generate virtual images of the user trying on outfits. TensorFlow is used for this image generation. The input is a refined outfit idea and a pre-processed full-body photo of the user, and the output is a virtual try-on image.

[1029] Step 8:

[1030] The server sends the generated outfit ideas and virtual images to the terminal. The input is the virtual try-on image and outfit ideas, and the output is the data sent to the terminal.

[1031] Step 9:

[1032] The terminal displays the received coordinate list and virtual image to the user. The user can review these, make selections, or provide feedback. The input is data sent from the server, and the output is the user's display screen.

[1033] Step 10:

[1034] The user's feedback is sent back to the server. The server analyzes this feedback and sentiment data to retrain the model and optimize the proposed algorithm. The input is the user's feedback data, and the output is the optimized proposed algorithm.

[1035] 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.

[1036] The data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of the data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">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.

[1037] 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.

[1038] [Fourth Embodiment]

[1039] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1040] 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.

[1041] 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).

[1042] 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.

[1043] 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.

[1044] 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).

[1045] 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.

[1046] 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.

[1047] 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.

[1048] 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.

[1049] 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.

[1050] 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.

[1051] 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".

[1052] This invention relates to a system for users to receive fashion coordination suggestions that suit their body shape and preferences. Specific embodiments thereof are described below.

[1053] The user first installs the system's application on their device and creates an account. The user then enters their height, weight, gender, and a full-body photograph into the application. The device sends this information to the server. At this point, the device checks the format of the entered information and only sends it to the server if the format is correct.

[1054] The server preprocesses the received full-body photos and analyzes the user's body shape. Specifically, it uses image processing technology to extract the user's body shape information (height, shoulder width, waist size, etc.). Then, based on the user's specified outfit requirements (e.g., date, casual, want to wear a jacket), the server uses an AI model to generate dozens of outfit ideas.

[1055] For example, a casual outfit for a date might be generated, such as a white T-shirt, blue jeans, and sneakers. This generated outfit idea is then further adapted to the user's body shape, creating an image of what it would look like to actually wear those clothes.

[1056] The server sends the generated outfit ideas and image files to the terminal. The terminal displays this information to the user. The user browses the suggested outfits and selects their favorite. Furthermore, the user can provide feedback on the suggestions (e.g., "Good," "Bad," "Points to improve," etc.).

[1057] The terminal sends user feedback to the server. The server analyzes this feedback and optimizes the suggestion algorithm. This improves the accuracy of future coordination suggestions.

[1058] As a concrete example, consider a male user who is 170cm tall and weighs 60kg and wants a casual outfit for a date. The user first uploads a full-body photo to the application and specifies the requirements. The server analyzes this information and makes suggestions such as "white T-shirt, blue jeans, sneakers" that are best suited for the user, and also generates image files of the user wearing those clothes. The user reviews these suggestions and provides feedback, which helps to make future suggestions even more accurate.

[1059] As described above, the present invention aims to provide a system that proposes the optimal fashion coordination based on the user's body shape and requirements, thereby increasing user satisfaction.

[1060] The following describes the processing flow.

[1061] Step 1:

[1062] The user installs the application on their device and creates an account. The user enters their height, weight, gender, and a full-body photo.

[1063] Step 2:

[1064] The terminal checks the information entered by the user and verifies whether the input format is correct. If the format is correct, it sends the information to the server.

[1065] Step 3:

[1066] The server preprocesses the received full-body images. This preprocessing includes adjusting the image resolution and removing noise.

[1067] Step 4:

[1068] The server analyzes the user's body shape information (e.g., height, weight, shoulder width, waist size) based on pre-processed full-body photographs. This is done using an image recognition algorithm.

[1069] Step 5:

[1070] Users specify their outfit requirements within the application. This includes the situation (e.g., date, work), genre (e.g., casual, formal), and items they want to use (e.g., jacket, jeans).

[1071] Step 6:

[1072] The terminal sends the user's specified coordination requirements to the server.

[1073] Step 7:

[1074] The server uses an AI model to generate multiple outfit ideas based on the user's body shape information and specified requirements. For example, based on "date" and "casual" criteria, it might select "white T-shirt, blue jeans, and sneakers."

[1075] Step 8:

[1076] The server generates image renderings of what the user would look like wearing the generated outfit ideas. This image generation uses deep learning-based image synthesis technology.

[1077] Step 9:

[1078] The server sends the generated outfit ideas and image files to the terminal.

[1079] Step 10:

[1080] The device displays a list of suggested outfits and image files to the user.

[1081] Step 11:

[1082] Users review the suggested outfits and select their favorites. They can also optionally provide feedback (e.g., "Good," "Bad," "Suggestions for Improvement").

[1083] Step 12:

[1084] The device sends user feedback to the server.

[1085] Step 13:

[1086] The server analyzes user feedback and optimizes the proposed algorithm. This process includes retraining the machine learning model using the feedback data.

[1087] This will improve the accuracy of future outfit suggestions and increase user satisfaction.

[1088] (Example 1)

[1089] 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".

[1090] Conventional fashion coordination support systems lacked sufficient mechanisms to provide optimal coordination tailored to the user's body shape and preferences, making it difficult to offer highly accurate suggestions. Furthermore, the optimization of suggestion algorithms based on user feedback was not adequately implemented, posing a challenge in improving user satisfaction.

[1091] 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.

[1092] In this invention, the server includes means for pre-processing a full-body photograph of the user and analyzing the user's body shape, means for generating outfit ideas according to the user's specified requirements based on the analysis results, and means for generating outfit ideas using a generation AI model. This enables highly accurate outfit suggestions tailored to the user's body shape and preferences. Furthermore, it allows for optimization of the suggestion algorithm based on user feedback, thereby improving user satisfaction.

[1093] "User" refers to a person who uses this system, and specifically to a person who inputs personal information such as height, weight, gender, and full-body photos to receive outfit suggestions.

[1094] "Means for inputting height, weight, gender, and full-body photos" refers to technology that provides an interface for users to input their own physical data and images.

[1095] "Means for specifying coordination requirements" refers to an interface that allows users to input and specify their coordination needs (for example, "for a date," "casual," etc.).

[1096] "Means of verifying format" refers to a function that allows the terminal to verify that the information entered by the user is in the correct format and check for errors.

[1097] "Methods for pre-processing full-body images" refers to processes such as resizing and noise reduction performed to prepare the received images for easier analysis by the server.

[1098] "Means for analyzing a user's body shape" refers to technology in which a server uses image processing techniques to extract and analyze body shape information based on a full-body photograph of the user.

[1099] "Methods for generating coordination ideas" refers to technology in which a server generates multiple fashion coordination suggestions using AI models or similar tools, based on analysis results and user-specified requirements.

[1100] A "generative AI model" refers to an algorithm or technology that uses artificial intelligence to generate outfit ideas tailored to the user's preferences and body type.

[1101] "Methods for generating image data" refers to technology that creates images simulating how a user would look wearing an outfit based on outfit ideas generated by a server.

[1102] "Means for displaying suggested outfit lists and image files" refers to technology that visually displays outfit suggestions and image files received by the terminal from the server to the user.

[1103] "Means of providing feedback" refers to a function that allows users to input their opinions and requests for improvements regarding the suggested outfits through the application.

[1104] "Methods for optimizing the suggestion algorithm" refers to the technology in which the server analyzes user feedback and adjusts the algorithm to improve the accuracy and quality of future coordination suggestions.

[1105] This invention relates to a system for users to receive fashion coordination suggestions that suit their body shape and preferences. Specific embodiments thereof are described below.

[1106] Users first install the system's application on their device and create an account. During this process, users enter their height, weight, gender, and a full-body photograph into the application. This information is checked by the device for formatting, and only sent to the server if it is in the correct format.

[1107] The server preprocesses the received full-body photograph and analyzes the user's body shape. Specifically, it uses image processing techniques to extract the user's body shape information (height, shoulder width, waist size, etc.). Specific image processing techniques used here include OpenCV and TensorFlow. Based on this information, the server uses a generative AI model to generate dozens of outfit ideas according to the user's specified outfit requirements (e.g., "date," "casual," "want to wear a jacket").

[1108] For example, a "casual" outfit for a "date" might be generated, such as "white T-shirt, blue jeans, and sneakers." This generated outfit idea is then further processed to produce an image tailored to the user's body shape. The generative AI model used here could be, for example, a GAN (Generative Opposing Network) model.

[1109] The server sends the generated outfit ideas and image files to the terminal. The terminal displays this information to the user, allowing the user to browse the suggested outfits. Furthermore, the user can select their favorite outfit.

[1110] Users can provide feedback on the suggested outfits (e.g., "Good," "Bad," "Points to improve," etc.). The device sends the user's feedback to the server. The server analyzes this feedback and optimizes the suggestion algorithm. This improves the accuracy of outfit suggestions in the future.

[1111] As a concrete example, consider a male user who is 170cm tall and weighs 60kg and wants a casual outfit for a date. The user first uploads a full-body photo to the application and specifies the requirements. The server analyzes this information and makes suggestions such as "white T-shirt, blue jeans, sneakers" that are best suited to the user, and also generates image renderings of the user wearing those clothes. The user reviews these suggestions and provides feedback, which helps to make future suggestions even more accurate.

[1112] Examples of prompt statements are as follows:

[1113] 1. "Please suggest a casual outfit for a date. I am male, 170cm tall, 60kg."

[1114] 2. "I'd like some office-appropriate outfit ideas using a casual jacket. I'm 160cm tall, weigh 50kg, and am female."

[1115] 3. "Please suggest a fashion outfit suitable for a weekend outing. I am a male, 180cm tall and weigh 70kg."

[1116] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1117] Step 1:

[1118] The user installs the system's application on their device and creates an account.

[1119] Input: Application installation, user information (name, email address, password)

[1120] Output: User account creation complete message

[1121] Specific actions: The user downloads the application, enters the required information, and creates an account.

[1122] Step 2:

[1123] The user enters their height, weight, gender, and a full-body photo into the application.

[1124] Input: Height, weight, gender, full-body photo

[1125] Output: Confirmation message for input information

[1126] Specific operation: Following the application's instructions, the user enters the requested information. Photos can be taken using the device's camera or existing photos can be uploaded.

[1127] Step 3:

[1128] The terminal checks the format of the entered information and sends the information to the server if the format is correct.

[1129] Input: User's height, weight, gender, and full-body photo.

[1130] Output: Data transmission result to the server (success / failure)

[1131] Specific operation: The terminal validates the input information to check if it is in the correct format. If correct, it sends the information to the server. If incorrect, it displays an error message.

[1132] Step 4:

[1133] The server preprocesses the received full-body photos and analyzes the user's body shape.

[1134] Input: Full body photo

[1135] Output: Body shape analysis data (height, shoulder width, waist size, etc.)

[1136] Specific operation: The server processes images using OpenCV and TensorFlow, performing preprocessing such as noise reduction and resizing. Then, it extracts the user's body shape information using an image analysis algorithm.

[1137] Step 5:

[1138] The server generates coordination ideas based on the analysis results, according to the user's specified requirements.

[1139] Input: Body shape analysis data, outfit requirements (e.g., "date," "casual")

[1140] Output: Coordination Ideas

[1141] Specific operation: The server generates the most suitable fashion combination for the user's body type and requirements based on predefined coordination rules and style guides.

[1142] Step 6:

[1143] The server uses a generative AI model to generate outfit ideas and create image files tailored to the user's body shape.

[1144] Input: Outfit ideas, body shape analysis data

[1145] Output: Image

[1146] Specific operation: The server uses a generative AI model (e.g., a GAN model) to convert the generated outfit ideas into image files tailored to the user's body shape.

[1147] Step 7:

[1148] The server sends the generated outfit ideas and image files to the terminal.

[1149] Input: Outfit ideas, image

[1150] Output: Data transmission result to the terminal (success / failure)

[1151] Specific operation: The server sends the generated coordination idea and image to the terminal. If the transmission is successful, proceed to the next step.

[1152] Step 8:

[1153] The device displays a list of suggested outfits and image files to the user.

[1154] Input: Outfit ideas, image

[1155] Output: Content displayed to the user

[1156] Specific operation: The terminal displays suggested outfits and image files to the user based on data received from the server. The user is then made able to view them.

[1157] Step 9:

[1158] Users view the suggested outfits and provide feedback.

[1159] Input: Outfit suggestions, image

[1160] Output: Feedback (e.g., "Good," "Bad," "Areas for Improvement")

[1161] Specific actions: The user reviews the suggestion and selects / enters appropriate feedback on the screen. This feedback will be used in the next step.

[1162] Step 10:

[1163] The device sends user feedback to the server.

[1164] Input: Feedback

[1165] Output: Data transmission result to the server (success / failure)

[1166] Specific operation: The device collects user feedback information and sends it to the server. If the transmission is successful, it proceeds to the next step.

[1167] Step 11:

[1168] The server analyzes the feedback and optimizes the proposed algorithm.

[1169] Input: Feedback

[1170] Output: Optimized proposed algorithm

[1171] Specific operation: The server analyzes the feedback and adjusts specific parameters and models to improve the accuracy of future coordination suggestions.

[1172] (Application Example 1)

[1173] 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".

[1174] Traditional fashion coordination systems made it difficult for users to visually confirm clothing that suited their body type and preferences. Furthermore, they did not adequately optimize coordination based on user feedback. Therefore, there was a need for a means to improve user satisfaction.

[1175] 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.

[1176] In this invention, the server includes means for the user to input height, weight, gender, and a full-body photograph; means for the user to specify coordination requirements; means for the server to analyze the user's body shape based on the full-body photograph; means for the server to generate coordination ideas according to the user's specified requirements based on the analysis results; means for the server to generate image representations of coordinations that the server deems suitable for the user; means for the server to transmit the generated coordination ideas and image representations to a terminal; means for the terminal to display a list of suggested coordinations and image representations to the user; means for the user to provide feedback; means for the server to analyze the user's feedback and optimize the suggestion algorithm; means for displaying the coordination selected by the user in the virtual store in real time; and means for the user to explore the virtual store using smart glasses and reflect the selected coordination on an avatar. This allows the user to visually confirm coordinations that suit their body shape and preferences and to have a real-time try-on experience in the virtual store.

[1177] A "user" is someone who uses the system to receive fashion coordination suggestions tailored to their body type and preferences.

[1178] "Height" refers to a physical measurement that indicates the vertical length from the user's head to their feet.

[1179] "Weight" refers to the user's body weight, which is generally measured in kilograms.

[1180] "Gender" refers to information that indicates which gender a user identifies with.

[1181] A "full-body photo" is an image that captures the user from head to toe in a single photograph.

[1182] "Coordination requirements" refer to the specific situation and clothing preferences specified by the user.

[1183] A "server" is a computer system that analyzes data sent by a user and performs the necessary processing.

[1184] "Body shape analysis" is the process of extracting the shape and dimensions of a user's body from a full-body photograph.

[1185] A "coordinate idea" is a combination of clothing items generated based on the user's requirements.

[1186] An "image" is a visual representation of an outfit optimized for the user's body shape.

[1187] A "device" refers to a computing device used by a user, such as a smartphone or smart glasses.

[1188] "Feedback" refers to the evaluations and opinions that users give regarding the suggested outfits.

[1189] A "suggestion algorithm" is an algorithm that generates coordinates based on user feedback.

[1190] A "virtual store" is a virtual space where users can virtually try on clothes through a computer screen or smart device.

[1191] "Smart glasses" are glasses-type devices that use augmented reality technology to display information to the user.

[1192] An "avatar" is a virtual representation of the user that acts on their behalf within a virtual store.

[1193] This invention relates to a system that suggests fashion coordinates tailored to a user's body shape and preferences. Specific embodiments thereof are described below.

[1194] Users explore virtual stores while wearing smart glasses. The main hardware used in this system is smart glasses, specifically a glasses-type device that utilizes augmented reality technology. Cloud servers are used for backend processing.

[1195] The user installs the application on smart glasses and enters their height, weight, gender, and a full-body photo. This information is sent from the smart glasses to a cloud server. The cloud server uses Python and OpenCV to analyze the full-body photo and extract the user's body shape information. This body shape information includes height, shoulder width, waist size, etc.

[1196] The server uses a generative AI model to generate multiple outfit ideas based on the extracted body shape information and the outfit requirements specified by the user. For example, for a "casual outfit for a date," a combination of "white T-shirt, blue jeans, and sneakers" is generated. These outfit ideas are further generated as image files tailored to the user's body shape.

[1197] The generated outfit ideas and image files are saved to cloud storage and sent back to the user's smart glasses. The smart glasses receive this information and display the outfits the user has selected in real time within the virtual store, so that they are reflected on the avatar in real time. The user can try on various outfits while exploring the virtual store.

[1198] When a user provides feedback on a suggested outfit, this feedback information is sent back to the cloud server. The server analyzes this feedback and optimizes the suggestion algorithm. This results in more accurate suggestions in the future.

[1199] As a concrete example, consider a male user who is 170cm tall and weighs 60kg and wants a casual outfit for a date. This user first uploads a full-body photo to the application and specifies the requirements. The server analyzes this information and generates suggestions for the most suitable outfit for the user, such as "white T-shirt, blue jeans, sneakers," and also generates image previews. The user can review these suggestions in a virtual store and try on the selected outfit. Furthermore, the user can provide feedback, which will help improve the accuracy of future suggestions.

[1200] An example of a prompt message is as follows:

[1201] "A male user, 170cm tall and weighing 60kg, is looking for a casual outfit for a date. Please generate an outfit including a white t-shirt, blue jeans, and sneakers that is ideal for him to try on in a virtual store. Based on the user's full-body photo, generate a real-time image that fits his body shape and display it on smart glasses."

[1202] This allows users to visually check outfits that suit their body type and preferences, and to try them on in real time within a virtual store.

[1203] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1204] Step 1:

[1205] The user launches an application installed on the smart glasses and enters their height, weight, gender, and a full-body photograph. The entered data is sent from the smart glasses to a cloud server. The input here is height, weight, gender, and a full-body photograph, and the output is the transmission of this data to the server.

[1206] Step 2:

[1207] The server preprocesses the received full-body images using image processing software (OpenCV). This preprocessing includes adjusting the resolution, removing the background, and reducing noise. The preprocessed full-body images become the input data for body shape analysis. The output is the preprocessed full-body image.

[1208] Step 3:

[1209] The server uses image analysis technology to extract the user's body shape information based on a pre-processed full-body photograph. Specifically, it obtains data such as height, shoulder width, and waist size. This analysis employs machine learning algorithms to perform calculations to obtain accurate body shape information. The input is a pre-processed full-body photograph, and the output is the extracted body shape information.

[1210] Step 4:

[1211] The server receives the user's specified outfit requirements (e.g., a casual outfit for a date) and processes them along with body shape information. A generative AI model (e.g., TensorFlow) is used to generate multiple outfit ideas. The input is the user's body shape information and outfit requirements, and the output is the generated outfit ideas.

[1212] Step 5:

[1213] The server generates an image tailored to the user's body shape based on the generated outfit idea. This uses computer graphics technology. The input is the outfit idea and body shape information, and the output is the generated image.

[1214] Step 6:

[1215] The server saves the generated outfit ideas and image files to cloud storage and sends them to the user's smart glasses. The input is the image files and outfit ideas, and the output is the transmission of this data to the user's smart glasses.

[1216] Step 7:

[1217] Smart glasses display received outfit images and ideas in real time. Users can explore a virtual store and have their selected outfits reflected on their avatar. In this process, the input is the user's clothing selection, and the output is the selected outfit displayed on the avatar.

[1218] Step 8:

[1219] The user provides feedback on the suggested outfit. This feedback is sent to the server via smart glasses. The input is the user's feedback, and the output is this feedback being sent to the server.

[1220] Step 9:

[1221] The server analyzes the feedback it receives and optimizes the proposal algorithm of the generated AI model. This improves the accuracy of future coordination suggestions. The input is user feedback, and the output is the optimized proposal algorithm.

[1222] 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.

[1223] This invention combines a system for users to receive fashion coordination suggestions tailored to their body shape and preferences with an emotion engine that recognizes the user's emotions. A specific embodiment of this system is described below.

[1224] The user first installs the system's application on their device and creates an account. The user then enters their height, weight, gender, and a full-body photograph. The device sends this information to the server. At this point, the device checks the format of the entered information and only sends it to the server if the format is correct.

[1225] The server preprocesses the received full-body photos and analyzes the user's body shape. Specifically, it uses image processing technology to extract the user's body shape information (height, shoulder width, waist size, etc.). Then, based on the user's specified outfit requirements (e.g., date, casual, want to wear a jacket), the server uses an AI model to generate dozens of outfit ideas.

[1226] This system also includes an emotion engine that can recognize the user's emotions from a full-body photo and feedback submitted by the user. The emotion engine analyzes the user's facial expressions and text-based feedback to determine their current emotional state. For example, it recognizes "joy" if the user is smiling and "dissatisfaction" if they are frowning.

[1227] The server adjusts outfit ideas based on the user's emotional data recognized by the emotion engine. For example, if a user wants a "date" and "casual" outfit, but the emotion engine detects "dissatisfaction" from the user's feedback, the server can consider the reasons why the user previously rejected an outfit and generate a different outfit idea.

[1228] The server generates image renderings of what the user would look like wearing the generated outfit ideas. This image generation uses deep learning-based image synthesis technology.

[1229] The server sends the generated outfit ideas and image files to the terminal. The terminal displays this information to the user. The user browses the suggested outfits and selects their favorite. Furthermore, the user can provide feedback on the suggestions (e.g., "Good," "Bad," "Points to improve").

[1230] The device sends user feedback to the server. The server analyzes the user feedback and sentiment data to optimize the proposed algorithm. This process includes retraining the machine learning model using the feedback and sentiment data.

[1231] As a concrete example, consider a male user who is 170cm tall and weighs 60kg, who wants a casual outfit for a date and provided "dissatisfied" feedback on the previous suggestion. The user first uploads a full-body photo to the application and specifies the requirements. The server analyzes this information and makes suggestions such as "white T-shirt, blue jeans, sneakers" that are best suited to the user, and also generates an image of the user wearing those clothes. If the emotion engine detects "dissatisfaction" with the user, the server re-evaluates the user's preferences and makes a different suggestion.

[1232] As described above, the present invention aims to provide a system that proposes the optimal fashion coordination based on the user's body shape and emotional state, thereby increasing user satisfaction.

[1233] The following describes the processing flow.

[1234] Step 1:

[1235] The user installs the application on their device and creates an account. The user enters their height, weight, gender, and a full-body photo.

[1236] Step 2:

[1237] The terminal checks the information entered by the user and verifies whether the input format is correct. If the format is correct, it sends the information to the server.

[1238] Step 3:

[1239] The server preprocesses the received full-body images. Preprocessing includes adjusting the image resolution and denoising.

[1240] Step 4:

[1241] The server analyzes the user's body shape information (e.g., height, weight, shoulder width, waist size) based on pre-processed full-body photographs. This is done using an image recognition algorithm.

[1242] Step 5:

[1243] Within the application, users specify their outfit requirements. Specifically, they select the situation (e.g., date, office), genre (e.g., casual, formal), and items they want to use (e.g., jacket, jeans).

[1244] Step 6:

[1245] The terminal sends the user's specified coordination requirements to the server.

[1246] Step 7:

[1247] Based on the received requirements and body shape information, the server uses an appropriate AI model to generate multiple outfit ideas. For example, based on "date" and "casual" preferences, it might select a combination of "white T-shirt, blue jeans, and sneakers."

[1248] Step 8:

[1249] Based on the generated outfit ideas, the server creates image renderings of what it would look like if the user were wearing these items. This image generation uses deep learning-based image synthesis technology.

[1250] Step 9:

[1251] The server sends the generated coordination ideas and image files to the terminal.

[1252] Step 10:

[1253] The device displays a list of suggested outfits and image files to the user.

[1254] Step 11:

[1255] Users review the suggested outfits and select their favorites. They can also optionally provide feedback (e.g., "Good," "Bad," "Suggests revision").

[1256] Step 12:

[1257] The device sends user feedback to the server.

[1258] Step 13:

[1259] The server uses an emotion engine to recognize the user's emotions from the feedback it receives. This is a process that analyzes the user's facial expressions and text-based feedback to identify their current emotional state. For example, it recognizes "joy" in response to "good" feedback and "dissatisfaction" in response to feedback requesting correction.

[1260] Step 14:

[1261] The server optimizes the suggestion algorithm based on the user's emotion data recognized by the emotion engine. This optimization includes adjusting the outfit suggestions to match the user's emotions. For example, if the user is "dissatisfied," a different outfit idea will be generated.

[1262] Step 15:

[1263] The server accumulates user emotional data and uses it as reference when suggesting outfits in the future. This makes it possible to provide more personalized outfit suggestions based on each user's individual preferences and emotions.

[1264] This allows the system to suggest the most suitable fashion coordinates based on the user's body shape and emotional state, thereby increasing user satisfaction.

[1265] (Example 2)

[1266] 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".

[1267] Conventional fashion coordination systems often failed to provide optimal suggestions based on the user's body shape and emotions, resulting in low user satisfaction. Furthermore, it was difficult to determine whether the generated coordination ideas were actually suitable for the user, making it difficult to incorporate user feedback into the system. This invention aims to solve these problems.

[1268] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1269] In this invention, the server includes means for pre-processing a full-body photograph to analyze the user's body shape, means for generating coordination ideas according to the user's specified requirements, and means for an emotion engine to analyze the user's facial expressions and feedback to identify their emotional state. This makes it possible to suggest the optimal fashion coordination based on the user's body shape and emotions.

[1270] A "user" is an individual who uses the system to receive fashion coordination suggestions based on their own body shape and preferences.

[1271] A "terminal" is a device used by a user to operate a system, and includes smartphones, tablets, and personal computers.

[1272] A "server" is a computer system that processes data sent from users or terminals and generates coordination ideas and image files.

[1273] A "full-body photograph" is a photograph that includes the user's entire appearance and is used for image analysis.

[1274] "Body shape" refers to data that indicates the user's physical characteristics, such as height, shoulder width, and waist size.

[1275] "Coordination requirements" refer to input information about the fashion style and situation the user desires, such as a casual style for a date.

[1276] "Coordination ideas" are fashion suggestions generated by the server based on the user's body shape and coordination requirements.

[1277] An "emotion engine" is software or an algorithm that analyzes a user's facial expressions and text-based feedback to identify their emotional state.

[1278] An "image rendering" is a simulated image showing how a user would look wearing the suggested outfit.

[1279] "Feedback" refers to the opinions and impressions that users provide regarding the suggested outfits, including "good," "bad," and "points for improvement."

[1280] A "suggestion algorithm" is an algorithm that generates optimal outfit ideas based on the user's body shape information and feedback.

[1281] This invention relates to a system that suggests the optimal fashion coordination based on the user's body shape and emotions. Specific embodiments are described below.

[1282] Hardware and software to be used

[1283] 1. Hardware

[1284] Terminal: A device used by a user to operate a system. Specific examples include smartphones, tablets, and personal computers.

[1285] 2. Software

[1286] Image processing libraries: Use OpenCV and TensorFlow to preprocess and analyze the user's full-body images.

[1287] AI Model: Generates outfit ideas using GPT-4 and StyleGAN.

[1288] Emotion Engine: Uses DeepFace and EmotionAPI to analyze user facial expressions and feedback to identify emotional states.

[1289] Image synthesis techniques: Generate images using GANs (e.g., StyleGAN and Pix2Pix).

[1290] System operation

[1291] 1. The user installs the system application on their device and creates their account. This involves entering information such as an email address and password.

[1292] 2. The user enters information such as their height, weight, gender, and a full-body photo into the application. They then specify the outfit requirements (e.g., date, casual).

[1293] 3. The terminal checks the format of the entered information and sends the information to the server only if the format is correct.

[1294] 4. The server preprocesses the received full-body images using OpenCV or TensorFlow to remove noise and adjust the resolution. Then, it analyzes body shape information (height, shoulder width, waist size, etc.) and stores it in a database.

[1295] 5. Based on the user's body shape information and coordination requirements, the server generates dozens of coordination ideas using GPT-4 or StyleGAN.

[1296] 6. The emotion engine included in the server (such as DeepFace or EmotionAPI) recognizes emotions from the user's full-body photo and feedback. Specifically, it performs facial expression analysis and text analysis to identify emotional states such as joy and dissatisfaction.

[1297] 7. The server adjusts the generated coordination ideas based on the emotional data recognized by the emotion engine. For example, if the user is perceived as "dissatisfied," a new suggestion will be generated based on the previous feedback.

[1298] 8. The server uses deep learning-based image synthesis techniques (such as StyleGAN or Pix2Pix) to generate image files of the user wearing the suggested items.

[1299] 9. The server sends the generated coordination ideas and image files to the terminal. The terminal displays these to the user, allowing the user to easily view the suggestions.

[1300] As a concrete example, consider a male user who is 170cm tall and weighs 60kg, who wants a casual outfit for a date and provided "dissatisfied" feedback on the previous suggestion. The user uploads a full-body photo and specifies the requirements. The server analyzes this information and makes suggestions such as a white T-shirt, blue jeans, and sneakers, and also generates an image of the user wearing those clothes. If the emotion engine detects "dissatisfaction," the server re-evaluates the user's preferences and makes a different suggestion.

[1301] Example of a prompt:

[1302] "A male user, 170cm tall and weighing 60kg, is requesting a casual outfit for a date. He gave negative feedback on the previous suggestion. Please generate a new suggestion and its image."

[1303] This system enables the suggestion of optimal fashion coordinates based on the user's body shape and emotions, thereby increasing user satisfaction.

[1304] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1305] The processing flow of this system's program

[1306] Step 1:

[1307] The user installs the system application on their device and creates an account. The user enters the required information (e.g., email address, password, etc.). The input in this step is the information entered by the user, and the output is a notification that the account has been created.

[1308] Step 2:

[1309] The user enters information such as their height, weight, gender, and a full-body photo into the application. They then specify their outfit requirements (e.g., date, casual). The input for this step consists of the user's physical information and outfit requirements, while the output is a confirmation screen of the entered information.

[1310] Step 3:

[1311] The terminal checks the format of the information entered by the user and sends the information to the server only if the format is correct. Specifically, it uses a format verification algorithm to check the integrity of the data. The input for this step is the information entered by the user, and the output is the result of the verification of whether the format is correct.

[1312] Step 4:

[1313] The server preprocesses the received full-body image using OpenCV or TensorFlow to remove noise and adjust the resolution. Next, it analyzes the user's body shape information (height, shoulder width, waist size, etc.) and stores it in a database. The input for this step is the user's full-body image, and the output is the analyzed body shape information.

[1314] Step 5:

[1315] The server generates dozens of outfit ideas using GPT-4 or StyleGAN based on the user's body shape information and outfit requirements. The AI ​​model processes the data based on the requirements specified by the user. The input for this step is the analyzed body shape information and outfit requirements, and the output is the generated outfit ideas.

[1316] Step 6:

[1317] The emotion engine (such as DeepFace or EmotionAPI) included in the server recognizes emotions from the user's full-body photo and feedback. Specifically, it performs facial expression analysis and text analysis to identify the user's emotional state. The input for this step is the user's full-body photo and feedback, and the output is the recognized emotion data.

[1318] Step 7:

[1319] The server adjusts the generated coordination ideas based on the emotion data recognized by the emotion engine. For example, if the user is identified as "dissatisfied," a new suggestion is generated based on the previous feedback. The input for this step is the emotion data and the previous feedback, and the output is the adjusted coordination idea.

[1320] Step 8:

[1321] Based on the generated outfit ideas, the server uses deep learning-based image synthesis techniques such as StyleGAN or Pix2Pix to generate image files of the user wearing the suggested items. The input for this step is the adjusted outfit idea, and the output is the generated image file.

[1322] Step 9:

[1323] The server sends generated outfit ideas and image files to the terminal. The terminal displays this information to the user, allowing them to easily view the suggested outfits. The input for this step is the data sent from the server, and the output is the outfit suggestions displayed to the user.

[1324] Step 10:

[1325] The user enters feedback on the suggested outfit (e.g., "Good," "Bad," "Points to improve"). The terminal sends the entered feedback data to the server. The input for this step is the user's feedback, and the output is the feedback data sent to the server.

[1326] Step 11:

[1327] The server analyzes the received feedback and sentiment data to optimize the proposed algorithm. Specifically, a machine learning model (e.g., retraining) is used to improve the accuracy of the next proposal. The input to this step is the feedback and sentiment data, and the output is the optimized proposed algorithm.

[1328] The above outlines the specific processing steps of this system.

[1329] (Application Example 2)

[1330] 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".

[1331] Traditional fashion coordination suggestion systems only generated outfits based on the user's body shape data, failing to consider the user's feelings. As a result, users were often dissatisfied with the suggestions, leading to a decline in overall satisfaction with the outfits. Furthermore, the lack of technology to simulate the user actually trying on the outfits made it difficult to grasp a concrete image of the suggested outfits.

[1332] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for recognizing the user's emotions using an emotion engine and analyzing the feedback, means for the server to adjust coordination ideas based on emotion data, and means for generating a virtual image of the user trying on the coordination using deep learning-based image synthesis technology. This makes it possible to propose coordinations that take the user's emotions into consideration and to provide concrete images through virtual try-on.

[1333] An "emotion engine" is a technology that analyzes a user's facial expressions and text-based feedback to recognize their current emotional state.

[1334] A "server" is a computer system that analyzes information sent by users and processes the data.

[1335] A "full-body photo" is image data that captures the user's entire body.

[1336] "Body shape data" refers to information about the user's physical dimensions, such as height, shoulder width, and waist size.

[1337] "Coordination ideas" are fashion combinations suggested based on the user's body shape and specified requirements.

[1338] "Deep learning-based image synthesis technology" is a technology that uses artificial intelligence to combine multiple images and generate new images.

[1339] "Feedback" refers to data that shows evaluations and opinions on suggestions provided by users.

[1340] A "virtual image" is a simulated image of how a user would look trying on a suggested outfit.

[1341] The "proposal algorithm" is a computational method that generates the optimal fashion coordination based on user data.

[1342] The system program that implements the example application is implemented as follows: First, the user inputs their height, weight, gender, and a full-body photo into the application using their smartphone. This information is first checked on the device for formatting, and only sent to the server if it is correct.

[1343] The server preprocesses the received full-body photographs and analyzes the user's body shape using image processing techniques. Image processing libraries such as OpenCV are used for this process. The data obtained from the body shape analysis includes specific dimensional information such as the user's height, shoulder width, and waist size.

[1344] Next, the server uses an AI model to generate dozens of outfit ideas based on the user's specified outfit requirements. This process utilizes machine learning libraries such as TensorFlow.

[1345] Furthermore, the server incorporates an emotion engine that recognizes the user's emotional state from full-body photos and feedback. It analyzes the user's facial expressions and text-based feedback to obtain emotional data such as "joy" and "dissatisfaction." Based on this emotional data, the server adjusts the outfit ideas.

[1346] Image synthesis technology based on deep learning is also used, generating virtual images of the user trying on the suggested outfits. TensorFlow is also used for this process.

[1347] The server generates outfit ideas and virtual images, which are then sent to the terminal, where the terminal displays this information to the user. The user can view the suggested outfits and provide feedback. The feedback is sent back to the server, which analyzes the feedback and sentiment data to optimize the suggestion algorithm.

[1348] As a concrete example, consider a male user who is 170cm tall and weighs 60kg and wants a casual outfit for a date, and who provided "dissatisfied" feedback on the previous suggestion. In this case, the user first uploads a full-body photo to the application and specifies the requirements. The server analyzes this information and makes suggestions such as "white T-shirt, blue jeans, sneakers," and also generates an image of the user wearing those clothes. If the emotion engine detects "dissatisfaction" with the user, the server re-evaluates the user's preferences and makes a different suggestion.

[1349] Examples of prompt statements to input into the generative AI model are as follows:

[1350] "A man who is 170cm tall and weighs 60kg is looking for a casual outfit for a date. Please generate images of a white T-shirt, blue jeans, and sneakers. The user is dissatisfied with the previous suggestions, so please consider more stylish suggestions."

[1351] As described above, this invention is a system that proposes the optimal fashion coordination based on the user's body shape and emotional state, thereby increasing user satisfaction.

[1352] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1353] Step 1:

[1354] The user launches the application using their smartphone and enters their height, weight, gender, and a full-body photo. After entering this information, the user specifies the outfit requirements (e.g., date, casual). The input data is formatted by the device, and only if it is in the correct format is the data sent to the server. The input includes height, weight, gender, full-body photo, and outfit requirements, and the output is the formatted user data.

[1355] Step 2:

[1356] The server preprocesses the received full-body photographs. Specifically, it uses image processing libraries such as OpenCV to perform denoising and resizing. The preprocessed images are then formatted to a format suitable for the next analysis step. The input is a full-body photograph of the user, and the output is the preprocessed image data.

[1357] Step 3:

[1358] The server analyzes the user's body shape using pre-processed full-body photographs. The server utilizes image processing techniques to extract body shape data such as height, shoulder width, and waist size. The OpenCV library is used for this analysis. The input is pre-processed image data, and the output is the user's body shape data.

[1359] Step 4:

[1360] The server uses an AI model to generate outfit ideas based on the user's specified outfit requirements. A machine learning model using TensorFlow is employed here. The input is body shape data and outfit requirements, and the output is multiple outfit ideas.

[1361] Step 5:

[1362] The emotion engine on the server analyzes emotional data from user-provided feedback and facial expression images. The emotion engine uses a specific algorithm to detect emotional states such as "joy" or "dissatisfaction." Input is the user's facial expression image and feedback text, and output is emotional data.

[1363] Step 6:

[1364] The server adjusts the generated coordination ideas based on emotional data. This is a process that modifies the priority and content of suggestions based on the user's emotional state. The input is coordination ideas and emotional data, and the output is the adjusted coordination ideas.

[1365] Step 7:

[1366] The server uses deep learning-based image synthesis technology to generate virtual images of the user trying on outfits. TensorFlow is used for this image generation. The input is a refined outfit idea and a pre-processed full-body photo of the user, and the output is a virtual try-on image.

[1367] Step 8:

[1368] The server sends the generated outfit ideas and virtual images to the terminal. The input is the virtual try-on image and outfit ideas, and the output is the data sent to the terminal.

[1369] Step 9:

[1370] The terminal displays the received coordinate list and virtual image to the user. The user can review these, make selections, or provide feedback. The input is data sent from the server, and the output is the user's display screen.

[1371] Step 10:

[1372] The user's feedback is sent back to the server. The server analyzes this feedback and sentiment data to retrain the model and optimize the proposed algorithm. The input is the user's feedback data, and the output is the optimized proposed algorithm.

[1373] 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.

[1374] The data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of the data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">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.

[1375] 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.

[1376] 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.

[1377] 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.

[1378] 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.

[1379] 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.

[1380] 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.

[1381] 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."

[1382] 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.

[1383] 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.

[1384] 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.

[1385] 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.

[1386] 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.

[1387] 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.

[1388] 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.

[1389] 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.

[1390] 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.

[1391] 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.

[1392] 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.

[1393] 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.

[1394] The following is further disclosed regarding the embodiments described above.

[1395] (Claim 1)

[1396] A means for the user to input height, weight, gender, and a full-body photo,

[1397] A means for the user to specify the requirements for the coordination,

[1398] A method by which the server analyzes the user's body shape based on a full-body photograph,

[1399] A means by which the server generates coordination ideas according to the user's specified requirements based on the analysis results,

[1400] A means for generating image representations of outfits that the server deems suitable for the user,

[1401] A means for the server to send generated coordination ideas and image files to the terminal,

[1402] A means by which the terminal displays a suggested outfit list and image to the user,

[1403] Means for users to provide feedback,

[1404] A system that includes means for a server to analyze user feedback and optimize the proposed algorithm.

[1405] (Claim 2)

[1406] The system according to claim 1, comprising means for a server to preprocess a full-body photograph of a user and use it for body shape analysis.

[1407] (Claim 3)

[1408] The system according to claim 1, comprising means for the terminal to check the format of the information entered and, if the format is correct, to send it to the server.

[1409] "Example 1"

[1410] (Claim 1)

[1411] A means for the user to input height, weight, gender, and a full-body photo,

[1412] A means for the user to specify the requirements for the coordination,

[1413] A means for the terminal to check the format of the entered information and send it to the server if the format is correct,

[1414] The server preprocesses full-body photos and analyzes the user's body shape.

[1415] A means by which the server generates coordination ideas according to the user's specified requirements based on the analysis results,

[1416] A means for generating coordination ideas using a server-generated AI model,

[1417] A means for generating image representations of outfits that the server deems suitable for the user,

[1418] A means for the server to send generated coordination ideas and image files to the terminal,

[1419] A means by which the terminal displays a suggested outfit list and image to the user,

[1420] Means for users to provide feedback,

[1421] A system that includes means for a server to analyze user feedback and optimize the proposed algorithm.

[1422] (Claim 2)

[1423] The system according to claim 1, comprising means for a server to preprocess a full-body photograph of a user and use it for body shape analysis.

[1424] (Claim 3)

[1425] The system according to claim 1, comprising means for the terminal to display generated coordination ideas and image files, and for sending user feedback to a server.

[1426] "Application Example 1"

[1427] (Claim 1)

[1428] A means for the user to input height, weight, gender, and a full-body photo,

[1429] A means for the user to specify the requirements for the coordination,

[1430] A method by which the server analyzes the user's body shape based on a full-body photograph,

[1431] A means by which the server generates coordination ideas according to the user's specified requirements based on the analysis results,

[1432] A means for generating image representations of outfits that the server deems suitable for the user,

[1433] A means for the server to send generated coordination ideas and image files to the terminal,

[1434] A means by which the terminal displays a suggested outfit list and image to the user,

[1435] Means for users to provide feedback,

[1436] A means by which the server analyzes user feedback and optimizes the proposed algorithm,

[1437] A means of displaying the outfit selected by the user in real time within a virtual store,

[1438] A system that includes a means of allowing users to explore a virtual store using smart glasses and reflecting their selected outfit on their avatar.

[1439] (Claim 2)

[1440] The system according to claim 1, comprising means for a server to preprocess a full-body photograph of a user and use it for body shape analysis.

[1441] (Claim 3)

[1442] The system according to claim 1, comprising means for the terminal to check the format of the information entered and, if the format is correct, to send it to the server.

[1443] "Example 2 of combining an emotion engine"

[1444] (Claim 1)

[1445] A means for the user to input height, weight, gender, and a full-body photo,

[1446] A means for the user to specify the requirements for the coordination,

[1447] A means for the terminal to check the format of the entered information and send it to the server if the format is correct,

[1448] The server preprocesses full-body photos and analyzes the user's body shape.

[1449] A means by which the server generates coordination ideas according to the user's specified requirements based on the analysis results,

[1450] The emotion engine included in the server analyzes the user's facial expressions and feedback to identify their emotional state,

[1451] A means by which the server adjusts coordination ideas based on the analysis results of the emotion engine,

[1452] A means for generating image representations of outfits that the server deems suitable for the user,

[1453] A means for the server to send generated coordination ideas and image files to the terminal,

[1454] A means by which the terminal displays a suggested outfit list and image to the user,

[1455] Means for users to provide feedback,

[1456] A system that includes means for a server to analyze user feedback and optimize the proposed algorithm.

[1457] (Claim 2)

[1458] The system according to claim 1, comprising means for a server to preprocess a full-body photograph of a user and use it for body shape analysis.

[1459] (Claim 3)

[1460] The system according to claim 1, comprising means for the terminal to check the format of the information entered and, if the format is correct, to send it to the server.

[1461] "Application example 2 when combining with an emotional engine"

[1462] (Claim 1)

[1463] A means for the user to input height, weight, gender, and a full-body photo,

[1464] A means for the user to specify the requirements for the coordination,

[1465] A method by which the server analyzes the user's body shape based on a full-body photograph,

[1466] A means by which the server generates coordination ideas according to the user's specified requirements based on the analysis results,

[1467] A means of recognizing user emotions using an emotion engine and analyzing feedback,

[1468] A means by which the server adjusts coordination ideas based on emotional data,

[1469] A means for generating a virtual image of a user trying on an outfit using deep learning-based image synthesis technology,

[1470] A means for the server to send generated coordination ideas and image files to the terminal,

[1471] A means by which the terminal displays a suggested outfit list and image to the user,

[1472] Means for users to provide feedback,

[1473] A system that includes means for a server to analyze user feedback and sentiment data and optimize the proposed algorithm.

[1474] (Claim 2)

[1475] The system according to claim 1, comprising means for a server to preprocess a full-body photograph of a user and use it for body shape analysis.

[1476] (Claim 3)

[1477] The system according to claim 1, comprising means for the terminal to check the format of the information entered and, if the format is correct, to send it to the server. [Explanation of symbols]

[1478] 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 input height, weight, gender, and a full-body photo, A means for the user to specify the requirements for the coordination, A method by which the server analyzes the user's body shape based on a full-body photograph, A means by which the server generates coordination ideas according to the user's specified requirements based on the analysis results, A means for generating image representations of outfits that the server deems suitable for the user, A means for the server to send generated coordination ideas and image files to the terminal, A means by which the terminal displays a suggested outfit list and image to the user, Means for users to provide feedback, A system that includes means for a server to analyze user feedback and optimize the proposed algorithm.

2. The system according to claim 1, comprising means for a server to preprocess a full-body photograph of a user and use it for body shape analysis.

3. The system according to claim 1, comprising means for the terminal to check the format of the information entered and, if the format is correct, to send it to the server.

Images