system

Abstract

Provide a system. A device for receiving image data of a user and analyzing the image data to recognize the user's body type and fashion style; means for acquiring survey data for users and integrating the survey data to generate a user profile; A means of suggesting fashion items based on user profiles; a means for collecting the latest trend data and generating new fashion designs based on the trend data; A means for providing a virtual try-on of the proposed fashion items using VR or AR technology; A system including:

Description

[Technical Field]

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

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

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

[0004] Online shopping presents a challenge: users cannot actually try on items, making it difficult to confirm whether an item will fit them before purchasing. It is also difficult to find items that best suit a user's individual body type and style, and it is also difficult to incorporate fashion designs that reflect the latest trends. These issues need to be addressed. [Means for solving the problem]

[0005] The present invention provides a system including means for receiving image data of a user and analyzing the image data to recognize the user's body type and fashion style, means for acquiring questionnaire data from the user and integrating the questionnaire data to generate a user profile, means for suggesting fashion items based on the user profile, means for collecting the latest trend data and generating new fashion designs based on the trend data, and means for providing a virtual try-on of the suggested fashion items using VR or AR technology. This system enables users to efficiently find fashion items that best suit their body type and style, and also enables them to check the fit and appearance of the items through the virtual try-on before purchasing.

[0006] "User Image Data" refers to a photograph or full-body image of the User provided by the User that is analyzed by the System.

[0007] An "image recognition algorithm" is a program that uses machine learning models and other analytical techniques to detect and analyze information in images.

[0008] "User's body shape" refers to the shape and proportions of the user's body, as recognized by an image recognition algorithm.

[0009] "Fashion style" refers to the clothing and appearance tendencies that a user typically chooses, and is determined based on image data and questionnaire data.

[0010] "Survey Data" refers to information provided by users to the system regarding preferred colors, styles, budgets, lifestyles, etc.

[0011] A "user profile" is a comprehensive collection of information about an individual user that is created by integrating the user's image data and survey data.

[0012] "Fashion items" refers to fashion-related products such as clothing, accessories, and shoes that are suggested to users.

[0013] "Trend data" is information about the latest fashion trends and trends, collected from fashion shows, social media, news sites, etc.

[0014] "New Fashion Designs" are unique clothing designs generated based on trend data and user profiles.

[0015] "VR technology" is an abbreviation for virtual reality technology, which uses computer graphics to create a virtual environment in which users feel immersed.

[0016] "AR technology" is an abbreviation for augmented reality technology, which is a technology that displays digital information overlaid on images of the real world.

[0017] "Virtual try-on" is the process of using VR or AR technology to allow users to try on selected fashion items in a virtual environment to check how they look and fit.

[0018] "Feedback" refers to the ratings and opinions provided by users about the items they try on, which are used to improve the system. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4]FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0020] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

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

[0023] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0024] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0025] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0027] [First embodiment]

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

[0029] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0030] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0032] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

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

[0034] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0036] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0037] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0039] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0040] As an embodiment of the present invention, the operation and processing of a specific system will be described below.

[0041] Collection and processing of user data

[0042] 1. Collecting user image data and survey data

[0043] Users upload a full-body photo of themselves to the platform's upload screen from a device such as a smartphone or PC.

[0044] Users fill out a survey provided on the platform and enter information about their preferred colors, fashion style, budget, and lifestyle.

[0045] The terminal collects this data and transmits it to the server.

[0046] Image analysis and user profile generation

[0047] 2. Image Recognition and Attribute Analysis

[0048] The server receives the uploaded image data and analyzes it using an image recognition algorithm.

[0049] The server recognizes the user's body type (e.g., slim, athletic, curvy, etc.), facial features, and usual fashion style (e.g., casual, formal, etc.).

[0050] 3. Integration with survey data

[0051] The server combines the results of the image analysis with the survey data to generate a detailed user profile for each individual user.

[0052] Fashion item suggestions

[0053] 4. AI-generated recommendations

[0054] The server inputs the generated user profile into an AI model, which includes recurrent neural networks and generative models, and is capable of suggesting appropriate fashion items based on past data.

[0055] Based on the user profile, the server generates a list of fashion items that match the user's body type, preferences, and lifestyle.

[0056] Trend analysis and design generation

[0057] 5. Trend data collection and analysis

[0058] The server regularly collects the latest fashion trend information from fashion shows, social media, news sites, etc.

[0059] The server inputs the collected data into an AI model and performs trend analysis.

[0060] 6. Generating new designs

[0061] The server uses AI design generation capabilities to generate unique fashion designs based on trend data and user profiles.

[0062] The server adds the generated new fashion design to a list of suggestions for the user.

[0063] Virtual try-on experience

[0064] 7. Displaying the proposed list and offering to try on the items

[0065] The terminal displays the suggested list of fashion items sent from the server to the user.

[0066] The user selects items of interest from the suggestion list.

[0067] The terminal displays a virtual try-on screen for the selected item using VR or AR technology.

[0068] Users can check the look and fit of items on a virtual try-on screen.

[0069] Gathering feedback and improving

[0070] 8. Gather feedback and improve the model

[0071] Users enter feedback about the items they try on (e.g., "looks good," "kind of weird," etc.) into the platform.

[0072] The server receives feedback from users and uses this data to improve user profiles and AI models.

[0073] These processes allow users to efficiently find the fashion items that best suit them and check them out before purchasing by virtually trying them on.

[0074] The processing flow will be explained below.

[0075] Step 1:

[0076] Users take a full-body photo of themselves and upload it to the platform's upload screen from their smartphone, PC, or other device. The uploaded image data is then sent from the device to the server.

[0077] Step 2:

[0078] Users answer a survey provided on the platform, entering information about their preferred colors, fashion style, budget, and lifestyle. The survey data is then sent from the device to the server.

[0079] Step 3:

[0080] The server receives the uploaded image data and analyzes it using image recognition algorithms to identify the user's body type (e.g., slim, athletic, chubby, etc.), facial features, and usual fashion style (e.g., casual, formal, etc.).

[0081] Step 4:

[0082] The server combines the results of the image analysis with the survey data to generate a detailed user profile for each individual user, including data such as body type, style preferences, and living environment.

[0083] Step 5:

[0084] The server inputs the generated user profile into an AI model, which uses recurrent neural networks and generative models to generate a list of fashion items that best suit the user.

[0085] Step 6:

[0086] The server periodically collects trend data from the latest fashion shows, social media, news sites, etc. This trend data is stored in a database within the server.

[0087] Step 7:

[0088] The server inputs the collected trend data into the AI ​​model for trend analysis, which then generates unique fashion designs based on the trend data, integrates them with the user profile, and adds them to the suggestion list.

[0089] Step 8:

[0090] The server transmits a list of fashion items generated based on the user profile to the user's terminal.

[0091] Step 9:

[0092] The terminal displays a list of suggested fashion items sent from the server to the user, who then selects an item of interest from the suggested list.

[0093] Step 10:

[0094] The device uses VR or AR technology to display a virtual try-on screen for the selected item, allowing the user to check the look and fit of the item.

[0095] Step 11:

[0096] Users input feedback (e.g., "looks good" or "not so good") about the items they try on into the platform. The feedback data is sent from the device to the server.

[0097] Step 12:

[0098] The server receives user feedback and uses this data to improve the user profile and the AI ​​model, which can then provide more accurate suggestions the next time the user uses the service.

[0099] Example 1

[0100] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0101] Conventional fashion item suggestion systems have been inadequate in suggesting items based on the user's body type and style, making it difficult to suggest items that are optimal for each individual user. Furthermore, there are limited ways for users to check how the suggested items will actually look on them. Furthermore, there is a lack of a mechanism for utilizing user feedback to improve the accuracy of suggestions.

[0102] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0103] In this invention, the server includes means for receiving user image data and analyzing the image data to recognize the user's body type and style, means for acquiring user questionnaire data and integrating the questionnaire data to generate a user profile, means for suggesting items based on the user profile, means for collecting the latest data and generating new designs based on the data, and means for providing a virtual try-on of the suggested items using augmented reality and virtual reality technologies, thereby suggesting fashion items that are optimal for each individual user and enabling the user to check the appearance and fit of the items through the virtual try-on before purchasing.

[0104] "Image data" is digital data containing visual information captured by an electronic device.

[0105] "Recognition" is the process of analyzing image data and survey data to identify specific characteristics and attributes of a user.

[0106] "Survey data" refers to data that includes information such as preferences, lifestyle, and budget entered by the user.

[0107] A "user profile" is detailed information about an individual user that integrates the results of analyzing image data and questionnaire data.

[0108] "Items" are fashion-related items such as clothing and accessories.

[0109] "Design" refers to the appearance or shape of an item based on a particular concept or style.

[0110] "Augmented reality technology" is a technology that displays virtual information overlaid on the real environment.

[0111] "Virtual reality technology" is a technology that allows users to experience immersion in a virtual environment.

[0112] "Feedback" refers to opinions and evaluations provided by users regarding proposed items or systems.

[0113] A "generative AI model" is an artificial intelligence model that generates new designs and proposals based on input data.

[0114] As an embodiment of the present invention, a series of processes from collecting user data to proposing fashion items, analyzing trends and creating designs, providing a virtual try-on experience, and collecting and improving feedback will be specifically described.

[0115] First, we will explain the collection of user data.

[0116] Users upload a full-body photo of themselves from their smartphone or PC to the platform's upload screen. It is recommended that the image be in JPEG or PNG format. Users then answer a survey provided on the platform, entering information such as their favorite colors, fashion style, budget, and lifestyle. This data is collected by the device and securely transmitted to the server via the HTTPS protocol.

[0117] Next, image analysis and user profile generation will be described.

[0118] The server runs an image recognition algorithm using TENSORFLOW® to analyze the received image data. Specifically, it uses deep learning models such as DeepLab to recognize the user's body type, facial features, and usual fashion style. To integrate the analysis results with the survey data, the server accesses a database system such as MySQL® or PostgreSQL to create a detailed user profile.

[0119] Next, the proposal of fashion items will be described.

[0120] The server inputs the generated user profile into a generative AI model such as a recurrent neural network (RNN) or generative adversarial network (GAN). This model is built using frameworks such as TensorFlow and PyTorch. The AI ​​model generates a list of suitable fashion items based on the user's body type, preferences, and lifestyle.

[0121] Trend analysis and design generation are as follows:

[0122] The server automatically collects the latest fashion trend information from fashion shows, social media, news sites, and other sources. This information is collected using web scraping technologies such as BeautifulSoup and Scrapy. The server then analyzes the collected data using natural language processing (NLP) techniques to identify fashion trends. Based on the trend data and user profiles, the server then generates new designs using AI design generation functions such as StyleGAN, and adds them to a list of suggestions.

[0123] Here's the virtual try-on experience:

[0124] The device displays the list of suggestions sent from the server to the user. The user selects items of interest from this list. For the selected items, the device displays a virtual try-on screen using augmented reality (ARKit or ARCore) or virtual reality technology, allowing the user to see how the items look and fit before purchasing.

[0125] Finally, we discuss collecting feedback and improving the model.

[0126] Users rate items on a virtual try-on screen. Feedback is in the form of simple ratings such as "looks good" or "not so good." The server collects this feedback and uses it to improve the user profile and the generative AI model. The feedback data is used as new training data to help improve the model's recommendation accuracy.

[0127] As described above, this system is designed to help users efficiently find the items that suit them best by suggesting the most suitable fashion items based on the user's image data and questionnaire data and providing a virtual try-on experience.

[0128] Prompt Sentence Examples

[0129] "You submit a full-body photo of yourself. Then, you answer a questionnaire about your preferred colors, fashion style, budget, and lifestyle. The system will use this information to suggest fashion items that are perfect for you."

[0130] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0131] Step 1: Collect user data

[0132] Users upload a full-body photo of themselves from their smartphone or PC to the platform's upload screen. The input data is image data in JPEG or PNG format.

[0133] Users answer a survey on the platform and enter information such as their favorite colors, fashion style, budget, and lifestyle. The survey data becomes the input data.

[0134] The terminal transmits the image data and questionnaire data collected from the user to the server using the secure HTTPS protocol. The output data is the image data and questionnaire data of the user transmitted to the server.

[0135] Step 2: Integrating image analysis and survey data

[0136] The server analyzes the received image data using TensorFlow. Specifically, it uses deep learning models such as DeepLab to recognize the user's body shape and facial features. The input data is the user's image data, and the output data is the analysis results regarding body shape and facial features.

[0137] The server accesses a database such as MySQL or PostgreSQL to integrate the analysis results with the user's survey data. The survey data and image analysis results are the input data, and the integrated user profile is the output data.

[0138] Step 3: Proposing fashion items

[0139] The server inputs the generated user profile into a generative AI model such as a Recurrent Neural Network (RNN) or Generative Adversarial Networks (GAN). The input data is the user profile, and the output data is a list of suggested items.

[0140] The server uses an AI model to suggest fashion items based on the user's body type, preferences, and lifestyle. Specifically, the AI ​​model generates an item list based on learned parameters.

[0141] Step 4: Collect and analyze trend data

[0142] The server collects the latest fashion trend information from external sources such as fashion shows, social media, and news sites. The input data is trend information from external sources. Specific operations involve using web scraping tools such as BeautifulSoup and Scrapy.

[0143] The server analyzes the collected trend data using natural language processing (NLP) technology. The input data is the collected trend information, and the output data is the trend keywords and themes extracted through the analysis.

[0144] Step 5: Generate a new design

[0145] The server generates new fashion designs using AI design generation functions such as StyleGAN based on trend data and user profiles. The input data is the trend data and user profiles, and the output data is the generated fashion designs.

[0146] The server adds the generated new design to the list of suggestions for the user. Specifically, the AI ​​model integrates trend information and user profiles to generate new designs.

[0147] Step 6: Offer a virtual try-on

[0148] The terminal displays the suggested list of fashion items sent from the server to the user. The input data is the suggested list from the server, and the output data is the suggested list displayed on the user's terminal.

[0149] The user selects an item of interest from the suggestion list, and the input data is the item selected by the user.

[0150] The device displays a virtual try-on screen for the selected item using augmented reality (ARKit or ARCore) or virtual reality technology. The user can check the appearance and fit of the item on the virtual try-on screen. The output data is visual information from the virtual try-on.

[0151] Step 7: Gather feedback

[0152] Users input their feedback on the items they virtually try on into the platform. The input data is the user's evaluation information (e.g., "looks good," "not so good," etc.).

[0153] The server collects user feedback and uses it to improve the user profile and the generated AI model. The output data is an updated user profile and AI model. Specifically, the feedback data is used as new training data for the machine learning model, improving the model's recommendation accuracy.

[0154] (Application example 1)

[0155] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0156] Conventional fashion item recommendation systems struggle to provide personalized recommendations based on a user's body type and fashion style. Furthermore, they lack a way for users to check the fit and appearance of items before trying them on. Furthermore, they lack a mechanism for efficiently integrating user feedback to improve the accuracy of recommendations. This creates a challenge: users spend a lot of time and effort in the process of finding the perfect fashion item.

[0157] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0158] In this invention, the server includes: means for receiving a user's image data and analyzing the image data to recognize the user's body type and fashion style; means for acquiring user survey data and integrating the survey data to generate a user profile; means for suggesting fashion items based on the user profile; means for collecting the latest trend data and generating new fashion designs based on the trend data; means for providing a virtual try-on of the suggested fashion items using VR or AR technology; means for analyzing the profile data and the proposed fashion items using an AI model stored in the server to suggest fashion coordinations; and means for obtaining feedback from the user regarding the virtually tried-on fashion items and improving the accuracy of the user profile and AI model based on the feedback. This allows users to efficiently find fashion items that suit their body type and preferences and check the fit and appearance of the items before purchasing. Furthermore, the accuracy of the suggestions can be continuously improved through feedback, providing a more satisfying shopping experience.

[0159] "User profile" refers to individual information generated based on a user's body type, fashion style, and survey data.

[0160] "Image recognition algorithm" refers to a method of analyzing a user's body shape and fashion style using a machine learning model.

[0161] "Fashion items" refers to fashion-related products such as clothing and accessories.

[0162] "VR technology" refers to virtual reality technology, which allows users to have a realistic fitting experience in a virtual space.

[0163] "AR technology" stands for augmented reality technology, and refers to the technology of overlaying virtual objects on the real world.

[0164] "Generative AI models" refer to artificial intelligence models used to generate new fashion items and designs based on past data.

[0165] "Trend data" refers to data on the latest fashion trends collected from fashion shows, social media, news sites, etc.

[0166] "Feedback" refers to evaluations and opinions obtained from users, and is information that is used to improve the system.

[0167] "Server" refers to the central processing unit that receives data from users and provides analysis and recommendations.

[0168] Specific system operations and processes will be described below for the embodiment of the present invention.

[0169] First, users upload a full-body photo of themselves to the platform's upload screen from their smartphone, PC, or other device. Then, they answer a questionnaire provided on the platform, entering information about their preferred colors, fashion style, budget, and lifestyle. The device collects this data and sends it to the server.

[0170] The server receives the uploaded image data and analyzes it using an image recognition algorithm. This algorithm is based on a machine learning model (e.g., using TensorFlow or Keras) and recognizes the user's body type, facial features, and usual fashion style. The server then combines the results of the image analysis with the survey data to generate a detailed user profile.

[0171] The generated user profile is input into a generative AI model on the server. This model uses recurrent neural networks and generative models (e.g., PyTorch) that have the ability to suggest appropriate fashion items based on past data. Based on the user profile, the server generates a list of fashion items that match the user's body type, preferences, and lifestyle.

[0172] The server also periodically collects the latest fashion trend information from fashion shows, social media, news sites, etc., and inputs it into the generative AI model for trend analysis. Based on the results of this analysis, new fashion designs are generated and added to the user's suggestion list.

[0173] The device then displays a list of suggested fashion items sent from the server to the user. The user selects an item of interest, and the device can then display a virtual try-on screen using VR or AR technology. This technology allows the user to check the look and fit of the item on the virtual try-on screen. Specifically, smart glasses or a head-mounted display are used.

[0174] Finally, users provide feedback on the items they try on to the platform, which is received by the server and used to refine the user's profile and AI model, allowing the system to continually improve its performance.

[0175] An example of a specific prompt is, "The user is 170 cm tall, weighs 65 kg, prefers casual fashion, and uses a lot of accessories. Please suggest an appropriate fashion coordination." This allows the AI ​​model to suggest the best coordination for the user, and allows for virtual try-on based on that information.

[0176] This system allows users to efficiently find fashion items that suit their body type and preferences, and check the fit and appearance before purchasing. Feedback can also be used to continuously improve the accuracy of suggestions, providing a more satisfying shopping experience.

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

[0178] Step 1:

[0179] Users upload a full-body photo of themselves from their smartphone or PC to the platform's upload screen.

[0180] The terminal collects the user's image data and transmits the data to a server.

[0181] Step 2:

[0182] Users fill out a survey on the platform, inputting information about their preferred colors, fashion style, budget and lifestyle.

[0183] The terminal collects the questionnaire data and transmits the data to the server.

[0184] Step 3:

[0185] The server receives the uploaded image data and analyzes it using an image recognition algorithm.

[0186] Through this analysis, the server can determine the user's body type (e.g., slim, athletic, chubby, etc.), facial features, and usual fashion style (e.g., casual, formal, etc.).

[0187] Input: Image data, Output: User's body shape and fashion style information

[0188] Step 4:

[0189] The server combines the survey data with the results of image analysis to generate a detailed user profile.

[0190] Input: Image analysis results, questionnaire data, Output: User profile

[0191] Step 5:

[0192] The server inputs the generated user profile into a generative AI model and suggests appropriate fashion items based on past data.

[0193] Generative AI models use recurrent neural networks and generative models.

[0194] Input: User profile, Output: List of fashion items

[0195] Step 6:

[0196] The server regularly collects the latest fashion trend information from fashion shows, social media, news sites, etc. and inputs it into the generative AI model.

[0197] The server performs trend analysis and generates new fashion designs.

[0198] Input: Trend data, Output: New fashion design

[0199] Step 7:

[0200] The server adds the generated new fashion design to a list of suggestions for the user.

[0201] Input: New fashion design, Output: Updated list of fashion items

[0202] Step 8:

[0203] The terminal displays the suggested list of fashion items sent from the server to the user.

[0204] The user selects the items of interest.

[0205] Input: List of fashion items, Output: User selection

[0206] Step 9:

[0207] The terminal uses VR or AR technology to display a virtual try-on screen for the item selected by the user.

[0208] Users can check the look and fit of items on a virtual try-on screen.

[0209] Input: User selection, Output: Virtual fitting screen

[0210] Step 10:

[0211] Users enter feedback on the items they try on into the platform.

[0212] The terminal sends the feedback to the server.

[0213] Input: User feedback, Output: Feedback data

[0214] Step 11:

[0215] The server receives feedback from users and uses it to improve the user profile and the generated AI model.

[0216] This allows the system to continuously improve its performance.

[0217] Input: Feedback data, Output: Improved user profiles and generative AI models

[0218] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0219] As an embodiment of the present invention, a system incorporating an emotion engine will be described in detail.

[0220] Collection and processing of user data

[0221] 1. Collecting user image data and survey data

[0222] Users upload a full-body photo of themselves to the platform's upload screen from their smartphone, PC, or other device. The uploaded image data is then sent from the device to the server.

[0223] Users answer a survey provided on the platform, entering information about their preferred colors, fashion style, budget, and lifestyle. The survey data is then sent from the device to the server.

[0224] Image analysis and user profile generation

[0225] 2. Image Recognition and Attribute Analysis

[0226] The server receives the uploaded image data and analyzes it using image recognition algorithms to identify the user's body type (e.g., slim, athletic, chubby, etc.), facial features, and usual fashion style (e.g., casual, formal, etc.).

[0227] 3. Emotion Recognition and Attribute Analysis

[0228] The server uses an emotion recognition algorithm to analyze the user's emotional state (e.g., joy, sadness, surprise, etc.) from the user's image data.

[0229] 4. Integration with survey data

[0230] The server combines the results of the image analysis, the emotion analysis, and the survey data to generate a detailed user profile for each individual user, including data such as body type, style preferences, emotional state, and living environment.

[0231] Fashion item suggestions

[0232] 5. AI-generated recommendations

[0233] The server inputs the generated user profile into an AI model, which includes recurrent neural networks and generative models, and generates a list of appropriate fashion items based on past data and the user's emotional data.

[0234] Trend analysis and design generation

[0235] 6. Trend data collection and analysis

[0236] The server periodically collects the latest fashion trend information from fashion shows, social media, news sites, etc. This trend data is stored in a database.

[0237] 7. Generating new designs

[0238] The server inputs the collected trend data into the AI ​​model for trend analysis, which then generates unique fashion designs based on the trend data, integrates them with the user profile, and adds them to the suggestion list.

[0239] Virtual try-on experience

[0240] 8. Displaying the proposed list and offering to try on the items

[0241] The terminal displays a list of suggested fashion items sent from the server to the user, who then selects an item of interest from the suggested list.

[0242] The device uses VR or AR technology to display a virtual try-on screen for the selected item, allowing the user to check the look and fit of the item.

[0243] Gathering feedback and improving

[0244] 9. Gather feedback and improve the model

[0245] Users input their feedback about the items they try on (e.g., "looks good," "not great," etc.) into the platform. The feedback data is sent from the device to the server.

[0246] The server receives user feedback and uses this data, along with emotional data, to improve the user profile and the AI ​​model, which can then provide more accurate suggestions the next time the user uses the app.

[0247] These processes allow users to efficiently find the perfect fashion item for them, and with the help of virtual try-on and emotion-recognition feedback, they can check before they buy.

[0248] The processing flow will be explained below.

[0249] Step 1:

[0250] Users upload a full-body photo of themselves to the platform's upload screen from their smartphone, PC, or other device. The uploaded image data is then sent from the device to the server.

[0251] Step 2:

[0252] Users answer a survey provided on the platform, entering information about their preferred colors, fashion style, budget, and lifestyle. The survey data is then sent from the device to the server.

[0253] Step 3:

[0254] The server receives the uploaded image data and analyzes it using image recognition algorithms to identify the user's body type (e.g., slim, athletic, chubby, etc.), facial features, and usual fashion style (e.g., casual, formal, etc.).

[0255] Step 4:

[0256] The server uses an emotion recognition algorithm to analyze the user's emotional state (e.g., joy, sadness, surprise, etc.) from the user's image data. The analysis results are stored as emotion data.

[0257] Step 5:

[0258] The server combines the results of the image analysis, the emotion analysis, and the survey data to generate a detailed user profile for each individual user, including data such as body type, style preferences, emotional state, and living environment.

[0259] Step 6:

[0260] The server inputs the generated user profile into an AI model, which uses recurrent neural networks and generative models to generate a list of appropriate fashion items based on past data and the user's emotional data.

[0261] Step 7:

[0262] The server periodically collects the latest fashion trend information from fashion shows, social media, news sites, etc. This trend data is stored in a database within the server.

[0263] Step 8:

[0264] The server inputs the collected trend data into the AI ​​model for trend analysis, which then generates unique fashion designs based on the trend data, integrates them with the user profile, and adds them to the suggestion list.

[0265] Step 9:

[0266] The server transmits a list of fashion items generated based on the user profile to the user's terminal.

[0267] Step 10:

[0268] The terminal displays a list of suggested fashion items sent from the server to the user, who then selects an item of interest from the suggested list.

[0269] Step 11:

[0270] The device uses VR or AR technology to display a virtual try-on screen for the selected item, allowing the user to check the look and fit of the item.

[0271] Step 12:

[0272] Users can input their feedback (e.g., "looks good" or "not so good") into the platform after trying on the item. When providing feedback, they can also reflect their own feelings and provide detailed impressions.

[0273] Step 13:

[0274] The server receives user feedback and sentiment data and uses this data to improve the user profile and the AI ​​model, which can then provide more accurate suggestions the next time the user uses the app.

[0275] Example 2

[0276] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0277] Conventional fashion suggestion systems primarily base their suggestions on analysis of the user's body type and style and trend data, but do not fully consider the user's emotions or feedback. As a result, they are unable to recommend the most suitable fashion items for the user, limiting their ability to improve user satisfaction. Furthermore, few systems utilize virtual try-on technology, making it difficult to try on and check items before purchasing. There is a need for a system that can solve these issues, provide more accurate fashion suggestions that take the user's emotional state into account, and enable users to check items before purchasing through virtual try-on.

[0278] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving user image data and analyzing the image data to recognize the user's body type and fashion style, means for acquiring user questionnaire data and integrating the questionnaire data to generate a user profile, means for suggesting fashion items based on the user profile, means for collecting the latest trend data and generating new fashion designs based on the trend data, means for providing a virtual try-on of the suggested fashion items using VR or AR technology, means for analyzing emotions from the user image data, and means for using a generative AI model to list appropriate fashion items based on the user profile. This makes it possible to suggest optimal fashion items to the user through fashion suggestions and virtual try-ons that take the user's emotional state into consideration.

[0279] "User" refers to a person who uses the system to suggest fashion items and virtually try them on.

[0280] "Image data" refers to photographs or videos of the user's entire body or parts that are used to recognize the user's body type, facial features, and fashion style.

[0281] "Server" refers to a computer system that receives data sent from users and performs various processes for analyzing and proposing fashion items.

[0282] "Survey data" refers to data entered by users regarding their preferred colors, fashion style, budget, and lifestyle.

[0283] A "user profile" refers to detailed information about a user that integrates the user's image data, survey data, sentiment analysis results, etc.

[0284] "Fashion items" refer to items such as clothing, accessories, and shoes that are suggested to users.

[0285] "Trend data" refers to information about the latest fashion collected from fashion shows, social media, news sites, etc.

[0286] "VR" refers to virtual reality technology, which provides users with a visual experience that makes them feel as if they are in a three-dimensional space.

[0287] "AR" refers to augmented reality technology, which displays digital information overlaid on real-world scenery.

[0288] "Emotion recognition algorithm" refers to a program for analyzing a user's emotional state from image data.

[0289] "Generative AI model" refers to the machine learning model used to list appropriate fashion items based on a user profile.

[0290] A "prompt sentence" is an input sentence given to a generative AI model, and refers to an instruction sentence to generate a response based on specific conditions or purposes.

[0291] "Feedback" refers to the impressions and evaluations that users input regarding the suggested fashion items.

[0292] MODE FOR CARRYING OUT THE INVENTION

[0293] As an embodiment of the present invention, a system incorporating an emotion recognition algorithm and a generative AI model will be described in detail.

[0294] System configuration

[0295] The system includes the following components:

[0296] User: A person who proposes fashion items and virtually tries them on.

[0297] Terminal: A device used by a user, such as a smartphone or PC, that connects to the platform to input and display data.

[0298] Server: Refers to a computer system that receives data sent from users and performs various processes for analyzing and proposing fashion items.

[0299] Hardware and software used

[0300] Hardware: smartphones, PCs, servers.

[0301] Software: image recognition algorithms (e.g. OpenCV), emotion recognition algorithms, recurrent neural networks (RNN), generative models (GAN), database management systems (e.g. MongoDB), virtual reality (VR) or augmented reality (AR) technologies.

[0302] Specific processing

[0303] User Data Collection

[0304] 1. Users log in to the platform using their smartphone or PC and upload a full-body photo of themselves.

[0305] 2. Users answer a survey provided on the platform and enter information about their preferred colors, fashion style, budget, and lifestyle.

[0306] 3. The terminal sends the uploaded image data and questionnaire data to the server.

[0307] Data analysis and profile generation

[0308] 4. The server receives the image data and uses image recognition algorithms to analyze the user's body type, facial features, and usual fashion style.

[0309] 5. The server analyzes the user's emotional state from the image data using emotion recognition algorithms.

[0310] 6. The server integrates the image analysis results, emotion analysis results, and survey data to generate a detailed user profile.

[0311] Item suggestions and trend analysis

[0312] 7. The server inputs the generated user profile into an AI model, which can be a recurrent neural network (RNN) or a generative neural network (GAN).

[0313] 8. The server runs the AI ​​model and generates a list of appropriate fashion items based on historical data and the user's emotional data.

[0314] Collecting trend data and generating new designs

[0315] 9. The server collects the latest trend data from fashion shows, social media, and news sites and stores it in a database.

[0316] 10. The server inputs the trend data into the AI ​​model, performs trend analysis, and generates unique fashion designs.

[0317] 11. The server merges the generated design with the user profile and adds it to the suggestion list.

[0318] Virtual try-on and feedback

[0319] 12. The device displays the list of suggestions sent by the server to the user, who selects items that interest them.

[0320] 13. The device will then display the selected items on a virtual try-on screen using VR or AR technology, allowing the user to check how they look and fit.

[0321] 14. The user enters feedback on the item they tried on into the platform, and the feedback data is sent to the server.

[0322] Using Feedback

[0323] 15. The server analyzes the received feedback data and uses it, along with the emotional data, to improve the user profile and AI model, enabling more accurate suggestions the next time the user uses the service.

[0324] Examples of concrete examples and prompts

[0325] For example, if a user is looking for "work" fashion items, the following prompt might be used:

[0326] Generate a user profile by combining a full-body photo of the user with survey data. Based on the profile, generate a list of suggested "work" fashion items and offer virtual try-on in VR.

[0327] This allows users to efficiently find the perfect fashion item for them, and allows them to check before they buy using virtual try-on and emotion-recognition based feedback.

[0328] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0329] Step 1:

[0330] Users upload a full-body photo of themselves to the platform's upload screen using their smartphone or PC.

[0331] The terminal transmits the uploaded image data to the server.

[0332] Specifically, the user takes a full-body photo using a camera, selects the image file using the file selection button, and presses the send button. The input is the full-body photo, and the output is the image data sent to the server.

[0333] Step 2:

[0334] Users fill out a survey provided on the platform and enter information about their preferred colors, fashion style, budget, and lifestyle.

[0335] The terminal transmits the inputted questionnaire data to the server.

[0336] Specifically, the user fills in the questionnaire form and presses the send button. The input is the questionnaire data, and the output is the questionnaire data sent to the server.

[0337] Step 3:

[0338] The server uses image recognition algorithms to analyze the received image data.

[0339] Specifically, the server analyzes the user's body type, facial features, and usual fashion style.

[0340] Specifically, the server uses the OpenCV library to perform face detection and body type classification. The input is image data, and the output is the analysis results (body type, facial features, and fashion style).

[0341] Step 4:

[0342] The server applies an emotion recognition algorithm based on the received image data.

[0343] The server identifies the user's emotional state (e.g., happy, sad, surprised, etc.) from the image.

[0344] Specifically, emotion recognition uses a facial expression recognition algorithm, where the input is image data and the output is the analysis result of the emotional state.

[0345] Step 5:

[0346] The server integrates the image analysis results, emotion analysis results, and survey data to generate a user profile.

[0347] The server stores this data in a database and records it in JSON format.

[0348] Specifically, it creates a database entry and saves the user profile. The input is the image analysis results, emotion analysis results, and questionnaire data, and the output is the generated user profile.

[0349] Step 6:

[0350] The server inputs the generated user profile into the AI ​​model.

[0351] The server runs an AI model (such as a recurrent neural network or a generative model) to generate a list of suitable fashion items.

[0352] Specifically, it calls an AI model, provides prompts, and generates a list of items based on the parameters: the input is a user profile, and the output is a list of fashion items.

[0353] Step 7:

[0354] The server periodically collects trend data from fashion shows, social media, and news sites.

[0355] The server stores this information in a database.

[0356] Specifically, it uses scraping scripts and APIs to obtain the latest trend information and stores it in a database. The input is trend data from various external sources, and the output is the stored trend data.

[0357] Step 8:

[0358] The server inputs the collected trend data into an AI model, performs trend analysis, and generates new fashion designs.

[0359] The server merges the generated design with the user profile and adds it to a list of suggestions.

[0360] Specifically, it runs an AI model to generate designs based on trend data and integrate it with the user profile. The input is trend data and the user profile, and the output is an updated list of suggestions.

[0361] Step 9:

[0362] The terminal displays the proposal list sent from the server to the user.

[0363] The user selects items of interest from the suggestion list.

[0364] The terminal displays the selected items on a virtual try-on screen using VR or AR technology.

[0365] Specifically, the device uses an AR kit and a VR app to perform virtual try-on. The input is a list of suggestions, and the output is a display of the virtual try-on.

[0366] Step 10:

[0367] Users enter feedback on the items they try on into the platform.

[0368] The terminal transmits the feedback data to the server.

[0369] Specifically, the user fills in the feedback form and presses the submit button. The input is the feedback, and the output is the feedback data sent to the server.

[0370] Step 11:

[0371] The server analyzes the received feedback and uses it, along with the emotional data, to improve the user profile and AI model.

[0372] The server will be able to make more accurate suggestions the next time you use the service.

[0373] Specifically, the feedback data is analyzed and the AI ​​model is retrained. The input is the feedback data, and the output is an improved AI model.

[0374] (Application example 2)

[0375] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0376] Existing fashion recommendation systems make suggestions based on the user's body type and fashion style, but they are unable to consider the emotional state and feedback of each individual user, making it difficult to fully increase user satisfaction. Furthermore, they lack the ability to make suggestions using the latest trend data or virtual try-on functions, making it difficult to provide a real-time fitting experience or suggestions tailored to individual preferences.

[0377] The identification processing by the identification 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 receiving image data of a user and analyzing the image data to recognize the user's body type and fashion style, means for acquiring questionnaire data for the user and integrating the questionnaire data to generate a user profile, means for using an emotion recognition algorithm to analyze the user's emotional state, means for using a generative AI model to suggest fashion items based on the user profile, means for collecting the latest trend data and generating new fashion designs based on the trend data, means for providing a virtual try-on of the suggested fashion items using VR or AR technology, means for accepting uploads of the user's full-body photo and questionnaire data, and means for collecting user feedback. This enables advanced fashion suggestions based on the generation of individual user profiles and emotion recognition, and can increase user satisfaction through virtual try-ons and feedback collection.

[0378] "User image data" refers to still images or video data taken or uploaded by a user using a terminal.

[0379] "Body type" is a concept that refers to the dimensions, shape, proportions, etc. that characterize the appearance and structure of a user's body.

[0380] "Fashion style" refers to the user's preferred clothing and style trends, genres, and designs.

[0381] "Survey Data" refers to information provided by users in the form of questions about their preferred colors, fashion style, budget, lifestyle, etc.

[0382] A "user profile" is a data set that includes the attributes, preferences, and characteristics of an individual user, generated by integrating user image data, survey data, and sentiment analysis results.

[0383] An "emotion recognition algorithm" is a technology that analyzes a user's image or video data to identify their emotional state at that time (e.g., joy, sadness, surprise, etc.).

[0384] A "generative AI model" is an artificial intelligence model that suggests new fashion items based on accumulated data and learning results.

[0385] "Trend data" refers to information about currently popular styles and designs collected from the latest fashion shows, social media, news sites, etc.

[0386] "Virtual try-on" is a feature that allows users to try on clothes in a digital space using VR (virtual reality) or AR (augmented reality) technology.

[0387] "Feedback" refers to the ratings, comments, and opinions provided by users based on their try-on and usage experiences.

[0388] The system for implementing the present invention includes various processes related to users, servers, and terminals. A specific embodiment of the system will be described below.

[0389] Collection and processing of user image data and survey data

[0390] 1. Collecting user image data and survey data

[0391] Users take a full-body photo of themselves using a device such as a smartphone or PC and upload it to the system. They also answer a questionnaire provided on the platform they use, providing information about their preferred colors, fashion style, budget, and lifestyle. This data is then sent from the device to the server.

[0392] Image analysis and user profile generation

[0393] 2. Image analysis and emotion recognition

[0394] The server receives the image data sent by the user and uses an image recognition algorithm (e.g., OpenCV, TensorFlow) to analyze the user's body shape, facial features, and usual fashion style. At the same time, it uses an emotion recognition algorithm (e.g., Microsoft® Azure® Face API) to analyze the user's emotional state (happiness, sadness, surprise, etc.).

[0395] 3. Integration with survey data and generation of user profiles

[0396] The results of image analysis and emotion recognition are combined with survey data to generate a detailed user profile for each individual user, including data such as body type, style preferences, emotional state, and living environment.

[0397] Fashion item suggestions

[0398] 4. AI-generated recommendations

[0399] The server inputs the generated user profile into a generative AI model (for example, a model using PyTorch or TensorFlow). The generative AI model generates a list of appropriate fashion items based on past data and the user's emotional data. This process suggests fashion items that take into account the user's preferences and emotional state.

[0400] Virtual try-on experience and feedback collection

[0401] 5. Displaying a list of suggestions and offering virtual try-ons

[0402] The device displays a list of suggested fashion items sent from the server. Users select items of interest from the suggested list and virtually try them on using VR or AR technology (e.g., Unity, ARKit, ARCore). Users can check the look and fit of the items on the virtual try-on screen.

[0403] 6. Gather feedback and improve the model

[0404] Users enter feedback on the items they try on into the platform. The feedback data sent from the device to the server, along with emotional data, is used to improve the user profile and generative AI model. The improved generative AI model can then make even more accurate suggestions the next time the user uses the platform.

[0405] Specific examples

[0406] Users open the app, take a full-body photo, and answer a questionnaire about their preferred colors, fashion style, budget, and lifestyle. Based on the uploaded data, the AI ​​will suggest three fashion items that suit the user, and they can virtually try on the items using AR. After the virtual try-on, users can enter and submit feedback, which will be reflected in the next suggestions.

[0407] Prompt Sentence Examples

[0408] "Female, in her 20s, slim build, prefers casual style. Prefers clothes in muted colors that are easy to move in. Budget is around 10,000 yen. Emotional state after trying on clothes: surprise and delight. Please recommend some fashion items based on the following information."

[0409] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0410] Step 1:

[0411] Users take a full-body photo of themselves using a device such as a smartphone or PC and upload it to the system. The uploaded image data is then sent from the device to the server.

[0412] Input: A full-body photo of the user

[0413] Data processing: Images taken on the device are converted into the appropriate format (e.g., JPEG, PNG).

[0414] Output: Image data sent to the server

[0415] Step 2:

[0416] Users answer a survey on the platform, providing information such as their preferred colors, fashion style, budget, lifestyle, etc. The survey data is sent from the device to the server.

[0417] Input: User's survey response

[0418] Data processing: Convert survey responses into data formats such as JSON and XML

[0419] Output: Survey data sent to the server

[0420] Step 3:

[0421] The server analyzes the received image data and uses image recognition algorithms (OpenCV, TensorFlow) to recognize the user's body type, facial features, and usual fashion style. The analysis results are integrated into a user profile.

[0422] Input: Image data

[0423] Data processing: Analyzes body shape, facial features, and fashion style using image recognition algorithms

[0424] Output: Analysis results (body shape, facial features, fashion style) data

[0425] Step 4:

[0426] The server uses an emotion recognition algorithm (Microsoft Azure Face API) to analyze the user's emotional state from their image data, which is then integrated into the user profile.

[0427] Input: Image data

[0428] Data processing: Analyze emotional states using emotion recognition algorithms

[0429] Output: Emotional state data

[0430] Step 5:

[0431] The server combines the image analysis results, emotion analysis results, and survey data to generate a detailed user profile, which includes the user's body type, style preferences, emotional state, living environment, and more.

[0432] Input: Image analysis results, emotion analysis results, questionnaire data

[0433] Data processing: Integrating data to generate user profiles

[0434] Output: User profile

[0435] Step 6:

[0436] The server inputs the generated user profile into the generative AI model to generate a list of appropriate fashion items, which are then stored on the server.

[0437] Input: User Profile

[0438] Data processing: Using generative AI models to suggest fashion items

[0439] Output: A list of fashion items

[0440] Step 7:

[0441] The terminal displays a list of suggested fashion items sent from the server to the user, who can then select the items they are interested in and try them on virtually.

[0442] Input: A list of fashion item suggestions

[0443] Output: Suggestion list displayed in terminal

[0444] Step 8:

[0445] The device uses VR or AR technology (Unity, ARKit, ARCore) to display a virtual try-on screen for the selected item, allowing the user to check the look and fit of the item.

[0446] Input: The item selected by the user

[0447] Data processing: Realizing virtual try-on using VR / AR technology

[0448] Output: Virtual fitting screen

[0449] Step 9:

[0450] Users enter their feedback on the items they try on into the platform, and the feedback data is sent from the device to the server.

[0451] Input: User feedback

[0452] Data processing: Convert feedback data into the appropriate format

[0453] Output: Feedback data sent to the server

[0454] Step 10:

[0455] The server receives user feedback and uses it, along with emotional data, to improve the user profile and the generated AI model, which is then reflected in the next proposal.

[0456] Input: Feedback data, emotion data

[0457] Data processing: Retraining generative AI models and updating user profiles

[0458] Output: An improved AI model and an updated user profile

[0459] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0460] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0461] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0462] [Second embodiment]

[0463] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0464] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0465] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0466] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0467] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0468] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0469] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0470] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0471] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0472] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0473] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0474] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0475] As an embodiment of the present invention, the operation and processing of a specific system will be described below.

[0476] Collection and processing of user data

[0477] 1. Collecting user image data and survey data

[0478] Users upload a full-body photo of themselves to the platform's upload screen from a device such as a smartphone or PC.

[0479] Users fill out a survey provided on the platform and enter information about their preferred colors, fashion style, budget, and lifestyle.

[0480] The terminal collects this data and transmits it to the server.

[0481] Image analysis and user profile generation

[0482] 2. Image Recognition and Attribute Analysis

[0483] The server receives the uploaded image data and analyzes it using an image recognition algorithm.

[0484] The server recognizes the user's body type (e.g., slim, athletic, curvy, etc.), facial features, and usual fashion style (e.g., casual, formal, etc.).

[0485] 3. Integration with survey data

[0486] The server combines the results of the image analysis with the survey data to generate a detailed user profile for each individual user.

[0487] Fashion item suggestions

[0488] 4. AI-generated recommendations

[0489] The server inputs the generated user profile into an AI model, which includes recurrent neural networks and generative models, and is capable of suggesting appropriate fashion items based on past data.

[0490] Based on the user profile, the server generates a list of fashion items that match the user's body type, preferences, and lifestyle.

[0491] Trend analysis and design generation

[0492] 5. Trend data collection and analysis

[0493] The server regularly collects the latest fashion trend information from fashion shows, social media, news sites, etc.

[0494] The server inputs the collected data into an AI model and performs trend analysis.

[0495] 6. Generating new designs

[0496] The server uses AI design generation capabilities to generate unique fashion designs based on trend data and user profiles.

[0497] The server adds the generated new fashion design to a list of suggestions for the user.

[0498] Virtual try-on experience

[0499] 7. Displaying the proposed list and offering to try on the items

[0500] The terminal displays the suggested list of fashion items sent from the server to the user.

[0501] The user selects items of interest from the suggestion list.

[0502] The terminal displays a virtual try-on screen for the selected item using VR or AR technology.

[0503] Users can check the look and fit of items on a virtual try-on screen.

[0504] Gathering feedback and improving

[0505] 8. Gather feedback and improve the model

[0506] Users enter feedback about the items they try on (e.g., "looks good," "kind of weird," etc.) into the platform.

[0507] The server receives feedback from users and uses this data to improve user profiles and AI models.

[0508] These processes allow users to efficiently find the fashion items that best suit them and check them out before purchasing by virtually trying them on.

[0509] The processing flow will be explained below.

[0510] Step 1:

[0511] Users take a full-body photo of themselves and upload it to the platform's upload screen from their smartphone, PC, or other device. The uploaded image data is then sent from the device to the server.

[0512] Step 2:

[0513] Users answer a survey provided on the platform, entering information about their preferred colors, fashion style, budget, and lifestyle. The survey data is then sent from the device to the server.

[0514] Step 3:

[0515] The server receives the uploaded image data and analyzes it using image recognition algorithms to identify the user's body type (e.g., slim, athletic, chubby, etc.), facial features, and usual fashion style (e.g., casual, formal, etc.).

[0516] Step 4:

[0517] The server combines the results of the image analysis with the survey data to generate a detailed user profile for each individual user, including data such as body type, style preferences, and living environment.

[0518] Step 5:

[0519] The server inputs the generated user profile into an AI model, which uses recurrent neural networks and generative models to generate a list of fashion items that best suit the user.

[0520] Step 6:

[0521] The server periodically collects trend data from the latest fashion shows, social media, news sites, etc. This trend data is stored in a database within the server.

[0522] Step 7:

[0523] The server inputs the collected trend data into the AI ​​model for trend analysis, which then generates unique fashion designs based on the trend data, integrates them with the user profile, and adds them to the suggestion list.

[0524] Step 8:

[0525] The server transmits a list of fashion items generated based on the user profile to the user's terminal.

[0526] Step 9:

[0527] The terminal displays a list of suggested fashion items sent from the server to the user, who then selects an item of interest from the suggested list.

[0528] Step 10:

[0529] The device uses VR or AR technology to display a virtual try-on screen for the selected item, allowing the user to check the look and fit of the item.

[0530] Step 11:

[0531] Users input feedback (e.g., "looks good" or "not so good") about the items they try on into the platform. The feedback data is sent from the device to the server.

[0532] Step 12:

[0533] The server receives user feedback and uses this data to improve the user profile and the AI ​​model, which can then provide more accurate suggestions the next time the user uses the service.

[0534] Example 1

[0535] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0536] Conventional fashion item suggestion systems have been inadequate in suggesting items based on the user's body type and style, making it difficult to suggest items that are optimal for each individual user. Furthermore, there are limited ways for users to check how the suggested items will actually look on them. Furthermore, there is a lack of a mechanism for utilizing user feedback to improve the accuracy of suggestions.

[0537] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0538] In this invention, the server includes means for receiving user image data and analyzing the image data to recognize the user's body type and style, means for acquiring user questionnaire data and integrating the questionnaire data to generate a user profile, means for suggesting items based on the user profile, means for collecting the latest data and generating new designs based on the data, and means for providing a virtual try-on of the suggested items using augmented reality and virtual reality technologies, thereby suggesting fashion items that are optimal for each individual user and enabling the user to check the appearance and fit of the items through the virtual try-on before purchasing.

[0539] "Image data" is digital data containing visual information captured by an electronic device.

[0540] "Recognition" is the process of analyzing image data and survey data to identify specific characteristics and attributes of a user.

[0541] "Survey data" refers to data that includes information such as preferences, lifestyle, and budget entered by the user.

[0542] A "user profile" is detailed information about an individual user that integrates the results of analyzing image data and questionnaire data.

[0543] "Items" are fashion-related items such as clothing and accessories.

[0544] "Design" refers to the appearance or shape of an item based on a particular concept or style.

[0545] "Augmented reality technology" is a technology that displays virtual information overlaid on the real environment.

[0546] "Virtual reality technology" is a technology that allows users to experience immersion in a virtual environment.

[0547] "Feedback" refers to opinions and evaluations provided by users regarding proposed items or systems.

[0548] A "generative AI model" is an artificial intelligence model that generates new designs and proposals based on input data.

[0549] As an embodiment of the present invention, a series of processes from collecting user data to proposing fashion items, analyzing trends and creating designs, providing a virtual try-on experience, and collecting and improving feedback will be specifically described.

[0550] First, we will explain the collection of user data.

[0551] Users upload a full-body photo of themselves from their smartphone or PC to the platform's upload screen. It is recommended that the image be in JPEG or PNG format. Users then answer a survey provided on the platform, entering information such as their favorite colors, fashion style, budget, and lifestyle. This data is collected by the device and securely transmitted to the server via the HTTPS protocol.

[0552] Next, image analysis and user profile generation will be described.

[0553] The server runs an image recognition algorithm using TensorFlow to analyze the received image data. Specifically, it uses deep learning models such as DeepLab to recognize the user's body type, facial features, and usual fashion style. To integrate the analysis results with the survey data, the server accesses a database system such as MySQL or PostgreSQL to create a detailed user profile.

[0554] Next, the proposal of fashion items will be described.

[0555] The server inputs the generated user profile into a generative AI model such as a recurrent neural network (RNN) or generative adversarial network (GAN). This model is built using frameworks such as TensorFlow and PyTorch. The AI ​​model generates a list of suitable fashion items based on the user's body type, preferences, and lifestyle.

[0556] Trend analysis and design generation are as follows:

[0557] The server automatically collects the latest fashion trend information from fashion shows, social media, news sites, and other sources. This information is collected using web scraping technologies such as BeautifulSoup and Scrapy. The server then analyzes the collected data using natural language processing (NLP) techniques to identify fashion trends. Based on the trend data and user profiles, the server then generates new designs using AI design generation functions such as StyleGAN, and adds them to a list of suggestions.

[0558] Here's the virtual try-on experience:

[0559] The device displays the list of suggestions sent from the server to the user. The user selects items of interest from this list. For the selected items, the device displays a virtual try-on screen using augmented reality (ARKit or ARCore) or virtual reality technology, allowing the user to see how the items look and fit before purchasing.

[0560] Finally, we discuss collecting feedback and improving the model.

[0561] Users rate items on a virtual try-on screen. Feedback is in the form of simple ratings such as "looks good" or "not so good." The server collects this feedback and uses it to improve the user profile and the generative AI model. The feedback data is used as new training data to help improve the model's recommendation accuracy.

[0562] As described above, this system is designed to help users efficiently find the items that suit them best by suggesting the most suitable fashion items based on the user's image data and questionnaire data and providing a virtual try-on experience.

[0563] Prompt Sentence Examples

[0564] "You submit a full-body photo of yourself. Then, you answer a questionnaire about your preferred colors, fashion style, budget, and lifestyle. The system will use this information to suggest fashion items that are perfect for you."

[0565] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0566] Step 1: Collect user data

[0567] Users upload a full-body photo of themselves from their smartphone or PC to the platform's upload screen. The input data is image data in JPEG or PNG format.

[0568] Users answer a survey on the platform and enter information such as their favorite colors, fashion style, budget, and lifestyle. The survey data becomes the input data.

[0569] The terminal transmits the image data and questionnaire data collected from the user to the server using the secure HTTPS protocol. The output data is the image data and questionnaire data of the user transmitted to the server.

[0570] Step 2: Integrating image analysis and survey data

[0571] The server analyzes the received image data using TensorFlow. Specifically, it uses deep learning models such as DeepLab to recognize the user's body shape and facial features. The input data is the user's image data, and the output data is the analysis results regarding body shape and facial features.

[0572] The server accesses a database such as MySQL or PostgreSQL to integrate the analysis results with user survey data. The survey data and image analysis results are the input data, and the integrated user profile is the output data.

[0573] Step 3: Proposing fashion items

[0574] The server inputs the generated user profile into a generative AI model such as a Recurrent Neural Network (RNN) or Generative Adversarial Networks (GAN). The input data is the user profile, and the output data is a list of suggested items.

[0575] The server uses an AI model to suggest fashion items based on the user's body type, preferences, and lifestyle. Specifically, the AI ​​model generates an item list based on learned parameters.

[0576] Step 4: Collect and analyze trend data

[0577] The server collects the latest fashion trend information from external sources such as fashion shows, social media, and news sites. The input data is trend information from external sources. Specific operations involve using web scraping tools such as BeautifulSoup and Scrapy.

[0578] The server analyzes the collected trend data using natural language processing (NLP) technology. The input data is the collected trend information, and the output data is the trend keywords and themes extracted by the analysis.

[0579] Step 5: Generate a new design

[0580] The server generates new fashion designs using AI design generation functions such as StyleGAN based on trend data and user profiles. The input data is the trend data and user profiles, and the output data is the generated fashion designs.

[0581] The server adds the new design to the list of suggestions for the user. Specifically, the AI ​​model integrates trend information and user profiles to generate new designs.

[0582] Step 6: Offer a virtual try-on

[0583] The terminal displays the suggested list of fashion items sent from the server to the user. The input data is the suggested list from the server, and the output data is the suggested list displayed on the user's terminal.

[0584] The user selects an item of interest from the suggestion list, and the input data is the item selected by the user.

[0585] The device displays a virtual try-on screen for the selected item using augmented reality (ARKit or ARCore) or virtual reality technology. The user can check the appearance and fit of the item on the virtual try-on screen. The output data is visual information from the virtual try-on.

[0586] Step 7: Gather feedback

[0587] Users input their feedback on the items they virtually try on into the platform. The input data is the user's evaluation information (e.g., "looks good," "not so good," etc.).

[0588] The server collects user feedback and uses it to improve the user profile and the generated AI model. The output data is an updated user profile and AI model. Specifically, the feedback data is used as new training data for the machine learning model, improving the model's recommendation accuracy.

[0589] (Application example 1)

[0590] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0591] Conventional fashion item recommendation systems struggle to provide personalized recommendations based on a user's body type and fashion style. Furthermore, they lack a way for users to check the fit and appearance of items before trying them on. Furthermore, they lack a mechanism for efficiently integrating user feedback to improve the accuracy of recommendations. This creates a challenge: users spend a lot of time and effort in the process of finding the perfect fashion item.

[0592] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0593] In this invention, the server includes: means for receiving a user's image data and analyzing the image data to recognize the user's body type and fashion style; means for acquiring user survey data and integrating the survey data to generate a user profile; means for suggesting fashion items based on the user profile; means for collecting the latest trend data and generating new fashion designs based on the trend data; means for providing a virtual try-on of the suggested fashion items using VR or AR technology; means for analyzing the profile data and the proposed fashion items using an AI model stored in the server to suggest fashion coordinations; and means for obtaining feedback from the user regarding the virtually tried-on fashion items and improving the accuracy of the user profile and AI model based on the feedback. This allows users to efficiently find fashion items that suit their body type and preferences and check the fit and appearance of the items before purchasing. Furthermore, the accuracy of the suggestions can be continuously improved through feedback, providing a more satisfying shopping experience.

[0594] "User profile" refers to individual information generated based on a user's body type, fashion style, and survey data.

[0595] "Image recognition algorithm" refers to a method of analyzing a user's body shape and fashion style using a machine learning model.

[0596] "Fashion items" refers to fashion-related products such as clothing and accessories.

[0597] "VR technology" refers to virtual reality technology, which allows users to have a realistic fitting experience in a virtual space.

[0598] "AR technology" stands for augmented reality technology, and refers to the technology of overlaying virtual objects on the real world.

[0599] "Generative AI models" refer to artificial intelligence models used to generate new fashion items and designs based on past data.

[0600] "Trend data" refers to data on the latest fashion trends collected from fashion shows, social media, news sites, etc.

[0601] "Feedback" refers to evaluations and opinions obtained from users, and is information that is used to improve the system.

[0602] "Server" refers to the central processing unit that receives data from users and provides analysis and recommendations.

[0603] Specific system operations and processes will be described below for the embodiment of the present invention.

[0604] First, users upload a full-body photo of themselves to the platform's upload screen from their smartphone, PC, or other device. Then, they answer a questionnaire provided on the platform, entering information about their preferred colors, fashion style, budget, and lifestyle. The device collects this data and sends it to the server.

[0605] The server receives the uploaded image data and analyzes it using an image recognition algorithm. This algorithm is based on a machine learning model (e.g., using TensorFlow or Keras) and recognizes the user's body type, facial features, and usual fashion style. The server then combines the results of the image analysis with the survey data to generate a detailed user profile.

[0606] The generated user profile is input into a generative AI model on the server. This model uses recurrent neural networks and generative models (e.g., PyTorch) that have the ability to suggest appropriate fashion items based on past data. Based on the user profile, the server generates a list of fashion items that match the user's body type, preferences, and lifestyle.

[0607] The server also periodically collects the latest fashion trend information from fashion shows, social media, news sites, etc., and inputs it into the generative AI model for trend analysis. Based on the results of this analysis, new fashion designs are generated and added to the user's suggestion list.

[0608] The device then displays a list of suggested fashion items sent from the server to the user. The user selects an item of interest, and the device can then display a virtual try-on screen using VR or AR technology. This technology allows the user to check the look and fit of the item on the virtual try-on screen. Specifically, smart glasses or a head-mounted display are used.

[0609] Finally, users provide feedback on the items they try on to the platform, which is received by the server and used to refine the user's profile and AI model, allowing the system to continually improve its performance.

[0610] An example of a specific prompt is, "The user is 170 cm tall, weighs 65 kg, prefers casual fashion, and uses a lot of accessories. Please suggest an appropriate fashion coordination." This allows the AI ​​model to suggest the best coordination for the user, and allows for virtual try-on based on that information.

[0611] This system allows users to efficiently find fashion items that suit their body type and preferences, and check the fit and appearance before purchasing. Feedback can also be used to continuously improve the accuracy of suggestions, providing a more satisfying shopping experience.

[0612] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0613] Step 1:

[0614] Users upload a full-body photo of themselves from their smartphone or PC to the platform's upload screen.

[0615] The terminal collects the user's image data and transmits the data to a server.

[0616] Step 2:

[0617] Users fill out a survey on the platform, inputting information about their preferred colors, fashion style, budget and lifestyle.

[0618] The terminal collects the questionnaire data and transmits the data to the server.

[0619] Step 3:

[0620] The server receives the uploaded image data and analyzes it using an image recognition algorithm.

[0621] Through this analysis, the server can determine the user's body type (e.g., slim, athletic, chubby, etc.), facial features, and usual fashion style (e.g., casual, formal, etc.).

[0622] Input: Image data, Output: User's body shape and fashion style information

[0623] Step 4:

[0624] The server combines the survey data with the results of image analysis to generate a detailed user profile.

[0625] Input: Image analysis results, questionnaire data, Output: User profile

[0626] Step 5:

[0627] The server inputs the generated user profile into a generative AI model and suggests appropriate fashion items based on past data.

[0628] Generative AI models use recurrent neural networks and generative models.

[0629] Input: User profile, Output: List of fashion items

[0630] Step 6:

[0631] The server regularly collects the latest fashion trend information from fashion shows, social media, news sites, etc. and inputs it into the generative AI model.

[0632] The server performs trend analysis and generates new fashion designs.

[0633] Input: Trend data, Output: New fashion design

[0634] Step 7:

[0635] The server adds the generated new fashion design to a list of suggestions for the user.

[0636] Input: New fashion design, Output: Updated list of fashion items

[0637] Step 8:

[0638] The terminal displays the suggested list of fashion items sent from the server to the user.

[0639] The user selects the items of interest.

[0640] Input: List of fashion items, Output: User selection

[0641] Step 9:

[0642] The terminal uses VR or AR technology to display a virtual try-on screen for the item selected by the user.

[0643] Users can check the look and fit of items on a virtual try-on screen.

[0644] Input: User selection, Output: Virtual fitting screen

[0645] Step 10:

[0646] Users enter feedback on the items they try on into the platform.

[0647] The terminal sends the feedback to the server.

[0648] Input: User feedback, Output: Feedback data

[0649] Step 11:

[0650] The server receives feedback from users and uses it to improve the user profile and the generated AI model.

[0651] This allows the system to continuously improve its performance.

[0652] Input: Feedback data, Output: Improved user profiles and generative AI models

[0653] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0654] As an embodiment of the present invention, a system incorporating an emotion engine will be described in detail.

[0655] Collection and processing of user data

[0656] 1. Collecting user image data and survey data

[0657] Users upload a full-body photo of themselves to the platform's upload screen from their smartphone, PC, or other device. The uploaded image data is then sent from the device to the server.

[0658] Users answer a survey provided on the platform, entering information about their preferred colors, fashion style, budget, and lifestyle. The survey data is then sent from the device to the server.

[0659] Image analysis and user profile generation

[0660] 2. Image Recognition and Attribute Analysis

[0661] The server receives the uploaded image data and analyzes it using image recognition algorithms to identify the user's body type (e.g., slim, athletic, chubby, etc.), facial features, and usual fashion style (e.g., casual, formal, etc.).

[0662] 3. Emotion Recognition and Attribute Analysis

[0663] The server uses an emotion recognition algorithm to analyze the user's emotional state (e.g., joy, sadness, surprise, etc.) from the user's image data.

[0664] 4. Integration with survey data

[0665] The server combines the results of the image analysis, the emotion analysis, and the survey data to generate a detailed user profile for each individual user, including data such as body type, style preferences, emotional state, and living environment.

[0666] Fashion item suggestions

[0667] 5. AI-generated recommendations

[0668] The server inputs the generated user profile into an AI model, which includes recurrent neural networks and generative models, and generates a list of appropriate fashion items based on past data and the user's emotional data.

[0669] Trend analysis and design generation

[0670] 6. Trend data collection and analysis

[0671] The server periodically collects the latest fashion trend information from fashion shows, social media, news sites, etc. This trend data is stored in a database.

[0672] 7. Generating new designs

[0673] The server inputs the collected trend data into the AI ​​model for trend analysis, which then generates unique fashion designs based on the trend data, integrates them with the user profile, and adds them to the suggestion list.

[0674] Virtual try-on experience

[0675] 8. Displaying the proposed list and offering to try on the items

[0676] The terminal displays a list of suggested fashion items sent from the server to the user, who then selects an item of interest from the suggested list.

[0677] The device uses VR or AR technology to display a virtual try-on screen for the selected item, allowing the user to check the look and fit of the item.

[0678] Gathering feedback and improving

[0679] 9. Gather feedback and improve the model

[0680] Users input their feedback about the items they try on (e.g., "looks good," "not great," etc.) into the platform. The feedback data is sent from the device to the server.

[0681] The server receives user feedback and uses this data, along with emotional data, to improve the user profile and the AI ​​model, which can then provide more accurate suggestions the next time the user uses the app.

[0682] These processes allow users to efficiently find the perfect fashion item for them, and with the help of virtual try-on and emotion-recognition feedback, they can check before they buy.

[0683] The processing flow will be explained below.

[0684] Step 1:

[0685] Users upload a full-body photo of themselves to the platform's upload screen from their smartphone, PC, or other device. The uploaded image data is then sent from the device to the server.

[0686] Step 2:

[0687] Users answer a survey provided on the platform, entering information about their preferred colors, fashion style, budget, and lifestyle. The survey data is then sent from the device to the server.

[0688] Step 3:

[0689] The server receives the uploaded image data and analyzes it using image recognition algorithms to identify the user's body type (e.g., slim, athletic, chubby, etc.), facial features, and usual fashion style (e.g., casual, formal, etc.).

[0690] Step 4:

[0691] The server uses an emotion recognition algorithm to analyze the user's emotional state (e.g., joy, sadness, surprise, etc.) from the user's image data. The analysis results are stored as emotion data.

[0692] Step 5:

[0693] The server combines the results of the image analysis, the emotion analysis, and the survey data to generate a detailed user profile for each individual user, including data such as body type, style preferences, emotional state, and living environment.

[0694] Step 6:

[0695] The server inputs the generated user profile into an AI model, which uses recurrent neural networks and generative models to generate a list of appropriate fashion items based on past data and the user's emotional data.

[0696] Step 7:

[0697] The server periodically collects the latest fashion trend information from fashion shows, social media, news sites, etc. This trend data is stored in a database within the server.

[0698] Step 8:

[0699] The server inputs the collected trend data into the AI ​​model for trend analysis, which then generates unique fashion designs based on the trend data, integrates them with the user profile, and adds them to the suggestion list.

[0700] Step 9:

[0701] The server transmits a list of fashion items generated based on the user profile to the user's terminal.

[0702] Step 10:

[0703] The terminal displays a list of suggested fashion items sent from the server to the user, who then selects an item of interest from the suggested list.

[0704] Step 11:

[0705] The device uses VR or AR technology to display a virtual try-on screen for the selected item, allowing the user to check the look and fit of the item.

[0706] Step 12:

[0707] Users can input their feedback (e.g., "looks good" or "not so good") into the platform after trying on the item. When providing feedback, they can also reflect their own feelings and provide detailed impressions.

[0708] Step 13:

[0709] The server receives user feedback and sentiment data and uses this data to improve the user profile and the AI ​​model, which can then provide more accurate suggestions the next time the user uses the app.

[0710] Example 2

[0711] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0712] Conventional fashion suggestion systems primarily base their suggestions on analysis of the user's body type and style and trend data, but do not fully consider the user's emotions or feedback. As a result, they are unable to recommend the most suitable fashion items for the user, limiting their ability to improve user satisfaction. Furthermore, few systems utilize virtual try-on technology, making it difficult to try on and check items before purchasing. There is a need for a system that can solve these issues, provide more accurate fashion suggestions that take the user's emotional state into account, and enable users to check items before purchasing through virtual try-on.

[0713] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving user image data and analyzing the image data to recognize the user's body type and fashion style, means for acquiring user questionnaire data and integrating the questionnaire data to generate a user profile, means for suggesting fashion items based on the user profile, means for collecting the latest trend data and generating new fashion designs based on the trend data, means for providing a virtual try-on of the suggested fashion items using VR or AR technology, means for analyzing emotions from the user image data, and means for using a generative AI model to list appropriate fashion items based on the user profile. This makes it possible to suggest optimal fashion items to the user through fashion suggestions and virtual try-ons that take the user's emotional state into consideration.

[0714] "User" refers to a person who uses the system to suggest fashion items and virtually try them on.

[0715] "Image data" refers to photographs or videos of the user's entire body or parts that are used to recognize the user's body type, facial features, and fashion style.

[0716] "Server" refers to a computer system that receives data sent from users and performs various processes for analyzing and proposing fashion items.

[0717] "Survey data" refers to data entered by users regarding their preferred colors, fashion style, budget, and lifestyle.

[0718] A "user profile" refers to detailed information about a user that integrates the user's image data, survey data, sentiment analysis results, etc.

[0719] "Fashion items" refer to items such as clothing, accessories, and shoes that are suggested to users.

[0720] "Trend data" refers to information about the latest fashion collected from fashion shows, social media, news sites, etc.

[0721] "VR" refers to virtual reality technology, which provides users with a visual experience that makes them feel as if they are in a three-dimensional space.

[0722] "AR" refers to augmented reality technology, which displays digital information overlaid on real-world scenery.

[0723] "Emotion recognition algorithm" refers to a program for analyzing a user's emotional state from image data.

[0724] "Generative AI model" refers to the machine learning model used to list appropriate fashion items based on a user profile.

[0725] A "prompt sentence" is an input sentence given to a generative AI model, and refers to an instruction sentence to generate a response based on specific conditions or purposes.

[0726] "Feedback" refers to the impressions and evaluations that users input regarding the suggested fashion items.

[0727] MODE FOR CARRYING OUT THE INVENTION

[0728] As an embodiment of the present invention, a system incorporating an emotion recognition algorithm and a generative AI model will be described in detail.

[0729] System configuration

[0730] The system includes the following components:

[0731] User: A person who proposes fashion items and virtually tries them on.

[0732] Terminal: A device used by a user, such as a smartphone or PC, that connects to the platform to input and display data.

[0733] Server: Refers to a computer system that receives data sent from users and performs various processes for analyzing and proposing fashion items.

[0734] Hardware and software used

[0735] Hardware: smartphones, PCs, servers.

[0736] Software: image recognition algorithms (e.g. OpenCV), emotion recognition algorithms, recurrent neural networks (RNN), generative models (GAN), database management systems (e.g. MongoDB), virtual reality (VR) or augmented reality (AR) technologies.

[0737] Specific processing

[0738] User Data Collection

[0739] 1. Users log in to the platform using their smartphone or PC and upload a full-body photo of themselves.

[0740] 2. Users answer a survey provided on the platform and enter information about their preferred colors, fashion style, budget, and lifestyle.

[0741] 3. The terminal sends the uploaded image data and questionnaire data to the server.

[0742] Data analysis and profile generation

[0743] 4. The server receives the image data and uses image recognition algorithms to analyze the user's body type, facial features, and usual fashion style.

[0744] 5. The server analyzes the user's emotional state from the image data using emotion recognition algorithms.

[0745] 6. The server integrates the image analysis results, emotion analysis results, and survey data to generate a detailed user profile.

[0746] Item suggestions and trend analysis

[0747] 7. The server inputs the generated user profile into an AI model, which can be a recurrent neural network (RNN) or a generative neural network (GAN).

[0748] 8. The server runs the AI ​​model and generates a list of appropriate fashion items based on historical data and the user's emotional data.

[0749] Collecting trend data and generating new designs

[0750] 9. The server collects the latest trend data from fashion shows, social media, and news sites and stores it in a database.

[0751] 10. The server inputs the trend data into the AI ​​model, performs trend analysis, and generates unique fashion designs.

[0752] 11. The server merges the generated design with the user profile and adds it to the suggestion list.

[0753] Virtual try-on and feedback

[0754] 12. The device displays the list of suggestions sent by the server to the user, who selects items that interest them.

[0755] 13. The device will then display the selected items on a virtual try-on screen using VR or AR technology, allowing the user to check how they look and fit.

[0756] 14. The user enters feedback on the item they tried on into the platform, and the feedback data is sent to the server.

[0757] Using Feedback

[0758] 15. The server analyzes the received feedback data and uses it, along with the emotional data, to improve the user profile and AI model, enabling more accurate suggestions the next time the user uses the service.

[0759] Examples of concrete examples and prompts

[0760] For example, if a user is looking for "work" fashion items, the following prompt might be used:

[0761] Generate a user profile by combining a full-body photo of the user with survey data. Based on the profile, generate a list of suggested "work" fashion items and offer virtual try-on in VR.

[0762] This allows users to efficiently find the perfect fashion item for them, and allows them to check before they buy using virtual try-on and emotion-recognition based feedback.

[0763] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0764] Step 1:

[0765] Users upload a full-body photo of themselves to the platform's upload screen using their smartphone or PC.

[0766] The terminal transmits the uploaded image data to the server.

[0767] Specifically, the user takes a full-body photo using a camera, selects the image file using the file selection button, and presses the send button. The input is the full-body photo, and the output is the image data sent to the server.

[0768] Step 2:

[0769] Users fill out a survey provided on the platform and enter information about their preferred colors, fashion style, budget, and lifestyle.

[0770] The terminal transmits the inputted questionnaire data to the server.

[0771] Specifically, the user fills in the questionnaire form and presses the send button. The input is the questionnaire data, and the output is the questionnaire data sent to the server.

[0772] Step 3:

[0773] The server uses image recognition algorithms to analyze the received image data.

[0774] Specifically, the server analyzes the user's body type, facial features, and usual fashion style.

[0775] Specifically, the server uses the OpenCV library to perform face detection and body type classification. The input is image data, and the output is the analysis results (body type, facial features, and fashion style).

[0776] Step 4:

[0777] The server applies an emotion recognition algorithm based on the received image data.

[0778] The server identifies the user's emotional state (e.g., happy, sad, surprised, etc.) from the image.

[0779] Specifically, emotion recognition uses a facial expression recognition algorithm, where the input is image data and the output is the analysis result of the emotional state.

[0780] Step 5:

[0781] The server integrates the image analysis results, emotion analysis results, and survey data to generate a user profile.

[0782] The server stores this data in a database and records it in JSON format.

[0783] Specifically, it creates a database entry and saves the user profile. The input is the image analysis results, emotion analysis results, and questionnaire data, and the output is the generated user profile.

[0784] Step 6:

[0785] The server inputs the generated user profile into the AI ​​model.

[0786] The server runs an AI model (such as a recurrent neural network or a generative model) to generate a list of suitable fashion items.

[0787] Specifically, it calls an AI model, provides prompts, and generates a list of items based on the parameters: the input is a user profile, and the output is a list of fashion items.

[0788] Step 7:

[0789] The server periodically collects trend data from fashion shows, social media, and news sites.

[0790] The server stores this information in a database.

[0791] Specifically, it uses scraping scripts and APIs to obtain the latest trend information and stores it in a database. The input is trend data from various external sources, and the output is the stored trend data.

[0792] Step 8:

[0793] The server inputs the collected trend data into an AI model, performs trend analysis, and generates new fashion designs.

[0794] The server merges the generated design with the user profile and adds it to a list of suggestions.

[0795] Specifically, it runs an AI model to generate designs based on trend data and integrate it with the user profile. The input is trend data and the user profile, and the output is an updated list of suggestions.

[0796] Step 9:

[0797] The terminal displays the proposal list sent from the server to the user.

[0798] The user selects items of interest from the suggestion list.

[0799] The terminal displays the selected items on a virtual try-on screen using VR or AR technology.

[0800] Specifically, the device uses an AR kit and a VR app to perform virtual try-on. The input is a list of suggestions, and the output is a display of the virtual try-on.

[0801] Step 10:

[0802] Users enter feedback on the items they try on into the platform.

[0803] The terminal transmits the feedback data to the server.

[0804] Specifically, the user fills in the feedback form and presses the submit button. The input is the feedback, and the output is the feedback data sent to the server.

[0805] Step 11:

[0806] The server analyzes the received feedback and uses it, along with the emotional data, to improve the user profile and AI model.

[0807] The server will be able to make more accurate suggestions the next time you use the service.

[0808] Specifically, the feedback data is analyzed and the AI ​​model is retrained. The input is the feedback data, and the output is an improved AI model.

[0809] (Application example 2)

[0810] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0811] Existing fashion recommendation systems make suggestions based on the user's body type and fashion style, but they are unable to consider the emotional state and feedback of each individual user, making it difficult to fully increase user satisfaction. Furthermore, they lack the ability to make suggestions using the latest trend data or virtual try-on functions, making it difficult to provide a real-time fitting experience or suggestions tailored to individual preferences.

[0812] The identification processing by the identification 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 receiving image data of a user and analyzing the image data to recognize the user's body type and fashion style, means for acquiring questionnaire data for the user and integrating the questionnaire data to generate a user profile, means for using an emotion recognition algorithm to analyze the user's emotional state, means for using a generative AI model to suggest fashion items based on the user profile, means for collecting the latest trend data and generating new fashion designs based on the trend data, means for providing a virtual try-on of the suggested fashion items using VR or AR technology, means for accepting uploads of the user's full-body photo and questionnaire data, and means for collecting user feedback. This enables advanced fashion suggestions based on the generation of individual user profiles and emotion recognition, and can increase user satisfaction through virtual try-ons and feedback collection.

[0813] "User image data" refers to still images or video data taken or uploaded by a user using a terminal.

[0814] "Body type" is a concept that refers to the dimensions, shape, proportions, etc. that characterize the appearance and structure of a user's body.

[0815] "Fashion style" refers to the user's preferred clothing and style trends, genres, and designs.

[0816] "Survey Data" refers to information provided by users in the form of questions about their preferred colors, fashion style, budget, lifestyle, etc.

[0817] A "user profile" is a data set that includes the attributes, preferences, and characteristics of an individual user, generated by integrating user image data, survey data, and sentiment analysis results.

[0818] An "emotion recognition algorithm" is a technology that analyzes a user's image or video data to identify their emotional state at that time (e.g., joy, sadness, surprise, etc.).

[0819] A "generative AI model" is an artificial intelligence model that suggests new fashion items based on accumulated data and learning results.

[0820] "Trend data" refers to information about currently popular styles and designs collected from the latest fashion shows, social media, news sites, etc.

[0821] "Virtual try-on" is a feature that allows users to try on clothes in a digital space using VR (virtual reality) or AR (augmented reality) technology.

[0822] "Feedback" refers to the ratings, comments, and opinions provided by users based on their try-on and usage experiences.

[0823] The system for implementing the present invention includes various processes related to users, servers, and terminals. A specific embodiment of the system will be described below.

[0824] Collection and processing of user image data and survey data

[0825] 1. Collecting user image data and survey data

[0826] Users take a full-body photo of themselves using a device such as a smartphone or PC and upload it to the system. They also answer a questionnaire provided on the platform they use, providing information about their preferred colors, fashion style, budget, and lifestyle. This data is then sent from the device to the server.

[0827] Image analysis and user profile generation

[0828] 2. Image analysis and emotion recognition

[0829] The server receives the image data sent by the user and uses an image recognition algorithm (e.g., OpenCV, TensorFlow) to analyze the user's body shape, facial features, and usual fashion style, while simultaneously using an emotion recognition algorithm (e.g., Microsoft Azure Face API) to analyze the user's emotional state (e.g., joy, sadness, surprise, etc.).

[0830] 3. Integration with survey data and generation of user profiles

[0831] The results of image analysis and emotion recognition are combined with survey data to generate a detailed user profile for each individual user, including data such as body type, style preferences, emotional state, and living environment.

[0832] Fashion item suggestions

[0833] 4. AI-generated recommendations

[0834] The server inputs the generated user profile into a generative AI model (for example, a model using PyTorch or TensorFlow). The generative AI model generates a list of appropriate fashion items based on past data and the user's emotional data. This process suggests fashion items that take into account the user's preferences and emotional state.

[0835] Virtual try-on experience and feedback collection

[0836] 5. Displaying a list of suggestions and offering virtual try-ons

[0837] The device displays a list of suggested fashion items sent from the server. Users select items of interest from the suggested list and virtually try them on using VR or AR technology (e.g., Unity, ARKit, ARCore). Users can check the look and fit of the items on the virtual try-on screen.

[0838] 6. Gather feedback and improve the model

[0839] Users enter feedback on the items they try on into the platform. The feedback data sent from the device to the server, along with emotional data, is used to improve the user profile and generative AI model. The improved generative AI model can then make even more accurate suggestions the next time the user uses the platform.

[0840] Specific examples

[0841] Users open the app, take a full-body photo, and answer a questionnaire about their preferred colors, fashion style, budget, and lifestyle. Based on the uploaded data, the AI ​​will suggest three fashion items that suit the user, and they can virtually try on the items using AR. After the virtual try-on, users can enter and submit feedback, which will be reflected in the next suggestions.

[0842] Prompt Sentence Examples

[0843] "Female, in her 20s, slim build, prefers casual style. Prefers clothes in muted colors that are easy to move in. Budget is around 10,000 yen. Emotional state after trying on clothes: surprise and delight. Please recommend some fashion items based on the following information."

[0844] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0845] Step 1:

[0846] Users take a full-body photo of themselves using a device such as a smartphone or PC and upload it to the system. The uploaded image data is then sent from the device to the server.

[0847] Input: A full-body photo of the user

[0848] Data processing: Images taken on the device are converted into the appropriate format (e.g., JPEG, PNG).

[0849] Output: Image data sent to the server

[0850] Step 2:

[0851] Users answer a survey on the platform, providing information such as their preferred colors, fashion style, budget, lifestyle, etc. The survey data is sent from the device to the server.

[0852] Input: User's survey response

[0853] Data processing: Convert survey responses into data formats such as JSON and XML

[0854] Output: Survey data sent to the server

[0855] Step 3:

[0856] The server analyzes the received image data and uses image recognition algorithms (OpenCV, TensorFlow) to recognize the user's body type, facial features, and usual fashion style. The analysis results are integrated into a user profile.

[0857] Input: Image data

[0858] Data processing: Analyzes body shape, facial features, and fashion style using image recognition algorithms

[0859] Output: Analysis results (body shape, facial features, fashion style) data

[0860] Step 4:

[0861] The server uses an emotion recognition algorithm (Microsoft Azure Face API) to analyze the user's emotional state from their image data, which is then integrated into the user profile.

[0862] Input: Image data

[0863] Data processing: Analyze emotional states using emotion recognition algorithms

[0864] Output: Emotional state data

[0865] Step 5:

[0866] The server combines the image analysis results, emotion analysis results, and survey data to generate a detailed user profile, which includes the user's body type, style preferences, emotional state, living environment, and more.

[0867] Input: Image analysis results, emotion analysis results, questionnaire data

[0868] Data processing: Integrating data to generate user profiles

[0869] Output: User profile

[0870] Step 6:

[0871] The server inputs the generated user profile into the generative AI model to generate a list of appropriate fashion items, which are then stored on the server.

[0872] Input: User Profile

[0873] Data processing: Using generative AI models to suggest fashion items

[0874] Output: A list of fashion items

[0875] Step 7:

[0876] The terminal displays a list of suggested fashion items sent from the server to the user, who can then select the items they are interested in and try them on virtually.

[0877] Input: A list of fashion item suggestions

[0878] Output: Suggestion list displayed in terminal

[0879] Step 8:

[0880] The device uses VR or AR technology (Unity, ARKit, ARCore) to display a virtual try-on screen for the selected item, allowing the user to check the look and fit of the item.

[0881] Input: The item selected by the user

[0882] Data processing: Realizing virtual try-on using VR / AR technology

[0883] Output: Virtual fitting screen

[0884] Step 9:

[0885] Users enter their feedback on the items they try on into the platform, and the feedback data is sent from the device to the server.

[0886] Input: User feedback

[0887] Data processing: Convert feedback data into the appropriate format

[0888] Output: Feedback data sent to the server

[0889] Step 10:

[0890] The server receives user feedback and uses it, along with emotional data, to improve the user profile and the generated AI model, which is then reflected in the next proposal.

[0891] Input: Feedback data, emotion data

[0892] Data processing: Retraining generative AI models and updating user profiles

[0893] Output: An improved AI model and an updated user profile

[0894] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0895] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0896] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0897] [Third embodiment]

[0898] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0899] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0900] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0901] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0902] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0903] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0904] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0905] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0906] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0907] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0908] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0909] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0910] As an embodiment of the present invention, the operation and processing of a specific system will be described below.

[0911] Collection and processing of user data

[0912] 1. Collecting user image data and survey data

[0913] Users upload a full-body photo of themselves to the platform's upload screen from a device such as a smartphone or PC.

[0914] Users fill out a survey provided on the platform and enter information about their preferred colors, fashion style, budget, and lifestyle.

[0915] The terminal collects this data and transmits it to the server.

[0916] Image analysis and user profile generation

[0917] 2. Image Recognition and Attribute Analysis

[0918] The server receives the uploaded image data and analyzes it using an image recognition algorithm.

[0919] The server recognizes the user's body type (e.g., slim, athletic, curvy, etc.), facial features, and usual fashion style (e.g., casual, formal, etc.).

[0920] 3. Integration with survey data

[0921] The server combines the results of the image analysis with the survey data to generate a detailed user profile for each individual user.

[0922] Fashion item suggestions

[0923] 4. AI-generated recommendations

[0924] The server inputs the generated user profile into an AI model, which includes recurrent neural networks and generative models, and is capable of suggesting appropriate fashion items based on past data.

[0925] Based on the user profile, the server generates a list of fashion items that match the user's body type, preferences, and lifestyle.

[0926] Trend analysis and design generation

[0927] 5. Trend data collection and analysis

[0928] The server regularly collects the latest fashion trend information from fashion shows, social media, news sites, etc.

[0929] The server inputs the collected data into an AI model and performs trend analysis.

[0930] 6. Generating new designs

[0931] The server uses AI design generation capabilities to generate unique fashion designs based on trend data and user profiles.

[0932] The server adds the generated new fashion design to a list of suggestions for the user.

[0933] Virtual try-on experience

[0934] 7. Displaying the proposed list and offering to try on the items

[0935] The terminal displays the suggested list of fashion items sent from the server to the user.

[0936] The user selects items of interest from the suggestion list.

[0937] The terminal displays a virtual try-on screen for the selected item using VR or AR technology.

[0938] Users can check the look and fit of items on a virtual try-on screen.

[0939] Gathering feedback and improving

[0940] 8. Gather feedback and improve the model

[0941] Users enter feedback about the items they try on (e.g., "looks good," "kind of weird," etc.) into the platform.

[0942] The server receives feedback from users and uses this data to improve user profiles and AI models.

[0943] These processes allow users to efficiently find the fashion items that best suit them and check them out before purchasing by virtually trying them on.

[0944] The processing flow will be explained below.

[0945] Step 1:

[0946] Users take a full-body photo of themselves and upload it to the platform's upload screen from their smartphone, PC, or other device. The uploaded image data is then sent from the device to the server.

[0947] Step 2:

[0948] Users answer a survey provided on the platform, entering information about their preferred colors, fashion style, budget, and lifestyle. The survey data is then sent from the device to the server.

[0949] Step 3:

[0950] The server receives the uploaded image data and analyzes it using image recognition algorithms to identify the user's body type (e.g., slim, athletic, chubby, etc.), facial features, and usual fashion style (e.g., casual, formal, etc.).

[0951] Step 4:

[0952] The server combines the results of the image analysis with the survey data to generate a detailed user profile for each individual user, including data such as body type, style preferences, and living environment.

[0953] Step 5:

[0954] The server inputs the generated user profile into an AI model, which uses recurrent neural networks and generative models to generate a list of fashion items that best suit the user.

[0955] Step 6:

[0956] The server periodically collects trend data from the latest fashion shows, social media, news sites, etc. This trend data is stored in a database within the server.

[0957] Step 7:

[0958] The server inputs the collected trend data into the AI ​​model for trend analysis, which then generates unique fashion designs based on the trend data, integrates them with the user profile, and adds them to the suggestion list.

[0959] Step 8:

[0960] The server transmits a list of fashion items generated based on the user profile to the user's terminal.

[0961] Step 9:

[0962] The terminal displays a list of suggested fashion items sent from the server to the user, who then selects an item of interest from the suggested list.

[0963] Step 10:

[0964] The device uses VR or AR technology to display a virtual try-on screen for the selected item, allowing the user to check the look and fit of the item.

[0965] Step 11:

[0966] Users input feedback (e.g., "looks good" or "not so good") about the items they try on into the platform. The feedback data is sent from the device to the server.

[0967] Step 12:

[0968] The server receives user feedback and uses this data to improve the user profile and the AI ​​model, which can then provide more accurate suggestions the next time the user uses the service.

[0969] Example 1

[0970] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0971] Conventional fashion item suggestion systems have been inadequate in suggesting items based on the user's body type and style, making it difficult to suggest items that are optimal for each individual user. Furthermore, there are limited ways for users to check how the suggested items will actually look on them. Furthermore, there is a lack of a mechanism for utilizing user feedback to improve the accuracy of suggestions.

[0972] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0973] In this invention, the server includes means for receiving user image data and analyzing the image data to recognize the user's body type and style, means for acquiring user questionnaire data and integrating the questionnaire data to generate a user profile, means for suggesting items based on the user profile, means for collecting the latest data and generating new designs based on the data, and means for providing a virtual try-on of the suggested items using augmented reality and virtual reality technologies, thereby suggesting fashion items that are optimal for each individual user and enabling the user to check the appearance and fit of the items through the virtual try-on before purchasing.

[0974] "Image data" is digital data containing visual information captured by an electronic device.

[0975] "Recognition" is the process of analyzing image data and survey data to identify specific characteristics and attributes of a user.

[0976] "Survey data" refers to data that includes information such as preferences, lifestyle, and budget entered by the user.

[0977] A "user profile" is detailed information about an individual user that integrates the results of analyzing image data and questionnaire data.

[0978] "Items" are fashion-related items such as clothing and accessories.

[0979] "Design" refers to the appearance or shape of an item based on a particular concept or style.

[0980] "Augmented reality technology" is a technology that displays virtual information overlaid on the real environment.

[0981] "Virtual reality technology" is a technology that allows users to experience immersion in a virtual environment.

[0982] "Feedback" refers to opinions and evaluations provided by users regarding proposed items or systems.

[0983] A "generative AI model" is an artificial intelligence model that generates new designs and proposals based on input data.

[0984] As an embodiment of the present invention, a series of processes from collecting user data to proposing fashion items, analyzing trends and creating designs, providing a virtual try-on experience, and collecting and improving feedback will be specifically described.

[0985] First, we will explain the collection of user data.

[0986] Users upload a full-body photo of themselves from their smartphone or PC to the platform's upload screen. It is recommended that the image be in JPEG or PNG format. Users then answer a survey provided on the platform, entering information such as their favorite colors, fashion style, budget, and lifestyle. This data is collected by the device and securely transmitted to the server via the HTTPS protocol.

[0987] Next, image analysis and user profile generation will be described.

[0988] The server runs an image recognition algorithm using TensorFlow to analyze the received image data. Specifically, it uses deep learning models such as DeepLab to recognize the user's body type, facial features, and usual fashion style. To integrate the analysis results with the survey data, the server accesses a database system such as MySQL or PostgreSQL to create a detailed user profile.

[0989] Next, the proposal of fashion items will be described.

[0990] The server inputs the generated user profile into a generative AI model such as a recurrent neural network (RNN) or generative adversarial network (GAN). This model is built using frameworks such as TensorFlow and PyTorch. The AI ​​model generates a list of suitable fashion items based on the user's body type, preferences, and lifestyle.

[0991] Trend analysis and design generation are as follows:

[0992] The server automatically collects the latest fashion trend information from fashion shows, social media, news sites, and other sources. This information is collected using web scraping technologies such as BeautifulSoup and Scrapy. The server then analyzes the collected data using natural language processing (NLP) techniques to identify fashion trends. Based on the trend data and user profiles, the server then generates new designs using AI design generation functions such as StyleGAN, and adds them to a list of suggestions.

[0993] Here's the virtual try-on experience:

[0994] The device displays the list of suggestions sent from the server to the user. The user selects items of interest from this list. For the selected items, the device displays a virtual try-on screen using augmented reality (ARKit or ARCore) or virtual reality technology, allowing the user to see how the items look and fit before purchasing.

[0995] Finally, we discuss collecting feedback and improving the model.

[0996] Users rate items on a virtual try-on screen. Feedback is in the form of simple ratings such as "looks good" or "not so good." The server collects this feedback and uses it to improve the user profile and the generative AI model. The feedback data is used as new training data to help improve the model's recommendation accuracy.

[0997] As described above, this system is designed to help users efficiently find the items that suit them best by suggesting the most suitable fashion items based on the user's image data and questionnaire data and providing a virtual try-on experience.

[0998] Prompt Sentence Examples

[0999] "You submit a full-body photo of yourself. Then, you answer a questionnaire about your preferred colors, fashion style, budget, and lifestyle. The system will use this information to suggest fashion items that are perfect for you."

[1000] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1001] Step 1: Collect user data

[1002] Users upload a full-body photo of themselves from their smartphone or PC to the platform's upload screen. The input data is image data in JPEG or PNG format.

[1003] Users answer a survey on the platform and enter information such as their favorite colors, fashion style, budget, and lifestyle. The survey data becomes the input data.

[1004] The terminal transmits the image data and questionnaire data collected from the user to the server using the secure HTTPS protocol. The output data is the image data and questionnaire data of the user transmitted to the server.

[1005] Step 2: Integrating image analysis and survey data

[1006] The server analyzes the received image data using TensorFlow. Specifically, it uses deep learning models such as DeepLab to recognize the user's body shape and facial features. The input data is the user's image data, and the output data is the analysis results regarding body shape and facial features.

[1007] The server accesses a database such as MySQL or PostgreSQL to integrate the analysis results with the user's survey data. The survey data and image analysis results are the input data, and the integrated user profile is the output data.

[1008] Step 3: Proposing fashion items

[1009] The server inputs the generated user profile into a generative AI model such as a Recurrent Neural Network (RNN) or Generative Adversarial Networks (GAN). The input data is the user profile, and the output data is a list of suggested items.

[1010] The server uses an AI model to suggest fashion items based on the user's body type, preferences, and lifestyle. Specifically, the AI ​​model generates an item list based on learned parameters.

[1011] Step 4: Collect and analyze trend data

[1012] The server collects the latest fashion trend information from external sources such as fashion shows, social media, and news sites. The input data is trend information from external sources. Specific operations involve using web scraping tools such as BeautifulSoup and Scrapy.

[1013] The server analyzes the collected trend data using natural language processing (NLP) technology. The input data is the collected trend information, and the output data is the trend keywords and themes extracted through the analysis.

[1014] Step 5: Generate a new design

[1015] The server generates new fashion designs using AI design generation functions such as StyleGAN based on trend data and user profiles. The input data is the trend data and user profiles, and the output data is the generated fashion designs.

[1016] The server adds the generated new design to the list of suggestions for the user. Specifically, the AI ​​model integrates trend information and user profiles to generate new designs.

[1017] Step 6: Offer a virtual try-on

[1018] The terminal displays the suggested list of fashion items sent from the server to the user. The input data is the suggested list from the server, and the output data is the suggested list displayed on the user's terminal.

[1019] The user selects an item of interest from the suggestion list, and the input data is the item selected by the user.

[1020] The device displays a virtual try-on screen for the selected item using augmented reality (ARKit or ARCore) or virtual reality technology. The user can check the appearance and fit of the item on the virtual try-on screen. The output data is visual information from the virtual try-on.

[1021] Step 7: Gather feedback

[1022] Users input their feedback on the items they virtually try on into the platform. The input data is the user's evaluation information (e.g., "looks good," "not so good," etc.).

[1023] The server collects user feedback and uses it to improve the user profile and the generated AI model. The output data is an updated user profile and AI model. Specifically, the feedback data is used as new training data for the machine learning model, improving the model's recommendation accuracy.

[1024] (Application example 1)

[1025] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1026] Conventional fashion item recommendation systems struggle to provide personalized recommendations based on a user's body type and fashion style. Furthermore, they lack a way for users to check the fit and appearance of items before trying them on. Furthermore, they lack a mechanism for efficiently integrating user feedback to improve the accuracy of recommendations. This creates a challenge: users spend a lot of time and effort in the process of finding the perfect fashion item.

[1027] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1028] In this invention, the server includes: means for receiving a user's image data and analyzing the image data to recognize the user's body type and fashion style; means for acquiring user survey data and integrating the survey data to generate a user profile; means for suggesting fashion items based on the user profile; means for collecting the latest trend data and generating new fashion designs based on the trend data; means for providing a virtual try-on of the suggested fashion items using VR or AR technology; means for analyzing the profile data and the proposed fashion items using an AI model stored in the server to suggest fashion coordinations; and means for obtaining feedback from the user regarding the virtually tried-on fashion items and improving the accuracy of the user profile and AI model based on the feedback. This allows users to efficiently find fashion items that suit their body type and preferences and check the fit and appearance of the items before purchasing. Furthermore, the accuracy of the suggestions can be continuously improved through feedback, providing a more satisfying shopping experience.

[1029] "User profile" refers to individual information generated based on a user's body type, fashion style, and survey data.

[1030] "Image recognition algorithm" refers to a method of analyzing a user's body shape and fashion style using a machine learning model.

[1031] "Fashion items" refers to fashion-related products such as clothing and accessories.

[1032] "VR technology" refers to virtual reality technology, which allows users to have a realistic fitting experience in a virtual space.

[1033] "AR technology" stands for augmented reality technology, and refers to the technology of overlaying virtual objects on the real world.

[1034] "Generative AI models" refer to artificial intelligence models used to generate new fashion items and designs based on past data.

[1035] "Trend data" refers to data on the latest fashion trends collected from fashion shows, social media, news sites, etc.

[1036] "Feedback" refers to evaluations and opinions obtained from users, and is information that is used to improve the system.

[1037] "Server" refers to the central processing unit that receives data from users and provides analysis and recommendations.

[1038] Specific system operations and processes will be described below for the embodiment of the present invention.

[1039] First, users upload a full-body photo of themselves to the platform's upload screen from their smartphone, PC, or other device. Then, they answer a questionnaire provided on the platform, entering information about their preferred colors, fashion style, budget, and lifestyle. The device collects this data and sends it to the server.

[1040] The server receives the uploaded image data and analyzes it using an image recognition algorithm. This algorithm is based on a machine learning model (e.g., using TensorFlow or Keras) and recognizes the user's body type, facial features, and usual fashion style. The server then combines the results of the image analysis with the survey data to generate a detailed user profile.

[1041] The generated user profile is input into a generative AI model on the server. This model uses recurrent neural networks and generative models (e.g., PyTorch) that have the ability to suggest appropriate fashion items based on past data. Based on the user profile, the server generates a list of fashion items that match the user's body type, preferences, and lifestyle.

[1042] The server also periodically collects the latest fashion trend information from fashion shows, social media, news sites, etc., and inputs it into the generative AI model for trend analysis. Based on the results of this analysis, new fashion designs are generated and added to the user's suggestion list.

[1043] The device then displays a list of suggested fashion items sent from the server to the user. The user selects an item of interest, and the device can then display a virtual try-on screen using VR or AR technology. This technology allows the user to check the look and fit of the item on the virtual try-on screen. Specifically, smart glasses or a head-mounted display are used.

[1044] Finally, users provide feedback on the items they try on to the platform, which is received by the server and used to refine the user's profile and AI model, allowing the system to continually improve its performance.

[1045] An example of a specific prompt is, "The user is 170 cm tall, weighs 65 kg, prefers casual fashion, and uses a lot of accessories. Please suggest an appropriate fashion coordination." This allows the AI ​​model to suggest the best coordination for the user, and allows for virtual try-on based on that information.

[1046] This system allows users to efficiently find fashion items that suit their body type and preferences, and check the fit and appearance before purchasing. Feedback can also be used to continuously improve the accuracy of suggestions, providing a more satisfying shopping experience.

[1047] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1048] Step 1:

[1049] Users upload a full-body photo of themselves from their smartphone or PC to the platform's upload screen.

[1050] The terminal collects the user's image data and transmits the data to a server.

[1051] Step 2:

[1052] Users fill out a survey on the platform, inputting information about their preferred colors, fashion style, budget and lifestyle.

[1053] The terminal collects the questionnaire data and transmits the data to the server.

[1054] Step 3:

[1055] The server receives the uploaded image data and analyzes it using an image recognition algorithm.

[1056] Through this analysis, the server can determine the user's body type (e.g., slim, athletic, chubby, etc.), facial features, and usual fashion style (e.g., casual, formal, etc.).

[1057] Input: Image data, Output: User's body shape and fashion style information

[1058] Step 4:

[1059] The server combines the survey data with the results of image analysis to generate a detailed user profile.

[1060] Input: Image analysis results, questionnaire data, Output: User profile

[1061] Step 5:

[1062] The server inputs the generated user profile into a generative AI model and suggests appropriate fashion items based on past data.

[1063] Generative AI models use recurrent neural networks and generative models.

[1064] Input: User profile, Output: List of fashion items

[1065] Step 6:

[1066] The server regularly collects the latest fashion trend information from fashion shows, social media, news sites, etc. and inputs it into the generative AI model.

[1067] The server performs trend analysis and generates new fashion designs.

[1068] Input: Trend data, Output: New fashion design

[1069] Step 7:

[1070] The server adds the generated new fashion design to a list of suggestions for the user.

[1071] Input: New fashion design, Output: Updated list of fashion items

[1072] Step 8:

[1073] The terminal displays the suggested list of fashion items sent from the server to the user.

[1074] The user selects the items of interest.

[1075] Input: List of fashion items, Output: User selection

[1076] Step 9:

[1077] The terminal uses VR or AR technology to display a virtual try-on screen for the item selected by the user.

[1078] Users can check the look and fit of items on a virtual try-on screen.

[1079] Input: User selection, Output: Virtual fitting screen

[1080] Step 10:

[1081] Users enter feedback on the items they try on into the platform.

[1082] The terminal sends the feedback to the server.

[1083] Input: User feedback, Output: Feedback data

[1084] Step 11:

[1085] The server receives feedback from users and uses it to improve the user profile and the generated AI model.

[1086] This allows the system to continuously improve its performance.

[1087] Input: Feedback data, Output: Improved user profiles and generative AI models

[1088] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1089] As an embodiment of the present invention, a system incorporating an emotion engine will be described in detail.

[1090] Collection and processing of user data

[1091] 1. Collecting user image data and survey data

[1092] Users upload a full-body photo of themselves to the platform's upload screen from their smartphone, PC, or other device. The uploaded image data is then sent from the device to the server.

[1093] Users answer a survey provided on the platform, entering information about their preferred colors, fashion style, budget, and lifestyle. The survey data is then sent from the device to the server.

[1094] Image analysis and user profile generation

[1095] 2. Image Recognition and Attribute Analysis

[1096] The server receives the uploaded image data and analyzes it using image recognition algorithms to identify the user's body type (e.g., slim, athletic, chubby, etc.), facial features, and usual fashion style (e.g., casual, formal, etc.).

[1097] 3. Emotion Recognition and Attribute Analysis

[1098] The server uses an emotion recognition algorithm to analyze the user's emotional state (e.g., joy, sadness, surprise, etc.) from the user's image data.

[1099] 4. Integration with survey data

[1100] The server combines the results of the image analysis, the emotion analysis, and the survey data to generate a detailed user profile for each individual user, including data such as body type, style preferences, emotional state, and living environment.

[1101] Fashion item suggestions

[1102] 5. AI-generated recommendations

[1103] The server inputs the generated user profile into an AI model, which includes recurrent neural networks and generative models, and generates a list of appropriate fashion items based on past data and the user's emotional data.

[1104] Trend analysis and design generation

[1105] 6. Trend data collection and analysis

[1106] The server periodically collects the latest fashion trend information from fashion shows, social media, news sites, etc. This trend data is stored in a database.

[1107] 7. Generating new designs

[1108] The server inputs the collected trend data into the AI ​​model for trend analysis, which then generates unique fashion designs based on the trend data, integrates them with the user profile, and adds them to the suggestion list.

[1109] Virtual try-on experience

[1110] 8. Displaying the proposed list and offering to try on the items

[1111] The terminal displays a list of suggested fashion items sent from the server to the user, who then selects an item of interest from the suggested list.

[1112] The device uses VR or AR technology to display a virtual try-on screen for the selected item, allowing the user to check the look and fit of the item.

[1113] Gathering feedback and improving

[1114] 9. Gather feedback and improve the model

[1115] Users input their feedback about the items they try on (e.g., "looks good," "not great," etc.) into the platform. The feedback data is sent from the device to the server.

[1116] The server receives user feedback and uses this data, along with emotional data, to improve the user profile and the AI ​​model, which can then provide more accurate suggestions the next time the user uses the app.

[1117] These processes allow users to efficiently find the perfect fashion item for them, and with the help of virtual try-on and emotion-recognition feedback, they can check before they buy.

[1118] The processing flow will be explained below.

[1119] Step 1:

[1120] Users upload a full-body photo of themselves to the platform's upload screen from their smartphone, PC, or other device. The uploaded image data is then sent from the device to the server.

[1121] Step 2:

[1122] Users answer a survey provided on the platform, entering information about their preferred colors, fashion style, budget, and lifestyle. The survey data is then sent from the device to the server.

[1123] Step 3:

[1124] The server receives the uploaded image data and analyzes it using image recognition algorithms to identify the user's body type (e.g., slim, athletic, chubby, etc.), facial features, and usual fashion style (e.g., casual, formal, etc.).

[1125] Step 4:

[1126] The server uses an emotion recognition algorithm to analyze the user's emotional state (e.g., joy, sadness, surprise, etc.) from the user's image data. The analysis results are stored as emotion data.

[1127] Step 5:

[1128] The server combines the results of the image analysis, the emotion analysis, and the survey data to generate a detailed user profile for each individual user, including data such as body type, style preferences, emotional state, and living environment.

[1129] Step 6:

[1130] The server inputs the generated user profile into an AI model, which uses recurrent neural networks and generative models to generate a list of appropriate fashion items based on past data and the user's emotional data.

[1131] Step 7:

[1132] The server periodically collects the latest fashion trend information from fashion shows, social media, news sites, etc. This trend data is stored in a database within the server.

[1133] Step 8:

[1134] The server inputs the collected trend data into the AI ​​model for trend analysis, which then generates unique fashion designs based on the trend data, integrates them with the user profile, and adds them to the suggestion list.

[1135] Step 9:

[1136] The server transmits a list of fashion items generated based on the user profile to the user's terminal.

[1137] Step 10:

[1138] The terminal displays a list of suggested fashion items sent from the server to the user, who then selects an item of interest from the suggested list.

[1139] Step 11:

[1140] The device uses VR or AR technology to display a virtual try-on screen for the selected item, allowing the user to check the look and fit of the item.

[1141] Step 12:

[1142] Users can input their feedback (e.g., "looks good" or "not so good") into the platform after trying on the item. When providing feedback, they can also reflect their own feelings and provide detailed impressions.

[1143] Step 13:

[1144] The server receives user feedback and sentiment data and uses this data to improve the user profile and the AI ​​model, which can then provide more accurate suggestions the next time the user uses the app.

[1145] Example 2

[1146] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1147] Conventional fashion suggestion systems primarily base their suggestions on analysis of the user's body type and style and trend data, but do not fully consider the user's emotions or feedback. As a result, they are unable to recommend the most suitable fashion items for the user, limiting their ability to improve user satisfaction. Furthermore, few systems utilize virtual try-on technology, making it difficult to try on and check items before purchasing. There is a need for a system that can solve these issues, provide more accurate fashion suggestions that take the user's emotional state into account, and enable users to check items before purchasing through virtual try-on.

[1148] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving user image data and analyzing the image data to recognize the user's body type and fashion style, means for acquiring user questionnaire data and integrating the questionnaire data to generate a user profile, means for suggesting fashion items based on the user profile, means for collecting the latest trend data and generating new fashion designs based on the trend data, means for providing a virtual try-on of the suggested fashion items using VR or AR technology, means for analyzing emotions from the user image data, and means for using a generative AI model to list appropriate fashion items based on the user profile. This makes it possible to suggest optimal fashion items to the user through fashion suggestions and virtual try-ons that take the user's emotional state into consideration.

[1149] "User" refers to a person who uses the system to suggest fashion items and virtually try them on.

[1150] "Image data" refers to photographs or videos of the user's entire body or parts that are used to recognize the user's body type, facial features, and fashion style.

[1151] "Server" refers to a computer system that receives data sent from users and performs various processes for analyzing and proposing fashion items.

[1152] "Survey data" refers to data entered by users regarding their preferred colors, fashion style, budget, and lifestyle.

[1153] A "user profile" refers to detailed information about a user that integrates the user's image data, survey data, sentiment analysis results, etc.

[1154] "Fashion items" refer to items such as clothing, accessories, and shoes that are suggested to users.

[1155] "Trend data" refers to information about the latest fashion collected from fashion shows, social media, news sites, etc.

[1156] "VR" refers to virtual reality technology, which provides users with a visual experience that makes them feel as if they are in a three-dimensional space.

[1157] "AR" refers to augmented reality technology, which displays digital information overlaid on real-world scenery.

[1158] "Emotion recognition algorithm" refers to a program for analyzing a user's emotional state from image data.

[1159] "Generative AI model" refers to the machine learning model used to list appropriate fashion items based on a user profile.

[1160] A "prompt sentence" is an input sentence given to a generative AI model, and refers to an instruction sentence to generate a response based on specific conditions or purposes.

[1161] "Feedback" refers to the impressions and evaluations that users input regarding the suggested fashion items.

[1162] MODE FOR CARRYING OUT THE INVENTION

[1163] As an embodiment of the present invention, a system incorporating an emotion recognition algorithm and a generative AI model will be described in detail.

[1164] System configuration

[1165] The system includes the following components:

[1166] User: A person who proposes fashion items and virtually tries them on.

[1167] Terminal: A device used by a user, such as a smartphone or PC, that connects to the platform to input and display data.

[1168] Server: Refers to a computer system that receives data sent from users and performs various processes for analyzing and proposing fashion items.

[1169] Hardware and software used

[1170] Hardware: smartphones, PCs, servers.

[1171] Software: image recognition algorithms (e.g. OpenCV), emotion recognition algorithms, recurrent neural networks (RNN), generative models (GAN), database management systems (e.g. MongoDB), virtual reality (VR) or augmented reality (AR) technologies.

[1172] Specific processing

[1173] User Data Collection

[1174] 1. Users log in to the platform using their smartphone or PC and upload a full-body photo of themselves.

[1175] 2. Users answer a survey provided on the platform and enter information about their preferred colors, fashion style, budget, and lifestyle.

[1176] 3. The terminal sends the uploaded image data and questionnaire data to the server.

[1177] Data analysis and profile generation

[1178] 4. The server receives the image data and uses image recognition algorithms to analyze the user's body type, facial features, and usual fashion style.

[1179] 5. The server analyzes the user's emotional state from the image data using emotion recognition algorithms.

[1180] 6. The server integrates the image analysis results, emotion analysis results, and survey data to generate a detailed user profile.

[1181] Item suggestions and trend analysis

[1182] 7. The server inputs the generated user profile into an AI model, which can be a recurrent neural network (RNN) or a generative neural network (GAN).

[1183] 8. The server runs the AI ​​model and generates a list of appropriate fashion items based on historical data and the user's emotional data.

[1184] Collecting trend data and generating new designs

[1185] 9. The server collects the latest trend data from fashion shows, social media, and news sites and stores it in a database.

[1186] 10. The server inputs the trend data into the AI ​​model, performs trend analysis, and generates unique fashion designs.

[1187] 11. The server merges the generated design with the user profile and adds it to the suggestion list.

[1188] Virtual try-on and feedback

[1189] 12. The device displays the list of suggestions sent by the server to the user, who selects items that interest them.

[1190] 13. The device will then display the selected items on a virtual try-on screen using VR or AR technology, allowing the user to check how they look and fit.

[1191] 14. The user enters feedback on the item they tried on into the platform, and the feedback data is sent to the server.

[1192] Using Feedback

[1193] 15. The server analyzes the received feedback data and uses it, along with the emotional data, to improve the user profile and AI model, enabling more accurate suggestions the next time the user uses the service.

[1194] Examples of concrete examples and prompts

[1195] For example, if a user is looking for "work" fashion items, the following prompt might be used:

[1196] Generate a user profile by combining a full-body photo of the user with survey data. Based on the profile, generate a list of suggested "work" fashion items and offer virtual try-on in VR.

[1197] This allows users to efficiently find the perfect fashion item for them, and allows them to check before they buy using virtual try-on and emotion-recognition based feedback.

[1198] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1199] Step 1:

[1200] Users upload a full-body photo of themselves to the platform's upload screen using their smartphone or PC.

[1201] The terminal transmits the uploaded image data to the server.

[1202] Specifically, the user takes a full-body photo using a camera, selects the image file using the file selection button, and presses the send button. The input is the full-body photo, and the output is the image data sent to the server.

[1203] Step 2:

[1204] Users fill out a survey provided on the platform and enter information about their preferred colors, fashion style, budget, and lifestyle.

[1205] The terminal transmits the inputted questionnaire data to the server.

[1206] Specifically, the user fills in the questionnaire form and presses the send button. The input is the questionnaire data, and the output is the questionnaire data sent to the server.

[1207] Step 3:

[1208] The server uses image recognition algorithms to analyze the received image data.

[1209] Specifically, the server analyzes the user's body type, facial features, and usual fashion style.

[1210] Specifically, the server uses the OpenCV library to perform face detection and body type classification. The input is image data, and the output is the analysis results (body type, facial features, and fashion style).

[1211] Step 4:

[1212] The server applies an emotion recognition algorithm based on the received image data.

[1213] The server identifies the user's emotional state (e.g., happy, sad, surprised, etc.) from the image.

[1214] Specifically, emotion recognition uses a facial expression recognition algorithm, where the input is image data and the output is the analysis result of the emotional state.

[1215] Step 5:

[1216] The server integrates the image analysis results, emotion analysis results, and survey data to generate a user profile.

[1217] The server stores this data in a database and records it in JSON format.

[1218] Specifically, it creates a database entry and saves the user profile. The input is the image analysis results, emotion analysis results, and questionnaire data, and the output is the generated user profile.

[1219] Step 6:

[1220] The server inputs the generated user profile into the AI ​​model.

[1221] The server runs an AI model (such as a recurrent neural network or a generative model) to generate a list of suitable fashion items.

[1222] Specifically, it calls an AI model, provides prompts, and generates a list of items based on the parameters: the input is a user profile, and the output is a list of fashion items.

[1223] Step 7:

[1224] The server periodically collects trend data from fashion shows, social media, and news sites.

[1225] The server stores this information in a database.

[1226] Specifically, it uses scraping scripts and APIs to obtain the latest trend information and stores it in a database. The input is trend data from various external sources, and the output is the stored trend data.

[1227] Step 8:

[1228] The server inputs the collected trend data into an AI model, performs trend analysis, and generates new fashion designs.

[1229] The server merges the generated design with the user profile and adds it to a list of suggestions.

[1230] Specifically, it runs an AI model to generate designs based on trend data and integrate it with the user profile. The input is trend data and the user profile, and the output is an updated list of suggestions.

[1231] Step 9:

[1232] The terminal displays the proposal list sent from the server to the user.

[1233] The user selects items of interest from the suggestion list.

[1234] The terminal displays the selected items on a virtual try-on screen using VR or AR technology.

[1235] Specifically, the device uses an AR kit and a VR app to perform virtual try-on. The input is a list of suggestions, and the output is a display of the virtual try-on.

[1236] Step 10:

[1237] Users enter feedback on the items they try on into the platform.

[1238] The terminal transmits the feedback data to the server.

[1239] Specifically, the user fills in the feedback form and presses the submit button. The input is the feedback, and the output is the feedback data sent to the server.

[1240] Step 11:

[1241] The server analyzes the received feedback and uses it, along with the emotional data, to improve the user profile and AI model.

[1242] The server will be able to make more accurate suggestions the next time you use the service.

[1243] Specifically, the feedback data is analyzed and the AI ​​model is retrained. The input is the feedback data, and the output is an improved AI model.

[1244] (Application example 2)

[1245] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1246] Existing fashion recommendation systems make suggestions based on the user's body type and fashion style, but they are unable to consider the emotional state and feedback of each individual user, making it difficult to fully increase user satisfaction. Furthermore, they lack the ability to make suggestions using the latest trend data or virtual try-on functions, making it difficult to provide a real-time fitting experience or suggestions tailored to individual preferences.

[1247] The identification processing by the identification 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 receiving image data of a user and analyzing the image data to recognize the user's body type and fashion style, means for acquiring questionnaire data for the user and integrating the questionnaire data to generate a user profile, means for using an emotion recognition algorithm to analyze the user's emotional state, means for using a generative AI model to suggest fashion items based on the user profile, means for collecting the latest trend data and generating new fashion designs based on the trend data, means for providing a virtual try-on of the suggested fashion items using VR or AR technology, means for accepting uploads of the user's full-body photo and questionnaire data, and means for collecting user feedback. This enables advanced fashion suggestions based on the generation of individual user profiles and emotion recognition, and can increase user satisfaction through virtual try-ons and feedback collection.

[1248] "User image data" refers to still images or video data taken or uploaded by a user using a terminal.

[1249] "Body type" is a concept that refers to the dimensions, shape, proportions, etc. that characterize the appearance and structure of a user's body.

[1250] "Fashion style" refers to the user's preferred clothing and style trends, genres, and designs.

[1251] "Survey Data" refers to information provided by users in the form of questions about their preferred colors, fashion style, budget, lifestyle, etc.

[1252] A "user profile" is a data set that includes the attributes, preferences, and characteristics of an individual user, generated by integrating user image data, survey data, and sentiment analysis results.

[1253] An "emotion recognition algorithm" is a technology that analyzes a user's image or video data to identify their emotional state at that time (e.g., joy, sadness, surprise, etc.).

[1254] A "generative AI model" is an artificial intelligence model that suggests new fashion items based on accumulated data and learning results.

[1255] "Trend data" refers to information about currently popular styles and designs collected from the latest fashion shows, social media, news sites, etc.

[1256] "Virtual try-on" is a feature that allows users to try on clothes in a digital space using VR (virtual reality) or AR (augmented reality) technology.

[1257] "Feedback" refers to the ratings, comments, and opinions provided by users based on their try-on and usage experiences.

[1258] The system for implementing the present invention includes various processes related to users, servers, and terminals. A specific embodiment of the system will be described below.

[1259] Collection and processing of user image data and survey data

[1260] 1. Collecting user image data and survey data

[1261] Users take a full-body photo of themselves using a device such as a smartphone or PC and upload it to the system. They also answer a questionnaire provided on the platform they use, providing information about their preferred colors, fashion style, budget, and lifestyle. This data is then sent from the device to the server.

[1262] Image analysis and user profile generation

[1263] 2. Image analysis and emotion recognition

[1264] The server receives the image data sent by the user and uses an image recognition algorithm (e.g., OpenCV, TensorFlow) to analyze the user's body shape, facial features, and usual fashion style, while simultaneously using an emotion recognition algorithm (e.g., Microsoft Azure Face API) to analyze the user's emotional state (e.g., joy, sadness, surprise, etc.).

[1265] 3. Integration with survey data and generation of user profiles

[1266] The results of image analysis and emotion recognition are combined with survey data to generate a detailed user profile for each individual user, including data such as body type, style preferences, emotional state, and living environment.

[1267] Fashion item suggestions

[1268] 4. AI-generated recommendations

[1269] The server inputs the generated user profile into a generative AI model (for example, a model using PyTorch or TensorFlow). The generative AI model generates a list of appropriate fashion items based on past data and the user's emotional data. This process suggests fashion items that take into account the user's preferences and emotional state.

[1270] Virtual try-on experience and feedback collection

[1271] 5. Displaying a list of suggestions and offering virtual try-ons

[1272] The device displays a list of suggested fashion items sent from the server. Users select items of interest from the suggested list and virtually try them on using VR or AR technology (e.g., Unity, ARKit, ARCore). Users can check the look and fit of the items on the virtual try-on screen.

[1273] 6. Gather feedback and improve the model

[1274] Users enter feedback on the items they try on into the platform. The feedback data sent from the device to the server, along with emotional data, is used to improve the user profile and generative AI model. The improved generative AI model can then make even more accurate suggestions the next time the user uses the platform.

[1275] Specific examples

[1276] Users open the app, take a full-body photo, and answer a questionnaire about their preferred colors, fashion style, budget, and lifestyle. Based on the uploaded data, the AI ​​will suggest three fashion items that suit the user, and they can virtually try on the items using AR. After the virtual try-on, users can enter and submit feedback, which will be reflected in the next suggestions.

[1277] Prompt Sentence Examples

[1278] "Female, in her 20s, slim build, prefers casual style. Prefers clothes in muted colors that are easy to move in. Budget is around 10,000 yen. Emotional state after trying on clothes: surprise and delight. Please recommend some fashion items based on the following information."

[1279] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1280] Step 1:

[1281] Users take a full-body photo of themselves using a device such as a smartphone or PC and upload it to the system. The uploaded image data is then sent from the device to the server.

[1282] Input: A full-body photo of the user

[1283] Data processing: Images taken on the device are converted into the appropriate format (e.g., JPEG, PNG).

[1284] Output: Image data sent to the server

[1285] Step 2:

[1286] Users answer a survey on the platform, providing information such as their preferred colors, fashion style, budget, lifestyle, etc. The survey data is sent from the device to the server.

[1287] Input: User's survey response

[1288] Data processing: Convert survey responses into data formats such as JSON and XML

[1289] Output: Survey data sent to the server

[1290] Step 3:

[1291] The server analyzes the received image data and uses image recognition algorithms (OpenCV, TensorFlow) to recognize the user's body type, facial features, and usual fashion style. The analysis results are integrated into a user profile.

[1292] Input: Image data

[1293] Data processing: Analyzes body shape, facial features, and fashion style using image recognition algorithms

[1294] Output: Analysis results (body shape, facial features, fashion style) data

[1295] Step 4:

[1296] The server uses an emotion recognition algorithm (Microsoft Azure Face API) to analyze the user's emotional state from their image data, which is then integrated into the user profile.

[1297] Input: Image data

[1298] Data processing: Analyze emotional states using emotion recognition algorithms

[1299] Output: Emotional state data

[1300] Step 5:

[1301] The server combines the image analysis results, emotion analysis results, and survey data to generate a detailed user profile, which includes the user's body type, style preferences, emotional state, living environment, and more.

[1302] Input: Image analysis results, emotion analysis results, questionnaire data

[1303] Data processing: Integrating data to generate user profiles

[1304] Output: User profile

[1305] Step 6:

[1306] The server inputs the generated user profile into the generative AI model to generate a list of appropriate fashion items, which are then stored on the server.

[1307] Input: User Profile

[1308] Data processing: Using generative AI models to suggest fashion items

[1309] Output: A list of fashion items

[1310] Step 7:

[1311] The terminal displays a list of suggested fashion items sent from the server to the user, who can then select the items they are interested in and try them on virtually.

[1312] Input: A list of fashion item suggestions

[1313] Output: Suggestion list displayed in terminal

[1314] Step 8:

[1315] The device uses VR or AR technology (Unity, ARKit, ARCore) to display a virtual try-on screen for the selected item, allowing the user to check the look and fit of the item.

[1316] Input: The item selected by the user

[1317] Data processing: Realizing virtual try-on using VR / AR technology

[1318] Output: Virtual fitting screen

[1319] Step 9:

[1320] Users enter their feedback on the items they try on into the platform, and the feedback data is sent from the device to the server.

[1321] Input: User feedback

[1322] Data processing: Convert feedback data into the appropriate format

[1323] Output: Feedback data sent to the server

[1324] Step 10:

[1325] The server receives user feedback and uses it, along with emotional data, to improve the user profile and the generated AI model, which is then reflected in the next proposal.

[1326] Input: Feedback data, emotion data

[1327] Data processing: Retraining generative AI models and updating user profiles

[1328] Output: An improved AI model and an updated user profile

[1329] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1330] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1331] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1332] [Fourth embodiment]

[1333] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1334] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1335] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1336] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1337] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1338] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1339] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1340] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1341] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1342] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1343] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1344] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1345] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1346] As an embodiment of the present invention, the operation and processing of a specific system will be described below.

[1347] Collection and processing of user data

[1348] 1. Collecting user image data and survey data

[1349] Users upload a full-body photo of themselves to the platform's upload screen from a device such as a smartphone or PC.

[1350] Users fill out a survey provided on the platform and enter information about their preferred colors, fashion style, budget, and lifestyle.

[1351] The terminal collects this data and transmits it to the server.

[1352] Image analysis and user profile generation

[1353] 2. Image Recognition and Attribute Analysis

[1354] The server receives the uploaded image data and analyzes it using an image recognition algorithm.

[1355] The server recognizes the user's body type (e.g., slim, athletic, curvy, etc.), facial features, and usual fashion style (e.g., casual, formal, etc.).

[1356] 3. Integration with survey data

[1357] The server combines the results of the image analysis with the survey data to generate a detailed user profile for each individual user.

[1358] Fashion item suggestions

[1359] 4. AI-generated recommendations

[1360] The server inputs the generated user profile into an AI model, which includes recurrent neural networks and generative models, and is capable of suggesting appropriate fashion items based on past data.

[1361] Based on the user profile, the server generates a list of fashion items that match the user's body type, preferences, and lifestyle.

[1362] Trend analysis and design generation

[1363] 5. Trend data collection and analysis

[1364] The server regularly collects the latest fashion trend information from fashion shows, social media, news sites, etc.

[1365] The server inputs the collected data into an AI model and performs trend analysis.

[1366] 6. Generating new designs

[1367] The server uses AI design generation capabilities to generate unique fashion designs based on trend data and user profiles.

[1368] The server adds the generated new fashion design to a list of suggestions for the user.

[1369] Virtual try-on experience

[1370] 7. Displaying the proposed list and offering to try on the items

[1371] The terminal displays the suggested list of fashion items sent from the server to the user.

[1372] The user selects items of interest from the suggestion list.

[1373] The terminal displays a virtual try-on screen for the selected item using VR or AR technology.

[1374] Users can check the look and fit of items on a virtual try-on screen.

[1375] Gathering feedback and improving

[1376] 8. Gather feedback and improve the model

[1377] Users enter feedback about the items they try on (e.g., "looks good," "kind of weird," etc.) into the platform.

[1378] The server receives feedback from users and uses this data to improve user profiles and AI models.

[1379] These processes allow users to efficiently find the fashion items that best suit them and check them out before purchasing by virtually trying them on.

[1380] The processing flow will be explained below.

[1381] Step 1:

[1382] Users take a full-body photo of themselves and upload it to the platform's upload screen from their smartphone, PC, or other device. The uploaded image data is then sent from the device to the server.

[1383] Step 2:

[1384] Users answer a survey provided on the platform, entering information about their preferred colors, fashion style, budget, and lifestyle. The survey data is then sent from the device to the server.

[1385] Step 3:

[1386] The server receives the uploaded image data and analyzes it using image recognition algorithms to identify the user's body type (e.g., slim, athletic, chubby, etc.), facial features, and usual fashion style (e.g., casual, formal, etc.).

[1387] Step 4:

[1388] The server combines the results of the image analysis with the survey data to generate a detailed user profile for each individual user, including data such as body type, style preferences, and living environment.

[1389] Step 5:

[1390] The server inputs the generated user profile into an AI model, which uses recurrent neural networks and generative models to generate a list of fashion items that best suit the user.

[1391] Step 6:

[1392] The server periodically collects trend data from the latest fashion shows, social media, news sites, etc. This trend data is stored in a database within the server.

[1393] Step 7:

[1394] The server inputs the collected trend data into the AI ​​model for trend analysis, which then generates unique fashion designs based on the trend data, integrates them with the user profile, and adds them to the suggestion list.

[1395] Step 8:

[1396] The server transmits a list of fashion items generated based on the user profile to the user's terminal.

[1397] Step 9:

[1398] The terminal displays a list of suggested fashion items sent from the server to the user, who then selects an item of interest from the suggested list.

[1399] Step 10:

[1400] The device uses VR or AR technology to display a virtual try-on screen for the selected item, allowing the user to check the look and fit of the item.

[1401] Step 11:

[1402] Users input feedback (e.g., "looks good" or "not so good") about the items they try on into the platform. The feedback data is sent from the device to the server.

[1403] Step 12:

[1404] The server receives user feedback and uses this data to improve the user profile and the AI ​​model, which can then provide more accurate suggestions the next time the user uses the service.

[1405] Example 1

[1406] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1407] Conventional fashion item suggestion systems have been inadequate in suggesting items based on the user's body type and style, making it difficult to suggest items that are optimal for each individual user. Furthermore, there are limited ways for users to check how the suggested items will actually look on them. Furthermore, there is a lack of a mechanism for utilizing user feedback to improve the accuracy of suggestions.

[1408] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1409] In this invention, the server includes means for receiving user image data and analyzing the image data to recognize the user's body type and style, means for acquiring user questionnaire data and integrating the questionnaire data to generate a user profile, means for suggesting items based on the user profile, means for collecting the latest data and generating new designs based on the data, and means for providing a virtual try-on of the suggested items using augmented reality and virtual reality technologies, thereby suggesting fashion items that are optimal for each individual user and enabling the user to check the appearance and fit of the items through the virtual try-on before purchasing.

[1410] "Image data" is digital data containing visual information captured by an electronic device.

[1411] "Recognition" is the process of analyzing image data and survey data to identify specific characteristics and attributes of a user.

[1412] "Survey data" refers to data that includes information such as preferences, lifestyle, and budget entered by the user.

[1413] A "user profile" is detailed information about an individual user that integrates the results of analyzing image data and questionnaire data.

[1414] "Items" are fashion-related items such as clothing and accessories.

[1415] "Design" refers to the appearance or shape of an item based on a particular concept or style.

[1416] "Augmented reality technology" is a technology that displays virtual information overlaid on the real environment.

[1417] "Virtual reality technology" is a technology that allows users to experience immersion in a virtual environment.

[1418] "Feedback" refers to opinions and evaluations provided by users regarding proposed items or systems.

[1419] A "generative AI model" is an artificial intelligence model that generates new designs and proposals based on input data.

[1420] As an embodiment of the present invention, a series of processes from collecting user data to proposing fashion items, analyzing trends and creating designs, providing a virtual try-on experience, and collecting and improving feedback will be specifically described.

[1421] First, we will explain the collection of user data.

[1422] Users upload a full-body photo of themselves from their smartphone or PC to the platform's upload screen. It is recommended that the image be in JPEG or PNG format. Users then answer a survey provided on the platform, entering information such as their favorite colors, fashion style, budget, and lifestyle. This data is collected by the device and securely transmitted to the server via the HTTPS protocol.

[1423] Next, image analysis and user profile generation will be described.

[1424] The server runs an image recognition algorithm using TensorFlow to analyze the received image data. Specifically, it uses deep learning models such as DeepLab to recognize the user's body type, facial features, and usual fashion style. To integrate the analysis results with the survey data, the server accesses a database system such as MySQL or PostgreSQL to create a detailed user profile.

[1425] Next, the proposal of fashion items will be described.

[1426] The server inputs the generated user profile into a generative AI model such as a recurrent neural network (RNN) or generative adversarial network (GAN). This model is built using frameworks such as TensorFlow and PyTorch. The AI ​​model generates a list of suitable fashion items based on the user's body type, preferences, and lifestyle.

[1427] Trend analysis and design generation are as follows:

[1428] The server automatically collects the latest fashion trend information from fashion shows, social media, news sites, and other sources. This information is collected using web scraping technologies such as BeautifulSoup and Scrapy. The server then analyzes the collected data using natural language processing (NLP) techniques to identify fashion trends. Based on the trend data and user profiles, the server then generates new designs using AI design generation functions such as StyleGAN, and adds them to a list of suggestions.

[1429] Here's the virtual try-on experience:

[1430] The device displays the list of suggestions sent from the server to the user. The user selects items of interest from this list. For the selected items, the device displays a virtual try-on screen using augmented reality (ARKit or ARCore) or virtual reality technology, allowing the user to see how the items look and fit before purchasing.

[1431] Finally, we discuss collecting feedback and improving the model.

[1432] Users rate items on a virtual try-on screen. Feedback is in the form of simple ratings such as "looks good" or "not so good." The server collects this feedback and uses it to improve the user profile and the generative AI model. The feedback data is used as new training data to help improve the model's recommendation accuracy.

[1433] As described above, this system is designed to help users efficiently find the items that suit them best by suggesting the most suitable fashion items based on the user's image data and questionnaire data and providing a virtual try-on experience.

[1434] Prompt Sentence Examples

[1435] "You submit a full-body photo of yourself. Then, you answer a questionnaire about your preferred colors, fashion style, budget, and lifestyle. The system will use this information to suggest fashion items that are perfect for you."

[1436] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1437] Step 1: Collect user data

[1438] Users upload a full-body photo of themselves from their smartphone or PC to the platform's upload screen. The input data is image data in JPEG or PNG format.

[1439] Users answer a survey on the platform and enter information such as their favorite colors, fashion style, budget, and lifestyle. The survey data becomes the input data.

[1440] The terminal transmits the image data and questionnaire data collected from the user to the server using the secure HTTPS protocol. The output data is the image data and questionnaire data of the user transmitted to the server.

[1441] Step 2: Integrating image analysis and survey data

[1442] The server analyzes the received image data using TensorFlow. Specifically, it uses deep learning models such as DeepLab to recognize the user's body shape and facial features. The input data is the user's image data, and the output data is the analysis results regarding body shape and facial features.

[1443] The server accesses a database such as MySQL or PostgreSQL to integrate the analysis results with the user's survey data. The survey data and image analysis results are the input data, and the integrated user profile is the output data.

[1444] Step 3: Proposing fashion items

[1445] The server inputs the generated user profile into a generative AI model such as a Recurrent Neural Network (RNN) or Generative Adversarial Networks (GAN). The input data is the user profile, and the output data is a list of suggested items.

[1446] The server uses an AI model to suggest fashion items based on the user's body type, preferences, and lifestyle. Specifically, the AI ​​model generates an item list based on learned parameters.

[1447] Step 4: Collect and analyze trend data

[1448] The server collects the latest fashion trend information from external sources such as fashion shows, social media, and news sites. The input data is trend information from external sources. Specific operations involve using web scraping tools such as BeautifulSoup and Scrapy.

[1449] The server analyzes the collected trend data using natural language processing (NLP) technology. The input data is the collected trend information, and the output data is the trend keywords and themes extracted through the analysis.

[1450] Step 5: Generate a new design

[1451] The server generates new fashion designs using AI design generation functions such as StyleGAN based on trend data and user profiles. The input data is the trend data and user profiles, and the output data is the generated fashion designs.

[1452] The server adds the generated new design to the list of suggestions for the user. Specifically, the AI ​​model integrates trend information and user profiles to generate new designs.

[1453] Step 6: Offer a virtual try-on

[1454] The terminal displays the suggested list of fashion items sent from the server to the user. The input data is the suggested list from the server, and the output data is the suggested list displayed on the user's terminal.

[1455] The user selects an item of interest from the suggestion list, and the input data is the item selected by the user.

[1456] The device displays a virtual try-on screen for the selected item using augmented reality (ARKit or ARCore) or virtual reality technology. The user can check the appearance and fit of the item on the virtual try-on screen. The output data is visual information from the virtual try-on.

[1457] Step 7: Gather feedback

[1458] Users input their feedback on the items they virtually try on into the platform. The input data is the user's evaluation information (e.g., "looks good," "not so good," etc.).

[1459] The server collects user feedback and uses it to improve the user profile and the generated AI model. The output data is an updated user profile and AI model. Specifically, the feedback data is used as new training data for the machine learning model, improving the model's recommendation accuracy.

[1460] (Application example 1)

[1461] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1462] Conventional fashion item recommendation systems struggle to provide personalized recommendations based on a user's body type and fashion style. Furthermore, they lack a way for users to check the fit and appearance of items before trying them on. Furthermore, they lack a mechanism for efficiently integrating user feedback to improve the accuracy of recommendations. This creates a challenge: users spend a lot of time and effort in the process of finding the perfect fashion item.

[1463] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1464] In this invention, the server includes: means for receiving a user's image data and analyzing the image data to recognize the user's body type and fashion style; means for acquiring user survey data and integrating the survey data to generate a user profile; means for suggesting fashion items based on the user profile; means for collecting the latest trend data and generating new fashion designs based on the trend data; means for providing a virtual try-on of the suggested fashion items using VR or AR technology; means for analyzing the profile data and the proposed fashion items using an AI model stored in the server to suggest fashion coordinations; and means for obtaining feedback from the user regarding the virtually tried-on fashion items and improving the accuracy of the user profile and AI model based on the feedback. This allows users to efficiently find fashion items that suit their body type and preferences and check the fit and appearance of the items before purchasing. Furthermore, the accuracy of the suggestions can be continuously improved through feedback, providing a more satisfying shopping experience.

[1465] "User profile" refers to individual information generated based on a user's body type, fashion style, and survey data.

[1466] "Image recognition algorithm" refers to a method of analyzing a user's body shape and fashion style using a machine learning model.

[1467] "Fashion items" refers to fashion-related products such as clothing and accessories.

[1468] "VR technology" refers to virtual reality technology, which allows users to have a realistic fitting experience in a virtual space.

[1469] "AR technology" stands for augmented reality technology, and refers to the technology of overlaying virtual objects on the real world.

[1470] "Generative AI models" refer to artificial intelligence models used to generate new fashion items and designs based on past data.

[1471] "Trend data" refers to data on the latest fashion trends collected from fashion shows, social media, news sites, etc.

[1472] "Feedback" refers to evaluations and opinions obtained from users, and is information that is used to improve the system.

[1473] "Server" refers to the central processing unit that receives data from users and provides analysis and recommendations.

[1474] Specific system operations and processes will be described below for the embodiment of the present invention.

[1475] First, users upload a full-body photo of themselves to the platform's upload screen from their smartphone, PC, or other device. Then, they answer a questionnaire provided on the platform, entering information about their preferred colors, fashion style, budget, and lifestyle. The device collects this data and sends it to the server.

[1476] The server receives the uploaded image data and analyzes it using an image recognition algorithm. This algorithm is based on a machine learning model (e.g., using TensorFlow or Keras) and recognizes the user's body type, facial features, and usual fashion style. The server then combines the results of the image analysis with the survey data to generate a detailed user profile.

[1477] The generated user profile is input into a generative AI model on the server. This model uses recurrent neural networks and generative models (e.g., PyTorch) that have the ability to suggest appropriate fashion items based on past data. Based on the user profile, the server generates a list of fashion items that match the user's body type, preferences, and lifestyle.

[1478] The server also periodically collects the latest fashion trend information from fashion shows, social media, news sites, etc., and inputs it into the generative AI model for trend analysis. Based on the results of this analysis, new fashion designs are generated and added to the user's suggestion list.

[1479] The device then displays a list of suggested fashion items sent from the server to the user. The user selects an item of interest, and the device can then display a virtual try-on screen using VR or AR technology. This technology allows the user to check the look and fit of the item on the virtual try-on screen. Specifically, smart glasses or a head-mounted display are used.

[1480] Finally, users provide feedback on the items they try on to the platform, which is received by the server and used to refine the user's profile and AI model, allowing the system to continually improve its performance.

[1481] An example of a specific prompt is, "The user is 170 cm tall, weighs 65 kg, prefers casual fashion, and uses a lot of accessories. Please suggest an appropriate fashion coordination." This allows the AI ​​model to suggest the best coordination for the user, and allows for virtual try-on based on that information.

[1482] This system allows users to efficiently find fashion items that suit their body type and preferences, and check the fit and appearance before purchasing. Feedback can also be used to continuously improve the accuracy of suggestions, providing a more satisfying shopping experience.

[1483] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1484] Step 1:

[1485] Users upload a full-body photo of themselves from their smartphone or PC to the platform's upload screen.

[1486] The terminal collects the user's image data and transmits the data to a server.

[1487] Step 2:

[1488] Users fill out a survey on the platform, inputting information about their preferred colors, fashion style, budget and lifestyle.

[1489] The terminal collects the questionnaire data and transmits the data to the server.

[1490] Step 3:

[1491] The server receives the uploaded image data and analyzes it using an image recognition algorithm.

[1492] Through this analysis, the server can determine the user's body type (e.g., slim, athletic, chubby, etc.), facial features, and usual fashion style (e.g., casual, formal, etc.).

[1493] Input: Image data, Output: User's body shape and fashion style information

[1494] Step 4:

[1495] The server combines the survey data with the results of image analysis to generate a detailed user profile.

[1496] Input: Image analysis results, questionnaire data, Output: User profile

[1497] Step 5:

[1498] The server inputs the generated user profile into a generative AI model and suggests appropriate fashion items based on past data.

[1499] Generative AI models use recurrent neural networks and generative models.

[1500] Input: User profile, Output: List of fashion items

[1501] Step 6:

[1502] The server regularly collects the latest fashion trend information from fashion shows, social media, news sites, etc. and inputs it into the generative AI model.

[1503] The server performs trend analysis and generates new fashion designs.

[1504] Input: Trend data, Output: New fashion design

[1505] Step 7:

[1506] The server adds the generated new fashion design to a list of suggestions for the user.

[1507] Input: New fashion design, Output: Updated list of fashion items

[1508] Step 8:

[1509] The terminal displays the suggested list of fashion items sent from the server to the user.

[1510] The user selects the items of interest.

[1511] Input: List of fashion items, Output: User selection

[1512] Step 9:

[1513] The terminal uses VR or AR technology to display a virtual try-on screen for the item selected by the user.

[1514] Users can check the look and fit of items on a virtual try-on screen.

[1515] Input: User selection, Output: Virtual fitting screen

[1516] Step 10:

[1517] Users enter feedback on the items they try on into the platform.

[1518] The terminal sends the feedback to the server.

[1519] Input: User feedback, Output: Feedback data

[1520] Step 11:

[1521] The server receives feedback from users and uses it to improve the user profile and the generated AI model.

[1522] This allows the system to continuously improve its performance.

[1523] Input: Feedback data, Output: Improved user profiles and generative AI models

[1524] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1525] As an embodiment of the present invention, a system incorporating an emotion engine will be described in detail.

[1526] Collection and processing of user data

[1527] 1. Collecting user image data and survey data

[1528] Users upload a full-body photo of themselves to the platform's upload screen from their smartphone, PC, or other device. The uploaded image data is then sent from the device to the server.

[1529] Users answer a survey provided on the platform, entering information about their preferred colors, fashion style, budget, and lifestyle. The survey data is then sent from the device to the server.

[1530] Image analysis and user profile generation

[1531] 2. Image Recognition and Attribute Analysis

[1532] The server receives the uploaded image data and analyzes it using image recognition algorithms to identify the user's body type (e.g., slim, athletic, chubby, etc.), facial features, and usual fashion style (e.g., casual, formal, etc.).

[1533] 3. Emotion Recognition and Attribute Analysis

[1534] The server uses an emotion recognition algorithm to analyze the user's emotional state (e.g., joy, sadness, surprise, etc.) from the user's image data.

[1535] 4. Integration with survey data

[1536] The server combines the results of the image analysis, the emotion analysis, and the survey data to generate a detailed user profile for each individual user, including data such as body type, style preferences, emotional state, and living environment.

[1537] Fashion item suggestions

[1538] 5. AI-generated recommendations

[1539] The server inputs the generated user profile into an AI model, which includes recurrent neural networks and generative models, and generates a list of appropriate fashion items based on past data and the user's emotional data.

[1540] Trend analysis and design generation

[1541] 6. Trend data collection and analysis

[1542] The server periodically collects the latest fashion trend information from fashion shows, social media, news sites, etc. This trend data is stored in a database.

[1543] 7. Generating new designs

[1544] The server inputs the collected trend data into the AI ​​model for trend analysis, which then generates unique fashion designs based on the trend data, integrates them with the user profile, and adds them to the suggestion list.

[1545] Virtual try-on experience

[1546] 8. Displaying the proposed list and offering to try on the items

[1547] The terminal displays a list of suggested fashion items sent from the server to the user, who then selects an item of interest from the suggested list.

[1548] The device uses VR or AR technology to display a virtual try-on screen for the selected item, allowing the user to check the look and fit of the item.

[1549] Gathering feedback and improving

[1550] 9. Gather feedback and improve the model

[1551] Users input their feedback about the items they try on (e.g., "looks good," "not great," etc.) into the platform. The feedback data is sent from the device to the server.

[1552] The server receives user feedback and uses this data, along with emotional data, to improve the user profile and the AI ​​model, which can then provide more accurate suggestions the next time the user uses the app.

[1553] These processes allow users to efficiently find the perfect fashion item for them, and with the help of virtual try-on and emotion-recognition feedback, they can check before they buy.

[1554] The processing flow will be explained below.

[1555] Step 1:

[1556] Users upload a full-body photo of themselves to the platform's upload screen from their smartphone, PC, or other device. The uploaded image data is then sent from the device to the server.

[1557] Step 2:

[1558] Users answer a survey provided on the platform, entering information about their preferred colors, fashion style, budget, and lifestyle. The survey data is then sent from the device to the server.

[1559] Step 3:

[1560] The server receives the uploaded image data and analyzes it using image recognition algorithms to identify the user's body type (e.g., slim, athletic, chubby, etc.), facial features, and usual fashion style (e.g., casual, formal, etc.).

[1561] Step 4:

[1562] The server uses an emotion recognition algorithm to analyze the user's emotional state (e.g., joy, sadness, surprise, etc.) from the user's image data. The analysis results are stored as emotion data.

[1563] Step 5:

[1564] The server combines the results of the image analysis, the emotion analysis, and the survey data to generate a detailed user profile for each individual user, including data such as body type, style preferences, emotional state, and living environment.

[1565] Step 6:

[1566] The server inputs the generated user profile into an AI model, which uses recurrent neural networks and generative models to generate a list of appropriate fashion items based on past data and the user's emotional data.

[1567] Step 7:

[1568] The server periodically collects the latest fashion trend information from fashion shows, social media, news sites, etc. This trend data is stored in a database within the server.

[1569] Step 8:

[1570] The server inputs the collected trend data into the AI ​​model for trend analysis, which then generates unique fashion designs based on the trend data, integrates them with the user profile, and adds them to the suggestion list.

[1571] Step 9:

[1572] The server transmits a list of fashion items generated based on the user profile to the user's terminal.

[1573] Step 10:

[1574] The terminal displays a list of suggested fashion items sent from the server to the user, who then selects an item of interest from the suggested list.

[1575] Step 11:

[1576] The device uses VR or AR technology to display a virtual try-on screen for the selected item, allowing the user to check the look and fit of the item.

[1577] Step 12:

[1578] Users can input their feedback (e.g., "looks good" or "not so good") into the platform after trying on the item. When providing feedback, they can also reflect their own feelings and provide detailed impressions.

[1579] Step 13:

[1580] The server receives user feedback and sentiment data and uses this data to improve the user profile and the AI ​​model, which can then provide more accurate suggestions the next time the user uses the app.

[1581] Example 2

[1582] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1583] Conventional fashion suggestion systems primarily base their suggestions on analysis of the user's body type and style and trend data, but do not fully consider the user's emotions or feedback. As a result, they are unable to recommend the most suitable fashion items for the user, limiting their ability to improve user satisfaction. Furthermore, few systems utilize virtual try-on technology, making it difficult to try on and check items before purchasing. There is a need for a system that can solve these issues, provide more accurate fashion suggestions that take the user's emotional state into account, and enable users to check items before purchasing through virtual try-on.

[1584] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving user image data and analyzing the image data to recognize the user's body type and fashion style, means for acquiring user questionnaire data and integrating the questionnaire data to generate a user profile, means for suggesting fashion items based on the user profile, means for collecting the latest trend data and generating new fashion designs based on the trend data, means for providing a virtual try-on of the suggested fashion items using VR or AR technology, means for analyzing emotions from the user image data, and means for using a generative AI model to list appropriate fashion items based on the user profile. This makes it possible to suggest optimal fashion items to the user through fashion suggestions and virtual try-ons that take the user's emotional state into consideration.

[1585] "User" refers to a person who uses the system to suggest fashion items and virtually try them on.

[1586] "Image data" refers to photographs or videos of the user's entire body or parts that are used to recognize the user's body type, facial features, and fashion style.

[1587] "Server" refers to a computer system that receives data sent from users and performs various processes for analyzing and proposing fashion items.

[1588] "Survey data" refers to data entered by users regarding their preferred colors, fashion style, budget, and lifestyle.

[1589] A "user profile" refers to detailed information about a user that integrates the user's image data, survey data, sentiment analysis results, etc.

[1590] "Fashion items" refer to items such as clothing, accessories, and shoes that are suggested to users.

[1591] "Trend data" refers to information about the latest fashion collected from fashion shows, social media, news sites, etc.

[1592] "VR" refers to virtual reality technology, which provides users with a visual experience that makes them feel as if they are in a three-dimensional space.

[1593] "AR" refers to augmented reality technology, which displays digital information overlaid on real-world scenery.

[1594] "Emotion recognition algorithm" refers to a program for analyzing a user's emotional state from image data.

[1595] "Generative AI model" refers to the machine learning model used to list appropriate fashion items based on a user profile.

[1596] A "prompt sentence" is an input sentence given to a generative AI model, and refers to an instruction sentence to generate a response based on specific conditions or purposes.

[1597] "Feedback" refers to the impressions and evaluations that users input regarding the suggested fashion items.

[1598] MODE FOR CARRYING OUT THE INVENTION

[1599] As an embodiment of the present invention, a system incorporating an emotion recognition algorithm and a generative AI model will be described in detail.

[1600] System configuration

[1601] The system includes the following components:

[1602] User: A person who proposes fashion items and virtually tries them on.

[1603] Terminal: A device used by a user, such as a smartphone or PC, that connects to the platform to input and display data.

[1604] Server: Refers to a computer system that receives data sent from users and performs various processes for analyzing and proposing fashion items.

[1605] Hardware and software used

[1606] Hardware: smartphones, PCs, servers.

[1607] Software: image recognition algorithms (e.g. OpenCV), emotion recognition algorithms, recurrent neural networks (RNN), generative models (GAN), database management systems (e.g. MongoDB), virtual reality (VR) or augmented reality (AR) technologies.

[1608] Specific processing

[1609] User Data Collection

[1610] 1. Users log in to the platform using their smartphone or PC and upload a full-body photo of themselves.

[1611] 2. Users answer a survey provided on the platform and enter information about their preferred colors, fashion style, budget, and lifestyle.

[1612] 3. The terminal sends the uploaded image data and questionnaire data to the server.

[1613] Data analysis and profile generation

[1614] 4. The server receives the image data and uses image recognition algorithms to analyze the user's body type, facial features, and usual fashion style.

[1615] 5. The server analyzes the user's emotional state from the image data using emotion recognition algorithms.

[1616] 6. The server integrates the image analysis results, emotion analysis results, and survey data to generate a detailed user profile.

[1617] Item suggestions and trend analysis

[1618] 7. The server inputs the generated user profile into an AI model, which can be a recurrent neural network (RNN) or a generative neural network (GAN).

[1619] 8. The server runs the AI ​​model and generates a list of appropriate fashion items based on historical data and the user's emotional data.

[1620] Collecting trend data and generating new designs

[1621] 9. The server collects the latest trend data from fashion shows, social media, and news sites and stores it in a database.

[1622] 10. The server inputs the trend data into the AI ​​model, performs trend analysis, and generates unique fashion designs.

[1623] 11. The server merges the generated design with the user profile and adds it to the suggestion list.

[1624] Virtual try-on and feedback

[1625] 12. The device displays the list of suggestions sent by the server to the user, who selects items that interest them.

[1626] 13. The device will then display the selected items on a virtual try-on screen using VR or AR technology, allowing the user to check how they look and fit.

[1627] 14. The user enters feedback on the item they tried on into the platform, and the feedback data is sent to the server.

[1628] Using Feedback

[1629] 15. The server analyzes the received feedback data and uses it, along with the emotional data, to improve the user profile and AI model, enabling more accurate suggestions the next time the user uses the service.

[1630] Examples of concrete examples and prompts

[1631] For example, if a user is looking for "work" fashion items, the following prompt might be used:

[1632] Generate a user profile by combining a full-body photo of the user with survey data. Based on the profile, generate a list of suggested "work" fashion items and offer virtual try-on in VR.

[1633] This allows users to efficiently find the perfect fashion item for them, and allows them to check before they buy using virtual try-on and emotion-recognition based feedback.

[1634] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1635] Step 1:

[1636] Users upload a full-body photo of themselves to the platform's upload screen using their smartphone or PC.

[1637] The terminal transmits the uploaded image data to the server.

[1638] Specifically, the user takes a full-body photo using a camera, selects the image file using the file selection button, and presses the send button. The input is the full-body photo, and the output is the image data sent to the server.

[1639] Step 2:

[1640] Users fill out a survey provided on the platform and enter information about their preferred colors, fashion style, budget, and lifestyle.

[1641] The terminal transmits the inputted questionnaire data to the server.

[1642] Specifically, the user fills in the questionnaire form and presses the send button. The input is the questionnaire data, and the output is the questionnaire data sent to the server.

[1643] Step 3:

[1644] The server uses image recognition algorithms to analyze the received image data.

[1645] Specifically, the server analyzes the user's body type, facial features, and usual fashion style.

[1646] Specifically, the server uses the OpenCV library to perform face detection and body type classification. The input is image data, and the output is the analysis results (body type, facial features, and fashion style).

[1647] Step 4:

[1648] The server applies an emotion recognition algorithm based on the received image data.

[1649] The server identifies the user's emotional state (e.g., happy, sad, surprised, etc.) from the image.

[1650] Specifically, emotion recognition uses a facial expression recognition algorithm, where the input is image data and the output is the analysis result of the emotional state.

[1651] Step 5:

[1652] The server integrates the image analysis results, emotion analysis results, and survey data to generate a user profile.

[1653] The server stores this data in a database and records it in JSON format.

[1654] Specifically, it creates a database entry and saves the user profile. The input is the image analysis results, emotion analysis results, and questionnaire data, and the output is the generated user profile.

[1655] Step 6:

[1656] The server inputs the generated user profile into the AI ​​model.

[1657] The server runs an AI model (such as a recurrent neural network or a generative model) to generate a list of suitable fashion items.

[1658] Specifically, it calls an AI model, provides prompts, and generates a list of items based on the parameters: the input is a user profile, and the output is a list of fashion items.

[1659] Step 7:

[1660] The server periodically collects trend data from fashion shows, social media, and news sites.

[1661] The server stores this information in a database.

[1662] Specifically, it uses scraping scripts and APIs to obtain the latest trend information and stores it in a database. The input is trend data from various external sources, and the output is the stored trend data.

[1663] Step 8:

[1664] The server inputs the collected trend data into an AI model, performs trend analysis, and generates new fashion designs.

[1665] The server merges the generated design with the user profile and adds it to a list of suggestions.

[1666] Specifically, it runs an AI model to generate designs based on trend data and integrate it with the user profile. The input is trend data and the user profile, and the output is an updated list of suggestions.

[1667] Step 9:

[1668] The terminal displays the proposal list sent from the server to the user.

[1669] The user selects items of interest from the suggestion list.

[1670] The terminal displays the selected items on a virtual try-on screen using VR or AR technology.

[1671] Specifically, the device uses an AR kit and a VR app to perform virtual try-on. The input is a list of suggestions, and the output is a display of the virtual try-on.

[1672] Step 10:

[1673] Users enter feedback on the items they try on into the platform.

[1674] The terminal transmits the feedback data to the server.

[1675] Specifically, the user fills in the feedback form and presses the submit button. The input is the feedback, and the output is the feedback data sent to the server.

[1676] Step 11:

[1677] The server analyzes the received feedback and uses it, along with the emotional data, to improve the user profile and AI model.

[1678] The server will be able to make more accurate suggestions the next time you use the service.

[1679] Specifically, the feedback data is analyzed and the AI ​​model is retrained. The input is the feedback data, and the output is an improved AI model.

[1680] (Application example 2)

[1681] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1682] Existing fashion recommendation systems make suggestions based on the user's body type and fashion style, but they are unable to consider the emotional state and feedback of each individual user, making it difficult to fully increase user satisfaction. Furthermore, they lack the ability to make suggestions using the latest trend data or virtual try-on functions, making it difficult to provide a real-time fitting experience or suggestions tailored to individual preferences.

[1683] The identification processing by the identification 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 receiving image data of a user and analyzing the image data to recognize the user's body type and fashion style, means for acquiring questionnaire data for the user and integrating the questionnaire data to generate a user profile, means for using an emotion recognition algorithm to analyze the user's emotional state, means for using a generative AI model to suggest fashion items based on the user profile, means for collecting the latest trend data and generating new fashion designs based on the trend data, means for providing a virtual try-on of the suggested fashion items using VR or AR technology, means for accepting uploads of the user's full-body photo and questionnaire data, and means for collecting user feedback. This enables advanced fashion suggestions based on the generation of individual user profiles and emotion recognition, and can increase user satisfaction through virtual try-ons and feedback collection.

[1684] "User image data" refers to still images or video data taken or uploaded by a user using a terminal.

[1685] "Body type" is a concept that refers to the dimensions, shape, proportions, etc. that characterize the appearance and structure of a user's body.

[1686] "Fashion style" refers to the user's preferred clothing and style trends, genres, and designs.

[1687] "Survey Data" refers to information provided by users in the form of questions about their preferred colors, fashion style, budget, lifestyle, etc.

[1688] A "user profile" is a data set that includes the attributes, preferences, and characteristics of an individual user, generated by integrating user image data, survey data, and sentiment analysis results.

[1689] An "emotion recognition algorithm" is a technology that analyzes a user's image or video data to identify their emotional state at that time (e.g., joy, sadness, surprise, etc.).

[1690] A "generative AI model" is an artificial intelligence model that suggests new fashion items based on accumulated data and learning results.

[1691] "Trend data" refers to information about currently popular styles and designs collected from the latest fashion shows, social media, news sites, etc.

[1692] "Virtual try-on" is a feature that allows users to try on clothes in a digital space using VR (virtual reality) or AR (augmented reality) technology.

[1693] "Feedback" refers to the ratings, comments, and opinions provided by users based on their try-on and usage experiences.

[1694] The system for implementing the present invention includes various processes related to users, servers, and terminals. A specific embodiment of the system will be described below.

[1695] Collection and processing of user image data and survey data

[1696] 1. Collecting user image data and survey data

[1697] Users take a full-body photo of themselves using a device such as a smartphone or PC and upload it to the system. They also answer a questionnaire provided on the platform they use, providing information about their preferred colors, fashion style, budget, and lifestyle. This data is then sent from the device to the server.

[1698] Image analysis and user profile generation

[1699] 2. Image analysis and emotion recognition

[1700] The server receives the image data sent by the user and uses an image recognition algorithm (e.g., OpenCV, TensorFlow) to analyze the user's body shape, facial features, and usual fashion style, while simultaneously using an emotion recognition algorithm (e.g., Microsoft Azure Face API) to analyze the user's emotional state (e.g., joy, sadness, surprise, etc.).

[1701] 3. Integration with survey data and generation of user profiles

[1702] The results of image analysis and emotion recognition are combined with survey data to generate a detailed user profile for each individual user, including data such as body type, style preferences, emotional state, and living environment.

[1703] Fashion item suggestions

[1704] 4. AI-generated recommendations

[1705] The server inputs the generated user profile into a generative AI model (for example, a model using PyTorch or TensorFlow). The generative AI model generates a list of appropriate fashion items based on past data and the user's emotional data. This process suggests fashion items that take into account the user's preferences and emotional state.

[1706] Virtual try-on experience and feedback collection

[1707] 5. Displaying a list of suggestions and offering virtual try-ons

[1708] The device displays a list of suggested fashion items sent from the server. Users select items of interest from the suggested list and virtually try them on using VR or AR technology (e.g., Unity, ARKit, ARCore). Users can check the look and fit of the items on the virtual try-on screen.

[1709] 6. Gather feedback and improve the model

[1710] Users enter feedback on the items they try on into the platform. The feedback data sent from the device to the server, along with emotional data, is used to improve the user profile and generative AI model. The improved generative AI model can then make even more accurate suggestions the next time the user uses the platform.

[1711] Specific examples

[1712] Users open the app, take a full-body photo, and answer a questionnaire about their preferred colors, fashion style, budget, and lifestyle. Based on the uploaded data, the AI ​​will suggest three fashion items that suit the user, and they can virtually try on the items using AR. After the virtual try-on, users can enter and submit feedback, which will be reflected in the next suggestions.

[1713] Prompt Sentence Examples

[1714] "Female, in her 20s, slim build, prefers casual style. Prefers clothes in muted colors that are easy to move in. Budget is around 10,000 yen. Emotional state after trying on clothes: surprise and delight. Please recommend some fashion items based on the following information."

[1715] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1716] Step 1:

[1717] Users take a full-body photo of themselves using a device such as a smartphone or PC and upload it to the system. The uploaded image data is then sent from the device to the server.

[1718] Input: A full-body photo of the user

[1719] Data processing: Images taken on the device are converted into the appropriate format (e.g., JPEG, PNG).

[1720] Output: Image data sent to the server

[1721] Step 2:

[1722] Users answer a survey on the platform, providing information such as their preferred colors, fashion style, budget, lifestyle, etc. The survey data is sent from the device to the server.

[1723] Input: User's survey response

[1724] Data processing: Convert survey responses into data formats such as JSON and XML

[1725] Output: Survey data sent to the server

[1726] Step 3:

[1727] The server analyzes the received image data and uses image recognition algorithms (OpenCV, TensorFlow) to recognize the user's body type, facial features, and usual fashion style. The analysis results are integrated into a user profile.

[1728] Input: Image data

[1729] Data processing: Analyzes body shape, facial features, and fashion style using image recognition algorithms

[1730] Output: Analysis results (body shape, facial features, fashion style) data

[1731] Step 4:

[1732] The server uses an emotion recognition algorithm (Microsoft Azure Face API) to analyze the user's emotional state from their image data, which is then integrated into the user profile.

[1733] Input: Image data

[1734] Data processing: Analyze emotional states using emotion recognition algorithms

[1735] Output: Emotional state data

[1736] Step 5:

[1737] The server combines the image analysis results, emotion analysis results, and survey data to generate a detailed user profile, which includes the user's body type, style preferences, emotional state, living environment, and more.

[1738] Input: Image analysis results, emotion analysis results, questionnaire data

[1739] Data processing: Integrating data to generate user profiles

[1740] Output: User profile

[1741] Step 6:

[1742] The server inputs the generated user profile into the generative AI model to generate a list of appropriate fashion items, which are then stored on the server.

[1743] Input: User Profile

[1744] Data processing: Using generative AI models to suggest fashion items

[1745] Output: A list of fashion items

[1746] Step 7:

[1747] The terminal displays a list of suggested fashion items sent from the server to the user, who can then select the items they are interested in and try them on virtually.

[1748] Input: A list of fashion item suggestions

[1749] Output: Suggestion list displayed in terminal

[1750] Step 8:

[1751] The device uses VR or AR technology (Unity, ARKit, ARCore) to display a virtual try-on screen for the selected item, allowing the user to check the look and fit of the item.

[1752] Input: The item selected by the user

[1753] Data processing: Realizing virtual try-on using VR / AR technology

[1754] Output: Virtual fitting screen

[1755] Step 9:

[1756] Users enter their feedback on the items they try on into the platform, and the feedback data is sent from the device to the server.

[1757] Input: User feedback

[1758] Data processing: Convert feedback data into the appropriate format

[1759] Output: Feedback data sent to the server

[1760] Step 10:

[1761] The server receives user feedback and uses it, along with emotional data, to improve the user profile and the generated AI model, which is then reflected in the next proposal.

[1762] Input: Feedback data, emotion data

[1763] Data processing: Retraining generative AI models and updating user profiles

[1764] Output: An improved AI model and an updated user profile

[1765] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1766] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1767] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1768] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1769] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1770] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1771] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1772] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1773] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1774] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1775] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1776] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1777] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1778] 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.

[1779] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1780] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1781] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1782] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1783] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1784] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1785] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1786] The following is further disclosed regarding the above embodiment.

[1787] (Claim 1)

[1788] means for receiving image data of a user and analyzing the image data to recognize the user's body type and fashion style;

[1789] means for acquiring survey data for users and integrating the survey data to generate a user profile;

[1790] A means of suggesting fashion items based on user profiles;

[1791] a means for collecting the latest trend data and generating new fashion designs based on the trend data;

[1792] A means for providing a virtual try-on of the proposed fashion items using VR or AR technology;

[1793] A system including:

[1794] (Claim 2)

[1795] 10. The system of claim 1, further comprising means for collecting feedback from users and using the feedback to improve the user profile and the AI ​​model.

[1796] (Claim 3)

[1797] 10. The system of claim 1, further comprising means for analyzing the user's body type and fashion style using an image recognition algorithm, the image recognition algorithm being based on a machine learning model.

[1798] "Example 1"

[1799] (Claim 1)

[1800] means for receiving image data of a user and analyzing the image data to recognize the user's body type and style;

[1801] means for acquiring survey data for users and integrating the survey data to generate a user profile;

[1802] a means for suggesting items based on a user profile;

[1803] means for collecting up-to-date data and generating new designs based on the data;

[1804] means for providing a virtual try-on of the proposed items using augmented reality and virtual reality technologies;

[1805] A system including:

[1806] (Claim 2)

[1807] 10. The system of claim 1, further comprising means for collecting feedback and using the feedback to improve the user profile and the generated AI model.

[1808] (Claim 3)

[1809] 10. The system of claim 1, further comprising means for analyzing the user's body type and style using an image recognition algorithm, the image recognition algorithm being based on a machine learning model.

[1810] "Application Example 1"

[1811] (Claim 1)

[1812] means for receiving image data of a user and analyzing the image data to recognize the user's body type and fashion style;

[1813] means for acquiring survey data for users and integrating the survey data to generate a user profile;

[1814] A means of suggesting fashion items based on user profiles;

[1815] a means for collecting the latest trend data and generating new fashion designs based on the trend data;

[1816] A means for providing a virtual try-on of the proposed fashion items using VR or AR technology;

[1817] A means for analyzing profile data and fashion item suggestion results based on an AI model stored in the server and proposing fashion coordination;

[1818] A means for obtaining feedback from the user regarding the virtually tried-on fashion items and improving the accuracy of the user profile and the AI ​​model based on the feedback;

[1819] A system including:

[1820] (Claim 2)

[1821] 10. The system of claim 1, further comprising means for collecting feedback from users and using the feedback to improve the user profile and the AI ​​model.

[1822] (Claim 3)

[1823] 10. The system of claim 1, further comprising means for analyzing the user's body type and fashion style using an image recognition algorithm, the image recognition algorithm being based on a machine learning model.

[1824] "Example 2: Combining Emotion Engines"

[1825] (Claim 1)

[1826] means for receiving image data of a user and analyzing the image data to recognize the user's body type and fashion style;

[1827] means for acquiring survey data for users and integrating the survey data to generate a user profile;

[1828] A means of suggesting fashion items based on user profiles;

[1829] a means for collecting the latest trend data and generating new fashion designs based on the trend data;

[1830] A means for providing a virtual try-on of the proposed fashion items using VR or AR technology;

[1831] means for analyzing emotions from image data of a user;

[1832] A means to use a generative AI model to list appropriate fashion items based on a user profile; and

[1833] A system including:

[1834] (Claim 2)

[1835] 10. The system of claim 1, further comprising means for collecting feedback from users and using the feedback to improve the user profile and the AI ​​model.

[1836] (Claim 3)

[1837] 10. The system of claim 1, further comprising means for analyzing the user's body type and fashion style using an image recognition algorithm, the image recognition algorithm being based on a machine learning model.

[1838] "Application example 2 when combining emotion engines"

[1839] (Claim 1)

[1840] means for receiving image data of a user and analyzing the image data to recognize the user's body type and fashion style;

[1841] means for acquiring survey data for users and integrating the survey data to generate a user profile;

[1842] means for using an emotion recognition algorithm to analyze the emotional state of the user;

[1843] a means for using a generative AI model to suggest fashion items based on a user profile;

[1844] a means for collecting the latest trend data and generating new fashion designs based on the trend data;

[1845] A means for providing a virtual try-on of the proposed fashion items using VR or AR technology;

[1846] a means for accepting uploads of a user's full-body photograph and survey data;

[1847] a means of collecting user feedback;

[1848] A system including:

[1849] (Claim 2)

[1850] 10. The system of claim 1, further comprising means for collecting feedback from users and using the feedback to improve the user profile and the generated AI model.

[1851] (Claim 3)

[1852] 10. The system of claim 1, further comprising means for analyzing the user's body type and fashion style using an image recognition algorithm, the image recognition algorithm being based on a machine learning model. [Explanation of symbols]

[1853] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving image data of a user and analyzing the image data to recognize the user's body type and fashion style; means for acquiring survey data for users and integrating the survey data to generate a user profile; A means of suggesting fashion items based on user profiles; a means for collecting the latest trend data and generating new fashion designs based on the trend data; A means for providing a virtual try-on of the proposed fashion items using VR or AR technology; A system including:

2. 10. The system of claim 1, further comprising means for collecting feedback from users and using the feedback to improve the user profile and the AI ​​model.

3. 10. The system of claim 1, further comprising means for analyzing the user's body type and fashion style using an image recognition algorithm, the image recognition algorithm being based on a machine learning model.

Images