System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting information of personal preferences and clothing owned; means for analyzing the collected information and generating a feature vector of a user; means for generating optimal coordination using a generative model with the feature vector as an input; means for displaying the generated coordination to the user; and means for collecting feedback from the user and continuously improving the generative model.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Currently, there are many different ways to choose clothes, such as store displays, online purchases, and try-ons using AR technology. However, these methods often make it difficult to match clothes with an individual's existing clothing or find clothes that perfectly suit their tastes. Therefore, there is a need for a system that can suggest optimal outfits that take into account an individual's preferences and combine them with the clothes they already own. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system that includes: means for collecting information on personal preferences and clothing owned by a user; means for analyzing the collected information to generate a feature vector for the user; means for generating optimal outfits based on the generated feature vector using a generative model; means for presenting the generated outfits to the user; and means for collecting feedback from the user and continuously improving the generative model. This system can suggest optimal outfits for individual users, enabling more personalized clothing selection and can also accommodate suggestions for outfits for specific events or household members.

[0006] "Personal preferences" refers to a user's personal tastes and preferences in fashion, such as preferred colors, styles, brands, etc.

[0007] "Clothing owned" refers to the type, quantity, color, style, etc. of clothing that the user already owns.

[0008] "Means for collecting information" refers to a method or device for collecting information from a user about personal preferences and clothing items owned.

[0009] "Analysis" refers to the process of analyzing the collected information and extracting the user's preferences and clothing characteristics from it.

[0010] A "feature vector" refers to a numerical representation of a user's hobbies, preferences, and clothing characteristics.

[0011] A "generative model" refers to an algorithm or system that uses machine learning and artificial intelligence technology to generate optimal outfits based on a user's feature vectors.

[0012] "Coordination" refers to the combination of clothing that is considered optimal based on the user's preferences and the clothing they own.

[0013] "Feedback" refers to the user's evaluation or thoughts on the proposed outfit.

[0014] "Continuous improvement means" refers to methods and devices that update generative models based on collected feedback to improve the accuracy of suggestions.

[0015] The term "system" refers to a configuration that integrally includes a series of means and processes in the present invention. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] The present invention is a system that collects information on an individual's preferences and clothing possessions, and proposes optimal outfits using feature vectors generated based on the information. This system has the following main functions:

[0038] User Data Collection

[0039] User:

[0040] When using the system for the first time, users enter their basic information and fashion preferences. They can also upload photos of the clothes they own at home.

[0041] Device:

[0042] It provides an interface that displays the information entered by the user and the images uploaded on the screen, allowing the user to confirm the entered information.

[0043] server:

[0044] It receives the input data and stores it in a database, and also uses image analysis tools to analyze the uploaded photos of clothing and classify the characteristics of each item (color, shape, style, etc.).

[0045] Data analysis and feature vector generation

[0046] server:

[0047] The collected information is used to analyze the user's hobbies, preferences, and clothing characteristics. Based on the analysis results, a feature vector for the user is generated. This feature vector is made up of numerical data corresponding to each attribute, such as color, style, and type of item.

[0048] Generating optimal coordination

[0049] server:

[0050] The generated feature vectors are input into a generative model to generate optimal outfits. This generative model takes into account the user's preferences, the clothing they own, the current season, and specific events to suggest optimal outfit combinations.

[0051] example:

[0052] If a user inputs "I like the color blue," "I have three pairs of jeans," and "I like a casual style," the generative model will use this information to suggest outfits such as "a blue shirt, jeans, and white sneakers."

[0053] Suggestion display and user interaction

[0054] Device:

[0055] The generated outfit suggestions are displayed to the user, along with detailed information about each item (brand name, price, etc.), allowing the user to confirm the suggestions.

[0056] User:

[0057] Users can review the provided outfits, request to change some items if necessary, and even rate and provide feedback on the suggestions.

[0058] Gathering feedback and improving the generative model

[0059] server:

[0060] Collect user feedback, analyze the data, and retrain the generative model based on the feedback data to improve the accuracy of the suggestions.

[0061] example:

[0062] If the user rates the proposed outfit as "very satisfied," the server will reflect this information in future suggestions.

[0063] This system allows users to easily find the perfect outfit based on their preferences and the clothing they own. It can also suggest outfits for specific events or outfits to coordinate with other members of the household. This improves the user experience and provides personalized fashion suggestions.

[0064] The processing flow will be explained below.

[0065] Step 1:

[0066] User:

[0067] When users first access the system, they enter basic information and their fashion preferences, such as their favorite colors, styles, and brands, and also upload photos of the clothes they own.

[0068] Step 2:

[0069] Device:

[0070] The information entered and the image uploaded by the user are displayed on the screen for confirmation. The user can check the information entered and the image and make corrections as necessary.

[0071] Step 3:

[0072] server:

[0073] The system receives the data submitted by users and stores it in a database. Photos of uploaded clothing are then run through image analysis tools to classify the item's color, shape, style, and other characteristics.

[0074] Step 4:

[0075] server:

[0076] The collected information is analyzed to extract the user's hobbies, preferences, and clothing characteristics. These characteristics are then used to generate a feature vector, which consists of numerical data corresponding to attributes such as color, style, and item type.

[0077] Step 5:

[0078] server:

[0079] The generated feature vector is input into a generative model, which then generates the optimal outfit based on the user's feature vector. The model selects outfit combinations taking into account the user's preferences, clothing they own, the season, specific events, and other factors.

[0080] Step 6:

[0081] Device:

[0082] The generated outfit suggestions are displayed to the user, along with detailed information (such as brand name, price, and purchase link) so that the user can review the suggestions.

[0083] Step 7:

[0084] User:

[0085] Check the displayed outfits, request to change some items as needed, and enter your rating and feedback on the suggestions.

[0086] Step 8:

[0087] server:

[0088] The system analyzes the feedback collected from users and stores the evaluation data in a database.The system then retrains the generative model based on the feedback data to improve the accuracy of future suggestions.

[0089] By going through these steps, personalized and optimal coordination suggestions are provided to the user.

[0090] Example 1

[0091] 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."

[0092] Currently, it is not easy for individuals to find the optimal fashion coordination based on their own preferences and the clothing they own. Choosing the right outfit for a specific event or situation requires a lot of time and effort. It is also difficult to suggest coordinated outfits that are also harmonious with other members of the household. There is a need for a system that can solve these issues and easily provide personalized fashion suggestions to individuals.

[0093] 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.

[0094] In this invention, the server includes means for collecting information on personal preferences and clothing owned by the user, means for storing the collected information in a database and analyzing uploaded clothing images to classify the characteristics of each item, means for generating a feature vector for the user based on the collected information and the analyzed characteristics, means for inputting the feature vector into a generative model to generate an optimal outfit, means for displaying the generated outfit to the user and providing detailed information about each item, and means for collecting feedback from the user and retraining the generative model based on that data to improve the accuracy of suggestions. This enables the server to automatically suggest optimal outfits based on personal preferences and clothing owned by the user, making it possible to suggest outfits that are harmonious for specific events or with other members of the household.

[0095] "Personal preferences" refers to fashion trends, colors, styles, brands, etc. that a user recognizes as his or her own preferences.

[0096] "Clothing you own" refers to items such as clothes, accessories, and shoes that you already own.

[0097] "Means of collection" refers to the functions and interfaces that allow the system to capture information entered by users and images uploaded by users.

[0098] "Database" refers to a collection of electronic records that store and manage collected information and analytical data.

[0099] "Image Analysis Method" means software or algorithms that analyze uploaded photos of clothing to identify and classify the characteristics of each item (e.g., color, shape, style, etc.).

[0100] "Means of classification" refers to the function of categorizing each item based on the analyzed data.

[0101] A "feature vector" refers to a numerical representation of a user's preferences and the characteristics of items they own.

[0102] A "generative model" refers to a machine learning model or algorithm that takes a user's feature vector as input and generates the optimal outfit.

[0103] "Coordination" refers to suggestions for outfits that combine multiple items of clothing and accessories.

[0104] "Displaying means" refers to an interface for displaying the generated coordinates and their detailed information on the user's device.

[0105] "Means for collecting feedback" refers to a function that allows users to input their evaluations of proposed outfits and requests for changes.

[0106] "Means for retraining the generative model" refers to a process for improving the accuracy of the generative model and the quality of suggestions based on collected feedback data.

[0107] "Means for improving the accuracy of suggestions" refers to a series of processes or methods for improving the performance of the generative model and proposing outfits that are more suitable for the user.

[0108] "Particular events or situations" refers to specific occasions or settings, such as weddings, business meetings, or casual outings.

[0109] "Other members of the household" refers to people who live with the user, such as family members or roommates.

[0110] "Clothing suggestions" refers to suggesting appropriate clothing combinations for individual users and situations.

[0111] The present invention is a system that collects information on an individual's preferences and clothing possessions, and uses feature vectors generated based on the collected information to suggest optimal outfits. This system is implemented using the following hardware and software.

[0112] User:

[0113] When using the system for the first time, users use a device such as a smartphone or PC to enter their basic information (such as name, age, and gender) and fashion preferences (favorite colors, styles, and brands). They also take photos of the clothes they own and upload them to the system.

[0114] Device:

[0115] It provides an interface that displays user-entered information and uploaded images. This interface can be implemented as a web browser or a mobile application. For example, it can include operations such as uploading photos of clothing taken with a smartphone camera app.

[0116] server:

[0117] The server receives data entered by users and uploaded images of clothing and stores them in a database. The server uses image analysis tools (e.g., TENSORFLOW (registered trademark) or OpenCV) to analyze the uploaded images and classify the characteristics of each item (color, shape, style, etc.). For example, it extracts information such as "blue shirt" or "jeans."

[0118] Next, the server generates a feature vector for the user based on the collected information and analysis results. This feature vector represents color, style, type of item, etc. as numerical data. For example, if a user inputs "I like the color blue," "I have three pairs of jeans," and "I like casual styles," the feature vector will be a numerical representation of these.

[0119] The server inputs this feature vector into a generative AI model (e.g., GPT-4 (registered trademark) or BERT) to generate the optimal outfit. An example of a prompt sentence input to the model is, "The user's characteristics are as follows: 1. Favorite color: blue, 2. Items owned: three pairs of jeans, 3. Style: casual. Please suggest the optimal outfit based on this information." Based on this information, the generative model suggests outfits such as "a blue shirt, jeans, and white sneakers."

[0120] The generated outfits are sent to the terminal and displayed to the user. Detailed information about each item (brand name, price, etc.) is provided for the user to review. The user can also enter their rating and feedback on the proposed outfits, and this feedback data is collected by the server.

[0121] Finally, the server analyzes the collected feedback data and retrains the generative model to improve the accuracy of the suggestions. For example, if a user rates a suggested outfit as "very satisfying," this information will be reflected in future suggestions. This allows the system to continuously provide optimal fashion suggestions based on the user's preferences and the clothes they own.

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

[0123] Step 1:

[0124] Entering and collecting user data

[0125] User:

[0126] Using a device such as a smartphone or PC, users enter their basic information (such as name, age, and gender) and fashion preferences (favorite colors, styles, and brands), and also take photos of clothing they own and upload them to the system.

[0127] input:

[0128] User's basic information, preferences, and photos of clothing

[0129] output:

[0130] The entered information and uploaded images are sent to the system.

[0131] Specific behavior:

[0132] Users open the app on their smartphone, select their favorite color and style, take a photo of the clothing they own, and press the upload button to send the photo to the system.

[0133] Step 2:

[0134] Data storage and image analysis

[0135] server:

[0136] It receives input data and uploaded images, stores them in a database, and uses image analysis tools (TensorFlow and OpenCV) to analyze the uploaded images and classify the characteristics of each item (color, shape, style, etc.).

[0137] input:

[0138] Basic information, preference information, and photos of clothing sent by the user

[0139] output:

[0140] User information and clothing characteristics data stored in a database

[0141] Specific behavior:

[0142] The server processes the images it receives using an analysis tool, extracts characteristic information such as "blue shirt" or "jeans," and stores this information in a database.

[0143] Step 3:

[0144] Feature Vector Generation

[0145] server:

[0146] The collected information and analyzed characteristic data are used to generate a feature vector for the user, which is expressed as numerical data such as color, style, and item type.

[0147] input:

[0148] User basic information, preference information, and clothing characteristics data

[0149] output:

[0150] User feature vector

[0151] Specific behavior:

[0152] The server extracts user information and characteristic data from the database and generates a feature vector such as "Color: Blue, Style: Casual, Item: 3 pairs of jeans."

[0153] Step 4:

[0154] Generating optimal coordination

[0155] server:

[0156] The generated feature vector is input into a generative AI model to generate optimal outfits. The generative model takes into account the user's preferences, the clothing they own, the current season, and specific events to suggest outfit combinations.

[0157] input:

[0158] User feature vector

[0159] output:

[0160] Optimal coordination suggestions

[0161] Specific behavior:

[0162] The server inputs the feature vector into a generative AI model and generates outfits such as "blue shirt, jeans, and white sneakers."

[0163] Example prompt sentence:

[0164] "The user's characteristics are as follows: 1. Favorite color: Blue, 2. Owned items: Three pairs of jeans, 3. Style: Casual. Please suggest the best outfit based on these."

[0165] Step 5:

[0166] Coordination display and user interaction

[0167] Device:

[0168] The generated coordination suggestions are displayed to the user, and detailed information about each item (brand name, price, etc.) is provided.

[0169] User:

[0170] Check the proposed outfits, request to change some items as needed, and enter your rating and feedback on the suggestions.

[0171] input:

[0172] Coordination suggestions sent from the server

[0173] output:

[0174] User Review and Feedback

[0175] Specific behavior:

[0176] Users can check the outfit on their smartphone or PC screen and send feedback such as "very satisfied."

[0177] Step 6:

[0178] Gathering feedback and improving the generative model

[0179] server:

[0180] It collects user feedback, analyzes that data, and retrains the generative model to improve the accuracy of future suggestions.

[0181] input:

[0182] User feedback data

[0183] output:

[0184] Improved generative models

[0185] Specific behavior:

[0186] The server receives the feedback of "very satisfied" and uses that information to retrain the generative model and reflect it in the next proposal.

[0187] This allows the entire system to continue to provide optimal fashion coordination based on the user's information.

[0188] (Application example 1)

[0189] 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."

[0190] It is difficult for users to find the perfect outfit based on their preferences and the clothes they own in a physical store. Furthermore, due to the lack of an environment where users can visually check the outfits provided, it is difficult for users to grasp the actual appearance of the outfit suggestions. Furthermore, if these outfit suggestions are not improved based on user feedback, the accuracy of the suggestions may decrease.

[0191] 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.

[0192] In this invention, the server includes: means for collecting information on personal preferences and clothing owned by the user; means for analyzing the collected information and generating a feature vector for the user; means for using the feature vector as an input and generating an optimal outfit using a generative model; means for displaying the generated outfit to the user; means for collecting feedback from the user and continuously improving the generative model; means for scanning products in a store and acquiring product information that matches the user's feature vector; means for using an augmented reality algorithm to visually display outfit suggestions in real space; and means for displaying detailed information for each item of the outfit suggestions. This allows the user to visually confirm the optimal outfit based on their preferences in a physical store and make adjustments as necessary.

[0193] "Personal preferences" refers to a user's fashion preferences, such as preferred colors, styles, brands, etc.

[0194] "Information about clothing owned" is detailed information about clothing items owned by the user, such as clothes, shoes, and accessories.

[0195] A "feature vector" is a numerical representation of a user's preferences and the characteristics of the clothing they own.

[0196] A "generative model" is a machine learning algorithm that takes a user's feature vector as input and generates the optimal outfit.

[0197] "Feedback" refers to information such as user evaluations, opinions, and impressions regarding suggestions.

[0198] "Continuous improvement" is the process of improving the accuracy of the generative model based on collected feedback.

[0199] "Scanning products in a store" means analyzing products in the store using image recognition technology and obtaining information about them.

[0200] "Augmented reality algorithm" is a technology that displays digital information overlaid on real space.

[0201] "Visually displaying coordinated outfit suggestions" means displaying the suggested coordinated outfits so that the user can actually visually confirm them.

[0202] "Detailed information" refers to detailed information such as the brand name, price, and size of each product.

[0203] MODE FOR CARRYING OUT THE INVENTION

[0204] This invention is a system that utilizes information on personal preferences and clothing owned by a customer to propose optimal outfits in physical stores. Specific implementation procedures are described below.

[0205] Hardware and Software Configuration

[0206] (server)

[0207] The server has the following main responsibilities:

[0208] 1. Information collection: Collects basic information about the user, their fashion preferences, and the clothing they own. Users use their smartphones or computers to enter text and upload images.

[0209] 2. Data analysis: Analyze the collected data and generate a feature vector for the user. Image analysis uses image recognition tools such as OpenCV.

[0210] 3. Coordination generation: The generated feature vector is input into a machine learning model (e.g., TensorFlow) to generate the optimal coordination.

[0211] 4. Model Improvement: Collect user feedback to continuously improve the generative model. Feedback is provided by the user via smart glasses or a head-mounted display.

[0212] (Terminal)

[0213] The terminal has the following main roles:

[0214] 1. Information display: The generated outfit suggestions are visually displayed to the user. Using smart glasses or a head-mounted display, augmented reality algorithms are applied to in-store product images, overlaying digital information on them.

[0215] 2. Product scanning: Scan products in the store with a camera and send the information to the server, which retrieves product information that matches the user's feature vector.

[0216] 3. Displaying detailed information: Displaying detailed information (brand name, price, size, etc.) for each item in the suggested outfits to the user, making it easier for the user to select suggested items.

[0217] (User)

[0218] Users can use the system in the following ways:

[0219] 1. Enter your basic information and clothing: Enter your basic information, fashion preferences, and clothing information through the app. Specifically, upload photos of your favorite colors, styles, and items you own.

[0220] 2. Wearing smart glasses: After entering a physical store, customers put on smart glasses or a head-mounted display and scan the products in the store.

[0221] 3. Check your outfit: Check the outfit suggestions displayed on the smart glasses and check the details of each item.

[0222] 4. Providing feedback: Feedback your evaluation and opinions on the coordination proposal to the system.

[0223] Specific examples

[0224] Suppose a user enters a physical store, their favorite color is black, and they like a casual style. They own a black jacket, white sneakers, and a blue denim shirt. The user puts on smart glasses and scans the products in the store. The server generates a feature vector for the user and inputs it into a machine learning model to suggest the optimal outfit. In this case, the suggested outfit would be "a black jacket, white sneakers, and a blue denim shirt."

[0225] Prompt Sentence Examples

[0226] "Users' favorite color is black, they like casual style, and they own multiple pairs of jeans."

[0227] "I own a black jacket, white sneakers, and a blue denim shirt."

[0228] In this way, the system can visually suggest optimal outfits based on the user's preferences in a physical store.

[0229] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0230] Step 1:

[0231] Users use their smartphones or computers to enter their basic information, fashion preferences, and information about the clothing they own. The information entered includes text data and image data, and this information becomes the input for the system.

[0232] Step 2:

[0233] The server receives the data sent by the user and stores it in a database. At this time, the image data is analyzed using image recognition tools such as OpenCV to extract characteristics such as color, shape, and style. This data processing provides the analysis results of the user's preferences and detailed information about the clothing they own.

[0234] Step 3:

[0235] The server generates a feature vector for the user based on the collected and analyzed information. The feature vector is a numerical representation of the user's preference data (favorite color, preferred style, etc.) and the characteristics of the clothing they own (color, shape, style). Once the feature vector is generated, it becomes the input data for the generative model.

[0236] Step 4:

[0237] The server uses the generated feature vector to generate the optimal outfit using a machine learning algorithm (e.g., TensorFlow). The generative model proposes the optimal combination of items based on the user's feature vector and the data learned by the model. This process generates the optimal outfit.

[0238] Step 5:

[0239] The terminal receives the outfit suggestions generated by the server and displays them to the user. Specifically, augmented reality algorithms are used in smart glasses or head-mounted displays to overlay digital information onto in-store product images. The user can visually confirm the outfit suggestions by combining real space and digital information.

[0240] Step 6:

[0241] The user wears smart glasses or a head-mounted display and scans the products in the store. This displays product information in the store on the device in real time, and product information that matches the user's feature vector is sent to the server, where the product information in the store is added as input data.

[0242] Step 7:

[0243] Based on the scanned product information, the device identifies products that match the user's feature vector and displays product details based on the generated coordination suggestions. Specifically, detailed information such as brand name, price, and size is displayed, allowing the user to make product selections.

[0244] Step 8:

[0245] The user sends feedback on the outfit suggestions from their device to the server. The feedback includes evaluations, opinions, and impressions of the outfit suggestions. This becomes new input data.

[0246] Step 9:

[0247] The server analyzes the feedback collected from users and retrains the generative model. Based on the feedback data, it adjusts the parameters of the generative model to improve the accuracy of future outfit suggestions. This process continuously improves the performance of the entire system.

[0248] 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.

[0249] The present invention is a system that collects information on an individual's preferences and clothing possessions, and proposes optimal outfits using feature vectors generated based on the collected information, and further combines it with an emotion engine that recognizes the user's emotions to provide more personalized suggestions. The following is a specific embodiment of the system.

[0250] User data and sentiment collection

[0251] User:

[0252] When accessing the system for the first time, users enter basic information and fashion preferences. They also upload photos of their clothing. While using the system, users can input their emotional state in real time or detect their emotions using the device's built-in camera and sensors.

[0253] Device:

[0254] It provides an interface that displays and allows users to confirm information they have entered, images they have uploaded, and emotional data on the screen.

[0255] server:

[0256] The system receives data sent by the user (preference information, photos of clothing owned, and emotional data) and stores it in a database. It uses an image analysis tool to classify the clothing images. It also uses an emotion engine to analyze the user's emotions.

[0257] Data analysis and feature vector generation

[0258] server:

[0259] The collected preference information, clothing characteristics, and emotional data are analyzed to generate a feature vector for the user. This feature vector is composed of numerical data corresponding to attributes such as color, style, and item type. Furthermore, based on the emotional data, weighting is applied to reflect the user's current mood.

[0260] Generating optimal coordination

[0261] server:

[0262] The generated feature vector is input into a generative model to generate optimal outfits, taking into account the user's emotional state. The generative model then suggests outfit combinations based on the user's preferences, clothing, season, specific events, and emotional state.

[0263] example:

[0264] If a user inputs "I like the color blue," "I have three pairs of jeans," "I like casual styles," and the emotion engine recognizes that "I'm in a good mood today," the generative model will suggest an outfit such as "a blue shirt, jeans, and white sneakers." However, if the emotion engine recognizes that "I'm feeling down today," it will suggest a more relaxing style and color combination.

[0265] Suggestion display and user interaction

[0266] Device:

[0267] The generated outfit suggestions are displayed to the user, along with detailed information (such as brand name, price, and purchase link) so that the user can review the suggestions.

[0268] User:

[0269] Check the displayed outfits, request to change some items as needed, and enter your rating and feedback on the suggestions.

[0270] Gathering feedback and improving the generative model

[0271] server:

[0272] The system analyzes feedback collected from users and stores the evaluation data in a database. The system retrains the generative model based on the feedback data to improve the accuracy of future suggestions.

[0273] example:

[0274] If a user rates a suggested outfit as "very satisfied," the server will reflect this information in future suggestions. It also analyzes how the user's emotional data influences future suggestions.

[0275] This system not only provides optimal outfits based on the user's preferences and the clothing they own, but also takes the user's emotions into account, allowing for more personalized suggestions, improving the user experience.

[0276] The processing flow will be explained below.

[0277] Step 1:

[0278] User:

[0279] When accessing the system for the first time, users enter their basic information (name, gender, age, etc.) and fashion preferences (favorite colors, styles, brands, etc.), and also upload several photos of clothing they own.

[0280] Step 2:

[0281] Device:

[0282] A screen will be displayed where the user can confirm the basic information and preference information they have entered, as well as the photos of their clothing they have uploaded. The user can check the information they have entered and the images and make any necessary corrections.

[0283] Step 3:

[0284] server:

[0285] It receives data sent by users and stores it in a database, runs image analysis tools on uploaded clothing photos to classify characteristics such as color, shape, and style, and activates an emotion engine to collect emotional data.

[0286] Step 4:

[0287] server:

[0288] While the user is using the system, the emotion engine analyzes the user's facial expressions and input data in real time to infer their current emotional state. The inferred emotional data is stored in a database.

[0289] Step 5:

[0290] server:

[0291] The collected preference information, clothing characteristics, and emotional data are analyzed to generate a feature vector for the user, which includes numerical data representing color, style, item type, and emotional state.

[0292] Step 6:

[0293] server:

[0294] The generated feature vector is input into a generative model to generate optimal outfits that take into account the user's emotional state. The generative model selects outfit combinations by comprehensively evaluating the user's preferences, clothing, season, specific events, and emotional state.

[0295] example:

[0296] If a user inputs "I like the color blue," "I have three pairs of jeans," and "I like casual style," and the emotion engine recognizes that "I'm in a good mood today," the generative model will suggest an outfit consisting of "a blue shirt, jeans, and white sneakers."

[0297] Step 7:

[0298] Device:

[0299] The generated outfit suggestions are displayed to the user, along with detailed information (such as brand name, price, and purchase link) so that the user can review the suggestions.

[0300] Step 8:

[0301] User:

[0302] Check the displayed outfits, request to change some items as needed, and enter your rating and feedback on the suggestions.

[0303] Step 9:

[0304] server:

[0305] The system analyzes feedback collected from users and stores the evaluation data in a database. The system retrains the generative model based on the feedback data to improve the accuracy of future suggestions.

[0306] example:

[0307] If a user rates a suggested outfit as "very satisfying," the server will reflect this information in future suggestions. It will also analyze how the emotional data influenced the suggestions and use this information to improve them.

[0308] Through these steps, personalized and optimal outfit suggestions are provided to the user. Furthermore, the introduction of an emotion engine enables more personalized suggestions that take into account the user's emotional state, improving the user experience.

[0309] Example 2

[0310] 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."

[0311] Many systems exist that collect information about an individual's fashion preferences and clothing possessions and then suggest optimal outfits based on that information. However, these systems often fail to take into account the user's emotional state, resulting in low user satisfaction. Furthermore, these systems lack the functionality to continuously improve the system based on feedback. This means that consistent results cannot be expected with each use.

[0312] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0313] In this invention, the server includes: means for collecting information on personal preferences and clothing owned by the user; means for providing an interface for inputting preference information, clothing information, and emotional data; means for analyzing the collected information and generating a feature vector for the user; means for analyzing the feature vector and emotional data and weighting the feature vector to reflect the user's current emotional state; means for using the feature vector as input and generating an optimal outfit using a generative model; means for displaying the generated outfit to the user and providing detailed information; and means for collecting user feedback and continuously improving the generative model. This enables more personalized outfit suggestions that take into account the user's preferences and current emotional state. Furthermore, by continuously improving the system based on user feedback, high levels of satisfaction can be maintained over the long term.

[0314] "Personal preferences" refers to information about a user's fashion preferences, such as their favorite colors, styles, and brands.

[0315] "Clothes owned" is a list of clothes owned by the user and their detailed information (color, size, brand, frequency of use, etc.).

[0316] "Emotion data" is information that represents the user's current mood or emotional state, and is acquired through sensors or user input.

[0317] A "feature vector" is a data set that quantifies a user's preference information, characteristics of clothing owned, and emotional data, and is composed of numerical data corresponding to each attribute.

[0318] A "generative model" is a machine learning algorithm or artificial intelligence model that takes a user's feature vector as input and generates the optimal outfit.

[0319] A "coordination" is a combination of clothing suggested by a generative model that takes into account the user's preferences and emotional state.

[0320] "Feedback" refers to information about satisfaction with the evaluations, comments, and suggestions that users make to the system.

[0321] An "interface" is an operation screen or input means that allows a user to input information into the system and confirm suggestions from the system.

[0322] The present invention is a system that collects information on personal preferences and clothing owned by a user, generates feature vectors based on the collected information, and then recognizes the user's emotions to suggest optimal outfits. This system is implemented as follows.

[0323] User data and sentiment collection

[0324] User:

[0325] When accessing the system for the first time, users enter basic information (such as name, age, and gender) and fashion preferences (favorite color, preferred style, etc.). They also upload photos of clothing they own. While using the system, users can input their own emotional state or have their emotions detected using the device's built-in camera and sensors.

[0326] Specifically, users take a photo of their clothing using the camera on their smartphone or PC and upload it to the system. To input their emotional state, a special form is displayed with options, allowing them to select states such as "happy," "sad," and "tired" in real time.

[0327] Device:

[0328] It provides an interface for users to check the information they enter and the images of their clothing they upload, and also has the ability to detect emotions using cameras and sensors.

[0329] Specifically, the device detects the user's face in real time and analyzes their facial expressions, and the analysis results are displayed to the user on a confirmation screen.

[0330] server:

[0331] The system receives preference information, photos of clothing owned, and emotion data sent by the user and stores them in a database. It uses an image analysis tool (e.g., OpenCV) to classify the clothing images and an emotion engine (e.g., facial recognition technology) to analyze the user's emotions.

[0332] Specifically, the server uses the photos of clothing received to automatically identify the color, pattern, and item (shirt, pants, etc.), converts them into text information, and stores it in a database.

[0333] Data analysis and feature vector generation

[0334] server:

[0335] The collected preference information, clothing characteristics, and emotional data are analyzed, and a feature vector for the user is generated based on this data. This feature vector is composed of numerical data corresponding to attributes such as color, style, and item type. Furthermore, weighting is performed based on the emotional data to reflect the user's current mood.

[0336] Specifically, the server analyzes the data, quantifies features such as "I like the color blue," "I have three pairs of jeans," and "I'm in a good mood today," and uses this data to generate a feature vector.

[0337] Generating optimal coordination

[0338] server:

[0339] The generated feature vectors are input into a generative AI model (e.g., a generative model) to generate optimal outfits taking into account the user's emotional state. This generative model then suggests outfit combinations taking into account the user's preferences, clothing, season, specific events, and emotional state.

[0340] Specific examples of prompts are as follows:

[0341] User Information:

[0342] Preferences: I like the color blue

[0343] Clothing: 3 pairs of jeans, 1 white shirt, 2 blue shirts

[0344] Style: Casual

[0345] Emotional state: Feeling good

[0346] Based on this information, we will suggest the best outfit for you.

[0347] Suggestion display and user interaction

[0348] Device:

[0349] The generated outfit suggestions are displayed to the user, along with detailed information (such as brand name, price, and purchase link) so that the user can review the suggestions.

[0350] Specifically, the device displays images and detailed information of outfits on the screen, allowing users to check them. By clicking on the selection options or links, users can be taken to the purchase page for each item.

[0351] User:

[0352] Check the displayed outfits, request to change some items as needed, and enter your rating and feedback on the suggestions.

[0353] Specifically, when a user makes a change request, such as "I want the shoes to be black," the system will again generate the optimal proposal. The user can also select "Very Satisfied," "Satisfied," or "Dissatisfied" in the evaluation form and enter their comments.

[0354] Gathering feedback and improving the generative model

[0355] server:

[0356] The system analyzes the feedback collected from users and stores the evaluation data in a database, which is used to retrain the generative model and improve the accuracy of future suggestions.

[0357] Specifically, the server analyzes the feedback data, adjusts the parameters of the generative AI model based on the evaluation scores and comments, and retrains it to improve the accuracy of the next proposal.

[0358] This system not only provides optimal outfits based on the user's preferences and the clothes they own, but also takes into account the user's emotions to enable more personalized suggestions. Furthermore, by continuously improving the system based on user feedback, it is possible to maintain high levels of satisfaction over the long term.

[0359] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0360] Step 1:

[0361] User Data Collection

[0362] Specific behavior:

[0363] First, users enter basic information and fashion preferences into the system and upload multiple photos of clothing they own.

[0364] Input: User basic information, preferences, and clothing photos.

[0365] Output: User information and uploaded clothing photo data sent to the server.

[0366] The server receives the data sent by the user (basic information, preference information, and photos of clothing owned) and stores it in a database.

[0367] Specific behavior:

[0368] The server receives the data and stores it in a database, storing information such as name, age, gender, preferred colors and styles, and uploaded photos of the clothing.

[0369] Input: Basic information, preferences, and clothing photos received from the user.

[0370] Output: User dataset stored in a database.

[0371] Step 2:

[0372] Collecting Emotional Data

[0373] Specific behavior:

[0374] Users can input their emotional state in real time or use the device's camera or sensors to detect emotions.

[0375] Input: User's emotional state (or device-detected emotional data).

[0376] Output: Emotion data sent to the server.

[0377] The terminal displays the emotional state data entered by the user or the detected emotional data on the screen and provides a confirmation interface.

[0378] Specific behavior:

[0379] The device uses cameras and sensors to detect the user's face in real time, analyzes their facial expressions, and displays the analysis results to the user on a confirmation screen.

[0380] Input: User's emotional state (or device-detected emotional data).

[0381] Output: An emotional state confirmation interface displayed on the screen.

[0382] The server receives the emotion data sent by the user, stores it in a database, and analyzes the emotion using an emotion engine.

[0383] Specific behavior:

[0384] The server uses an emotion analysis tool to analyze the user's emotion data and stores the results in a database.

[0385] Input: Emotion data received from the user.

[0386] Output: Sentiment analysis results stored in a database.

[0387] Step 3:

[0388] Data analysis and feature vector generation

[0389] Specific behavior:

[0390] The server analyzes the collected preference information, clothing characteristics, and emotional data to generate a feature vector for the user.

[0391] Input: Preference information stored in the database, characteristics of clothing owned, and emotional data.

[0392] Output: A feature vector for the user.

[0393] Based on the analyzed data, the server generates numerical data corresponding to each attribute, such as color, style, and item type, and also weights the data based on the emotion data to reflect the user's current mood.

[0394] Specific behavior:

[0395] The server quantifies the data, assigning a score to color preference (for example, red = 2, blue = 5, green = 1) and generates a feature vector. At the same time, it assigns weights based on the emotional data (for example, good mood = 1.2, bad mood = 0.8).

[0396] Input: Analyzed preference information, clothing characteristics, and emotional data.

[0397] Output: A quantified feature vector.

[0398] Step 4:

[0399] Generating optimal coordination

[0400] Specific behavior:

[0401] The server inputs the generated feature vector into a generative AI model and generates the optimal outfit, taking into account the user's emotional state.

[0402] Input: User feature vector.

[0403] Output: The optimal coordinates generated by the generative AI model.

[0404] The generative model suggests outfit combinations based on the user's preferences, clothing, season, specific events, and emotional state.

[0405] Specific prompt examples:

[0406] User Information:

[0407] Preferences: I like the color blue

[0408] Clothing: 3 pairs of jeans, 1 white shirt, 2 blue shirts

[0409] Style: Casual

[0410] Emotional state: Feeling good

[0411] Based on this information, we will suggest the best outfit for you.

[0412] Specific behavior:

[0413] The server sends a prompt to the AI ​​model, which then generates the optimal coordinates based on this.

[0414] Input: User feature vector, emotional state.

[0415] Output: The optimal coordinates suggested to the user.

[0416] Step 5:

[0417] Displaying outfit suggestions

[0418] Specific behavior:

[0419] The device displays the generated outfit suggestions to the user, along with detailed information (such as brand name, price, and purchase link) so the user can review the suggestions.

[0420] Input: The generated coordinates.

[0421] Output: Coordination suggestions and detailed information displayed on the device screen.

[0422] Specifically, the device displays images and detailed information of outfits on the screen, allowing users to check them. By clicking on the selection options or links, users can be taken to the purchase page for each item.

[0423] Input: Generated coordinates, detailed information.

[0424] Output: Coordination suggestions and detailed information displayed on the device screen.

[0425] Step 6:

[0426] Gathering user feedback

[0427] Specific behavior:

[0428] The user can check the proposed outfits, request to change some items as needed, and enter their ratings and feedback on the suggestions.

[0429] Input: Proposed coordinates, user feedback.

[0430] Output: User feedback sent to the server.

[0431] Specifically, the user makes a change request, such as "I want the shoes to be black," and the system receives it and makes a new suggestion. The user also selects "Very Satisfied," "Satisfied," or "Dissatisfied" in the evaluation form and enters comments.

[0432] Input: User feedback.

[0433] Output: Feedback data stored on the server.

[0434] Step 7:

[0435] Improving generative models

[0436] Specific behavior:

[0437] The server analyzes user feedback and stores the evaluation data in a database, which is used to retrain the generative model and improve the accuracy of future suggestions.

[0438] Input: Feedback data from users.

[0439] Output: An improved generative AI model.

[0440] Specifically, the server analyzes the feedback data, adjusts the parameters of the generative AI model based on the evaluation scores and comments, and retrains it to improve the accuracy of the next proposal.

[0441] Input: Feedback data.

[0442] Output: The updated AI model.

[0443] (Application example 2)

[0444] 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."

[0445] Conventional outfit suggestion systems can make suggestions based on a user's personal preferences and the clothing they own, but they cannot take the user's emotional state into account, making it impossible to provide optimal outfits that match the user's mood and psychological state. Therefore, to further improve the user experience, personalized suggestions that take the user's emotional state into account are needed.

[0446] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0447] In this invention, the server includes means for collecting information on the user's preferences and clothing possessions, means for collecting the user's emotional state, and means for analyzing the collected information and emotional state to generate a feature vector of the user, thereby enabling more personalized and optimal outfit suggestions that take into account the user's preferences and current emotional state.

[0448] The "means for collecting information on personal preferences and clothing owned" refers to a device or method for collecting information on fashion preferences entered by a user and photos and detailed information on clothing owned by the user.

[0449] "Means for collecting a user's emotional state" means a device or method for detecting and recording a user's emotional or psychological state in real time, including, for example, biometric analysis using cameras or sensors.

[0450] "Means for analyzing collected information and emotional state and generating a feature vector of the user" refers to a device or method that converts the user's fashion trends and current emotions into numerical data based on the collected user preference information, clothing information, and emotional data, and expresses them as a feature vector.

[0451] A "means for generating optimal outfits using a generative model" is a device or method that inputs a user's feature vector into a generative AI model and, from the results, suggests optimal clothing combinations based on the user's preferences and emotional state.

[0452] The "means for displaying the generated coordinated outfits to the user" refers to a device or method for displaying the proposed clothing combinations so that the user can check them and select or modify them.

[0453] "Means for collecting user feedback and continuously improving the generative model" refers to a device or method that collects user ratings and opinions on the proposed outfits, and then uses that data to retrain the generative model and improve its accuracy.

[0454] This invention is a system that proposes optimal outfits that take into account a user's emotional state based on information about the user's fashion preferences and the clothing they own. The system is realized by the following steps.

[0455] User data and sentiment collection

[0456] User: The user launches an application installed on their smartphone or head-mounted display (HMD) and inputs basic information and fashion preferences. They also upload photos of their clothing through the application. Furthermore, their emotional state is collected in real time using the smartphone camera and the HMD's built-in sensors.

[0457] Data analysis and feature vector generation

[0458] Server: The collected user preference information, clothing information, and emotional data are sent to a cloud server. The server analyzes the uploaded clothing images using Google® Cloud Vision API to classify the type, color, and style of the clothing. Meanwhile, the emotional data is analyzed using IBM Watson® Tone Analyzer. Next, a feature vector for the user is generated based on this data. This feature vector represents the color, style, type of item, emotional state, and other factors as numerical data.

[0459] Generating optimal coordination

[0460] Server: The generated feature vectors and emotion data are input into a generative AI model (e.g., OpenAI (registered trademark) GPT-3 (registered trademark)) to generate optimal outfits based on the user's preferences and current emotional state. The generated outfit suggestions take into account the user's preferences, clothing they own, the season, specific events, and their emotional state to suggest outfit combinations.

[0461] As a specific example, if a user inputs "I like casual style," "I like blue items," "I have several pairs of jeans," and also has emotional data such as "I'm in a good mood today," the generative AI model will suggest an outfit such as "a blue shirt, jeans, and white sneakers."

[0462] An example prompt is:

[0463] The user's preferred style is casual. The clothing they own is blue items and jeans. Their current emotional state is good. Based on this information, please suggest the best outfit for them.

[0464] Suggestion display and user interaction

[0465] Device: The suggested outfits are displayed on the user's smartphone or HMD. The user can review the suggested outfits and check detailed information (e.g., brand name, price, purchase link, etc.). Furthermore, if the user is not satisfied with the suggested outfits, they can request to change some items within the application.

[0466] Gathering feedback and improving the generative model

[0467] Server: Collects feedback entered by users on outfit suggestions. The collected feedback data is stored in a database and used to train the next generation model. This allows the generation model to continuously improve, resulting in more accurate suggestions in the future.

[0468] This system makes it possible to propose outfits that take into account the user's individual preferences and emotional state, significantly improving the user experience.

[0469] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0470] Step 1:

[0471] The user enters basic information and preference information

[0472] A user launches an application installed on a smartphone or head-mounted display (HMD) and inputs basic information (e.g., name, gender, height) and fashion preferences (e.g., favorite color, favorite style). The input information is temporarily stored in the application's local storage and then sent to a cloud server. A dataset containing the input data is formed.

[0473] Step 2:

[0474] Upload photos of clothing that users own

[0475] Users take photos of their clothing and upload them to the application. The uploaded image data is sent to a cloud server and subjected to image analysis. Specifically, the smartphone's camera application is launched, and the image is transferred to the server after it has been taken.

[0476] Step 3:

[0477] Collecting emotional states

[0478] To collect the user's current emotional state, the smartphone camera and the HMD's built-in sensors are activated to collect facial expression data and information from biometric sensors. The collected emotional data is also sent to a cloud server. Specifically, the application acquires data using the camera and sensors in real time.

[0479] Step 4:

[0480] Data analysis

[0481] The server analyzes the collected user preference information, photos of the clothing they own, and emotional data. The photos of the clothing are classified using the Google Cloud Vision API to determine the color, style, and type of each item. The emotional data is analyzed using IBM Watson Tone Analyzer, and the user's emotional state is quantified. The input data are image files, emotional data, and text information, and the output is the analysis results and feature vectors.

[0482] Step 5:

[0483] Feature Vector Generation

[0484] The server generates a feature vector for the user based on the analyzed preference information, clothing information, and emotional data. This feature vector contains numerical data corresponding to each attribute, such as color, style, item type, and emotional state. The input data is the analysis result, and the output is the feature vector.

[0485] Step 6:

[0486] Generating optimal coordination

[0487] Based on the generated feature vector and emotion data, the server inputs the feature vector into a generative AI model (e.g., OpenAI GPT-3) to generate the optimal outfit. An example of a prompt sentence is, "The user's preferred style is casual. The clothing they own is blue items and jeans. Their current emotional state is good. Please suggest the optimal outfit based on this information." The input data is the feature vector, and the output data is the outfit suggestion.

[0488] Step 7:

[0489] Displaying suggestions to the user

[0490] The generated outfit suggestions are displayed on the user's smartphone or HMD. The user can review the suggested outfits and check their details (e.g., brand name, price, and purchase link). The input data is the outfit suggestions, and the output data is the user's feedback.

[0491] Step 8:

[0492] Gathering feedback and improving the model

[0493] The server collects user ratings and correction requests for outfit suggestions. The collected feedback data is stored in a database and used to train the next generative model. This allows the generative model to be continuously improved, resulting in improved proposal accuracy from the next time onwards. The input data is user feedback, and the output data is updated model parameters.

[0494] 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.

[0495] 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.

[0496] 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.

[0497] [Second embodiment]

[0498] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0499] 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.

[0500] 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).

[0501] 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.

[0502] 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.

[0503] 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).

[0504] 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.

[0505] 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.

[0506] 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.

[0507] 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.

[0508] 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.

[0509] 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."

[0510] The present invention is a system that collects information on an individual's preferences and clothing possessions, and proposes optimal outfits using feature vectors generated based on the information. This system has the following main functions:

[0511] User Data Collection

[0512] User:

[0513] When using the system for the first time, users enter their basic information and fashion preferences. They can also upload photos of the clothes they own at home.

[0514] Device:

[0515] It provides an interface that displays the information entered by the user and the images uploaded on the screen, allowing the user to confirm the entered information.

[0516] server:

[0517] It receives the input data and stores it in a database, and also uses image analysis tools to analyze the uploaded photos of clothing and classify the characteristics of each item (color, shape, style, etc.).

[0518] Data analysis and feature vector generation

[0519] server:

[0520] The collected information is used to analyze the user's hobbies, preferences, and clothing characteristics. Based on the analysis results, a feature vector for the user is generated. This feature vector is made up of numerical data corresponding to each attribute, such as color, style, and type of item.

[0521] Generating optimal coordination

[0522] server:

[0523] The generated feature vectors are input into a generative model to generate optimal outfits. This generative model takes into account the user's preferences, the clothing they own, the current season, and specific events to suggest optimal outfit combinations.

[0524] example:

[0525] If a user inputs "I like the color blue," "I have three pairs of jeans," and "I like a casual style," the generative model will use this information to suggest outfits such as "a blue shirt, jeans, and white sneakers."

[0526] Suggestion display and user interaction

[0527] Device:

[0528] The generated outfit suggestions are displayed to the user, along with detailed information about each item (brand name, price, etc.), allowing the user to confirm the suggestions.

[0529] User:

[0530] Users can review the provided outfits, request to change some items if necessary, and even rate and provide feedback on the suggestions.

[0531] Gathering feedback and improving the generative model

[0532] server:

[0533] Collect user feedback, analyze the data, and retrain the generative model based on the feedback data to improve the accuracy of the suggestions.

[0534] example:

[0535] If the user rates the proposed outfit as "very satisfied," the server will reflect this information in future suggestions.

[0536] This system allows users to easily find the perfect outfit based on their preferences and the clothing they own. It can also suggest outfits for specific events or outfits to coordinate with other members of the household. This improves the user experience and provides personalized fashion suggestions.

[0537] The processing flow will be explained below.

[0538] Step 1:

[0539] User:

[0540] When users first access the system, they enter basic information and their fashion preferences, such as their favorite colors, styles, and brands, and also upload photos of the clothes they own.

[0541] Step 2:

[0542] Device:

[0543] The information entered and the image uploaded by the user are displayed on the screen for confirmation. The user can check the information entered and the image and make corrections as necessary.

[0544] Step 3:

[0545] server:

[0546] The system receives the data submitted by users and stores it in a database. Photos of uploaded clothing are then run through image analysis tools to classify the item's color, shape, style, and other characteristics.

[0547] Step 4:

[0548] server:

[0549] The collected information is analyzed to extract the user's hobbies, preferences, and clothing characteristics. These characteristics are then used to generate a feature vector, which consists of numerical data corresponding to attributes such as color, style, and item type.

[0550] Step 5:

[0551] server:

[0552] The generated feature vector is input into a generative model, which then generates the optimal outfit based on the user's feature vector. The model selects outfit combinations taking into account the user's preferences, clothing they own, the season, specific events, and other factors.

[0553] Step 6:

[0554] Device:

[0555] The generated outfit suggestions are displayed to the user, along with detailed information (such as brand name, price, and purchase link) so that the user can review the suggestions.

[0556] Step 7:

[0557] User:

[0558] Check the displayed outfits, request to change some items as needed, and enter your rating and feedback on the suggestions.

[0559] Step 8:

[0560] server:

[0561] The system analyzes the feedback collected from users and stores the evaluation data in a database.The system then retrains the generative model based on the feedback data to improve the accuracy of future suggestions.

[0562] By going through these steps, personalized and optimal coordination suggestions are provided to the user.

[0563] Example 1

[0564] 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."

[0565] Currently, it is not easy for individuals to find the optimal fashion coordination based on their own preferences and the clothing they own. Choosing the right outfit for a specific event or situation requires a lot of time and effort. It is also difficult to suggest coordinated outfits that are also harmonious with other members of the household. There is a need for a system that can solve these issues and easily provide personalized fashion suggestions to individuals.

[0566] 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.

[0567] In this invention, the server includes means for collecting information on personal preferences and clothing owned by the user, means for storing the collected information in a database and analyzing uploaded clothing images to classify the characteristics of each item, means for generating a feature vector for the user based on the collected information and the analyzed characteristics, means for inputting the feature vector into a generative model to generate an optimal outfit, means for displaying the generated outfit to the user and providing detailed information about each item, and means for collecting feedback from the user and retraining the generative model based on that data to improve the accuracy of suggestions. This enables the server to automatically suggest optimal outfits based on personal preferences and clothing owned by the user, making it possible to suggest outfits that are harmonious for specific events or with other members of the household.

[0568] "Personal preferences" refers to fashion trends, colors, styles, brands, etc. that a user recognizes as his or her own preferences.

[0569] "Clothing you own" refers to items such as clothes, accessories, and shoes that you already own.

[0570] "Means of collection" refers to the functions and interfaces that allow the system to capture information entered by users and images uploaded by users.

[0571] "Database" refers to a collection of electronic records that store and manage collected information and analytical data.

[0572] "Image Analysis Method" means software or algorithms that analyze uploaded photos of clothing to identify and classify the characteristics of each item (e.g., color, shape, style, etc.).

[0573] "Means of classification" refers to the function of categorizing each item based on the analyzed data.

[0574] A "feature vector" refers to a numerical representation of a user's preferences and the characteristics of items they own.

[0575] A "generative model" refers to a machine learning model or algorithm that takes a user's feature vector as input and generates the optimal outfit.

[0576] "Coordination" refers to suggestions for outfits that combine multiple items of clothing and accessories.

[0577] "Displaying means" refers to an interface for displaying the generated coordinates and their detailed information on the user's device.

[0578] "Means for collecting feedback" refers to a function that allows users to input their evaluations of proposed outfits and requests for changes.

[0579] "Means for retraining the generative model" refers to a process for improving the accuracy of the generative model and the quality of suggestions based on collected feedback data.

[0580] "Means for improving the accuracy of suggestions" refers to a series of processes or methods for improving the performance of the generative model and proposing outfits that are more suitable for the user.

[0581] "Particular events or situations" refers to specific occasions or settings, such as weddings, business meetings, or casual outings.

[0582] "Other members of the household" refers to people who live with the user, such as family members or roommates.

[0583] "Clothing suggestions" refers to suggesting appropriate clothing combinations for individual users and situations.

[0584] The present invention is a system that collects information on an individual's preferences and clothing possessions, and uses feature vectors generated based on the collected information to suggest optimal outfits. This system is implemented using the following hardware and software.

[0585] User:

[0586] When using the system for the first time, users use a device such as a smartphone or PC to enter their basic information (such as name, age, and gender) and fashion preferences (favorite colors, styles, and brands). They also take photos of the clothes they own and upload them to the system.

[0587] Device:

[0588] It provides an interface that displays user-entered information and uploaded images. This interface can be implemented as a web browser or a mobile application. For example, it can include operations such as uploading photos of clothing taken with a smartphone camera app.

[0589] server:

[0590] The server receives data entered by users and uploaded images of clothing and stores them in a database. The server uses image analysis tools (e.g., TensorFlow or OpenCV) to analyze the uploaded images and classify the characteristics of each item (color, shape, style, etc.). For example, it extracts information such as "blue shirt" or "jeans."

[0591] Next, the server generates a feature vector for the user based on the collected information and analysis results. This feature vector represents color, style, type of item, etc. as numerical data. For example, if a user inputs "I like the color blue," "I have three pairs of jeans," and "I like casual styles," the feature vector will be a numerical representation of these.

[0592] The server inputs this feature vector into a generative AI model (e.g., GPT-4 or BERT) to generate the optimal outfit. An example of a prompt sentence input to the model would be, "The user's characteristics are as follows: 1. Favorite color: blue, 2. Items owned: 3 pairs of jeans, 3. Style: casual. Please suggest the optimal outfit based on this information." Based on this information, the generative model suggests outfits such as "a blue shirt, jeans, and white sneakers."

[0593] The generated outfits are sent to the terminal and displayed to the user. Detailed information about each item (brand name, price, etc.) is provided for the user to review. The user can also enter their rating and feedback on the proposed outfits, and this feedback data is collected by the server.

[0594] Finally, the server analyzes the collected feedback data and retrains the generative model to improve the accuracy of the suggestions. For example, if a user rates a suggested outfit as "very satisfying," this information will be reflected in future suggestions. This allows the system to continuously provide optimal fashion suggestions based on the user's preferences and the clothes they own.

[0595] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0596] Step 1:

[0597] Entering and collecting user data

[0598] User:

[0599] Using a device such as a smartphone or PC, users enter their basic information (such as name, age, and gender) and fashion preferences (favorite colors, styles, and brands), and also take photos of clothing they own and upload them to the system.

[0600] input:

[0601] User's basic information, preferences, and photos of clothing

[0602] output:

[0603] The entered information and uploaded images are sent to the system.

[0604] Specific behavior:

[0605] Users open the app on their smartphone, select their favorite color and style, take a photo of the clothing they own, and press the upload button to send the photo to the system.

[0606] Step 2:

[0607] Data storage and image analysis

[0608] server:

[0609] It receives input data and uploaded images, stores them in a database, and uses image analysis tools (TensorFlow and OpenCV) to analyze the uploaded images and classify the characteristics of each item (color, shape, style, etc.).

[0610] input:

[0611] Basic information, preference information, and photos of clothing sent by the user

[0612] output:

[0613] User information and clothing characteristics data stored in a database

[0614] Specific behavior:

[0615] The server processes the images it receives using an analysis tool, extracts characteristic information such as "blue shirt" or "jeans," and stores this information in a database.

[0616] Step 3:

[0617] Feature Vector Generation

[0618] server:

[0619] The collected information and analyzed characteristic data are used to generate a feature vector for the user, which is expressed as numerical data such as color, style, and item type.

[0620] input:

[0621] User basic information, preference information, and clothing characteristics data

[0622] output:

[0623] User feature vector

[0624] Specific behavior:

[0625] The server extracts user information and characteristic data from the database and generates a feature vector such as "Color: Blue, Style: Casual, Item: 3 pairs of jeans."

[0626] Step 4:

[0627] Generating optimal coordination

[0628] server:

[0629] The generated feature vector is input into a generative AI model to generate optimal outfits. The generative model takes into account the user's preferences, the clothing they own, the current season, and specific events to suggest outfit combinations.

[0630] input:

[0631] User feature vector

[0632] output:

[0633] Optimal coordination suggestions

[0634] Specific behavior:

[0635] The server inputs the feature vector into a generative AI model and generates outfits such as "blue shirt, jeans, and white sneakers."

[0636] Example prompt sentence:

[0637] "The user's characteristics are as follows: 1. Favorite color: Blue, 2. Owned items: Three pairs of jeans, 3. Style: Casual. Please suggest the best outfit based on these."

[0638] Step 5:

[0639] Coordination display and user interaction

[0640] Device:

[0641] The generated coordination suggestions are displayed to the user, and detailed information about each item (brand name, price, etc.) is provided.

[0642] User:

[0643] Check the proposed outfits, request to change some items as needed, and enter your rating and feedback on the suggestions.

[0644] input:

[0645] Coordination suggestions sent from the server

[0646] output:

[0647] User Review and Feedback

[0648] Specific behavior:

[0649] Users can check the outfit on their smartphone or PC screen and send feedback such as "very satisfied."

[0650] Step 6:

[0651] Gathering feedback and improving the generative model

[0652] server:

[0653] It collects user feedback, analyzes that data, and retrains the generative model to improve the accuracy of future suggestions.

[0654] input:

[0655] User feedback data

[0656] output:

[0657] Improved generative models

[0658] Specific behavior:

[0659] The server receives the feedback of "very satisfied" and uses that information to retrain the generative model and reflect it in the next proposal.

[0660] This allows the entire system to continue to provide optimal fashion coordination based on the user's information.

[0661] (Application example 1)

[0662] 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."

[0663] It is difficult for users to find the perfect outfit based on their preferences and the clothes they own in a physical store. Furthermore, due to the lack of an environment where users can visually check the outfits provided, it is difficult for users to grasp the actual appearance of the outfit suggestions. Furthermore, if these outfit suggestions are not improved based on user feedback, the accuracy of the suggestions may decrease.

[0664] 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.

[0665] In this invention, the server includes: means for collecting information on personal preferences and clothing owned by the user; means for analyzing the collected information and generating a feature vector for the user; means for using the feature vector as an input and generating an optimal outfit using a generative model; means for displaying the generated outfit to the user; means for collecting feedback from the user and continuously improving the generative model; means for scanning products in a store and acquiring product information that matches the user's feature vector; means for using an augmented reality algorithm to visually display outfit suggestions in real space; and means for displaying detailed information for each item of the outfit suggestions. This allows the user to visually confirm the optimal outfit based on their preferences in a physical store and make adjustments as necessary.

[0666] "Personal preferences" refers to a user's fashion preferences, such as preferred colors, styles, brands, etc.

[0667] "Information about clothing owned" is detailed information about clothing items owned by the user, such as clothes, shoes, and accessories.

[0668] A "feature vector" is a numerical representation of a user's preferences and the characteristics of the clothing they own.

[0669] A "generative model" is a machine learning algorithm that takes a user's feature vector as input and generates the optimal outfit.

[0670] "Feedback" refers to information such as user evaluations, opinions, and impressions regarding suggestions.

[0671] "Continuous improvement" is the process of improving the accuracy of the generative model based on collected feedback.

[0672] "Scanning products in a store" means analyzing products in the store using image recognition technology and obtaining information about them.

[0673] "Augmented reality algorithm" is a technology that displays digital information overlaid on real space.

[0674] "Visually displaying coordinated outfit suggestions" means displaying the suggested coordinated outfits so that the user can actually visually confirm them.

[0675] "Detailed information" refers to detailed information such as the brand name, price, and size of each product.

[0676] MODE FOR CARRYING OUT THE INVENTION

[0677] This invention is a system that utilizes information on personal preferences and clothing owned by a customer to propose optimal outfits in physical stores. Specific implementation procedures are described below.

[0678] Hardware and Software Configuration

[0679] (server)

[0680] The server has the following main responsibilities:

[0681] 1. Information collection: Collects basic information about the user, their fashion preferences, and the clothing they own. Users use their smartphones or computers to enter text and upload images.

[0682] 2. Data analysis: Analyze the collected data and generate a feature vector for the user. Image analysis uses image recognition tools such as OpenCV.

[0683] 3. Coordination generation: The generated feature vector is input into a machine learning model (e.g., TensorFlow) to generate the optimal coordination.

[0684] 4. Model Improvement: Collect user feedback to continuously improve the generative model. Feedback is provided by the user via smart glasses or a head-mounted display.

[0685] (Terminal)

[0686] The terminal has the following main roles:

[0687] 1. Information display: The generated outfit suggestions are visually displayed to the user. Using smart glasses or a head-mounted display, augmented reality algorithms are applied to in-store product images, overlaying digital information on them.

[0688] 2. Product scanning: Scan products in the store with a camera and send the information to the server, which retrieves product information that matches the user's feature vector.

[0689] 3. Displaying detailed information: Displaying detailed information (brand name, price, size, etc.) for each item in the suggested outfits to the user, making it easier for the user to select suggested items.

[0690] (User)

[0691] Users can use the system in the following ways:

[0692] 1. Enter your basic information and clothing: Enter your basic information, fashion preferences, and clothing information through the app. Specifically, upload photos of your favorite colors, styles, and items you own.

[0693] 2. Wearing smart glasses: After entering a physical store, customers put on smart glasses or a head-mounted display and scan the products in the store.

[0694] 3. Check your outfit: Check the outfit suggestions displayed on the smart glasses and check the details of each item.

[0695] 4. Providing feedback: Feedback your evaluation and opinions on the coordination proposal to the system.

[0696] Specific examples

[0697] Suppose a user enters a physical store, their favorite color is black, and they like a casual style. They own a black jacket, white sneakers, and a blue denim shirt. The user puts on smart glasses and scans the products in the store. The server generates a feature vector for the user and inputs it into a machine learning model to suggest the optimal outfit. In this case, the suggested outfit would be "a black jacket, white sneakers, and a blue denim shirt."

[0698] Prompt Sentence Examples

[0699] "Users' favorite color is black, they like casual style, and they own multiple pairs of jeans."

[0700] "I own a black jacket, white sneakers, and a blue denim shirt."

[0701] In this way, the system can visually suggest optimal outfits based on the user's preferences in a physical store.

[0702] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0703] Step 1:

[0704] Users use their smartphones or computers to enter their basic information, fashion preferences, and information about the clothing they own. The information entered includes text data and image data, and this information becomes the input for the system.

[0705] Step 2:

[0706] The server receives the data sent by the user and stores it in a database. At this time, the image data is analyzed using image recognition tools such as OpenCV to extract characteristics such as color, shape, and style. This data processing provides the analysis results of the user's preferences and detailed information about the clothing they own.

[0707] Step 3:

[0708] The server generates a feature vector for the user based on the collected and analyzed information. The feature vector is a numerical representation of the user's preference data (favorite color, preferred style, etc.) and the characteristics of the clothing they own (color, shape, style). Once the feature vector is generated, it becomes the input data for the generative model.

[0709] Step 4:

[0710] The server uses the generated feature vector to generate the optimal outfit using a machine learning algorithm (e.g., TensorFlow). The generative model proposes the optimal combination of items based on the user's feature vector and the data learned by the model. This process generates the optimal outfit.

[0711] Step 5:

[0712] The terminal receives the outfit suggestions generated by the server and displays them to the user. Specifically, augmented reality algorithms are used in smart glasses or head-mounted displays to overlay digital information onto in-store product images. The user can visually confirm the outfit suggestions by combining real space and digital information.

[0713] Step 6:

[0714] The user wears smart glasses or a head-mounted display and scans the products in the store. This displays product information in the store on the device in real time, and product information that matches the user's feature vector is sent to the server, where the product information in the store is added as input data.

[0715] Step 7:

[0716] Based on the scanned product information, the device identifies products that match the user's feature vector and displays product details based on the generated coordination suggestions. Specifically, detailed information such as brand name, price, and size is displayed, allowing the user to make product selections.

[0717] Step 8:

[0718] The user sends feedback on the outfit suggestions from their device to the server. The feedback includes evaluations, opinions, and impressions of the outfit suggestions. This becomes new input data.

[0719] Step 9:

[0720] The server analyzes the feedback collected from users and retrains the generative model. Based on the feedback data, it adjusts the parameters of the generative model to improve the accuracy of future outfit suggestions. This process continuously improves the performance of the entire system.

[0721] 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.

[0722] The present invention is a system that collects information on an individual's preferences and clothing possessions, and proposes optimal outfits using feature vectors generated based on the collected information, and further combines it with an emotion engine that recognizes the user's emotions to provide more personalized suggestions. The following is a specific embodiment of the system.

[0723] User data and sentiment collection

[0724] User:

[0725] When accessing the system for the first time, users enter basic information and fashion preferences. They also upload photos of their clothing. While using the system, users can input their emotional state in real time or detect their emotions using the device's built-in camera and sensors.

[0726] Device:

[0727] It provides an interface that displays and allows users to confirm information they have entered, images they have uploaded, and emotional data on the screen.

[0728] server:

[0729] The system receives data sent by the user (preference information, photos of clothing owned, and emotional data) and stores it in a database. It uses an image analysis tool to classify the clothing images. It also uses an emotion engine to analyze the user's emotions.

[0730] Data analysis and feature vector generation

[0731] server:

[0732] The collected preference information, clothing characteristics, and emotional data are analyzed to generate a feature vector for the user. This feature vector is composed of numerical data corresponding to attributes such as color, style, and item type. Furthermore, based on the emotional data, weighting is applied to reflect the user's current mood.

[0733] Generating optimal coordination

[0734] server:

[0735] The generated feature vector is input into a generative model to generate optimal outfits, taking into account the user's emotional state. The generative model then suggests outfit combinations based on the user's preferences, clothing, season, specific events, and emotional state.

[0736] example:

[0737] If a user inputs "I like the color blue," "I have three pairs of jeans," "I like casual styles," and the emotion engine recognizes that "I'm in a good mood today," the generative model will suggest an outfit such as "a blue shirt, jeans, and white sneakers." However, if the emotion engine recognizes that "I'm feeling down today," it will suggest a more relaxing style and color combination.

[0738] Suggestion display and user interaction

[0739] Device:

[0740] The generated outfit suggestions are displayed to the user, along with detailed information (such as brand name, price, and purchase link) so that the user can review the suggestions.

[0741] User:

[0742] Check the displayed outfits, request to change some items as needed, and enter your rating and feedback on the suggestions.

[0743] Gathering feedback and improving the generative model

[0744] server:

[0745] The system analyzes feedback collected from users and stores the evaluation data in a database. The system retrains the generative model based on the feedback data to improve the accuracy of future suggestions.

[0746] example:

[0747] If a user rates a suggested outfit as "very satisfied," the server will reflect this information in future suggestions. It also analyzes how the user's emotional data influences future suggestions.

[0748] This system not only provides optimal outfits based on the user's preferences and the clothing they own, but also takes the user's emotions into account, allowing for more personalized suggestions, improving the user experience.

[0749] The processing flow will be explained below.

[0750] Step 1:

[0751] User:

[0752] When accessing the system for the first time, users enter their basic information (name, gender, age, etc.) and fashion preferences (favorite colors, styles, brands, etc.), and also upload several photos of clothing they own.

[0753] Step 2:

[0754] Device:

[0755] A screen will be displayed where the user can confirm the basic information and preference information they have entered, as well as the photos of their clothing they have uploaded. The user can check the information they have entered and the images and make any necessary corrections.

[0756] Step 3:

[0757] server:

[0758] It receives data sent by users and stores it in a database, runs image analysis tools on uploaded clothing photos to classify characteristics such as color, shape, and style, and activates an emotion engine to collect emotional data.

[0759] Step 4:

[0760] server:

[0761] While the user is using the system, the emotion engine analyzes the user's facial expressions and input data in real time to infer their current emotional state. The inferred emotional data is stored in a database.

[0762] Step 5:

[0763] server:

[0764] The collected preference information, clothing characteristics, and emotional data are analyzed to generate a feature vector for the user, which includes numerical data representing color, style, item type, and emotional state.

[0765] Step 6:

[0766] server:

[0767] The generated feature vector is input into a generative model to generate optimal outfits that take into account the user's emotional state. The generative model selects outfit combinations by comprehensively evaluating the user's preferences, clothing, season, specific events, and emotional state.

[0768] example:

[0769] If a user inputs "I like the color blue," "I have three pairs of jeans," and "I like casual style," and the emotion engine recognizes that "I'm in a good mood today," the generative model will suggest an outfit consisting of "a blue shirt, jeans, and white sneakers."

[0770] Step 7:

[0771] Device:

[0772] The generated outfit suggestions are displayed to the user, along with detailed information (such as brand name, price, and purchase link) so that the user can review the suggestions.

[0773] Step 8:

[0774] User:

[0775] Check the displayed outfits, request to change some items as needed, and enter your rating and feedback on the suggestions.

[0776] Step 9:

[0777] server:

[0778] The system analyzes feedback collected from users and stores the evaluation data in a database. The system retrains the generative model based on the feedback data to improve the accuracy of future suggestions.

[0779] example:

[0780] If a user rates a suggested outfit as "very satisfying," the server will reflect this information in future suggestions. It will also analyze how the emotional data influenced the suggestions and use this information to improve them.

[0781] Through these steps, personalized and optimal outfit suggestions are provided to the user. Furthermore, the introduction of an emotion engine enables more personalized suggestions that take into account the user's emotional state, improving the user experience.

[0782] Example 2

[0783] 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."

[0784] Many systems exist that collect information about an individual's fashion preferences and clothing possessions and then suggest optimal outfits based on that information. However, these systems often fail to take into account the user's emotional state, resulting in low user satisfaction. Furthermore, these systems lack the functionality to continuously improve the system based on feedback. This means that consistent results cannot be expected with each use.

[0785] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0786] In this invention, the server includes: means for collecting information on personal preferences and clothing owned by the user; means for providing an interface for inputting preference information, clothing information, and emotional data; means for analyzing the collected information and generating a feature vector for the user; means for analyzing the feature vector and emotional data and weighting the feature vector to reflect the user's current emotional state; means for using the feature vector as input and generating an optimal outfit using a generative model; means for displaying the generated outfit to the user and providing detailed information; and means for collecting user feedback and continuously improving the generative model. This enables more personalized outfit suggestions that take into account the user's preferences and current emotional state. Furthermore, by continuously improving the system based on user feedback, high levels of satisfaction can be maintained over the long term.

[0787] "Personal preferences" refers to information about a user's fashion preferences, such as their favorite colors, styles, and brands.

[0788] "Clothes owned" is a list of clothes owned by the user and their detailed information (color, size, brand, frequency of use, etc.).

[0789] "Emotion data" is information that represents the user's current mood or emotional state, and is acquired through sensors or user input.

[0790] A "feature vector" is a data set that quantifies a user's preference information, characteristics of clothing owned, and emotional data, and is composed of numerical data corresponding to each attribute.

[0791] A "generative model" is a machine learning algorithm or artificial intelligence model that takes a user's feature vector as input and generates the optimal outfit.

[0792] A "coordination" is a combination of clothing suggested by a generative model that takes into account the user's preferences and emotional state.

[0793] "Feedback" refers to information about satisfaction with the evaluations, comments, and suggestions that users make to the system.

[0794] An "interface" is an operation screen or input means that allows a user to input information into the system and confirm suggestions from the system.

[0795] The present invention is a system that collects information on personal preferences and clothing owned by a user, generates feature vectors based on the collected information, and then recognizes the user's emotions to suggest optimal outfits. This system is implemented as follows.

[0796] User data and sentiment collection

[0797] User:

[0798] When accessing the system for the first time, users enter basic information (such as name, age, and gender) and fashion preferences (favorite color, preferred style, etc.). They also upload photos of clothing they own. While using the system, users can input their own emotional state or have their emotions detected using the device's built-in camera and sensors.

[0799] Specifically, users take a photo of their clothing using the camera on their smartphone or PC and upload it to the system. To input their emotional state, a special form is displayed with options, allowing them to select states such as "happy," "sad," and "tired" in real time.

[0800] Device:

[0801] It provides an interface for users to check the information they enter and the images of their clothing they upload, and also has the ability to detect emotions using cameras and sensors.

[0802] Specifically, the device detects the user's face in real time and analyzes their facial expressions, and the analysis results are displayed to the user on a confirmation screen.

[0803] server:

[0804] The system receives preference information, photos of clothing owned, and emotion data sent by the user and stores them in a database. It uses an image analysis tool (e.g., OpenCV) to classify the clothing images and an emotion engine (e.g., facial recognition technology) to analyze the user's emotions.

[0805] Specifically, the server uses the photos of clothing received to automatically identify the color, pattern, and item (shirt, pants, etc.), converts them into text information, and stores it in a database.

[0806] Data analysis and feature vector generation

[0807] server:

[0808] The collected preference information, clothing characteristics, and emotional data are analyzed, and a feature vector for the user is generated based on this data. This feature vector is composed of numerical data corresponding to attributes such as color, style, and item type. Furthermore, weighting is performed based on the emotional data to reflect the user's current mood.

[0809] Specifically, the server analyzes the data, quantifies features such as "I like the color blue," "I have three pairs of jeans," and "I'm in a good mood today," and uses this data to generate a feature vector.

[0810] Generating optimal coordination

[0811] server:

[0812] The generated feature vectors are input into a generative AI model (e.g., a generative model) to generate optimal outfits taking into account the user's emotional state. This generative model then suggests outfit combinations taking into account the user's preferences, clothing, season, specific events, and emotional state.

[0813] Specific examples of prompts are as follows:

[0814] User Information:

[0815] Preferences: I like the color blue

[0816] Clothing: 3 pairs of jeans, 1 white shirt, 2 blue shirts

[0817] Style: Casual

[0818] Emotional state: Feeling good

[0819] Based on this information, we will suggest the best outfit for you.

[0820] Suggestion display and user interaction

[0821] Device:

[0822] The generated outfit suggestions are displayed to the user, along with detailed information (such as brand name, price, and purchase link) so that the user can review the suggestions.

[0823] Specifically, the device displays images and detailed information of outfits on the screen, allowing users to check them. By clicking on the selection options or links, users can be taken to the purchase page for each item.

[0824] User:

[0825] Check the displayed outfits, request to change some items as needed, and enter your rating and feedback on the suggestions.

[0826] Specifically, when a user makes a change request, such as "I want the shoes to be black," the system will again generate the optimal proposal. The user can also select "Very Satisfied," "Satisfied," or "Dissatisfied" in the evaluation form and enter their comments.

[0827] Gathering feedback and improving the generative model

[0828] server:

[0829] The system analyzes the feedback collected from users and stores the evaluation data in a database, which is used to retrain the generative model and improve the accuracy of future suggestions.

[0830] Specifically, the server analyzes the feedback data, adjusts the parameters of the generative AI model based on the evaluation scores and comments, and retrains it to improve the accuracy of the next proposal.

[0831] This system not only provides optimal outfits based on the user's preferences and the clothes they own, but also takes into account the user's emotions to enable more personalized suggestions. Furthermore, by continuously improving the system based on user feedback, it is possible to maintain high levels of satisfaction over the long term.

[0832] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0833] Step 1:

[0834] User Data Collection

[0835] Specific behavior:

[0836] First, users enter basic information and fashion preferences into the system and upload multiple photos of clothing they own.

[0837] Input: User basic information, preferences, and clothing photos.

[0838] Output: User information and uploaded clothing photo data sent to the server.

[0839] The server receives the data sent by the user (basic information, preference information, and photos of clothing owned) and stores it in a database.

[0840] Specific behavior:

[0841] The server receives the data and stores it in a database, storing information such as name, age, gender, preferred colors and styles, and uploaded photos of the clothing.

[0842] Input: Basic information, preferences, and clothing photos received from the user.

[0843] Output: User dataset stored in a database.

[0844] Step 2:

[0845] Collecting Emotional Data

[0846] Specific behavior:

[0847] Users can input their emotional state in real time or use the device's camera or sensors to detect emotions.

[0848] Input: User's emotional state (or device-detected emotional data).

[0849] Output: Emotion data sent to the server.

[0850] The terminal displays the emotional state data entered by the user or the detected emotional data on the screen and provides a confirmation interface.

[0851] Specific behavior:

[0852] The device uses cameras and sensors to detect the user's face in real time, analyzes their facial expressions, and displays the analysis results to the user on a confirmation screen.

[0853] Input: User's emotional state (or device-detected emotional data).

[0854] Output: An emotional state confirmation interface displayed on the screen.

[0855] The server receives the emotion data sent by the user, stores it in a database, and analyzes the emotion using an emotion engine.

[0856] Specific behavior:

[0857] The server uses an emotion analysis tool to analyze the user's emotion data and stores the results in a database.

[0858] Input: Emotion data received from the user.

[0859] Output: Sentiment analysis results stored in a database.

[0860] Step 3:

[0861] Data analysis and feature vector generation

[0862] Specific behavior:

[0863] The server analyzes the collected preference information, clothing characteristics, and emotional data to generate a feature vector for the user.

[0864] Input: Preference information stored in the database, characteristics of clothing owned, and emotional data.

[0865] Output: A feature vector for the user.

[0866] Based on the analyzed data, the server generates numerical data corresponding to each attribute, such as color, style, and item type, and also weights the data based on the emotion data to reflect the user's current mood.

[0867] Specific behavior:

[0868] The server quantifies the data, assigning a score to color preference (for example, red = 2, blue = 5, green = 1) and generates a feature vector. At the same time, it assigns weights based on the emotional data (for example, good mood = 1.2, bad mood = 0.8).

[0869] Input: Analyzed preference information, clothing characteristics, and emotional data.

[0870] Output: A quantified feature vector.

[0871] Step 4:

[0872] Generating optimal coordination

[0873] Specific behavior:

[0874] The server inputs the generated feature vector into a generative AI model and generates the optimal outfit, taking into account the user's emotional state.

[0875] Input: User feature vector.

[0876] Output: The optimal coordinates generated by the generative AI model.

[0877] The generative model suggests outfit combinations based on the user's preferences, clothing, season, specific events, and emotional state.

[0878] Specific prompt examples:

[0879] User Information:

[0880] Preferences: I like the color blue

[0881] Clothing: 3 pairs of jeans, 1 white shirt, 2 blue shirts

[0882] Style: Casual

[0883] Emotional state: Feeling good

[0884] Based on this information, we will suggest the best outfit for you.

[0885] Specific behavior:

[0886] The server sends a prompt to the AI ​​model, which then generates the optimal coordinates based on this.

[0887] Input: User feature vector, emotional state.

[0888] Output: The optimal coordinates suggested to the user.

[0889] Step 5:

[0890] Displaying outfit suggestions

[0891] Specific behavior:

[0892] The device displays the generated outfit suggestions to the user, along with detailed information (such as brand name, price, and purchase link) so the user can review the suggestions.

[0893] Input: The generated coordinates.

[0894] Output: Coordination suggestions and detailed information displayed on the device screen.

[0895] Specifically, the device displays images and detailed information of outfits on the screen, allowing users to check them. By clicking on the selection options or links, users can be taken to the purchase page for each item.

[0896] Input: Generated coordinates, detailed information.

[0897] Output: Coordination suggestions and detailed information displayed on the device screen.

[0898] Step 6:

[0899] Gathering user feedback

[0900] Specific behavior:

[0901] The user can check the proposed outfits, request to change some items as needed, and enter their ratings and feedback on the suggestions.

[0902] Input: Proposed coordinates, user feedback.

[0903] Output: User feedback sent to the server.

[0904] Specifically, the user makes a change request, such as "I want the shoes to be black," and the system receives it and makes a new suggestion. The user also selects "Very Satisfied," "Satisfied," or "Dissatisfied" in the evaluation form and enters comments.

[0905] Input: User feedback.

[0906] Output: Feedback data stored on the server.

[0907] Step 7:

[0908] Improving generative models

[0909] Specific behavior:

[0910] The server analyzes user feedback and stores the evaluation data in a database, which is used to retrain the generative model and improve the accuracy of future suggestions.

[0911] Input: Feedback data from users.

[0912] Output: An improved generative AI model.

[0913] Specifically, the server analyzes the feedback data, adjusts the parameters of the generative AI model based on the evaluation scores and comments, and retrains it to improve the accuracy of the next proposal.

[0914] Input: Feedback data.

[0915] Output: The updated AI model.

[0916] (Application example 2)

[0917] 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."

[0918] Conventional outfit suggestion systems can make suggestions based on a user's personal preferences and the clothing they own, but they cannot take the user's emotional state into account, making it impossible to provide optimal outfits that match the user's mood and psychological state. Therefore, to further improve the user experience, personalized suggestions that take the user's emotional state into account are needed.

[0919] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0920] In this invention, the server includes means for collecting information on the user's preferences and clothing possessions, means for collecting the user's emotional state, and means for analyzing the collected information and emotional state to generate a feature vector of the user, thereby enabling more personalized and optimal outfit suggestions that take into account the user's preferences and current emotional state.

[0921] The "means for collecting information on personal preferences and clothing owned" refers to a device or method for collecting information on fashion preferences entered by a user and photos and detailed information on clothing owned by the user.

[0922] "Means for collecting a user's emotional state" means a device or method for detecting and recording a user's emotional or psychological state in real time, including, for example, biometric analysis using cameras or sensors.

[0923] "Means for analyzing collected information and emotional state and generating a feature vector of the user" refers to a device or method that converts the user's fashion trends and current emotions into numerical data based on the collected user preference information, clothing information, and emotional data, and expresses them as a feature vector.

[0924] A "means for generating optimal outfits using a generative model" is a device or method that inputs a user's feature vector into a generative AI model and, from the results, suggests optimal clothing combinations based on the user's preferences and emotional state.

[0925] The "means for displaying the generated coordinated outfits to the user" refers to a device or method for displaying the proposed clothing combinations so that the user can check them and select or modify them.

[0926] "Means for collecting user feedback and continuously improving the generative model" refers to a device or method that collects user ratings and opinions on the proposed outfits, and then uses that data to retrain the generative model and improve its accuracy.

[0927] This invention is a system that proposes optimal outfits that take into account a user's emotional state based on information about the user's fashion preferences and the clothing they own. The system is realized by the following steps.

[0928] User data and sentiment collection

[0929] User: The user launches an application installed on their smartphone or head-mounted display (HMD) and inputs basic information and fashion preferences. They also upload photos of their clothing through the application. Furthermore, their emotional state is collected in real time using the smartphone camera and the HMD's built-in sensors.

[0930] Data analysis and feature vector generation

[0931] Server: The collected user preference information, clothing information, and emotional data are sent to a cloud server. On the server side, the uploaded clothing images are analyzed using the Google Cloud Vision API to classify the type, color, and style of the clothing. Meanwhile, the emotional data is analyzed using IBM Watson Tone Analyzer. Next, a feature vector for the user is generated based on this data. This feature vector represents the color, style, type of item, emotional state, and other factors as numerical data.

[0932] Generating optimal coordination

[0933] Server: The generated feature vectors and emotion data are input into a generative AI model (e.g., OpenAI GPT-3) to generate optimal outfits based on the user's preferences and current emotional state. The generated outfit suggestions take into account the user's preferences, clothing they own, the season, specific events, and their emotional state to suggest outfit combinations.

[0934] As a specific example, if a user inputs "I like casual style," "I like blue items," "I have several pairs of jeans," and also has emotional data such as "I'm in a good mood today," the generative AI model will suggest an outfit such as "a blue shirt, jeans, and white sneakers."

[0935] An example prompt is:

[0936] The user's preferred style is casual. The clothing they own is blue items and jeans. Their current emotional state is good. Based on this information, please suggest the best outfit for them.

[0937] Suggestion display and user interaction

[0938] Device: The suggested outfits are displayed on the user's smartphone or HMD. The user can review the suggested outfits and check detailed information (e.g., brand name, price, purchase link, etc.). Furthermore, if the user is not satisfied with the suggested outfits, they can request to change some items within the application.

[0939] Gathering feedback and improving the generative model

[0940] Server: Collects feedback entered by users on outfit suggestions. The collected feedback data is stored in a database and used to train the next generation model. This allows the generation model to continuously improve, resulting in more accurate suggestions in the future.

[0941] This system makes it possible to propose outfits that take into account the user's individual preferences and emotional state, significantly improving the user experience.

[0942] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0943] Step 1:

[0944] The user enters basic information and preference information

[0945] A user launches an application installed on a smartphone or head-mounted display (HMD) and inputs basic information (e.g., name, gender, height) and fashion preferences (e.g., favorite color, favorite style). The input information is temporarily stored in the application's local storage and then sent to a cloud server. A dataset containing the input data is formed.

[0946] Step 2:

[0947] Upload photos of clothing that users own

[0948] Users take photos of their clothing and upload them to the application. The uploaded image data is sent to a cloud server and subjected to image analysis. Specifically, the smartphone's camera application is launched, and the image is transferred to the server after it has been taken.

[0949] Step 3:

[0950] Collecting emotional states

[0951] To collect the user's current emotional state, the smartphone camera and the HMD's built-in sensors are activated to collect facial expression data and information from biometric sensors. The collected emotional data is also sent to a cloud server. Specifically, the application acquires data using the camera and sensors in real time.

[0952] Step 4:

[0953] Data analysis

[0954] The server analyzes the collected user preference information, photos of the clothing they own, and emotional data. The photos of the clothing are classified using the Google Cloud Vision API to determine the color, style, and type of each item. The emotional data is analyzed using IBM Watson Tone Analyzer, and the user's emotional state is quantified. The input data are image files, emotional data, and text information, and the output is the analysis results and feature vectors.

[0955] Step 5:

[0956] Feature Vector Generation

[0957] The server generates a feature vector for the user based on the analyzed preference information, clothing information, and emotional data. This feature vector contains numerical data corresponding to each attribute, such as color, style, item type, and emotional state. The input data is the analysis result, and the output is the feature vector.

[0958] Step 6:

[0959] Generating optimal coordination

[0960] Based on the generated feature vector and emotion data, the server inputs the feature vector into a generative AI model (e.g., OpenAI GPT-3) to generate the optimal outfit. An example of a prompt sentence is, "The user's preferred style is casual. The clothing they own is blue items and jeans. Their current emotional state is good. Please suggest the optimal outfit based on this information." The input data is the feature vector, and the output data is the outfit suggestion.

[0961] Step 7:

[0962] Displaying suggestions to the user

[0963] The generated outfit suggestions are displayed on the user's smartphone or HMD. The user can review the suggested outfits and check their details (e.g., brand name, price, and purchase link). The input data is the outfit suggestions, and the output data is the user's feedback.

[0964] Step 8:

[0965] Gathering feedback and improving the model

[0966] The server collects user ratings and correction requests for outfit suggestions. The collected feedback data is stored in a database and used to train the next generative model. This allows the generative model to be continuously improved, resulting in improved proposal accuracy from the next time onwards. The input data is user feedback, and the output data is updated model parameters.

[0967] 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.

[0968] 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.

[0969] 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.

[0970] [Third embodiment]

[0971] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0972] 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.

[0973] 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).

[0974] 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.

[0975] 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.

[0976] 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).

[0977] 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.

[0978] 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.

[0979] 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.

[0980] 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.

[0981] 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.

[0982] 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."

[0983] The present invention is a system that collects information on an individual's preferences and clothing possessions, and proposes optimal outfits using feature vectors generated based on the information. This system has the following main functions:

[0984] User Data Collection

[0985] User:

[0986] When using the system for the first time, users enter their basic information and fashion preferences. They can also upload photos of the clothes they own at home.

[0987] Device:

[0988] It provides an interface that displays the information entered by the user and the images uploaded on the screen, allowing the user to confirm the entered information.

[0989] server:

[0990] It receives the input data and stores it in a database, and also uses image analysis tools to analyze the uploaded photos of clothing and classify the characteristics of each item (color, shape, style, etc.).

[0991] Data analysis and feature vector generation

[0992] server:

[0993] The collected information is used to analyze the user's hobbies, preferences, and clothing characteristics. Based on the analysis results, a feature vector for the user is generated. This feature vector is made up of numerical data corresponding to each attribute, such as color, style, and type of item.

[0994] Generating optimal coordination

[0995] server:

[0996] The generated feature vectors are input into a generative model to generate optimal outfits. This generative model takes into account the user's preferences, the clothing they own, the current season, and specific events to suggest optimal outfit combinations.

[0997] example:

[0998] If a user inputs "I like the color blue," "I have three pairs of jeans," and "I like a casual style," the generative model will use this information to suggest outfits such as "a blue shirt, jeans, and white sneakers."

[0999] Suggestion display and user interaction

[1000] Device:

[1001] The generated outfit suggestions are displayed to the user, along with detailed information about each item (brand name, price, etc.), allowing the user to confirm the suggestions.

[1002] User:

[1003] Users can review the provided outfits, request to change some items if necessary, and even rate and provide feedback on the suggestions.

[1004] Gathering feedback and improving the generative model

[1005] server:

[1006] Collect user feedback, analyze the data, and retrain the generative model based on the feedback data to improve the accuracy of the suggestions.

[1007] example:

[1008] If the user rates the proposed outfit as "very satisfied," the server will reflect this information in future suggestions.

[1009] This system allows users to easily find the perfect outfit based on their preferences and the clothing they own. It can also suggest outfits for specific events or outfits to coordinate with other members of the household. This improves the user experience and provides personalized fashion suggestions.

[1010] The processing flow will be explained below.

[1011] Step 1:

[1012] User:

[1013] When users first access the system, they enter basic information and their fashion preferences, such as their favorite colors, styles, and brands, and also upload photos of the clothes they own.

[1014] Step 2:

[1015] Device:

[1016] The information entered and the image uploaded by the user are displayed on the screen for confirmation. The user can check the information entered and the image and make corrections as necessary.

[1017] Step 3:

[1018] server:

[1019] The system receives the data submitted by users and stores it in a database. Photos of uploaded clothing are then run through image analysis tools to classify the item's color, shape, style, and other characteristics.

[1020] Step 4:

[1021] server:

[1022] The collected information is analyzed to extract the user's hobbies, preferences, and clothing characteristics. These characteristics are then used to generate a feature vector, which consists of numerical data corresponding to attributes such as color, style, and item type.

[1023] Step 5:

[1024] server:

[1025] The generated feature vector is input into a generative model, which then generates the optimal outfit based on the user's feature vector. The model selects outfit combinations taking into account the user's preferences, clothing they own, the season, specific events, and other factors.

[1026] Step 6:

[1027] Device:

[1028] The generated outfit suggestions are displayed to the user, along with detailed information (such as brand name, price, and purchase link) so that the user can review the suggestions.

[1029] Step 7:

[1030] User:

[1031] Check the displayed outfits, request to change some items as needed, and enter your rating and feedback on the suggestions.

[1032] Step 8:

[1033] server:

[1034] The system analyzes the feedback collected from users and stores the evaluation data in a database.The system then retrains the generative model based on the feedback data to improve the accuracy of future suggestions.

[1035] By going through these steps, personalized and optimal coordination suggestions are provided to the user.

[1036] Example 1

[1037] 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."

[1038] Currently, it is not easy for individuals to find the optimal fashion coordination based on their own preferences and the clothing they own. Choosing the right outfit for a specific event or situation requires a lot of time and effort. It is also difficult to suggest coordinated outfits that are also harmonious with other members of the household. There is a need for a system that can solve these issues and easily provide personalized fashion suggestions to individuals.

[1039] 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.

[1040] In this invention, the server includes means for collecting information on personal preferences and clothing owned by the user, means for storing the collected information in a database and analyzing uploaded clothing images to classify the characteristics of each item, means for generating a feature vector for the user based on the collected information and the analyzed characteristics, means for inputting the feature vector into a generative model to generate an optimal outfit, means for displaying the generated outfit to the user and providing detailed information about each item, and means for collecting feedback from the user and retraining the generative model based on that data to improve the accuracy of suggestions. This enables the server to automatically suggest optimal outfits based on personal preferences and clothing owned by the user, making it possible to suggest outfits that are harmonious for specific events or with other members of the household.

[1041] "Personal preferences" refers to fashion trends, colors, styles, brands, etc. that a user recognizes as his or her own preferences.

[1042] "Clothing you own" refers to items such as clothes, accessories, and shoes that you already own.

[1043] "Means of collection" refers to the functions and interfaces that allow the system to capture information entered by users and images uploaded by users.

[1044] "Database" refers to a collection of electronic records that store and manage collected information and analytical data.

[1045] "Image Analysis Method" means software or algorithms that analyze uploaded photos of clothing to identify and classify the characteristics of each item (e.g., color, shape, style, etc.).

[1046] "Means of classification" refers to the function of categorizing each item based on the analyzed data.

[1047] A "feature vector" refers to a numerical representation of a user's preferences and the characteristics of items they own.

[1048] A "generative model" refers to a machine learning model or algorithm that takes a user's feature vector as input and generates the optimal outfit.

[1049] "Coordination" refers to suggestions for outfits that combine multiple items of clothing and accessories.

[1050] "Displaying means" refers to an interface for displaying the generated coordinates and their detailed information on the user's device.

[1051] "Means for collecting feedback" refers to a function that allows users to input their evaluations of proposed outfits and requests for changes.

[1052] "Means for retraining the generative model" refers to a process for improving the accuracy of the generative model and the quality of suggestions based on collected feedback data.

[1053] "Means for improving the accuracy of suggestions" refers to a series of processes or methods for improving the performance of the generative model and proposing outfits that are more suitable for the user.

[1054] "Particular events or situations" refers to specific occasions or settings, such as weddings, business meetings, or casual outings.

[1055] "Other members of the household" refers to people who live with the user, such as family members or roommates.

[1056] "Clothing suggestions" refers to suggesting appropriate clothing combinations for individual users and situations.

[1057] The present invention is a system that collects information on an individual's preferences and clothing possessions, and uses feature vectors generated based on the collected information to suggest optimal outfits. This system is implemented using the following hardware and software.

[1058] User:

[1059] When using the system for the first time, users use a device such as a smartphone or PC to enter their basic information (such as name, age, and gender) and fashion preferences (favorite colors, styles, and brands). They also take photos of the clothes they own and upload them to the system.

[1060] Device:

[1061] It provides an interface that displays user-entered information and uploaded images. This interface can be implemented as a web browser or a mobile application. For example, it can include operations such as uploading photos of clothing taken with a smartphone camera app.

[1062] server:

[1063] The server receives data entered by users and uploaded images of clothing and stores them in a database. The server uses image analysis tools (e.g., TensorFlow or OpenCV) to analyze the uploaded images and classify the characteristics of each item (color, shape, style, etc.). For example, it extracts information such as "blue shirt" or "jeans."

[1064] Next, the server generates a feature vector for the user based on the collected information and analysis results. This feature vector represents color, style, type of item, etc. as numerical data. For example, if a user inputs "I like the color blue," "I have three pairs of jeans," and "I like casual styles," the feature vector will be a numerical representation of these.

[1065] The server inputs this feature vector into a generative AI model (e.g., GPT-4 or BERT) to generate the optimal outfit. An example of a prompt sentence input to the model would be, "The user's characteristics are as follows: 1. Favorite color: blue, 2. Items owned: 3 pairs of jeans, 3. Style: casual. Please suggest the optimal outfit based on this information." Based on this information, the generative model suggests outfits such as "a blue shirt, jeans, and white sneakers."

[1066] The generated outfits are sent to the terminal and displayed to the user. Detailed information about each item (brand name, price, etc.) is provided for the user to review. The user can also enter their rating and feedback on the proposed outfits, and this feedback data is collected by the server.

[1067] Finally, the server analyzes the collected feedback data and retrains the generative model to improve the accuracy of the suggestions. For example, if a user rates a suggested outfit as "very satisfying," this information will be reflected in future suggestions. This allows the system to continuously provide optimal fashion suggestions based on the user's preferences and the clothes they own.

[1068] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1069] Step 1:

[1070] Entering and collecting user data

[1071] User:

[1072] Using a device such as a smartphone or PC, users enter their basic information (such as name, age, and gender) and fashion preferences (favorite colors, styles, and brands), and also take photos of clothing they own and upload them to the system.

[1073] input:

[1074] User's basic information, preferences, and photos of clothing

[1075] output:

[1076] The entered information and uploaded images are sent to the system.

[1077] Specific behavior:

[1078] Users open the app on their smartphone, select their favorite color and style, take a photo of the clothing they own, and press the upload button to send the photo to the system.

[1079] Step 2:

[1080] Data storage and image analysis

[1081] server:

[1082] It receives input data and uploaded images, stores them in a database, and uses image analysis tools (TensorFlow and OpenCV) to analyze the uploaded images and classify the characteristics of each item (color, shape, style, etc.).

[1083] input:

[1084] Basic information, preference information, and photos of clothing sent by the user

[1085] output:

[1086] User information and clothing characteristics data stored in a database

[1087] Specific behavior:

[1088] The server processes the images it receives using an analysis tool, extracts characteristic information such as "blue shirt" or "jeans," and stores this information in a database.

[1089] Step 3:

[1090] Feature Vector Generation

[1091] server:

[1092] The collected information and analyzed characteristic data are used to generate a feature vector for the user, which is expressed as numerical data such as color, style, and item type.

[1093] input:

[1094] User basic information, preference information, and clothing characteristics data

[1095] output:

[1096] User feature vector

[1097] Specific behavior:

[1098] The server extracts user information and characteristic data from the database and generates a feature vector such as "Color: Blue, Style: Casual, Item: 3 pairs of jeans."

[1099] Step 4:

[1100] Generating optimal coordination

[1101] server:

[1102] The generated feature vector is input into a generative AI model to generate optimal outfits. The generative model takes into account the user's preferences, the clothing they own, the current season, and specific events to suggest outfit combinations.

[1103] input:

[1104] User feature vector

[1105] output:

[1106] Optimal coordination suggestions

[1107] Specific behavior:

[1108] The server inputs the feature vector into a generative AI model and generates outfits such as "blue shirt, jeans, and white sneakers."

[1109] Example prompt sentence:

[1110] "The user's characteristics are as follows: 1. Favorite color: Blue, 2. Owned items: Three pairs of jeans, 3. Style: Casual. Please suggest the best outfit based on these."

[1111] Step 5:

[1112] Coordination display and user interaction

[1113] Device:

[1114] The generated coordination suggestions are displayed to the user, and detailed information about each item (brand name, price, etc.) is provided.

[1115] User:

[1116] Check the proposed outfits, request to change some items as needed, and enter your rating and feedback on the suggestions.

[1117] input:

[1118] Coordination suggestions sent from the server

[1119] output:

[1120] User Review and Feedback

[1121] Specific behavior:

[1122] Users can check the outfit on their smartphone or PC screen and send feedback such as "very satisfied."

[1123] Step 6:

[1124] Gathering feedback and improving the generative model

[1125] server:

[1126] It collects user feedback, analyzes that data, and retrains the generative model to improve the accuracy of future suggestions.

[1127] input:

[1128] User feedback data

[1129] output:

[1130] Improved generative models

[1131] Specific behavior:

[1132] The server receives the feedback of "very satisfied" and uses that information to retrain the generative model and reflect it in the next proposal.

[1133] This allows the entire system to continue to provide optimal fashion coordination based on the user's information.

[1134] (Application example 1)

[1135] 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."

[1136] It is difficult for users to find the perfect outfit based on their preferences and the clothes they own in a physical store. Furthermore, due to the lack of an environment where users can visually check the outfits provided, it is difficult for users to grasp the actual appearance of the outfit suggestions. Furthermore, if these outfit suggestions are not improved based on user feedback, the accuracy of the suggestions may decrease.

[1137] 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.

[1138] In this invention, the server includes: means for collecting information on personal preferences and clothing owned by the user; means for analyzing the collected information and generating a feature vector for the user; means for using the feature vector as an input and generating an optimal outfit using a generative model; means for displaying the generated outfit to the user; means for collecting feedback from the user and continuously improving the generative model; means for scanning products in a store and acquiring product information that matches the user's feature vector; means for using an augmented reality algorithm to visually display outfit suggestions in real space; and means for displaying detailed information for each item of the outfit suggestions. This allows the user to visually confirm the optimal outfit based on their preferences in a physical store and make adjustments as necessary.

[1139] "Personal preferences" refers to a user's fashion preferences, such as preferred colors, styles, brands, etc.

[1140] "Information about clothing owned" is detailed information about clothing items owned by the user, such as clothes, shoes, and accessories.

[1141] A "feature vector" is a numerical representation of a user's preferences and the characteristics of the clothing they own.

[1142] A "generative model" is a machine learning algorithm that takes a user's feature vector as input and generates the optimal outfit.

[1143] "Feedback" refers to information such as user evaluations, opinions, and impressions regarding suggestions.

[1144] "Continuous improvement" is the process of improving the accuracy of the generative model based on collected feedback.

[1145] "Scanning products in a store" means analyzing products in the store using image recognition technology and obtaining information about them.

[1146] "Augmented reality algorithm" is a technology that displays digital information overlaid on real space.

[1147] "Visually displaying coordinated outfit suggestions" means displaying the suggested coordinated outfits so that the user can actually visually confirm them.

[1148] "Detailed information" refers to detailed information such as the brand name, price, and size of each product.

[1149] MODE FOR CARRYING OUT THE INVENTION

[1150] This invention is a system that utilizes information on personal preferences and clothing owned by a customer to propose optimal outfits in physical stores. Specific implementation procedures are described below.

[1151] Hardware and Software Configuration

[1152] (server)

[1153] The server has the following main responsibilities:

[1154] 1. Information collection: Collects basic information about the user, their fashion preferences, and the clothing they own. Users use their smartphones or computers to enter text and upload images.

[1155] 2. Data analysis: Analyze the collected data and generate a feature vector for the user. Image analysis uses image recognition tools such as OpenCV.

[1156] 3. Coordination generation: The generated feature vector is input into a machine learning model (e.g., TensorFlow) to generate the optimal coordination.

[1157] 4. Model Improvement: Collect user feedback to continuously improve the generative model. Feedback is provided by the user via smart glasses or a head-mounted display.

[1158] (Terminal)

[1159] The terminal has the following main roles:

[1160] 1. Information display: The generated outfit suggestions are visually displayed to the user. Using smart glasses or a head-mounted display, augmented reality algorithms are applied to in-store product images, overlaying digital information on them.

[1161] 2. Product scanning: Scan products in the store with a camera and send the information to the server, which retrieves product information that matches the user's feature vector.

[1162] 3. Displaying detailed information: Displaying detailed information (brand name, price, size, etc.) for each item in the suggested outfits to the user, making it easier for the user to select suggested items.

[1163] (User)

[1164] Users can use the system in the following ways:

[1165] 1. Enter your basic information and clothing: Enter your basic information, fashion preferences, and clothing information through the app. Specifically, upload photos of your favorite colors, styles, and items you own.

[1166] 2. Wearing smart glasses: After entering a physical store, customers put on smart glasses or a head-mounted display and scan the products in the store.

[1167] 3. Check your outfit: Check the outfit suggestions displayed on the smart glasses and check the details of each item.

[1168] 4. Providing feedback: Feedback your evaluation and opinions on the coordination proposal to the system.

[1169] Specific examples

[1170] Suppose a user enters a physical store, their favorite color is black, and they like a casual style. They own a black jacket, white sneakers, and a blue denim shirt. The user puts on smart glasses and scans the products in the store. The server generates a feature vector for the user and inputs it into a machine learning model to suggest the optimal outfit. In this case, the suggested outfit would be "a black jacket, white sneakers, and a blue denim shirt."

[1171] Prompt Sentence Examples

[1172] "Users' favorite color is black, they like casual style, and they own multiple pairs of jeans."

[1173] "I own a black jacket, white sneakers, and a blue denim shirt."

[1174] In this way, the system can visually suggest optimal outfits based on the user's preferences in a physical store.

[1175] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1176] Step 1:

[1177] Users use their smartphones or computers to enter their basic information, fashion preferences, and information about the clothing they own. The information entered includes text data and image data, and this information becomes the input for the system.

[1178] Step 2:

[1179] The server receives the data sent by the user and stores it in a database. At this time, the image data is analyzed using image recognition tools such as OpenCV to extract characteristics such as color, shape, and style. This data processing provides the analysis results of the user's preferences and detailed information about the clothing they own.

[1180] Step 3:

[1181] The server generates a feature vector for the user based on the collected and analyzed information. The feature vector is a numerical representation of the user's preference data (favorite color, preferred style, etc.) and the characteristics of the clothing they own (color, shape, style). Once the feature vector is generated, it becomes the input data for the generative model.

[1182] Step 4:

[1183] The server uses the generated feature vector to generate the optimal outfit using a machine learning algorithm (e.g., TensorFlow). The generative model proposes the optimal combination of items based on the user's feature vector and the data learned by the model. This process generates the optimal outfit.

[1184] Step 5:

[1185] The terminal receives the outfit suggestions generated by the server and displays them to the user. Specifically, augmented reality algorithms are used in smart glasses or head-mounted displays to overlay digital information onto in-store product images. The user can visually confirm the outfit suggestions by combining real space and digital information.

[1186] Step 6:

[1187] The user wears smart glasses or a head-mounted display and scans the products in the store. This displays product information in the store on the device in real time, and product information that matches the user's feature vector is sent to the server, where the product information in the store is added as input data.

[1188] Step 7:

[1189] Based on the scanned product information, the device identifies products that match the user's feature vector and displays product details based on the generated coordination suggestions. Specifically, detailed information such as brand name, price, and size is displayed, allowing the user to make product selections.

[1190] Step 8:

[1191] The user sends feedback on the outfit suggestions from their device to the server. The feedback includes evaluations, opinions, and impressions of the outfit suggestions. This becomes new input data.

[1192] Step 9:

[1193] The server analyzes the feedback collected from users and retrains the generative model. Based on the feedback data, it adjusts the parameters of the generative model to improve the accuracy of future outfit suggestions. This process continuously improves the performance of the entire system.

[1194] 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.

[1195] The present invention is a system that collects information on an individual's preferences and clothing possessions, and proposes optimal outfits using feature vectors generated based on the collected information, and further combines it with an emotion engine that recognizes the user's emotions to provide more personalized suggestions. The following is a specific embodiment of the system.

[1196] User data and sentiment collection

[1197] User:

[1198] When accessing the system for the first time, users enter basic information and fashion preferences. They also upload photos of their clothing. While using the system, users can input their emotional state in real time or detect their emotions using the device's built-in camera and sensors.

[1199] Device:

[1200] It provides an interface that displays and allows users to confirm information they have entered, images they have uploaded, and emotional data on the screen.

[1201] server:

[1202] The system receives data sent by the user (preference information, photos of clothing owned, and emotional data) and stores it in a database. It uses an image analysis tool to classify the clothing images. It also uses an emotion engine to analyze the user's emotions.

[1203] Data analysis and feature vector generation

[1204] server:

[1205] The collected preference information, clothing characteristics, and emotional data are analyzed to generate a feature vector for the user. This feature vector is composed of numerical data corresponding to attributes such as color, style, and item type. Furthermore, based on the emotional data, weighting is applied to reflect the user's current mood.

[1206] Generating optimal coordination

[1207] server:

[1208] The generated feature vector is input into a generative model to generate optimal outfits, taking into account the user's emotional state. The generative model then suggests outfit combinations based on the user's preferences, clothing, season, specific events, and emotional state.

[1209] example:

[1210] If a user inputs "I like the color blue," "I have three pairs of jeans," "I like casual styles," and the emotion engine recognizes that "I'm in a good mood today," the generative model will suggest an outfit such as "a blue shirt, jeans, and white sneakers." However, if the emotion engine recognizes that "I'm feeling down today," it will suggest a more relaxing style and color combination.

[1211] Suggestion display and user interaction

[1212] Device:

[1213] The generated outfit suggestions are displayed to the user, along with detailed information (such as brand name, price, and purchase link) so that the user can review the suggestions.

[1214] User:

[1215] Check the displayed outfits, request to change some items as needed, and enter your rating and feedback on the suggestions.

[1216] Gathering feedback and improving the generative model

[1217] server:

[1218] The system analyzes feedback collected from users and stores the evaluation data in a database. The system retrains the generative model based on the feedback data to improve the accuracy of future suggestions.

[1219] example:

[1220] If a user rates a suggested outfit as "very satisfied," the server will reflect this information in future suggestions. It also analyzes how the user's emotional data influences future suggestions.

[1221] This system not only provides optimal outfits based on the user's preferences and the clothing they own, but also takes the user's emotions into account, allowing for more personalized suggestions, improving the user experience.

[1222] The processing flow will be explained below.

[1223] Step 1:

[1224] User:

[1225] When accessing the system for the first time, users enter their basic information (name, gender, age, etc.) and fashion preferences (favorite colors, styles, brands, etc.), and also upload several photos of clothing they own.

[1226] Step 2:

[1227] Device:

[1228] A screen will be displayed where the user can confirm the basic information and preference information they have entered, as well as the photos of their clothing they have uploaded. The user can check the information they have entered and the images and make any necessary corrections.

[1229] Step 3:

[1230] server:

[1231] It receives data sent by users and stores it in a database, runs image analysis tools on uploaded clothing photos to classify characteristics such as color, shape, and style, and activates an emotion engine to collect emotional data.

[1232] Step 4:

[1233] server:

[1234] While the user is using the system, the emotion engine analyzes the user's facial expressions and input data in real time to infer their current emotional state. The inferred emotional data is stored in a database.

[1235] Step 5:

[1236] server:

[1237] The collected preference information, clothing characteristics, and emotional data are analyzed to generate a feature vector for the user, which includes numerical data representing color, style, item type, and emotional state.

[1238] Step 6:

[1239] server:

[1240] The generated feature vector is input into a generative model to generate optimal outfits that take into account the user's emotional state. The generative model selects outfit combinations by comprehensively evaluating the user's preferences, clothing, season, specific events, and emotional state.

[1241] example:

[1242] If a user inputs "I like the color blue," "I have three pairs of jeans," and "I like casual style," and the emotion engine recognizes that "I'm in a good mood today," the generative model will suggest an outfit consisting of "a blue shirt, jeans, and white sneakers."

[1243] Step 7:

[1244] Device:

[1245] The generated outfit suggestions are displayed to the user, along with detailed information (such as brand name, price, and purchase link) so that the user can review the suggestions.

[1246] Step 8:

[1247] User:

[1248] Check the displayed outfits, request to change some items as needed, and enter your rating and feedback on the suggestions.

[1249] Step 9:

[1250] server:

[1251] The system analyzes feedback collected from users and stores the evaluation data in a database. The system retrains the generative model based on the feedback data to improve the accuracy of future suggestions.

[1252] example:

[1253] If a user rates a suggested outfit as "very satisfying," the server will reflect this information in future suggestions. It will also analyze how the emotional data influenced the suggestions and use this information to improve them.

[1254] Through these steps, personalized and optimal outfit suggestions are provided to the user. Furthermore, the introduction of an emotion engine enables more personalized suggestions that take into account the user's emotional state, improving the user experience.

[1255] Example 2

[1256] 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."

[1257] Many systems exist that collect information about an individual's fashion preferences and clothing possessions and then suggest optimal outfits based on that information. However, these systems often fail to take into account the user's emotional state, resulting in low user satisfaction. Furthermore, these systems lack the functionality to continuously improve the system based on feedback. This means that consistent results cannot be expected with each use.

[1258] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1259] In this invention, the server includes: means for collecting information on personal preferences and clothing owned by the user; means for providing an interface for inputting preference information, clothing information, and emotional data; means for analyzing the collected information and generating a feature vector for the user; means for analyzing the feature vector and emotional data and weighting the feature vector to reflect the user's current emotional state; means for using the feature vector as input and generating an optimal outfit using a generative model; means for displaying the generated outfit to the user and providing detailed information; and means for collecting user feedback and continuously improving the generative model. This enables more personalized outfit suggestions that take into account the user's preferences and current emotional state. Furthermore, by continuously improving the system based on user feedback, high levels of satisfaction can be maintained over the long term.

[1260] "Personal preferences" refers to information about a user's fashion preferences, such as their favorite colors, styles, and brands.

[1261] "Clothes owned" is a list of clothes owned by the user and their detailed information (color, size, brand, frequency of use, etc.).

[1262] "Emotion data" is information that represents the user's current mood or emotional state, and is acquired through sensors or user input.

[1263] A "feature vector" is a data set that quantifies a user's preference information, characteristics of clothing owned, and emotional data, and is composed of numerical data corresponding to each attribute.

[1264] A "generative model" is a machine learning algorithm or artificial intelligence model that takes a user's feature vector as input and generates the optimal outfit.

[1265] A "coordination" is a combination of clothing suggested by a generative model that takes into account the user's preferences and emotional state.

[1266] "Feedback" refers to information about satisfaction with the evaluations, comments, and suggestions that users make to the system.

[1267] An "interface" is an operation screen or input means that allows a user to input information into the system and confirm suggestions from the system.

[1268] The present invention is a system that collects information on personal preferences and clothing owned by a user, generates feature vectors based on the collected information, and then recognizes the user's emotions to suggest optimal outfits. This system is implemented as follows.

[1269] User data and sentiment collection

[1270] User:

[1271] When accessing the system for the first time, users enter basic information (such as name, age, and gender) and fashion preferences (favorite color, preferred style, etc.). They also upload photos of clothing they own. While using the system, users can input their own emotional state or have their emotions detected using the device's built-in camera and sensors.

[1272] Specifically, users take a photo of their clothing using the camera on their smartphone or PC and upload it to the system. To input their emotional state, a special form is displayed with options, allowing them to select states such as "happy," "sad," and "tired" in real time.

[1273] Device:

[1274] It provides an interface for users to check the information they enter and the images of their clothing they upload, and also has the ability to detect emotions using cameras and sensors.

[1275] Specifically, the device detects the user's face in real time and analyzes their facial expressions, and the analysis results are displayed to the user on a confirmation screen.

[1276] server:

[1277] The system receives preference information, photos of clothing owned, and emotion data sent by the user and stores them in a database. It uses an image analysis tool (e.g., OpenCV) to classify the clothing images and an emotion engine (e.g., facial recognition technology) to analyze the user's emotions.

[1278] Specifically, the server uses the photos of clothing received to automatically identify the color, pattern, and item (shirt, pants, etc.), converts them into text information, and stores it in a database.

[1279] Data analysis and feature vector generation

[1280] server:

[1281] The collected preference information, clothing characteristics, and emotional data are analyzed, and a feature vector for the user is generated based on this data. This feature vector is composed of numerical data corresponding to attributes such as color, style, and item type. Furthermore, weighting is performed based on the emotional data to reflect the user's current mood.

[1282] Specifically, the server analyzes the data, quantifies features such as "I like the color blue," "I have three pairs of jeans," and "I'm in a good mood today," and uses this data to generate a feature vector.

[1283] Generating optimal coordination

[1284] server:

[1285] The generated feature vectors are input into a generative AI model (e.g., a generative model) to generate optimal outfits taking into account the user's emotional state. This generative model then suggests outfit combinations taking into account the user's preferences, clothing, season, specific events, and emotional state.

[1286] Specific examples of prompts are as follows:

[1287] User Information:

[1288] Preferences: I like the color blue

[1289] Clothing: 3 pairs of jeans, 1 white shirt, 2 blue shirts

[1290] Style: Casual

[1291] Emotional state: Feeling good

[1292] Based on this information, we will suggest the best outfit for you.

[1293] Suggestion display and user interaction

[1294] Device:

[1295] The generated outfit suggestions are displayed to the user, along with detailed information (such as brand name, price, and purchase link) so that the user can review the suggestions.

[1296] Specifically, the device displays images and detailed information of outfits on the screen, allowing users to check them. By clicking on the selection options or links, users can be taken to the purchase page for each item.

[1297] User:

[1298] Check the displayed outfits, request to change some items as needed, and enter your rating and feedback on the suggestions.

[1299] Specifically, when a user makes a change request, such as "I want the shoes to be black," the system will again generate the optimal proposal. The user can also select "Very Satisfied," "Satisfied," or "Dissatisfied" in the evaluation form and enter their comments.

[1300] Gathering feedback and improving the generative model

[1301] server:

[1302] The system analyzes the feedback collected from users and stores the evaluation data in a database, which is used to retrain the generative model and improve the accuracy of future suggestions.

[1303] Specifically, the server analyzes the feedback data, adjusts the parameters of the generative AI model based on the evaluation scores and comments, and retrains it to improve the accuracy of the next proposal.

[1304] This system not only provides optimal outfits based on the user's preferences and the clothes they own, but also takes into account the user's emotions to enable more personalized suggestions. Furthermore, by continuously improving the system based on user feedback, it is possible to maintain high levels of satisfaction over the long term.

[1305] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1306] Step 1:

[1307] User Data Collection

[1308] Specific behavior:

[1309] First, users enter basic information and fashion preferences into the system and upload multiple photos of clothing they own.

[1310] Input: User basic information, preferences, and clothing photos.

[1311] Output: User information and uploaded clothing photo data sent to the server.

[1312] The server receives the data sent by the user (basic information, preference information, and photos of clothing owned) and stores it in a database.

[1313] Specific behavior:

[1314] The server receives the data and stores it in a database, storing information such as name, age, gender, preferred colors and styles, and uploaded photos of the clothing.

[1315] Input: Basic information, preferences, and clothing photos received from the user.

[1316] Output: User dataset stored in a database.

[1317] Step 2:

[1318] Collecting Emotional Data

[1319] Specific behavior:

[1320] Users can input their emotional state in real time or use the device's camera or sensors to detect emotions.

[1321] Input: User's emotional state (or device-detected emotional data).

[1322] Output: Emotion data sent to the server.

[1323] The terminal displays the emotional state data entered by the user or the detected emotional data on the screen and provides a confirmation interface.

[1324] Specific behavior:

[1325] The device uses cameras and sensors to detect the user's face in real time, analyzes their facial expressions, and displays the analysis results to the user on a confirmation screen.

[1326] Input: User's emotional state (or device-detected emotional data).

[1327] Output: An emotional state confirmation interface displayed on the screen.

[1328] The server receives the emotion data sent by the user, stores it in a database, and analyzes the emotion using an emotion engine.

[1329] Specific behavior:

[1330] The server uses an emotion analysis tool to analyze the user's emotion data and stores the results in a database.

[1331] Input: Emotion data received from the user.

[1332] Output: Sentiment analysis results stored in a database.

[1333] Step 3:

[1334] Data analysis and feature vector generation

[1335] Specific behavior:

[1336] The server analyzes the collected preference information, clothing characteristics, and emotional data to generate a feature vector for the user.

[1337] Input: Preference information stored in the database, characteristics of clothing owned, and emotional data.

[1338] Output: A feature vector for the user.

[1339] Based on the analyzed data, the server generates numerical data corresponding to each attribute, such as color, style, and item type, and also weights the data based on the emotion data to reflect the user's current mood.

[1340] Specific behavior:

[1341] The server quantifies the data, assigning a score to color preference (for example, red = 2, blue = 5, green = 1) and generates a feature vector. At the same time, it assigns weights based on the emotional data (for example, good mood = 1.2, bad mood = 0.8).

[1342] Input: Analyzed preference information, clothing characteristics, and emotional data.

[1343] Output: A quantified feature vector.

[1344] Step 4:

[1345] Generating optimal coordination

[1346] Specific behavior:

[1347] The server inputs the generated feature vector into a generative AI model and generates the optimal outfit, taking into account the user's emotional state.

[1348] Input: User feature vector.

[1349] Output: The optimal coordinates generated by the generative AI model.

[1350] The generative model suggests outfit combinations based on the user's preferences, clothing, season, specific events, and emotional state.

[1351] Specific prompt examples:

[1352] User Information:

[1353] Preferences: I like the color blue

[1354] Clothing: 3 pairs of jeans, 1 white shirt, 2 blue shirts

[1355] Style: Casual

[1356] Emotional state: Feeling good

[1357] Based on this information, we will suggest the best outfit for you.

[1358] Specific behavior:

[1359] The server sends a prompt to the AI ​​model, which then generates the optimal coordinates based on this.

[1360] Input: User feature vector, emotional state.

[1361] Output: The optimal coordinates suggested to the user.

[1362] Step 5:

[1363] Displaying outfit suggestions

[1364] Specific behavior:

[1365] The device displays the generated outfit suggestions to the user, along with detailed information (such as brand name, price, and purchase link) so the user can review the suggestions.

[1366] Input: The generated coordinates.

[1367] Output: Coordination suggestions and detailed information displayed on the device screen.

[1368] Specifically, the device displays images and detailed information of outfits on the screen, allowing users to check them. By clicking on the selection options or links, users can be taken to the purchase page for each item.

[1369] Input: Generated coordinates, detailed information.

[1370] Output: Coordination suggestions and detailed information displayed on the device screen.

[1371] Step 6:

[1372] Gathering user feedback

[1373] Specific behavior:

[1374] The user can check the proposed outfits, request to change some items as needed, and enter their ratings and feedback on the suggestions.

[1375] Input: Proposed coordinates, user feedback.

[1376] Output: User feedback sent to the server.

[1377] Specifically, the user makes a change request, such as "I want the shoes to be black," and the system receives it and makes a new suggestion. The user also selects "Very Satisfied," "Satisfied," or "Dissatisfied" in the evaluation form and enters comments.

[1378] Input: User feedback.

[1379] Output: Feedback data stored on the server.

[1380] Step 7:

[1381] Improving generative models

[1382] Specific behavior:

[1383] The server analyzes user feedback and stores the evaluation data in a database, which is used to retrain the generative model and improve the accuracy of future suggestions.

[1384] Input: Feedback data from users.

[1385] Output: An improved generative AI model.

[1386] Specifically, the server analyzes the feedback data, adjusts the parameters of the generative AI model based on the evaluation scores and comments, and retrains it to improve the accuracy of the next proposal.

[1387] Input: Feedback data.

[1388] Output: The updated AI model.

[1389] (Application example 2)

[1390] 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."

[1391] Conventional outfit suggestion systems can make suggestions based on a user's personal preferences and the clothing they own, but they cannot take the user's emotional state into account, making it impossible to provide optimal outfits that match the user's mood and psychological state. Therefore, to further improve the user experience, personalized suggestions that take the user's emotional state into account are needed.

[1392] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1393] In this invention, the server includes means for collecting information on the user's preferences and clothing possessions, means for collecting the user's emotional state, and means for analyzing the collected information and emotional state to generate a feature vector of the user, thereby enabling more personalized and optimal outfit suggestions that take into account the user's preferences and current emotional state.

[1394] The "means for collecting information on personal preferences and clothing owned" refers to a device or method for collecting information on fashion preferences entered by a user and photos and detailed information on clothing owned by the user.

[1395] "Means for collecting a user's emotional state" means a device or method for detecting and recording a user's emotional or psychological state in real time, including, for example, biometric analysis using cameras or sensors.

[1396] "Means for analyzing collected information and emotional state and generating a feature vector of the user" refers to a device or method that converts the user's fashion trends and current emotions into numerical data based on the collected user preference information, clothing information, and emotional data, and expresses them as a feature vector.

[1397] A "means for generating optimal outfits using a generative model" is a device or method that inputs a user's feature vector into a generative AI model and, from the results, suggests optimal clothing combinations based on the user's preferences and emotional state.

[1398] The "means for displaying the generated coordinated outfits to the user" refers to a device or method for displaying the proposed clothing combinations so that the user can check them and select or modify them.

[1399] "Means for collecting user feedback and continuously improving the generative model" refers to a device or method that collects user ratings and opinions on the proposed outfits, and then uses that data to retrain the generative model and improve its accuracy.

[1400] This invention is a system that proposes optimal outfits that take into account a user's emotional state based on information about the user's fashion preferences and the clothing they own. The system is realized by the following steps.

[1401] User data and sentiment collection

[1402] User: The user launches an application installed on their smartphone or head-mounted display (HMD) and inputs basic information and fashion preferences. They also upload photos of their clothing through the application. Furthermore, their emotional state is collected in real time using the smartphone camera and the HMD's built-in sensors.

[1403] Data analysis and feature vector generation

[1404] Server: The collected user preference information, clothing information, and emotional data are sent to a cloud server. On the server side, the uploaded clothing images are analyzed using the Google Cloud Vision API to classify the type, color, and style of the clothing. Meanwhile, the emotional data is analyzed using IBM Watson Tone Analyzer. Next, a feature vector for the user is generated based on this data. This feature vector represents the color, style, type of item, emotional state, and other factors as numerical data.

[1405] Generating optimal coordination

[1406] Server: The generated feature vectors and emotion data are input into a generative AI model (e.g., OpenAI GPT-3) to generate optimal outfits based on the user's preferences and current emotional state. The generated outfit suggestions take into account the user's preferences, clothing they own, the season, specific events, and their emotional state to suggest outfit combinations.

[1407] As a specific example, if a user inputs "I like casual style," "I like blue items," "I have several pairs of jeans," and also has emotional data such as "I'm in a good mood today," the generative AI model will suggest an outfit such as "a blue shirt, jeans, and white sneakers."

[1408] An example prompt is:

[1409] The user's preferred style is casual. The clothing they own is blue items and jeans. Their current emotional state is good. Based on this information, please suggest the best outfit for them.

[1410] Suggestion display and user interaction

[1411] Device: The suggested outfits are displayed on the user's smartphone or HMD. The user can review the suggested outfits and check detailed information (e.g., brand name, price, purchase link, etc.). Furthermore, if the user is not satisfied with the suggested outfits, they can request to change some items within the application.

[1412] Gathering feedback and improving the generative model

[1413] Server: Collects feedback entered by users on outfit suggestions. The collected feedback data is stored in a database and used to train the next generation model. This allows the generation model to continuously improve, resulting in more accurate suggestions in the future.

[1414] This system makes it possible to propose outfits that take into account the user's individual preferences and emotional state, significantly improving the user experience.

[1415] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1416] Step 1:

[1417] The user enters basic information and preference information

[1418] A user launches an application installed on a smartphone or head-mounted display (HMD) and inputs basic information (e.g., name, gender, height) and fashion preferences (e.g., favorite color, favorite style). The input information is temporarily stored in the application's local storage and then sent to a cloud server. A dataset containing the input data is formed.

[1419] Step 2:

[1420] Upload photos of clothing that users own

[1421] Users take photos of their clothing and upload them to the application. The uploaded image data is sent to a cloud server and subjected to image analysis. Specifically, the smartphone's camera application is launched, and the image is transferred to the server after it has been taken.

[1422] Step 3:

[1423] Collecting emotional states

[1424] To collect the user's current emotional state, the smartphone camera and the HMD's built-in sensors are activated to collect facial expression data and information from biometric sensors. The collected emotional data is also sent to a cloud server. Specifically, the application acquires data using the camera and sensors in real time.

[1425] Step 4:

[1426] Data analysis

[1427] The server analyzes the collected user preference information, photos of the clothing they own, and emotional data. The photos of the clothing are classified using the Google Cloud Vision API to determine the color, style, and type of each item. The emotional data is analyzed using IBM Watson Tone Analyzer, and the user's emotional state is quantified. The input data are image files, emotional data, and text information, and the output is the analysis results and feature vectors.

[1428] Step 5:

[1429] Feature Vector Generation

[1430] The server generates a feature vector for the user based on the analyzed preference information, clothing information, and emotional data. This feature vector contains numerical data corresponding to each attribute, such as color, style, item type, and emotional state. The input data is the analysis result, and the output is the feature vector.

[1431] Step 6:

[1432] Generating optimal coordination

[1433] Based on the generated feature vector and emotion data, the server inputs the feature vector into a generative AI model (e.g., OpenAI GPT-3) to generate the optimal outfit. An example of a prompt sentence is, "The user's preferred style is casual. The clothing they own is blue items and jeans. Their current emotional state is good. Please suggest the optimal outfit based on this information." The input data is the feature vector, and the output data is the outfit suggestion.

[1434] Step 7:

[1435] Displaying suggestions to the user

[1436] The generated outfit suggestions are displayed on the user's smartphone or HMD. The user can review the suggested outfits and check their details (e.g., brand name, price, and purchase link). The input data is the outfit suggestions, and the output data is the user's feedback.

[1437] Step 8:

[1438] Gathering feedback and improving the model

[1439] The server collects user ratings and correction requests for outfit suggestions. The collected feedback data is stored in a database and used to train the next generative model. This allows the generative model to be continuously improved, resulting in improved proposal accuracy from the next time onwards. The input data is user feedback, and the output data is updated model parameters.

[1440] 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.

[1441] 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.

[1442] 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.

[1443] [Fourth embodiment]

[1444] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1445] 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.

[1446] 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).

[1447] 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.

[1448] 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.

[1449] 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).

[1450] 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.

[1451] 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.

[1452] 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.

[1453] 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.

[1454] 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.

[1455] 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.

[1456] 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."

[1457] The present invention is a system that collects information on an individual's preferences and clothing possessions, and proposes optimal outfits using feature vectors generated based on the information. This system has the following main functions:

[1458] User Data Collection

[1459] User:

[1460] When using the system for the first time, users enter their basic information and fashion preferences. They can also upload photos of the clothes they own at home.

[1461] Device:

[1462] It provides an interface that displays the information entered by the user and the images uploaded on the screen, allowing the user to confirm the entered information.

[1463] server:

[1464] It receives the input data and stores it in a database, and also uses image analysis tools to analyze the uploaded photos of clothing and classify the characteristics of each item (color, shape, style, etc.).

[1465] Data analysis and feature vector generation

[1466] server:

[1467] The collected information is used to analyze the user's hobbies, preferences, and clothing characteristics. Based on the analysis results, a feature vector for the user is generated. This feature vector is made up of numerical data corresponding to each attribute, such as color, style, and type of item.

[1468] Generating optimal coordination

[1469] server:

[1470] The generated feature vectors are input into a generative model to generate optimal outfits. This generative model takes into account the user's preferences, the clothing they own, the current season, and specific events to suggest optimal outfit combinations.

[1471] example:

[1472] If a user inputs "I like the color blue," "I have three pairs of jeans," and "I like a casual style," the generative model will use this information to suggest outfits such as "a blue shirt, jeans, and white sneakers."

[1473] Suggestion display and user interaction

[1474] Device:

[1475] The generated outfit suggestions are displayed to the user, along with detailed information about each item (brand name, price, etc.), allowing the user to confirm the suggestions.

[1476] User:

[1477] Users can review the provided outfits, request to change some items if necessary, and even rate and provide feedback on the suggestions.

[1478] Gathering feedback and improving the generative model

[1479] server:

[1480] Collect user feedback, analyze the data, and retrain the generative model based on the feedback data to improve the accuracy of the suggestions.

[1481] example:

[1482] If the user rates the proposed outfit as "very satisfied," the server will reflect this information in future suggestions.

[1483] This system allows users to easily find the perfect outfit based on their preferences and the clothing they own. It can also suggest outfits for specific events or outfits to coordinate with other members of the household. This improves the user experience and provides personalized fashion suggestions.

[1484] The processing flow will be explained below.

[1485] Step 1:

[1486] User:

[1487] When users first access the system, they enter basic information and their fashion preferences, such as their favorite colors, styles, and brands, and also upload photos of the clothes they own.

[1488] Step 2:

[1489] Device:

[1490] The information entered and the image uploaded by the user are displayed on the screen for confirmation. The user can check the information entered and the image and make corrections as necessary.

[1491] Step 3:

[1492] server:

[1493] The system receives the data submitted by users and stores it in a database. Photos of uploaded clothing are then run through image analysis tools to classify the item's color, shape, style, and other characteristics.

[1494] Step 4:

[1495] server:

[1496] The collected information is analyzed to extract the user's hobbies, preferences, and clothing characteristics. These characteristics are then used to generate a feature vector, which consists of numerical data corresponding to attributes such as color, style, and item type.

[1497] Step 5:

[1498] server:

[1499] The generated feature vector is input into a generative model, which then generates the optimal outfit based on the user's feature vector. The model selects outfit combinations taking into account the user's preferences, clothing they own, the season, specific events, and other factors.

[1500] Step 6:

[1501] Device:

[1502] The generated outfit suggestions are displayed to the user, along with detailed information (such as brand name, price, and purchase link) so that the user can review the suggestions.

[1503] Step 7:

[1504] User:

[1505] Check the displayed outfits, request to change some items as needed, and enter your rating and feedback on the suggestions.

[1506] Step 8:

[1507] server:

[1508] The system analyzes the feedback collected from users and stores the evaluation data in a database.The system then retrains the generative model based on the feedback data to improve the accuracy of future suggestions.

[1509] By going through these steps, personalized and optimal coordination suggestions are provided to the user.

[1510] Example 1

[1511] 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."

[1512] Currently, it is not easy for individuals to find the optimal fashion coordination based on their own preferences and the clothing they own. Choosing the right outfit for a specific event or situation requires a lot of time and effort. It is also difficult to suggest coordinated outfits that are also harmonious with other members of the household. There is a need for a system that can solve these issues and easily provide personalized fashion suggestions to individuals.

[1513] 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.

[1514] In this invention, the server includes means for collecting information on personal preferences and clothing owned by the user, means for storing the collected information in a database and analyzing uploaded clothing images to classify the characteristics of each item, means for generating a feature vector for the user based on the collected information and the analyzed characteristics, means for inputting the feature vector into a generative model to generate an optimal outfit, means for displaying the generated outfit to the user and providing detailed information about each item, and means for collecting feedback from the user and retraining the generative model based on that data to improve the accuracy of suggestions. This enables the server to automatically suggest optimal outfits based on personal preferences and clothing owned by the user, making it possible to suggest outfits that are harmonious for specific events or with other members of the household.

[1515] "Personal preferences" refers to fashion trends, colors, styles, brands, etc. that a user recognizes as his or her own preferences.

[1516] "Clothing you own" refers to items such as clothes, accessories, and shoes that you already own.

[1517] "Means of collection" refers to the functions and interfaces that allow the system to capture information entered by users and images uploaded by users.

[1518] "Database" refers to a collection of electronic records that store and manage collected information and analytical data.

[1519] "Image Analysis Method" means software or algorithms that analyze uploaded photos of clothing to identify and classify the characteristics of each item (e.g., color, shape, style, etc.).

[1520] "Means of classification" refers to the function of categorizing each item based on the analyzed data.

[1521] A "feature vector" refers to a numerical representation of a user's preferences and the characteristics of items they own.

[1522] A "generative model" refers to a machine learning model or algorithm that takes a user's feature vector as input and generates the optimal outfit.

[1523] "Coordination" refers to suggestions for outfits that combine multiple items of clothing and accessories.

[1524] "Displaying means" refers to an interface for displaying the generated coordinates and their detailed information on the user's device.

[1525] "Means for collecting feedback" refers to a function that allows users to input their evaluations of proposed outfits and requests for changes.

[1526] "Means for retraining the generative model" refers to a process for improving the accuracy of the generative model and the quality of suggestions based on collected feedback data.

[1527] "Means for improving the accuracy of suggestions" refers to a series of processes or methods for improving the performance of the generative model and proposing outfits that are more suitable for the user.

[1528] "Particular events or situations" refers to specific occasions or settings, such as weddings, business meetings, or casual outings.

[1529] "Other members of the household" refers to people who live with the user, such as family members or roommates.

[1530] "Clothing suggestions" refers to suggesting appropriate clothing combinations for individual users and situations.

[1531] The present invention is a system that collects information on an individual's preferences and clothing possessions, and uses feature vectors generated based on the collected information to suggest optimal outfits. This system is implemented using the following hardware and software.

[1532] User:

[1533] When using the system for the first time, users use a device such as a smartphone or PC to enter their basic information (such as name, age, and gender) and fashion preferences (favorite colors, styles, and brands). They also take photos of the clothes they own and upload them to the system.

[1534] Device:

[1535] It provides an interface that displays user-entered information and uploaded images. This interface can be implemented as a web browser or a mobile application. For example, it can include operations such as uploading photos of clothing taken with a smartphone camera app.

[1536] server:

[1537] The server receives data entered by users and uploaded images of clothing and stores them in a database. The server uses image analysis tools (e.g., TensorFlow or OpenCV) to analyze the uploaded images and classify the characteristics of each item (color, shape, style, etc.). For example, it extracts information such as "blue shirt" or "jeans."

[1538] Next, the server generates a feature vector for the user based on the collected information and analysis results. This feature vector represents color, style, type of item, etc. as numerical data. For example, if a user inputs "I like the color blue," "I have three pairs of jeans," and "I like casual styles," the feature vector will be a numerical representation of these.

[1539] The server inputs this feature vector into a generative AI model (e.g., GPT-4 or BERT) to generate the optimal outfit. An example of a prompt sentence input to the model would be, "The user's characteristics are as follows: 1. Favorite color: blue, 2. Items owned: 3 pairs of jeans, 3. Style: casual. Please suggest the optimal outfit based on this information." Based on this information, the generative model suggests outfits such as "a blue shirt, jeans, and white sneakers."

[1540] The generated outfits are sent to the terminal and displayed to the user. Detailed information about each item (brand name, price, etc.) is provided for the user to review. The user can also enter their rating and feedback on the proposed outfits, and this feedback data is collected by the server.

[1541] Finally, the server analyzes the collected feedback data and retrains the generative model to improve the accuracy of the suggestions. For example, if a user rates a suggested outfit as "very satisfying," this information will be reflected in future suggestions. This allows the system to continuously provide optimal fashion suggestions based on the user's preferences and the clothes they own.

[1542] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1543] Step 1:

[1544] Entering and collecting user data

[1545] User:

[1546] Using a device such as a smartphone or PC, users enter their basic information (such as name, age, and gender) and fashion preferences (favorite colors, styles, and brands), and also take photos of clothing they own and upload them to the system.

[1547] input:

[1548] User's basic information, preferences, and photos of clothing

[1549] output:

[1550] The entered information and uploaded images are sent to the system.

[1551] Specific behavior:

[1552] Users open the app on their smartphone, select their favorite color and style, take a photo of the clothing they own, and press the upload button to send the photo to the system.

[1553] Step 2:

[1554] Data storage and image analysis

[1555] server:

[1556] It receives input data and uploaded images, stores them in a database, and uses image analysis tools (TensorFlow and OpenCV) to analyze the uploaded images and classify the characteristics of each item (color, shape, style, etc.).

[1557] input:

[1558] Basic information, preference information, and photos of clothing sent by the user

[1559] output:

[1560] User information and clothing characteristics data stored in a database

[1561] Specific behavior:

[1562] The server processes the images it receives using an analysis tool, extracts characteristic information such as "blue shirt" or "jeans," and stores this information in a database.

[1563] Step 3:

[1564] Feature Vector Generation

[1565] server:

[1566] The collected information and analyzed characteristic data are used to generate a feature vector for the user, which is expressed as numerical data such as color, style, and item type.

[1567] input:

[1568] User basic information, preference information, and clothing characteristics data

[1569] output:

[1570] User feature vector

[1571] Specific behavior:

[1572] The server extracts user information and characteristic data from the database and generates a feature vector such as "Color: Blue, Style: Casual, Item: 3 pairs of jeans."

[1573] Step 4:

[1574] Generating optimal coordination

[1575] server:

[1576] The generated feature vector is input into a generative AI model to generate optimal outfits. The generative model takes into account the user's preferences, the clothing they own, the current season, and specific events to suggest outfit combinations.

[1577] input:

[1578] User feature vector

[1579] output:

[1580] Optimal coordination suggestions

[1581] Specific behavior:

[1582] The server inputs the feature vector into a generative AI model and generates outfits such as "blue shirt, jeans, and white sneakers."

[1583] Example prompt sentence:

[1584] "The user's characteristics are as follows: 1. Favorite color: Blue, 2. Owned items: Three pairs of jeans, 3. Style: Casual. Please suggest the best outfit based on these."

[1585] Step 5:

[1586] Coordination display and user interaction

[1587] Device:

[1588] The generated coordination suggestions are displayed to the user, and detailed information about each item (brand name, price, etc.) is provided.

[1589] User:

[1590] Check the proposed outfits, request to change some items as needed, and enter your rating and feedback on the suggestions.

[1591] input:

[1592] Coordination suggestions sent from the server

[1593] output:

[1594] User Review and Feedback

[1595] Specific behavior:

[1596] Users can check the outfit on their smartphone or PC screen and send feedback such as "very satisfied."

[1597] Step 6:

[1598] Gathering feedback and improving the generative model

[1599] server:

[1600] It collects user feedback, analyzes that data, and retrains the generative model to improve the accuracy of future suggestions.

[1601] input:

[1602] User feedback data

[1603] output:

[1604] Improved generative models

[1605] Specific behavior:

[1606] The server receives the feedback of "very satisfied" and uses that information to retrain the generative model and reflect it in the next proposal.

[1607] This allows the entire system to continue to provide optimal fashion coordination based on the user's information.

[1608] (Application example 1)

[1609] 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."

[1610] It is difficult for users to find the perfect outfit based on their preferences and the clothes they own in a physical store. Furthermore, due to the lack of an environment where users can visually check the outfits provided, it is difficult for users to grasp the actual appearance of the outfit suggestions. Furthermore, if these outfit suggestions are not improved based on user feedback, the accuracy of the suggestions may decrease.

[1611] 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.

[1612] In this invention, the server includes: means for collecting information on personal preferences and clothing owned by the user; means for analyzing the collected information and generating a feature vector for the user; means for using the feature vector as an input and generating an optimal outfit using a generative model; means for displaying the generated outfit to the user; means for collecting feedback from the user and continuously improving the generative model; means for scanning products in a store and acquiring product information that matches the user's feature vector; means for using an augmented reality algorithm to visually display outfit suggestions in real space; and means for displaying detailed information for each item of the outfit suggestions. This allows the user to visually confirm the optimal outfit based on their preferences in a physical store and make adjustments as necessary.

[1613] "Personal preferences" refers to a user's fashion preferences, such as preferred colors, styles, brands, etc.

[1614] "Information about clothing owned" is detailed information about clothing items owned by the user, such as clothes, shoes, and accessories.

[1615] A "feature vector" is a numerical representation of a user's preferences and the characteristics of the clothing they own.

[1616] A "generative model" is a machine learning algorithm that takes a user's feature vector as input and generates the optimal outfit.

[1617] "Feedback" refers to information such as user evaluations, opinions, and impressions regarding suggestions.

[1618] "Continuous improvement" is the process of improving the accuracy of the generative model based on collected feedback.

[1619] "Scanning products in a store" means analyzing products in the store using image recognition technology and obtaining information about them.

[1620] "Augmented reality algorithm" is a technology that displays digital information overlaid on real space.

[1621] "Visually displaying coordinated outfit suggestions" means displaying the suggested coordinated outfits so that the user can actually visually confirm them.

[1622] "Detailed information" refers to detailed information such as the brand name, price, and size of each product.

[1623] MODE FOR CARRYING OUT THE INVENTION

[1624] This invention is a system that utilizes information on personal preferences and clothing owned by a customer to propose optimal outfits in physical stores. Specific implementation procedures are described below.

[1625] Hardware and Software Configuration

[1626] (server)

[1627] The server has the following main responsibilities:

[1628] 1. Information collection: Collects basic information about the user, their fashion preferences, and the clothing they own. Users use their smartphones or computers to enter text and upload images.

[1629] 2. Data analysis: Analyze the collected data and generate a feature vector for the user. Image analysis uses image recognition tools such as OpenCV.

[1630] 3. Coordination generation: The generated feature vector is input into a machine learning model (e.g., TensorFlow) to generate the optimal coordination.

[1631] 4. Model Improvement: Collect user feedback to continuously improve the generative model. Feedback is provided by the user via smart glasses or a head-mounted display.

[1632] (Terminal)

[1633] The terminal has the following main roles:

[1634] 1. Information display: The generated outfit suggestions are visually displayed to the user. Using smart glasses or a head-mounted display, augmented reality algorithms are applied to in-store product images, overlaying digital information on them.

[1635] 2. Product scanning: Scan products in the store with a camera and send the information to the server, which retrieves product information that matches the user's feature vector.

[1636] 3. Displaying detailed information: Displaying detailed information (brand name, price, size, etc.) for each item in the suggested outfits to the user, making it easier for the user to select suggested items.

[1637] (User)

[1638] Users can use the system in the following ways:

[1639] 1. Enter your basic information and clothing: Enter your basic information, fashion preferences, and clothing information through the app. Specifically, upload photos of your favorite colors, styles, and items you own.

[1640] 2. Wearing smart glasses: After entering a physical store, customers put on smart glasses or a head-mounted display and scan the products in the store.

[1641] 3. Check your outfit: Check the outfit suggestions displayed on the smart glasses and check the details of each item.

[1642] 4. Providing feedback: Feedback your evaluation and opinions on the coordination proposal to the system.

[1643] Specific examples

[1644] Suppose a user enters a physical store, their favorite color is black, and they like a casual style. They own a black jacket, white sneakers, and a blue denim shirt. The user puts on smart glasses and scans the products in the store. The server generates a feature vector for the user and inputs it into a machine learning model to suggest the optimal outfit. In this case, the suggested outfit would be "a black jacket, white sneakers, and a blue denim shirt."

[1645] Prompt Sentence Examples

[1646] "Users' favorite color is black, they like casual style, and they own multiple pairs of jeans."

[1647] "I own a black jacket, white sneakers, and a blue denim shirt."

[1648] In this way, the system can visually suggest optimal outfits based on the user's preferences in a physical store.

[1649] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1650] Step 1:

[1651] Users use their smartphones or computers to enter their basic information, fashion preferences, and information about the clothing they own. The information entered includes text data and image data, and this information becomes the input for the system.

[1652] Step 2:

[1653] The server receives the data sent by the user and stores it in a database. At this time, the image data is analyzed using image recognition tools such as OpenCV to extract characteristics such as color, shape, and style. This data processing provides the analysis results of the user's preferences and detailed information about the clothing they own.

[1654] Step 3:

[1655] The server generates a feature vector for the user based on the collected and analyzed information. The feature vector is a numerical representation of the user's preference data (favorite color, preferred style, etc.) and the characteristics of the clothing they own (color, shape, style). Once the feature vector is generated, it becomes the input data for the generative model.

[1656] Step 4:

[1657] The server uses the generated feature vector to generate the optimal outfit using a machine learning algorithm (e.g., TensorFlow). The generative model proposes the optimal combination of items based on the user's feature vector and the data learned by the model. This process generates the optimal outfit.

[1658] Step 5:

[1659] The terminal receives the outfit suggestions generated by the server and displays them to the user. Specifically, augmented reality algorithms are used in smart glasses or head-mounted displays to overlay digital information onto in-store product images. The user can visually confirm the outfit suggestions by combining real space and digital information.

[1660] Step 6:

[1661] The user wears smart glasses or a head-mounted display and scans the products in the store. This displays product information in the store on the device in real time, and product information that matches the user's feature vector is sent to the server, where the product information in the store is added as input data.

[1662] Step 7:

[1663] Based on the scanned product information, the device identifies products that match the user's feature vector and displays product details based on the generated coordination suggestions. Specifically, detailed information such as brand name, price, and size is displayed, allowing the user to make product selections.

[1664] Step 8:

[1665] The user sends feedback on the outfit suggestions from their device to the server. The feedback includes evaluations, opinions, and impressions of the outfit suggestions. This becomes new input data.

[1666] Step 9:

[1667] The server analyzes the feedback collected from users and retrains the generative model. Based on the feedback data, it adjusts the parameters of the generative model to improve the accuracy of future outfit suggestions. This process continuously improves the performance of the entire system.

[1668] 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.

[1669] The present invention is a system that collects information on an individual's preferences and clothing possessions, and proposes optimal outfits using feature vectors generated based on the collected information, and further combines it with an emotion engine that recognizes the user's emotions to provide more personalized suggestions. The following is a specific embodiment of the system.

[1670] User data and sentiment collection

[1671] User:

[1672] When accessing the system for the first time, users enter basic information and fashion preferences. They also upload photos of their clothing. While using the system, users can input their emotional state in real time or detect their emotions using the device's built-in camera and sensors.

[1673] Device:

[1674] It provides an interface that displays and allows users to confirm information they have entered, images they have uploaded, and emotional data on the screen.

[1675] server:

[1676] The system receives data sent by the user (preference information, photos of clothing owned, and emotional data) and stores it in a database. It uses an image analysis tool to classify the clothing images. It also uses an emotion engine to analyze the user's emotions.

[1677] Data analysis and feature vector generation

[1678] server:

[1679] The collected preference information, clothing characteristics, and emotional data are analyzed to generate a feature vector for the user. This feature vector is composed of numerical data corresponding to attributes such as color, style, and item type. Furthermore, based on the emotional data, weighting is applied to reflect the user's current mood.

[1680] Generating optimal coordination

[1681] server:

[1682] The generated feature vector is input into a generative model to generate optimal outfits, taking into account the user's emotional state. The generative model then suggests outfit combinations based on the user's preferences, clothing, season, specific events, and emotional state.

[1683] example:

[1684] If a user inputs "I like the color blue," "I have three pairs of jeans," "I like casual styles," and the emotion engine recognizes that "I'm in a good mood today," the generative model will suggest an outfit such as "a blue shirt, jeans, and white sneakers." However, if the emotion engine recognizes that "I'm feeling down today," it will suggest a more relaxing style and color combination.

[1685] Suggestion display and user interaction

[1686] Device:

[1687] The generated outfit suggestions are displayed to the user, along with detailed information (such as brand name, price, and purchase link) so that the user can review the suggestions.

[1688] User:

[1689] Check the displayed outfits, request to change some items as needed, and enter your rating and feedback on the suggestions.

[1690] Gathering feedback and improving the generative model

[1691] server:

[1692] The system analyzes feedback collected from users and stores the evaluation data in a database. The system retrains the generative model based on the feedback data to improve the accuracy of future suggestions.

[1693] example:

[1694] If a user rates a suggested outfit as "very satisfied," the server will reflect this information in future suggestions. It also analyzes how the user's emotional data influences future suggestions.

[1695] This system not only provides optimal outfits based on the user's preferences and the clothing they own, but also takes the user's emotions into account, allowing for more personalized suggestions, improving the user experience.

[1696] The processing flow will be explained below.

[1697] Step 1:

[1698] User:

[1699] When accessing the system for the first time, users enter their basic information (name, gender, age, etc.) and fashion preferences (favorite colors, styles, brands, etc.), and also upload several photos of clothing they own.

[1700] Step 2:

[1701] Device:

[1702] A screen will be displayed where the user can confirm the basic information and preference information they have entered, as well as the photos of their clothing they have uploaded. The user can check the information they have entered and the images and make any necessary corrections.

[1703] Step 3:

[1704] server:

[1705] It receives data sent by users and stores it in a database, runs image analysis tools on uploaded clothing photos to classify characteristics such as color, shape, and style, and activates an emotion engine to collect emotional data.

[1706] Step 4:

[1707] server:

[1708] While the user is using the system, the emotion engine analyzes the user's facial expressions and input data in real time to infer their current emotional state. The inferred emotional data is stored in a database.

[1709] Step 5:

[1710] server:

[1711] The collected preference information, clothing characteristics, and emotional data are analyzed to generate a feature vector for the user, which includes numerical data representing color, style, item type, and emotional state.

[1712] Step 6:

[1713] server:

[1714] The generated feature vector is input into a generative model to generate optimal outfits that take into account the user's emotional state. The generative model selects outfit combinations by comprehensively evaluating the user's preferences, clothing, season, specific events, and emotional state.

[1715] example:

[1716] If a user inputs "I like the color blue," "I have three pairs of jeans," and "I like casual style," and the emotion engine recognizes that "I'm in a good mood today," the generative model will suggest an outfit consisting of "a blue shirt, jeans, and white sneakers."

[1717] Step 7:

[1718] Device:

[1719] The generated outfit suggestions are displayed to the user, along with detailed information (such as brand name, price, and purchase link) so that the user can review the suggestions.

[1720] Step 8:

[1721] User:

[1722] Check the displayed outfits, request to change some items as needed, and enter your rating and feedback on the suggestions.

[1723] Step 9:

[1724] server:

[1725] The system analyzes feedback collected from users and stores the evaluation data in a database. The system retrains the generative model based on the feedback data to improve the accuracy of future suggestions.

[1726] example:

[1727] If a user rates a suggested outfit as "very satisfying," the server will reflect this information in future suggestions. It will also analyze how the emotional data influenced the suggestions and use this information to improve them.

[1728] Through these steps, personalized and optimal outfit suggestions are provided to the user. Furthermore, the introduction of an emotion engine enables more personalized suggestions that take into account the user's emotional state, improving the user experience.

[1729] Example 2

[1730] 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."

[1731] Many systems exist that collect information about an individual's fashion preferences and clothing possessions and then suggest optimal outfits based on that information. However, these systems often fail to take into account the user's emotional state, resulting in low user satisfaction. Furthermore, these systems lack the functionality to continuously improve the system based on feedback. This means that consistent results cannot be expected with each use.

[1732] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1733] In this invention, the server includes: means for collecting information on personal preferences and clothing owned by the user; means for providing an interface for inputting preference information, clothing information, and emotional data; means for analyzing the collected information and generating a feature vector for the user; means for analyzing the feature vector and emotional data and weighting the feature vector to reflect the user's current emotional state; means for using the feature vector as input and generating an optimal outfit using a generative model; means for displaying the generated outfit to the user and providing detailed information; and means for collecting user feedback and continuously improving the generative model. This enables more personalized outfit suggestions that take into account the user's preferences and current emotional state. Furthermore, by continuously improving the system based on user feedback, high levels of satisfaction can be maintained over the long term.

[1734] "Personal preferences" refers to information about a user's fashion preferences, such as their favorite colors, styles, and brands.

[1735] "Clothes owned" is a list of clothes owned by the user and their detailed information (color, size, brand, frequency of use, etc.).

[1736] "Emotion data" is information that represents the user's current mood or emotional state, and is acquired through sensors or user input.

[1737] A "feature vector" is a data set that quantifies a user's preference information, characteristics of clothing owned, and emotional data, and is composed of numerical data corresponding to each attribute.

[1738] A "generative model" is a machine learning algorithm or artificial intelligence model that takes a user's feature vector as input and generates the optimal outfit.

[1739] A "coordination" is a combination of clothing suggested by a generative model that takes into account the user's preferences and emotional state.

[1740] "Feedback" refers to information about satisfaction with the evaluations, comments, and suggestions that users make to the system.

[1741] An "interface" is an operation screen or input means that allows a user to input information into the system and confirm suggestions from the system.

[1742] The present invention is a system that collects information on personal preferences and clothing owned by a user, generates feature vectors based on the collected information, and then recognizes the user's emotions to suggest optimal outfits. This system is implemented as follows.

[1743] User data and sentiment collection

[1744] User:

[1745] When accessing the system for the first time, users enter basic information (such as name, age, and gender) and fashion preferences (favorite color, preferred style, etc.). They also upload photos of clothing they own. While using the system, users can input their own emotional state or have their emotions detected using the device's built-in camera and sensors.

[1746] Specifically, users take a photo of their clothing using the camera on their smartphone or PC and upload it to the system. To input their emotional state, a special form is displayed with options, allowing them to select states such as "happy," "sad," and "tired" in real time.

[1747] Device:

[1748] It provides an interface for users to check the information they enter and the images of their clothing they upload, and also has the ability to detect emotions using cameras and sensors.

[1749] Specifically, the device detects the user's face in real time and analyzes their facial expressions, and the analysis results are displayed to the user on a confirmation screen.

[1750] server:

[1751] The system receives preference information, photos of clothing owned, and emotion data sent by the user and stores them in a database. It uses an image analysis tool (e.g., OpenCV) to classify the clothing images and an emotion engine (e.g., facial recognition technology) to analyze the user's emotions.

[1752] Specifically, the server uses the photos of clothing received to automatically identify the color, pattern, and item (shirt, pants, etc.), converts them into text information, and stores it in a database.

[1753] Data analysis and feature vector generation

[1754] server:

[1755] The collected preference information, clothing characteristics, and emotional data are analyzed, and a feature vector for the user is generated based on this data. This feature vector is composed of numerical data corresponding to attributes such as color, style, and item type. Furthermore, weighting is performed based on the emotional data to reflect the user's current mood.

[1756] Specifically, the server analyzes the data, quantifies features such as "I like the color blue," "I have three pairs of jeans," and "I'm in a good mood today," and uses this data to generate a feature vector.

[1757] Generating optimal coordination

[1758] server:

[1759] The generated feature vectors are input into a generative AI model (e.g., a generative model) to generate optimal outfits taking into account the user's emotional state. This generative model then suggests outfit combinations taking into account the user's preferences, clothing, season, specific events, and emotional state.

[1760] Specific examples of prompts are as follows:

[1761] User Information:

[1762] Preferences: I like the color blue

[1763] Clothing: 3 pairs of jeans, 1 white shirt, 2 blue shirts

[1764] Style: Casual

[1765] Emotional state: Feeling good

[1766] Based on this information, we will suggest the best outfit for you.

[1767] Suggestion display and user interaction

[1768] Device:

[1769] The generated outfit suggestions are displayed to the user, along with detailed information (such as brand name, price, and purchase link) so that the user can review the suggestions.

[1770] Specifically, the device displays images and detailed information of outfits on the screen, allowing users to check them. By clicking on the selection options or links, users can be taken to the purchase page for each item.

[1771] User:

[1772] Check the displayed outfits, request to change some items as needed, and enter your rating and feedback on the suggestions.

[1773] Specifically, when a user makes a change request, such as "I want the shoes to be black," the system will again generate the optimal proposal. The user can also select "Very Satisfied," "Satisfied," or "Dissatisfied" in the evaluation form and enter their comments.

[1774] Gathering feedback and improving the generative model

[1775] server:

[1776] The system analyzes the feedback collected from users and stores the evaluation data in a database, which is used to retrain the generative model and improve the accuracy of future suggestions.

[1777] Specifically, the server analyzes the feedback data, adjusts the parameters of the generative AI model based on the evaluation scores and comments, and retrains it to improve the accuracy of the next proposal.

[1778] This system not only provides optimal outfits based on the user's preferences and the clothes they own, but also takes into account the user's emotions to enable more personalized suggestions. Furthermore, by continuously improving the system based on user feedback, it is possible to maintain high levels of satisfaction over the long term.

[1779] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1780] Step 1:

[1781] User Data Collection

[1782] Specific behavior:

[1783] First, users enter basic information and fashion preferences into the system and upload multiple photos of clothing they own.

[1784] Input: User basic information, preferences, and clothing photos.

[1785] Output: User information and uploaded clothing photo data sent to the server.

[1786] The server receives the data sent by the user (basic information, preference information, and photos of clothing owned) and stores it in a database.

[1787] Specific behavior:

[1788] The server receives the data and stores it in a database, storing information such as name, age, gender, preferred colors and styles, and uploaded photos of the clothing.

[1789] Input: Basic information, preferences, and clothing photos received from the user.

[1790] Output: User dataset stored in a database.

[1791] Step 2:

[1792] Collecting Emotional Data

[1793] Specific behavior:

[1794] Users can input their emotional state in real time or use the device's camera or sensors to detect emotions.

[1795] Input: User's emotional state (or device-detected emotional data).

[1796] Output: Emotion data sent to the server.

[1797] The terminal displays the emotional state data entered by the user or the detected emotional data on the screen and provides a confirmation interface.

[1798] Specific behavior:

[1799] The device uses cameras and sensors to detect the user's face in real time, analyzes their facial expressions, and displays the analysis results to the user on a confirmation screen.

[1800] Input: User's emotional state (or device-detected emotional data).

[1801] Output: An emotional state confirmation interface displayed on the screen.

[1802] The server receives the emotion data sent by the user, stores it in a database, and analyzes the emotion using an emotion engine.

[1803] Specific behavior:

[1804] The server uses an emotion analysis tool to analyze the user's emotion data and stores the results in a database.

[1805] Input: Emotion data received from the user.

[1806] Output: Sentiment analysis results stored in a database.

[1807] Step 3:

[1808] Data analysis and feature vector generation

[1809] Specific behavior:

[1810] The server analyzes the collected preference information, clothing characteristics, and emotional data to generate a feature vector for the user.

[1811] Input: Preference information stored in the database, characteristics of clothing owned, and emotional data.

[1812] Output: A feature vector for the user.

[1813] Based on the analyzed data, the server generates numerical data corresponding to each attribute, such as color, style, and item type, and also weights the data based on the emotion data to reflect the user's current mood.

[1814] Specific behavior:

[1815] The server quantifies the data, assigning a score to color preference (for example, red = 2, blue = 5, green = 1) and generates a feature vector. At the same time, it assigns weights based on the emotional data (for example, good mood = 1.2, bad mood = 0.8).

[1816] Input: Analyzed preference information, clothing characteristics, and emotional data.

[1817] Output: A quantified feature vector.

[1818] Step 4:

[1819] Generating optimal coordination

[1820] Specific behavior:

[1821] The server inputs the generated feature vector into a generative AI model and generates the optimal outfit, taking into account the user's emotional state.

[1822] Input: User feature vector.

[1823] Output: The optimal coordinates generated by the generative AI model.

[1824] The generative model suggests outfit combinations based on the user's preferences, clothing, season, specific events, and emotional state.

[1825] Specific prompt examples:

[1826] User Information:

[1827] Preferences: I like the color blue

[1828] Clothing: 3 pairs of jeans, 1 white shirt, 2 blue shirts

[1829] Style: Casual

[1830] Emotional state: Feeling good

[1831] Based on this information, we will suggest the best outfit for you.

[1832] Specific behavior:

[1833] The server sends a prompt to the AI ​​model, which then generates the optimal coordinates based on this.

[1834] Input: User feature vector, emotional state.

[1835] Output: The optimal coordinates suggested to the user.

[1836] Step 5:

[1837] Displaying outfit suggestions

[1838] Specific behavior:

[1839] The device displays the generated outfit suggestions to the user, along with detailed information (such as brand name, price, and purchase link) so the user can review the suggestions.

[1840] Input: The generated coordinates.

[1841] Output: Coordination suggestions and detailed information displayed on the device screen.

[1842] Specifically, the device displays images and detailed information of outfits on the screen, allowing users to check them. By clicking on the selection options or links, users can be taken to the purchase page for each item.

[1843] Input: Generated coordinates, detailed information.

[1844] Output: Coordination suggestions and detailed information displayed on the device screen.

[1845] Step 6:

[1846] Gathering user feedback

[1847] Specific behavior:

[1848] The user can check the proposed outfits, request to change some items as needed, and enter their ratings and feedback on the suggestions.

[1849] Input: Proposed coordinates, user feedback.

[1850] Output: User feedback sent to the server.

[1851] Specifically, the user makes a change request, such as "I want the shoes to be black," and the system receives it and makes a new suggestion. The user also selects "Very Satisfied," "Satisfied," or "Dissatisfied" in the evaluation form and enters comments.

[1852] Input: User feedback.

[1853] Output: Feedback data stored on the server.

[1854] Step 7:

[1855] Improving generative models

[1856] Specific behavior:

[1857] The server analyzes user feedback and stores the evaluation data in a database, which is used to retrain the generative model and improve the accuracy of future suggestions.

[1858] Input: Feedback data from users.

[1859] Output: An improved generative AI model.

[1860] Specifically, the server analyzes the feedback data, adjusts the parameters of the generative AI model based on the evaluation scores and comments, and retrains it to improve the accuracy of the next proposal.

[1861] Input: Feedback data.

[1862] Output: The updated AI model.

[1863] (Application example 2)

[1864] 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."

[1865] Conventional outfit suggestion systems can make suggestions based on a user's personal preferences and the clothing they own, but they cannot take the user's emotional state into account, making it impossible to provide optimal outfits that match the user's mood and psychological state. Therefore, to further improve the user experience, personalized suggestions that take the user's emotional state into account are needed.

[1866] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1867] In this invention, the server includes means for collecting information on the user's preferences and clothing possessions, means for collecting the user's emotional state, and means for analyzing the collected information and emotional state to generate a feature vector of the user, thereby enabling more personalized and optimal outfit suggestions that take into account the user's preferences and current emotional state.

[1868] The "means for collecting information on personal preferences and clothing owned" refers to a device or method for collecting information on fashion preferences entered by a user and photos and detailed information on clothing owned by the user.

[1869] "Means for collecting a user's emotional state" means a device or method for detecting and recording a user's emotional or psychological state in real time, including, for example, biometric analysis using cameras or sensors.

[1870] "Means for analyzing collected information and emotional state and generating a feature vector of the user" refers to a device or method that converts the user's fashion trends and current emotions into numerical data based on the collected user preference information, clothing information, and emotional data, and expresses them as a feature vector.

[1871] A "means for generating optimal outfits using a generative model" is a device or method that inputs a user's feature vector into a generative AI model and, from the results, suggests optimal clothing combinations based on the user's preferences and emotional state.

[1872] The "means for displaying the generated coordinated outfits to the user" refers to a device or method for displaying the proposed clothing combinations so that the user can check them and select or modify them.

[1873] "Means for collecting user feedback and continuously improving the generative model" refers to a device or method that collects user ratings and opinions on the proposed outfits, and then uses that data to retrain the generative model and improve its accuracy.

[1874] This invention is a system that proposes optimal outfits that take into account a user's emotional state based on information about the user's fashion preferences and the clothing they own. The system is realized by the following steps.

[1875] User data and sentiment collection

[1876] User: The user launches an application installed on their smartphone or head-mounted display (HMD) and inputs basic information and fashion preferences. They also upload photos of their clothing through the application. Furthermore, their emotional state is collected in real time using the smartphone camera and the HMD's built-in sensors.

[1877] Data analysis and feature vector generation

[1878] Server: The collected user preference information, clothing information, and emotional data are sent to a cloud server. On the server side, the uploaded clothing images are analyzed using the Google Cloud Vision API to classify the type, color, and style of the clothing. Meanwhile, the emotional data is analyzed using IBM Watson Tone Analyzer. Next, a feature vector for the user is generated based on this data. This feature vector represents the color, style, type of item, emotional state, and other factors as numerical data.

[1879] Generating optimal coordination

[1880] Server: The generated feature vectors and emotion data are input into a generative AI model (e.g., OpenAI GPT-3) to generate optimal outfits based on the user's preferences and current emotional state. The generated outfit suggestions take into account the user's preferences, clothing they own, the season, specific events, and their emotional state to suggest outfit combinations.

[1881] As a specific example, if a user inputs "I like casual style," "I like blue items," "I have several pairs of jeans," and also has emotional data such as "I'm in a good mood today," the generative AI model will suggest an outfit such as "a blue shirt, jeans, and white sneakers."

[1882] An example prompt is:

[1883] The user's preferred style is casual. The clothing they own is blue items and jeans. Their current emotional state is good. Based on this information, please suggest the best outfit for them.

[1884] Suggestion display and user interaction

[1885] Device: The suggested outfits are displayed on the user's smartphone or HMD. The user can review the suggested outfits and check detailed information (e.g., brand name, price, purchase link, etc.). Furthermore, if the user is not satisfied with the suggested outfits, they can request to change some items within the application.

[1886] Gathering feedback and improving the generative model

[1887] Server: Collects feedback entered by users on outfit suggestions. The collected feedback data is stored in a database and used to train the next generation model. This allows the generation model to continuously improve, resulting in more accurate suggestions in the future.

[1888] This system makes it possible to propose outfits that take into account the user's individual preferences and emotional state, significantly improving the user experience.

[1889] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1890] Step 1:

[1891] The user enters basic information and preference information

[1892] A user launches an application installed on a smartphone or head-mounted display (HMD) and inputs basic information (e.g., name, gender, height) and fashion preferences (e.g., favorite color, favorite style). The input information is temporarily stored in the application's local storage and then sent to a cloud server. A dataset containing the input data is formed.

[1893] Step 2:

[1894] Upload photos of clothing that users own

[1895] Users take photos of their clothing and upload them to the application. The uploaded image data is sent to a cloud server and subjected to image analysis. Specifically, the smartphone's camera application is launched, and the image is transferred to the server after it has been taken.

[1896] Step 3:

[1897] Collecting emotional states

[1898] To collect the user's current emotional state, the smartphone camera and the HMD's built-in sensors are activated to collect facial expression data and information from biometric sensors. The collected emotional data is also sent to a cloud server. Specifically, the application acquires data using the camera and sensors in real time.

[1899] Step 4:

[1900] Data analysis

[1901] The server analyzes the collected user preference information, photos of the clothing they own, and emotional data. The photos of the clothing are classified using the Google Cloud Vision API to determine the color, style, and type of each item. The emotional data is analyzed using IBM Watson Tone Analyzer, and the user's emotional state is quantified. The input data are image files, emotional data, and text information, and the output is the analysis results and feature vectors.

[1902] Step 5:

[1903] Feature Vector Generation

[1904] The server generates a feature vector for the user based on the analyzed preference information, clothing information, and emotional data. This feature vector contains numerical data corresponding to each attribute, such as color, style, item type, and emotional state. The input data is the analysis result, and the output is the feature vector.

[1905] Step 6:

[1906] Generating optimal coordination

[1907] Based on the generated feature vector and emotion data, the server inputs the feature vector into a generative AI model (e.g., OpenAI GPT-3) to generate the optimal outfit. An example of a prompt sentence is, "The user's preferred style is casual. The clothing they own is blue items and jeans. Their current emotional state is good. Please suggest the optimal outfit based on this information." The input data is the feature vector, and the output data is the outfit suggestion.

[1908] Step 7:

[1909] Displaying suggestions to the user

[1910] The generated outfit suggestions are displayed on the user's smartphone or HMD. The user can review the suggested outfits and check their details (e.g., brand name, price, and purchase link). The input data is the outfit suggestions, and the output data is the user's feedback.

[1911] Step 8:

[1912] Gathering feedback and improving the model

[1913] The server collects user ratings and correction requests for outfit suggestions. The collected feedback data is stored in a database and used to train the next generative model. This allows the generative model to be continuously improved, resulting in improved proposal accuracy from the next time onwards. The input data is user feedback, and the output data is updated model parameters.

[1914] 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.

[1915] 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.

[1916] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1917] 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.

[1918] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1919] 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.

[1920] 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).

[1921] 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.

[1922] 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."

[1923] 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.

[1924] 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).

[1925] 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.

[1926] 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.

[1927] 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.

[1928] 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.

[1929] 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.

[1930] 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.

[1931] 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.

[1932] 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.

[1933] 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.

[1934] 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.

[1935] The following is further disclosed regarding the above embodiment.

[1936] (Claim 1)

[1937] A means for collecting information about personal preferences and clothing items owned;

[1938] means for analyzing the collected information and generating a feature vector for the user;

[1939] means for generating an optimal coordinate using a generative model with the feature vector as an input;

[1940] means for displaying the generated coordinates to a user;

[1941] The system includes means for collecting feedback from users and continuously improving the generative model.

[1942] (Claim 2)

[1943] 2. The system according to claim 1, which suggests clothing according to a specific event or situation of the user.

[1944] (Claim 3)

[1945] 10. The system according to claim 1, wherein the system makes coordination suggestions to other members in the user's household.

[1946] (Claim 4)

[1947] 10. The system of claim 1, further comprising means for analyzing images of clothing carried by a user and classifying their features.

[1948] (Claim 5)

[1949] 2. The system according to claim 1, which proposes clothing for a virtual avatar in a metaverse space.

[1950] "Example 1"

[1951] (Claim 1)

[1952] A means for collecting information about personal preferences and clothing possessions;

[1953] A means for storing the collected information in a database and analyzing the uploaded clothing images to classify the characteristics of each item;

[1954] means for generating a feature vector of the user based on the collected information and the analyzed characteristics;

[1955] means for inputting the feature vector into a generative model to generate an optimal coordinate;

[1956] a means for displaying the generated coordination to a user and providing detailed information about each item;

[1957] A means to collect user feedback and retrain the generative model based on that data to improve the accuracy of the suggestions.

[1958] A system including:

[1959] (Claim 2)

[1960] 2. The system according to claim 1, which suggests clothing according to a specific event or situation of the user.

[1961] (Claim 3)

[1962] 10. The system of claim 1, wherein the system makes coordination suggestions to other members of the user's household.

[1963] "Application Example 1"

[1964] (Claim 1)

[1965] a means for collecting information about an individual's preferences and clothing possessions;

[1966] means for analyzing the collected information and generating a feature vector for the user;

[1967] means for generating an optimal coordinate using a generative model with the feature vector as an input;

[1968] means for displaying the generated coordinates to a user;

[1969] a means for collecting user feedback and continuously improving the generative model;

[1970] A means for scanning products in a store and acquiring product information that matches a feature vector of a user;

[1971] A means using an augmented reality algorithm to visually display coordination suggestions in real space;

[1972] a means for displaying detailed information about each item of the coordination proposal;

[1973] A system including:

[1974] (Claim 2)

[1975] 2. The system according to claim 1, which suggests clothing according to a specific event or situation of the user.

[1976] (Claim 3)

[1977] 10. The system according to claim 1, wherein the system makes coordination suggestions to other members in the user's household.

[1978] "Example 2: Combining Emotion Engines"

[1979] (Claim 1)

[1980] A means for collecting information about personal preferences and clothing items owned;

[1981] A means for providing an interface for inputting preference information, clothing information, and emotion data;

[1982] means for analyzing the collected information and generating a feature vector for the user;

[1983] means for analyzing the feature vectors and emotion data and weighting them to reflect the current emotional state of the user;

[1984] means for generating an optimal coordinate using a generative model with the feature vector as an input;

[1985] means for displaying the generated coordinates to a user and providing detailed information;

[1986] The system includes means for collecting feedback from users and continuously improving the generative model.

[1987] (Claim 2)

[1988] 2. The system according to claim 1, which suggests clothing according to a specific event or situation of the user.

[1989] (Claim 3)

[1990] 10. The system according to claim 1, wherein the system makes coordination suggestions to other members in the user's household.

[1991] "Application example 2 when combining emotion engines"

[1992] (Claim 1)

[1993] A means for collecting information about personal preferences and clothing items owned;

[1994] means for collecting the user's emotional state;

[1995] means for analyzing the collected information and emotional state to generate a feature vector of the user;

[1996] means for generating an optimal coordinate using a generative model with the feature vector as an input;

[1997] means for displaying the generated coordinates to a user;

[1998] The system includes means for collecting feedback from users and continuously improving the generative model.

[1999] (Claim 2)

[2000] 2. The system according to claim 1, which suggests clothing according to a specific event or situation of the user.

[2001] (Claim 3)

[2002] 10. The system according to claim 1, wherein the system makes coordination suggestions to other members in the user's household. [Explanation of symbols]

[2003] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for collecting information about personal preferences and clothing items owned; means for analyzing the collected information and generating a feature vector for the user; means for generating an optimal coordinate using a generative model with the feature vector as an input; means for displaying the generated coordinates to a user; The system includes means for collecting feedback from users and continuously improving the generative model.

2. The system according to claim 1, wherein the system suggests clothing according to a specific event or situation of the user.

3. The system according to claim 1, wherein the system provides coordination suggestions to other members of the user's household.

4. 10. The system of claim 1, further comprising means for analyzing images of clothing carried by a user and classifying their features.

5. The system according to claim 1, wherein clothing suggestions are made to a virtual avatar in a metaverse space.

Images