System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting basic user information; means for collecting user's own item information; means for analyzing the collected user information and grasping user's preference and trend; means for causing a generative AI to learn commodity information; means for causing the generative AI to propose coordination based on the user information and the commodity information; and means for providing purchase, rental, and purchase from a free market of a commodity proposed to the user.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] Many people often have trouble deciding what clothes to wear in their daily lives or for special events. Fashion website operators are expected to provide products that best suit their customers' preferences, but this has not been fully achieved. A lack of personalized suggestions to customers also creates a problem of insufficient growth in website sales. The objective of the present invention is to solve these issues and increase sales on fashion websites while providing users with an optimal fashion experience. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for collecting basic user information, a means for collecting information about the user's inventory, a means for analyzing the collected user information to understand the user's preferences and trends, a means for training a generation AI on product data, a means for the generation AI to suggest outfits based on the user information and product data, a means for providing a virtual try-on function, and a means for the user to purchase, rent, or purchase the suggested items from a flea market. This system allows users to easily find the perfect fashion item and can also increase sales on fashion sites. Furthermore, the present invention provides a system that includes a means for storing the collected user's basic information and inventory information in a database and a means for filtering the outfits suggested by the generation AI to select those that best suit the user's preferences and the latest trends, thereby enabling more accurate and personalized fashion suggestions.

[0006] "Basic user information" refers to information relating to an individual, such as the user's age, sex, height, weight, preferred fashion style, preferred color, and event information.

[0007] "User's owned item information" is information about clothes, accessories, etc. that the user already owns, and is registered by photograph or manual input.

[0008] "Generative AI" is a type of artificial intelligence that learns user information and product data and suggests the best outfits for the user.

[0009] "Coordination suggestions" are combinations of clothing and accessories suggested by the AI ​​based on the user's preferences, items they own, and the latest trends.

[0010] The "virtual try-on function" is a simulation function that allows the user to visually check suggested outfits and virtually try on outfits that fit their own body type.

[0011] "Product data" refers to information about products on a fashion site, including detailed information such as category, size, color, style, and price.

[0012] "Filtering" is the process of selecting from the outfits proposed by the generation AI the one that best suits the user's preferences and the latest trends.

[0013] A "database" is a data storage system that stores collected user information and product information so that it can be accessed and analyzed later.

[0014] "Rental" is a service in which a user temporarily borrows a proposed product and returns the product after using it for a certain period of time.

[0015] A "flea market" is an online marketplace where users can purchase used items from other users. [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 for proposing optimal fashion coordination to a user, and specific embodiments thereof will be described below.

[0038] 1. Collection of User Information

[0039] A user starts the application and enters profile information (age, sex, height, weight, preferred fashion style, preferred colors, event information, etc.).

[0040] A user uses a device (such as a smartphone or PC) to enter their basic information into the application. For example, if a user is a 30-year-old woman whose preferred style is "business casual" and whose preferred color is "navy blue," they would enter this information.

[0041] The user registers information about the items they have on hand.

[0042] Additionally, users can register information about clothes and accessories they already own by taking photos or manually entering them, such as uploading a navy skirt, a white shirt, and black heels.

[0043] 2. Analysis of information

[0044] The terminal transmits user information and on-hand item information to the server.

[0045] The collected user basic information and information on items in hand is sent from the device to the server, which stores this information in a database and assigns each user a unique ID.

[0046] The server analyzes the user data.

[0047] The server performs an initial analysis of the received user information to understand basic fashion styles and trends. This analysis reveals the user's preferences and trends in detail.

[0048] 3. Product Data Learning

[0049] The server collects all product information on the fashion site.

[0050] The server collects all product information (category, size, color, style, price, etc.) on the fashion site and stores it in a database.

[0051] The server trains the AI ​​to learn the product data.

[0052] The collected product data is input into the generative AI, which then updates its model based on this information, allowing the AI ​​to understand the latest fashion trends and suggest appropriate outfits.

[0053] 4. Coordination Proposal Generation

[0054] The server generates AI based on user information and product data to suggest outfits.

[0055] The server inputs the analyzed user information and learned product data into the generation AI, which then generates the optimal outfit.

[0056] The server filters multiple coordination proposals.

[0057] From the multiple coordination suggestions generated by the AI, the server selects the one that best suits the user's preferences and the latest trends.

[0058] 5. Virtual try-on feature

[0059] The server generates virtual try-on data for the selected outfit.

[0060] The server generates virtual try-on data for the selected outfit and matches it with the user's body type information.

[0061] Users can visually check the product using the virtual try-on function.

[0062] Users can use the virtual try-on feature on their device to visually see how suggested outfits will look on them, simulating how a navy blazer and white blouse would look, for example.

[0063] 6. Purchasing, renting, and flea markets

[0064] The user decides on the suggested product options.

[0065] The user can browse the suggested items on the terminal and choose to buy, rent, or purchase from the flea market.

[0066] The terminal inputs payment information, and the server processes the payment.

[0067] The user enters payment information based on the option selected, and the server processes the payment.

[0068] The server arranges delivery.

[0069] The server will arrange delivery for items for which purchase or rental procedures have been completed. In the case of flea markets, the server will support communication between sellers and buyers and handle delivery procedures.

[0070] This series of program processes allows users to easily find the perfect fashion item, and fashion site operators can increase sales through personalized suggestions.

[0071] The processing flow will be explained below.

[0072] Step 1:

[0073] The user starts the application on the terminal and enters profile information (age, sex, height, weight, preferred fashion style, preferred colors, event information, etc.).

[0074] Step 2:

[0075] The user uses a terminal to register information about clothes and accessories that they already own by taking photos or manually entering the information.

[0076] Step 3:

[0077] The terminal transmits the user's basic information and information about items in hand to the server.

[0078] Step 4:

[0079] The server stores the received user information and on-hand item information in a database and assigns a unique ID to each user.

[0080] Step 5:

[0081] The server performs an initial analysis of user data to determine basic fashion styles and trends.

[0082] Step 6:

[0083] The server collects all product information (category, size, color, style, price, etc.) from the fashion site.

[0084] Step 7:

[0085] The server inputs the collected product data into the generation AI, which then updates the model based on this information.

[0086] Step 8:

[0087] The server inputs analyzed user information and learned product data into the generation AI to generate the optimal outfit.

[0088] Step 9:

[0089] From the multiple coordination suggestions generated by the AI, the server selects the one that best suits the user's preferences and the latest trends.

[0090] Step 10:

[0091] The server generates virtual try-on data for the selected outfit and matches it with the user's body type information.

[0092] Step 11:

[0093] The user can use the virtual try-on function on the device to visually check the suggested outfits.

[0094] Step 12:

[0095] The user browses the suggested items on the device and chooses to buy, rent, or purchase from a flea market.

[0096] Step 13:

[0097] The terminal inputs payment information based on the selection, and the server processes the payment.

[0098] Step 14:

[0099] The server will arrange delivery for items for which purchase or rental procedures have been completed. In the case of flea markets, it will support communication between sellers and buyers and delivery procedures.

[0100] This series of processing steps allows users to easily find the perfect fashion item, and fashion site operators to increase sales.

[0101] Example 1

[0102] 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."

[0103] Previous fashion coordination suggestion systems lacked the ability to provide personalized suggestions based on user preferences and trends, and users had limited means to visually confirm the suggested outfits. Furthermore, the procedures and delivery arrangements for purchasing the suggested items were cumbersome. This made it difficult for users to find the perfect fashion items, and prevented fashion site operators from fully increasing their sales.

[0104] 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.

[0105] In this invention, the server includes means for collecting basic information about the user, means for collecting information about items the user owns, means for transmitting the collected user information, means for analyzing the collected user information and understanding the user's preferences and trends, means for collecting product data, means for training a generation AI to learn the product data, means for the generation AI to suggest outfits based on the user information and the product data, means for filtering the outfits suggested by the generation AI and selecting those that best suit the user's preferences and the latest trends, means for generating virtual try-on data, means for providing a virtual try-on function, means for offering the user the option to purchase, rent, or purchase suggested items from a flea market, means for processing payments, and means for arranging delivery. This allows users to easily find the perfect fashion item, and fashion site operators can increase sales through personalized suggestions.

[0106] The "means for collecting basic information about the user" is a function for acquiring personal information about the user, such as age, sex, height, weight, preferred fashion style, preferred colors, and event information.

[0107] The "means for collecting information on items owned by the user" is a function for collecting information on clothes and accessories that the user already owns by taking photographs or manually entering the information.

[0108] The "means for transmitting collected user information" is a function for transmitting the user's basic information and on-hand item information collected by the terminal to the server.

[0109] "Means of analyzing collected user information and understanding user preferences and trends" refers to a function that allows the server to analyze information received from users and understand their preferences and current fashion trends.

[0110] "Means for collecting product data" is a function that allows the server to obtain all product information on the fashion site and store it in a database.

[0111] "Means for training the generative AI on product data" refers to a function that inputs collected product data into the generative AI, allowing the AI ​​to learn the latest fashion trends.

[0112] "A means for the generation AI to suggest coordination based on user information and product data" is a function that allows the generation AI to analyze user information and product data and suggest the optimal fashion coordination.

[0113] "Means of filtering the outfits proposed by the generation AI and selecting the one that best suits the user's preferences and the latest trends" is a function that selects the outfit that best suits the user's preferences and the latest trends from among the multiple outfit ideas created by the generation AI.

[0114] The "means for generating virtual try-on data" is a function for matching the selected outfit with the user's body type information and generating virtual try-on data that can be visually confirmed.

[0115] The "means for providing a virtual try-on function" is a function that allows a user to use a terminal to access virtual try-on data and visually check suggested outfits.

[0116] "Means for providing users with the ability to purchase, rent, or purchase suggested items from a flea market" is a feature that provides users with the option to purchase, rent, or purchase suggested items from a flea market.

[0117] "Means for processing payment" refers to the function that allows the server to process the payment required to purchase or rent the item selected by the user based on the payment information entered.

[0118] "Means for arranging delivery" refers to arranging delivery of items that have been purchased or rented, and in the case of flea markets, this is a function that supports communication between sellers and buyers and the delivery process.

[0119] This invention is a system for proposing optimal fashion coordination to a user. The system collects basic information about the user and information about items they own, analyzes this information, and then proposes coordination based on a generative AI model. It then provides a virtual try-on function, allowing the user to purchase, rent, or buy the proposed items from a flea market. A specific embodiment of the system is shown below.

[0120] Collection of User Information

[0121] After launching the application using a device such as a smartphone or PC, users enter their basic information. Input items include age, gender, height, weight, preferred fashion style, favorite color, and event information. For example, if you are a 30-year-old woman whose preferred style is "business casual" and favorite color is "navy," you would enter this information.

[0122] Users can also register information about clothes and accessories they already own by taking photos or manually entering them. For example, they can upload information about a navy skirt, a white shirt, and black heels to their device.

[0123] Analysis of information

[0124] The device sends the collected user basic information and information about items in their possession to the server. The server stores this information in a database and assigns each user a unique ID. The server performs an initial analysis based on the received information to understand the user's preferences and trends.

[0125] Learning product data

[0126] The server periodically collects all product information (category, size, color, style, price, etc.) from the fashion site and stores it in a database. The server inputs the collected product data into the generation AI and updates the generation AI model. This allows the generation AI to understand the latest fashion trends and propose appropriate outfits.

[0127] Generating outfit suggestions

[0128] The server inputs the analyzed user information and learned product data into the AI, which then proposes the optimal outfit. For example, it generates a combination of "navy skirt, white shirt, and black heels." The server then selects from the multiple outfit suggestions it has generated the one that best suits the user's preferences and the latest trends.

[0129] Providing virtual try-on functionality

[0130] The server generates virtual try-on data for the selected outfit and matches it with the user's body type. The user can then use the virtual try-on function on their device to visually check how the suggested outfit will suit them. For example, they can simulate how a navy blazer and white blouse would look.

[0131] Product purchases, rentals, and flea markets

[0132] The user browses the suggested items on their device and selects whether to buy, rent, or purchase from a flea market. Based on the option selected by the user, payment information is entered and the server processes the payment. Once the purchase or rental procedure is complete, the server arranges delivery of the item. In the case of a flea market, the server supports communication between the seller and buyer and the delivery procedure.

[0133] Specific examples

[0134] As a concrete example, let's say the user is a 30-year-old woman who likes business casual clothing and owns a navy skirt, a white shirt, and black heels. The system uses this information to suggest the best outfits. It also uses the virtual try-on feature to visually check how a navy blazer and a white blouse look.

[0135] Example prompt sentence:

[0136] "I'm a 30-year-old woman who likes business casual. I have a navy skirt, a white shirt, and black heels."

[0137] "I'd like to try on a virtual navy blazer and white blouse combination."

[0138] As described above, this system suggests the most suitable fashion items to users and makes it easy to purchase or rent them. This also enables fashion site operators to increase sales through personalized suggestions.

[0139] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0140] System program processing flow

[0141] Step 1:

[0142] Enter your user profile

[0143] Specific description:

[0144] The user starts the application and enters their profile information (age, gender, height, weight, preferred fashion style, preferred color, event information, etc.). For example, if a user is a 30-year-old woman whose preferred style is "business casual" and whose preferred color is "navy," they enter this information into the device.

[0145] Input and Output:

[0146] Input: User profile information

[0147] Output: User profile information is saved on the device

[0148] Step 2:

[0149] Registering on-hand item information

[0150] Specific description:

[0151] Users can register information about clothes and accessories they already own by taking photos or manually entering them, such as a navy skirt, a white shirt, and black heels, and uploading them to their device.

[0152] Input and Output:

[0153] Input: Information about items on hand

[0154] Output: Information about items in your possession is saved on the device.

[0155] Step 3:

[0156] Sending user information

[0157] Specific description:

[0158] The device sends the collected user information and item information to the server, which stores the information in a database and assigns a unique ID to each user.

[0159] Input and Output:

[0160] Input: User information and item information stored on the device

[0161] Output: User information and item information stored on the server

[0162] Step 4:

[0163] User information analysis

[0164] Specific description:

[0165] The server performs an initial analysis based on the received user information to understand the user's basic preferences and trends. For example, if the user prefers business casual attire, this tendency will be tracked.

[0166] Input and Output:

[0167] Input: User information stored in the database

[0168] Output: Analysis results of user preferences and trend information

[0169] Step 5:

[0170] Collecting product information

[0171] Specific description:

[0172] The server collects all product information from the fashion site and stores it in a database, including information such as category, size, color, style, and price.

[0173] Input and Output:

[0174] Input: Product information from a fashion website

[0175] Output: Product information stored in the database

[0176] Step 6:

[0177] Generative AI training

[0178] Specific description:

[0179] The server inputs the collected product data into the generation AI and updates the model, allowing the generation AI to understand the latest fashion trends and propose outfits.

[0180] Input and Output:

[0181] Input: Product information stored in the database

[0182] Output: A generative AI model that learns the latest fashion trends

[0183] Step 7:

[0184] Generating outfit suggestions

[0185] Specific description:

[0186] The server inputs the analyzed user information and learned product data into the AI, which then generates the optimal outfit. For example, it generates a combination of a navy skirt, a white shirt, and black heels.

[0187] Input and Output:

[0188] Input: User information, product information

[0189] Output: Generated outfit suggestions

[0190] Step 8:

[0191] Filtering outfit suggestions

[0192] Specific description:

[0193] The server selects from the multiple coordinated outfit suggestions generated the one that best suits the user's preferences and the latest trends.

[0194] Input and Output:

[0195] Input: Generated outfit suggestions

[0196] Output: Filtered optimal outfit suggestions

[0197] Step 9:

[0198] Generate virtual try-on data

[0199] Specific description:

[0200] The server generates virtual try-on data for the selected outfit and matches it with the user's body type information, allowing the user to visually check the suggested outfit.

[0201] Input and Output:

[0202] Input: Filtered outfit suggestions, user's body type information

[0203] Output: Generated virtual fitting data

[0204] Step 10:

[0205] Providing virtual try-on functionality

[0206] Specific description:

[0207] Users can use the virtual try-on feature on their device to see how suggested outfits will look on them, for example, simulating how a navy blazer and white blouse would look.

[0208] Input and Output:

[0209] Input: Virtual try-on data

[0210] Output: Visual confirmation through virtual try-on

[0211] Step 11:

[0212] Product selection and payment

[0213] Specific description:

[0214] The user browses the suggested items on the terminal and selects whether to buy, rent, or purchase from the flea market. After making a selection, the user enters payment information, and the server processes the payment.

[0215] Input and Output:

[0216] Input: Selected items, payment information

[0217] Output: Payment completion notification

[0218] Step 12:

[0219] Delivery arrangements

[0220] Specific description:

[0221] The server arranges delivery of purchased or rented items. In the case of a flea market, it supports communication between sellers and buyers and handles delivery procedures.

[0222] Input and Output:

[0223] Input: Payment completion notification, delivery information

[0224] Output: Delivery arrangement completion notification

[0225] This series of programs allows users to easily find the perfect fashion item to purchase or rent, and the virtual try-on feature allows users to see how it will look in real life.

[0226] (Application example 1)

[0227] 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."

[0228] Conventional fashion coordination systems have been unable to adequately address users' specific needs and preferences, and few of them have a virtual try-on function, making it difficult for users to easily find suitable fashion items at home. Another issue is the limited options for purchasing or renting various clothing items. Furthermore, few systems offer real-time virtual try-on functionality, which tends to discourage users from making purchases.

[0229] 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.

[0230] In this invention, the server includes means for collecting basic user information, means for collecting information on the user's owned items, means for analyzing the collected user information to understand the user's preferences and trends, means for training a generation AI to learn product data, means for the generation AI to suggest outfits based on the user information and product data, means for providing a virtual try-on function, means for offering the purchase, rental, or flea market purchase of suggested items in a virtual store, means for trying on items in a virtual space in real time using a head-mounted display, and means for arranging delivery of purchased or rented items. This allows users to easily try on fashion items virtually from the comfort of their own home and receive optimal outfit suggestions. Furthermore, the increased options for purchasing and renting products provide a more satisfying shopping experience.

[0231] "Means for collecting basic user information" refers to a method of providing an interface for users to enter profile information such as their age, gender, height, weight, preferred fashion style, favorite colors, and event information, and then incorporating this information into the system.

[0232] The "means for collecting information on items owned by the user" refers to a method by which the user registers information on the clothes and accessories that he or she owns by taking photographs or manually entering the information.

[0233] "Means for analyzing collected user information and understanding user preferences and trends" refers to technology that analyzes collected basic information about users and information about items they own, and identifies their preferences and current fashion trends.

[0234] "Method of having the generative AI learn product data" refers to a method of collecting all product information on a fashion site, inputting that data into the generative AI, and updating the model.

[0235] "Means for generative AI to suggest coordination based on user information and product data" refers to a method in which generative AI uses analyzed user information and learned product data to provide optimal fashion coordination.

[0236] The "means for providing a virtual try-on function" is a technology that allows a user to try on suggested fashion items in a virtual space and visually check them.

[0237] "Means for offering suggested items for purchase, rental, or purchase from a flea market within a virtual store" is a function that allows a user to choose to purchase, rent, or trade suggested items at a flea market.

[0238] "Means for trying on clothes in a virtual space in real time using a head-mounted display" is a technology that allows users to try on and experience fashion items in a virtual space in real time using a head-mounted display.

[0239] "Means for arranging delivery of purchased or rented products" refers to the procedures for delivering the products purchased or rented by the user to the specified address.

[0240] The system for implementing this invention mainly uses a server, a user terminal, and a head-mounted display (HMD). A specific form of the system is shown below.

[0241] System Configuration

[0242] Hardware and software used:

[0243] Server: General cloud computing service (e.g., Amazon Web Services EC2)

[0244] Database: Relational database system (e.g. Amazon RDS)

[0245] Generative AI models: advanced natural language generation systems (e.g., OpenAI GPT-4)

[0246] User device: Smartphone or personal computer

[0247] Virtual try-on engine: Advanced 3D engine (e.g. Unity 3D)

[0248] Head-mounted displays: commonly used VR devices (e.g., Oculus Rift or HTC Vive)

[0249] Program Overview

[0250] 1. User Information Collection:

[0251] The user uses the terminal to input profile information such as age, sex, height, weight, preferred fashion style, preferred colors, and event information.

[0252] Profile information is sent from the user's device to the server and stored in a database (Amazon RDS).

[0253] 2. Registering your inventory:

[0254] The user uses the device's camera to take photos of the clothes and accessories they own and registers them.

[0255] Using image recognition technology (e.g., Amazon Rekognition), item information is classified and stored in a database.

[0256] 3. Information analysis and product data learning:

[0257] The server analyzes the collected user information to understand user preferences and trends.

[0258] The latest item data is collected by scraping from fashion sites and trained on a generative AI (e.g., GPT-4).

[0259] 4. Coordination proposal generation:

[0260] The generative AI uses analyzed user information and the latest product data to generate optimal coordination suggestions.

[0261] Suggested outfits are filtered based on user preferences and the latest trends.

[0262] 5. Virtual try-on feature:

[0263] The user wears a head-mounted display and tries on the suggested items in a virtual space.

[0264] Using Unity 3D, you can try on your avatar in real time and visually check the fit.

[0265] 6. Product Purchases, Rentals, and Flea Markets:

[0266] The user can choose to buy, rent, or purchase the suggested items from a flea market.

[0267] Once the selected items are purchased, payment information is entered and delivery arrangements are made.

[0268] Specific examples

[0269] Example 1: Prompt when user enters profile information:

[0270] "30 years old, female, height 160cm, weight 55kg, preferred style is business casual, preferred color is navy, event information is company presentation."

[0271] Example 2: Prompt for collecting fashion item data:

[0272] "Collect the latest business casual fashion items and learn about categories, sizes, colors, styles, and pricing information."

[0273] In this way, users can easily find suitable fashion items at home, virtually try them on in real time, and enjoy a wide variety of choices, increasing user satisfaction.

[0274] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0275] Step 1: Collect user information

[0276] The user uses a device to enter profile information such as age, gender, height, weight, preferred fashion style, favorite colors, and event information. The entered information is sent from the device to the server and stored in a database. The input data is sent in JSON format, received by the server, and stored in the database. As an output, a record of the user information is added to the database.

[0277] Step 2: Register your inventory information

[0278] The user uses the device's camera to take a photo of the clothes or accessories they own and registers it. The image file and manually entered details are sent to the server. The server uses image recognition technology to identify the item and store the information in a database. The input data is the image file and a description, and the output is a record of the item information added to the database.

[0279] Step 3: Information analysis and product data learning

[0280] The server analyzes the collected user information and information on items in hand to understand the user's preferences and trends. The server then scrapes and collects the latest item data from fashion sites and trains the generative AI model. The input data is user information and item data, and the output is an analysis of the user's preferences and trends and an updated AI model.

[0281] Step 4: Generate outfit suggestions

[0282] The server uses a generative AI model to generate optimal outfit suggestions based on the analyzed user information and product data. The generated outfits are filtered based on user preferences and the latest trends. The input data are the analysis results and product data, and the output is a list of suggested outfits.

[0283] Step 5: Providing virtual try-on functionality

[0284] The user wears a head-mounted display and tries on the suggested items in a virtual space. The server uses the Unity 3D engine to have an avatar try on the items in real time, allowing the user to visually confirm them. The input data is the suggested outfit, and the output is a virtual try-on scene that is displayed on the user's HMD.

[0285] Step 6: Buying, renting, and going to the flea market

[0286] The user can choose to purchase, rent, or buy from a flea market of the suggested items. The selected item progresses through the purchase process by entering payment information, and the server arranges delivery. The input data is the user's selection and payment information, and the output is a purchase confirmation and notification of delivery arrangements.

[0287] 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.

[0288] The present invention combines an emotion engine with a system that proposes optimal fashion coordination to a user, and specific embodiments thereof are described below.

[0289] 1. Collection of User Information

[0290] A user starts the application and enters profile information (age, sex, height, weight, preferred fashion style, preferred colors, event information, etc.).

[0291] A user inputs their basic information into the application using a device (such as a smartphone or PC). For example, if a user is a 30-year-old woman whose preferred style is "business casual" and whose preferred color is "navy blue," the user inputs this information.

[0292] The user registers information about the items they have on hand.

[0293] Additionally, users can register information about clothes and accessories they already own by taking photos or manually entering them, such as uploading a navy skirt, a white shirt, and black heels.

[0294] 2. Analysis and storage of information

[0295] The terminal transmits user information and on-hand item information to the server.

[0296] The collected user basic information and information on items in hand is sent from the device to the server, which then stores this information in a database and assigns each user a unique ID.

[0297] The server analyzes the user data.

[0298] The server performs an initial analysis of the received user information to understand basic fashion styles and trends, thereby clarifying the user's preferences and current trends.

[0299] 3. Product Data Learning

[0300] The server collects all product information (category, size, color, style, price, etc.) from the fashion site.

[0301] The server collects all product information on the fashion site and stores it in a database.

[0302] The server trains the AI ​​to learn the product data.

[0303] The collected product data is input into the generative AI, which then updates its model based on this information, allowing the AI ​​to understand the latest fashion trends and suggest appropriate outfits.

[0304] 4. Coordination proposal generation and optimization

[0305] The server generates AI based on user information and product data to suggest outfits.

[0306] The server inputs the analyzed user information and learned product data into the generation AI to generate the optimal coordination.

[0307] The server filters multiple coordination proposals.

[0308] From the multiple coordination suggestions generated by the AI, the server selects the one that best suits the user's preferences and the latest trends.

[0309] 5. Emotion Recognition by Emotion Engine

[0310] As users visually check the virtual try-on feature, an emotion engine analyzes the user's current emotional state.

[0311] When a user uses the virtual try-on function on their device to visually check the suggested outfits, the emotion engine recognizes the user's emotional state based on their facial expressions, tone of voice, input actions, etc.

[0312] The server optimizes coordination suggestions based on the results of the emotion engine.

[0313] Based on the user's emotional state obtained by the emotion engine, the server reevaluates the coordination suggestions and, if necessary, changes the content or order of the suggestions.

[0314] 6. Purchasing, renting, and flea markets

[0315] The user decides on the suggested product options.

[0316] The user can browse the suggested items on the terminal and choose to buy, rent, or purchase from the flea market.

[0317] The terminal inputs payment information, and the server processes the payment.

[0318] The user enters payment information based on the option selected, and the server processes the payment.

[0319] The server arranges delivery.

[0320] The server will arrange delivery for items for which purchase or rental procedures have been completed. In the case of flea markets, the server will support communication between sellers and buyers and handle delivery procedures.

[0321] Specific examples

[0322] For example, suppose a user owns a "navy skirt, white blouse, and black heels" and is currently looking for a "business casual outfit." The user registers this information and uses the virtual try-on feature. If the emotion engine identifies positive emotions, such as joy or relief, while trying on the navy blazer and white blouse combination, further relevant suggestions may be made based on this information. For example, other accessories or small items that might be suitable for the user may be suggested. In this way, the emotion engine further personalizes the user's experience, potentially increasing their motivation to purchase.

[0323] This system, based on a series of processing steps, allows users to easily find the perfect fashion item, and the introduction of an emotion engine makes it possible to provide a more personalized experience, which in turn helps fashion site operators increase their sales.

[0324] The processing flow will be explained below.

[0325] Step 1:

[0326] The user starts the application on the terminal and enters profile information (age, sex, height, weight, preferred fashion style, preferred colors, event information, etc.).

[0327] Step 2:

[0328] The user uses a terminal to register information about clothes and accessories that they already own by taking photos or manually entering the information.

[0329] Step 3:

[0330] The terminal transmits the user's basic information and information about items in hand to the server.

[0331] Step 4:

[0332] The server stores the received user information and on-hand item information in a database and assigns a unique ID to each user.

[0333] Step 5:

[0334] The server performs an initial analysis of user data to determine basic fashion styles and trends.

[0335] Step 6:

[0336] The server collects all product information (category, size, color, style, price, etc.) from the fashion site.

[0337] Step 7:

[0338] The server inputs the collected product data into the generation AI, which then updates the model based on this information.

[0339] Step 8:

[0340] The server inputs analyzed user information and learned product data into the generation AI to generate the optimal outfit.

[0341] Step 9:

[0342] From the multiple coordination suggestions generated by the AI, the server selects the one that best suits the user's preferences and the latest trends.

[0343] Step 10:

[0344] The server generates virtual try-on data for the selected outfit and matches it with the user's body type information.

[0345] Step 11:

[0346] The user can use the virtual try-on function on the device to visually check the suggested outfits.

[0347] Step 12:

[0348] During virtual try-on, the emotion engine recognizes the user's emotional state based on facial expressions, tone of voice, input actions, etc.

[0349] Step 13:

[0350] The server optimizes the content and order of coordinated suggestions based on the user's emotional state obtained by the emotion engine.

[0351] Step 14:

[0352] The user browses the suggested items on the device and chooses to buy, rent, or purchase from a flea market.

[0353] Step 15:

[0354] The terminal inputs payment information based on the selection, and the server processes the payment.

[0355] Step 16:

[0356] The server will arrange delivery for items for which purchase or rental procedures have been completed. In the case of flea markets, it will support communication between sellers and buyers and delivery procedures.

[0357] This series of processing steps allows users to easily find the perfect fashion item, and the introduction of an emotion engine makes it possible to provide a more personalized experience. Fashion site operators can also increase their sales.

[0358] Example 2

[0359] 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."

[0360] Modern fashion suggestion systems offer coordinated outfit suggestions that take into account user preferences and trends, but these suggestions ignore the user's emotional state, which means they fail to provide sufficient satisfaction. Furthermore, there is a lack of integrated methods for providing choices between purchasing, renting, and flea market items.

[0361] 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.

[0362] In this invention, the server includes means for collecting basic information about the user, means for collecting information about items the user owns, means for analyzing the collected user information and understanding the user's preferences and trends, means for training a generation AI to learn product data, means for the generation AI to suggest outfits based on the user information and product data, means for providing a virtual try-on function, means for analyzing the user's emotions using an emotion engine when the user is trying on the items virtually, means for optimizing the outfit suggestions based on the user's emotional state, and means for offering the user the option to purchase, rent, or buy the suggested items from a flea market. This enables personalized outfit suggestions that take the user's emotional state into consideration, thereby improving user satisfaction and purchasing motivation.

[0363] "Basic user information" refers to information about a person, such as the user's age, sex, height, weight, preferred fashion style and color, and event information.

[0364] "Information about items in possession" refers to information about clothes and accessories that the user already owns, and specifically refers to data collected through photographs or manual input.

[0365] A "database" is a system that stores collected basic information about users and information about items they own, and manages it in a way that allows it to be searched and updated as needed.

[0366] "Collection means" refers to the method or device used to obtain basic information about a user and information about items held by that user, and specifically includes smartphones and personal computers.

[0367] "Analysis means" refers to the methods and technologies used to analyze collected user information and understand user preferences and trends, and specifically includes data analysis software and algorithms.

[0368] "Generative AI" is an artificial intelligence technology that trains models based on collected data and makes coordination suggestions, and specifically includes natural language processing models and machine learning models.

[0369] "Coordination suggestions" refer to fashion combinations created by the generation AI based on user information and product data.

[0370] The "virtual try-on function" is a function that allows users to try on outfits suggested digitally, and specifically includes technologies using AR (augmented reality) and VR (virtual reality).

[0371] An "emotion engine" is a technology that recognizes a user's emotional state by analyzing their facial expressions, tone of voice, input behavior, etc.

[0372] "Optimizing based on emotional state" refers to reevaluating the suggested outfits based on the acquired emotional data of the user and modifying them as necessary.

[0373] "Buy, rent, buy from flea market" means that the user can choose to buy the suggested fashion item, rent it for short-term use, or buy it second-hand.

[0374] The present invention combines an emotion engine with a system that proposes optimal fashion coordination to a user, and specific embodiments thereof are described below.

[0375] Collection of User Information

[0376] A user launches the application using a device (smartphone or PC). There, they enter their profile information (age, gender, height, weight, preferred fashion style and color, event information, etc.). For example, a 30-year-old woman might enter that she likes "business casual" style and "navy." In addition, the user can register information about clothes and accessories they already own by taking photos or manually entering them. Specifically, they might register a navy skirt, a white shirt, and black heels.

[0377] Analyzing and storing information

[0378] The device sends the collected user information and information about the items in their possession to the server, which stores this information in a database and assigns each user a unique ID. The server then performs an initial analysis of the received user information and uses data analysis software (e.g., Python's Pandas library) to identify user preferences and trends.

[0379] Learning product data

[0380] The server uses a web scraping tool (e.g., Beautiful Soup or Selenium) to collect all product information (e.g., category, size, color, style, price) from fashion websites and stores it in a database. The collected product data is input into a generative AI model (e.g., a GPT or Transformer-based model) to update the model so that the AI ​​can understand the latest fashion trends.

[0381] Coordination proposal generation and optimization

[0382] The server inputs prompts into the AI ​​based on the analyzed user information and learned product data to generate optimal outfit suggestions. For example, a prompt such as "Please suggest a business casual outfit that goes well with a navy skirt" can be used. From the multiple outfit suggestions generated by the AI, the server selects the one that best suits the user's preferences and the latest trends.

[0383] Emotion recognition by emotion engine

[0384] When a user uses the virtual try-on function on their device to visually check the suggested outfits, an emotion engine recognizes the user's emotional state based on their facial expressions, tone of voice, input actions, etc. (For example, Face++ or Microsoft Azure's Face API). The server analyzes the user's emotional state using the emotion engine, reevaluates the outfit suggestions based on that, and adjusts the content and order of the suggestions as necessary.

[0385] Product purchases, rentals, and flea markets

[0386] The user browses the proposed items on the device and selects whether to buy, rent, or purchase from the flea market. Based on the selected option, payment information is entered and the server processes the payment (e.g., Stripe or PayPal API). For purchased or rented items, the server also arranges delivery. In the case of the flea market, the server supports communication between the seller and buyer and the delivery process.

[0387] Specific examples

[0388] For example, suppose a user owns a navy skirt, a white blouse, and black heels and is currently looking for a business casual look. After registering this information, the user uses the virtual try-on feature. If the emotion engine identifies positive emotions, such as joy or relief, while trying on the navy blazer and white blouse combination, further relevant suggestions are made based on this. For example, other accessories or small items that would suit the user may be suggested. This further personalizes the user's experience and increases their motivation to purchase.

[0389] Examples of specific prompts include:

[0390] Please suggest some business casual outfits that would go well with a navy skirt.

[0391] I'm a 30-year-old woman, 160cm tall, 55kg, and my preferred fashion style is business casual. What outfits would you recommend?

[0392] This system allows users to easily find the perfect fashion item, and the introduction of an emotion engine can provide a more personalized experience.

[0393] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0394] Step 1:

[0395] The user uses the terminal to launch the application and enters profile information.

[0396] Input: User's age, gender, height, weight, preferred fashion style, favorite color, event information, etc.

[0397] Output: Basic user information data stored on the device.

[0398] Specific operation: The user launches the application, enters the required information into the input form on the screen, and clicks the submit button.

[0399] Step 2:

[0400] The user uses the terminal to register information about items on hand.

[0401] Input: Photos of clothes and accessories owned by the user, manual input information.

[0402] Output: On-hand item information data saved on the device.

[0403] What happens: Use the camera feature within the application to take photos of the items, manually enter the details of each item, and click the save button.

[0404] Step 3:

[0405] The terminal transmits the collected user information and on-hand item information to the server.

[0406] Input: User's basic information data and on-hand item information data stored on the device.

[0407] Output: User information and item information data sent to the server.

[0408] Specific operation: When the user clicks the information transmission button, the terminal encrypts the data and sends it to the server.

[0409] Step 4:

[0410] The server stores the received user information and on-hand item information in a database and performs an initial analysis.

[0411] Input: User information and item information data sent to the server.

[0412] Output: User information and item information data stored in the database, as well as analysis results.

[0413] Specific operation: The server stores the data in a database and uses data analysis software (e.g., Python's Pandas library) to extract user preferences and trends.

[0414] Step 5:

[0415] The server collects all product information on the fashion site.

[0416] Input: Fashion site URL and structure information.

[0417] Output: Product information data stored in a database.

[0418] What it does: The server uses a web scraping tool (such as Beautiful Soup or Selenium) to collect product information such as category, size, color, style, and price from across fashion sites and stores it in a database.

[0419] Step 6:

[0420] The product data collected by the server is trained into a generative AI model.

[0421] Input: Product information data stored in the database.

[0422] Output: An updated generative AI model.

[0423] Specific operation: The server inputs product data into a generative AI model (e.g., a GPT or Transformer-based model) and trains the model.

[0424] Step 7:

[0425] The server generates an AI model based on user information and product data to suggest outfits.

[0426] Input: Analyzed user information and trained product data.

[0427] Output: Coordination suggestions generated by the generative AI model.

[0428] Specific operation: The server inputs a prompt into the generated AI model, specifically, a prompt such as "Please suggest a business casual outfit that would go well with a navy skirt," and the AI ​​generates the optimal outfit.

[0429] Step 8:

[0430] The server filters multiple outfit suggestions and selects the one that best suits the user's preferences and the latest trends.

[0431] Input: Multiple outfit suggestions generated by the generative AI model.

[0432] Output: Optimal outfit suggestions after filtering.

[0433] Specific operation: The generated multiple coordination suggestions are scored using the user's preferences and trend data, and the coordination with the highest score is selected.

[0434] Step 9:

[0435] The user can use the virtual try-on function on the device to visually check the suggested outfits.

[0436] Input: Filtered optimal outfit suggestions.

[0437] Output: Visual feedback of the virtual try-on.

[0438] Specific operation: The user uses the device's camera and display to virtually try on clothes using AR (augmented reality) or VR (virtual reality) technology and check the suggested outfits.

[0439] Step 10:

[0440] The server uses an emotion engine to analyze the user's emotions and optimizes the coordination proposals.

[0441] Input: User's facial expressions, tone of voice, and input behavior data during virtual try-on.

[0442] Output: Optimized outfit suggestions based on emotion recognition results.

[0443] Specific operation: The emotion engine (for example, Face++ or Microsoft Azure's Face API) recognizes the user's emotional state in real time, and the server analyzes that data to reevaluate and revise the coordination suggestions.

[0444] Step 11:

[0445] The user browses the suggested items and chooses to buy, rent, or purchase from the flea market.

[0446] Input: Optimized coordination proposals.

[0447] Output: The purchase option selected by the user.

[0448] Specific operation: The user checks the coordination suggestions on the device screen, refers to detailed information about each item, and then selects whether to purchase, rent, or go to the flea market.

[0449] Step 12:

[0450] The terminal inputs payment information, and the server processes the payment.

[0451] Input: Your payment information (credit card information, PayPal information, etc.) and the purchase option you selected.

[0452] Output: Completed payment transaction.

[0453] Specific operation: The user enters payment information, the server receives it, and processes it through the payment process (e.g., Stripe or PayPal API).

[0454] Step 13:

[0455] The server arranges delivery.

[0456] Input: Completed payment processing and shipping information.

[0457] Output: Shipping process completed.

[0458] Specific operation: The server coordinates with delivery services (e.g., FedEx or DHL) to arrange for delivery of purchased or rented items. In the case of a flea market, it supports communication between sellers and buyers and the delivery process.

[0459] (Application example 2)

[0460] 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."

[0461] Conventional fashion coordination suggestion systems can make suggestions that take into account the user's basic information and the items they own, but it is difficult to optimize coordination suggestions by reflecting the user's emotional state in real time. As a result, it is difficult to make suggestions that truly satisfy the user, and there is a lack of improvement in increasing purchasing motivation and personalization of the experience.

[0462] 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.

[0463] In this invention, the server includes means for collecting basic information about the user, means for collecting information about items the user owns, means for analyzing the collected user information and understanding the user's preferences and trends, means for having a generating AI learn product data, means for the generating AI to suggest outfits based on the user information and product data, means for providing a virtual try-on function, means for analyzing the user's emotional state, means for optimizing the outfit suggestions based on the emotional state, and means for offering the suggested items to the user for purchase, rental, or purchase from a flea market. This makes it possible to analyze the user's emotional state and optimize the outfit suggestions in real time based on the analysis.

[0464] The "means for collecting basic information about a user" refers to a device or system for collecting basic information about a user, such as age, sex, height, weight, preferred fashion style, preferred colors, and event information.

[0465] The "means for collecting information on items owned by the user" refers to a device or system for collecting information on clothes and accessories already owned by the user by taking photographs or manually entering the information.

[0466] "Means for analyzing collected user information and understanding user preferences and trends" refers to a device or system that analyzes collected basic information and information on items owned by a user to understand the user's preferences and current fashion trends.

[0467] A "means for training a generating AI on product data" is a device or system that collects all product information (category, size, color, style, price, etc.) from a fashion site and inputs it into the generating AI, thereby training the generating AI.

[0468] "Means for a generation AI to suggest coordination based on user information and product data" refers to a device or system that enables a generation AI to generate optimal coordination based on analyzed user information and learned product data.

[0469] The "means for providing a virtual try-on function" is a device or system for providing a function that allows a user to virtually try on clothes.

[0470] The "means for analyzing the user's emotional state" is a device or system for recognizing the user's current emotional state based on the user's facial expression, tone of voice, input behavior, and the like.

[0471] The "means for optimizing coordination suggestions based on emotional state" refers to a device or system for reevaluating and optimizing coordination suggestions made by the generation AI based on the user's emotional state obtained by the emotion engine.

[0472] "Means for offering users the option to purchase, rent, or purchase suggested products from a flea market" refers to a device or system that offers users the option to purchase, rent, or purchase suggested products from a flea market, and that handles payment and delivery arrangements.

[0473] To realize this invention, hardware such as smart glasses and a server and software such as Python, OpenCV, and Keras are used.

[0474] The server collects and stores basic information about the user and the items they own. Specifically, the user enters their age, gender, height, weight, preferred fashion style, favorite colors, and event information through the smart glasses interface. They also register their items by taking photos or manually entering them. This information is sent to the server for initial analysis and stored in a database.

[0475] Next, product data is collected and trained by the generative AI. The server collects all product information from the fashion site and trains the generative AI model based on that information. This generative AI model generates optimal outfits using user information and product data as input.

[0476] When the user then uses the virtual try-on function through the smart glasses, the emotion engine recognizes the user's emotional state from their facial expressions and tone of voice. The server reevaluates and optimizes the outfit suggestions based on this emotional state. The resuggested outfits are displayed on the smart glasses in real time, and the user can choose to buy, rent, or purchase from a flea market.

[0477] For example, consider the suggestions displayed when a user tries on a navy skirt and a white blouse through smart glasses. If the emotion engine recognizes the user's sense of security, it can suggest additional related products, such as black heels and silver accessories, based on that emotion.

[0478] Below are some specific examples of input prompt sentences for the generative AI model.

[0479] The user is a 30-year-old woman who prefers a business casual style and likes the color navy. She is attending an event and has a navy skirt and a white blouse. Now that she has tried these items on, she feels comfortable wearing them. Based on this information, please suggest a suitable outfit.

[0480] This invention makes it possible to analyze a user's emotional state in real time and suggest optimal outfits based on that analysis, thereby increasing the user's purchasing motivation and providing a more personalized shopping experience.

[0481] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0482] Step 1:

[0483] The user inputs basic information through the smart glasses interface.

[0484] Input: Age, gender, height, weight, preferred fashion style, preferred color, event information

[0485] How it works: The user interacts with the smart glasses and provides the required information using text input or menu selections.

[0486] Output: Dataset of basic information entered

[0487] Step 2:

[0488] The user registers information about the items they have on hand.

[0489] Input: Information about the items you own (e.g., navy skirt, white blouse)

[0490] How it works: The user takes a picture of an item with the smart glasses' camera and manually enters the item's details (color, type, etc.).

[0491] Output: A dataset of registered items on hand

[0492] Step 3:

[0493] The server stores user information and item information in a database.

[0494] Input: User basic information dataset, on-hand item information dataset

[0495] How it works: The device sends the collected data to a server, which stores the information in a database.

[0496] Output: User information and items stored in the database

[0497] Step 4:

[0498] The server collects all product information on the fashion site.

[0499] Input: Product information (category, size, color, style, price, etc.) obtained from fashion site APIs or web pages

[0500] How it works: The server collects information using automated scripts and API calls.

[0501] Output: A dataset of collected product information

[0502] Step 5:

[0503] The server trains the generative AI model on product data.

[0504] Input: Product Information Dataset

[0505] How it works: The server provides product data as input to a generative AI model, updating the model to learn the latest trends.

[0506] Output: An updated generative AI model

[0507] Step 6:

[0508] The user uses the virtual try-on feature.

[0509] Input: Virtual try-on image data of the proposed item

[0510] How it works: The user tries on the suggested outfit through the smart glasses and visually checks it.

[0511] Output: facial expressions and movement data of the user while trying on the clothes

[0512] Step 7:

[0513] The server analyzes the user's emotional state.

[0514] Input: facial expressions and movement data of the user while trying on clothes

[0515] How it works: Facial images and audio data captured by the smart glasses' camera are sent to the emotion engine to recognize the user's emotional state.

[0516] Output: User's emotional state data (e.g., joy, relief, dissatisfaction, etc.)

[0517] Step 8:

[0518] The server optimizes coordination suggestions based on the emotional state.

[0519] Input: User's emotional state data, initial outfit suggestions from a generative AI model

[0520] How it works: The server re-evaluates the outfit based on the emotion data and recreates the suggestions that best fit the user's emotions using a generative AI model.

[0521] Output: Optimized outfit suggestion data

[0522] Step 9:

[0523] It offers users suggested products to buy, rent, or purchase from a flea market.

[0524] Input: Optimized outfit suggestion data

[0525] How it works: Presents users with options to buy, rent, or purchase from a flea market through the smart glasses interface, and then processes payment and shipping for selected items.

[0526] Output: User purchases, rentals, and completed purchases from the flea market

[0527] Through this series of processing steps, users receive suggested fashion coordinations that reflect their emotional state in real time, and can choose to purchase, rent, or buy from a flea market.Furthermore, as a specific example, the following prompt sentence is provided for the generative AI model.

[0528] The user is a 30-year-old woman who prefers a business casual style and likes the color navy. She is attending an event and has a navy skirt and a white blouse. Now that she has tried these items on, she feels comfortable wearing them. Based on this information, please suggest a suitable outfit.

[0529] 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.

[0530] 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.

[0531] 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.

[0532] [Second embodiment]

[0533] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0534] 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.

[0535] 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).

[0536] 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.

[0537] 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.

[0538] 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).

[0539] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for 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.

[0540] 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.

[0541] 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.

[0542] 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.

[0543] 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.

[0544] 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."

[0545] The present invention is a system for proposing optimal fashion coordination to a user, and specific embodiments thereof will be described below.

[0546] 1. Collection of User Information

[0547] A user starts the application and enters profile information (age, sex, height, weight, preferred fashion style, preferred colors, event information, etc.).

[0548] A user uses a device (such as a smartphone or PC) to enter their basic information into the application. For example, if a user is a 30-year-old woman whose preferred style is "business casual" and whose preferred color is "navy blue," they would enter this information.

[0549] The user registers information about the items they have on hand.

[0550] Additionally, users can register information about clothes and accessories they already own by taking photos or manually entering them, such as uploading a navy skirt, a white shirt, and black heels.

[0551] 2. Analysis of information

[0552] The terminal transmits user information and on-hand item information to the server.

[0553] The collected user basic information and information on items in hand is sent from the device to the server, which stores this information in a database and assigns each user a unique ID.

[0554] The server analyzes the user data.

[0555] The server performs an initial analysis of the received user information to understand basic fashion styles and trends. This analysis reveals the user's preferences and trends in detail.

[0556] 3. Product Data Learning

[0557] The server collects all product information on the fashion site.

[0558] The server collects all product information (category, size, color, style, price, etc.) on the fashion site and stores it in a database.

[0559] The server trains the AI ​​to learn the product data.

[0560] The collected product data is input into the generative AI, which then updates its model based on this information, allowing the AI ​​to understand the latest fashion trends and suggest appropriate outfits.

[0561] 4. Coordination Proposal Generation

[0562] The server generates AI based on user information and product data to suggest outfits.

[0563] The server inputs the analyzed user information and learned product data into the generation AI, which then generates the optimal outfit.

[0564] The server filters multiple coordination proposals.

[0565] From the multiple coordination suggestions generated by the AI, the server selects the one that best suits the user's preferences and the latest trends.

[0566] 5. Virtual try-on feature

[0567] The server generates virtual try-on data for the selected outfit.

[0568] The server generates virtual try-on data for the selected outfit and matches it with the user's body type information.

[0569] Users can visually check the product using the virtual try-on function.

[0570] Users can use the virtual try-on feature on their device to visually see how suggested outfits will look on them, simulating how a navy blazer and white blouse would look, for example.

[0571] 6. Purchasing, renting, and flea markets

[0572] The user decides on the suggested product options.

[0573] The user can browse the suggested items on the terminal and choose to buy, rent, or purchase from the flea market.

[0574] The terminal inputs payment information, and the server processes the payment.

[0575] The user enters payment information based on the option selected, and the server processes the payment.

[0576] The server arranges delivery.

[0577] The server will arrange delivery for items for which purchase or rental procedures have been completed. In the case of flea markets, the server will support communication between sellers and buyers and handle delivery procedures.

[0578] This series of program processes allows users to easily find the perfect fashion item, and fashion site operators can increase sales through personalized suggestions.

[0579] The processing flow will be explained below.

[0580] Step 1:

[0581] The user starts the application on the terminal and enters profile information (age, sex, height, weight, preferred fashion style, preferred colors, event information, etc.).

[0582] Step 2:

[0583] The user uses a terminal to register information about clothes and accessories that they already own by taking photos or manually entering the information.

[0584] Step 3:

[0585] The terminal transmits the user's basic information and information about items in hand to the server.

[0586] Step 4:

[0587] The server stores the received user information and on-hand item information in a database and assigns a unique ID to each user.

[0588] Step 5:

[0589] The server performs an initial analysis of user data to determine basic fashion styles and trends.

[0590] Step 6:

[0591] The server collects all product information (category, size, color, style, price, etc.) from the fashion site.

[0592] Step 7:

[0593] The server inputs the collected product data into the generation AI, which then updates the model based on this information.

[0594] Step 8:

[0595] The server inputs analyzed user information and learned product data into the generation AI to generate the optimal outfit.

[0596] Step 9:

[0597] From the multiple coordination suggestions generated by the AI, the server selects the one that best suits the user's preferences and the latest trends.

[0598] Step 10:

[0599] The server generates virtual try-on data for the selected outfit and matches it with the user's body type information.

[0600] Step 11:

[0601] The user can use the virtual try-on function on the device to visually check the suggested outfits.

[0602] Step 12:

[0603] The user browses the suggested items on the device and chooses to buy, rent, or purchase from a flea market.

[0604] Step 13:

[0605] The terminal inputs payment information based on the selection, and the server processes the payment.

[0606] Step 14:

[0607] The server will arrange delivery for items for which purchase or rental procedures have been completed. In the case of flea markets, it will support communication between sellers and buyers and delivery procedures.

[0608] This series of processing steps allows users to easily find the perfect fashion item, and fashion site operators to increase sales.

[0609] Example 1

[0610] 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."

[0611] Previous fashion coordination suggestion systems lacked the ability to provide personalized suggestions based on user preferences and trends, and users had limited means to visually confirm the suggested outfits. Furthermore, the procedures and delivery arrangements for purchasing the suggested items were cumbersome. This made it difficult for users to find the perfect fashion items, and prevented fashion site operators from fully increasing their sales.

[0612] 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.

[0613] In this invention, the server includes means for collecting basic information about the user, means for collecting information about items the user owns, means for transmitting the collected user information, means for analyzing the collected user information and understanding the user's preferences and trends, means for collecting product data, means for training a generation AI to learn the product data, means for the generation AI to suggest outfits based on the user information and the product data, means for filtering the outfits suggested by the generation AI and selecting those that best suit the user's preferences and the latest trends, means for generating virtual try-on data, means for providing a virtual try-on function, means for offering the user the option to purchase, rent, or purchase suggested items from a flea market, means for processing payments, and means for arranging delivery. This allows users to easily find the perfect fashion item, and fashion site operators can increase sales through personalized suggestions.

[0614] The "means for collecting basic information about the user" is a function for acquiring personal information about the user, such as age, sex, height, weight, preferred fashion style, preferred colors, and event information.

[0615] The "means for collecting information on items owned by the user" is a function for collecting information on clothes and accessories that the user already owns by taking photographs or manually entering the information.

[0616] The "means for transmitting collected user information" is a function for transmitting the user's basic information and on-hand item information collected by the terminal to the server.

[0617] "Means of analyzing collected user information and understanding user preferences and trends" refers to a function that allows the server to analyze information received from users and understand their preferences and current fashion trends.

[0618] "Means for collecting product data" is a function that allows the server to obtain all product information on the fashion site and store it in a database.

[0619] "Means for training the generative AI on product data" refers to a function that inputs collected product data into the generative AI, allowing the AI ​​to learn the latest fashion trends.

[0620] "A means for the generation AI to suggest coordination based on user information and product data" is a function that allows the generation AI to analyze user information and product data and suggest the optimal fashion coordination.

[0621] "Means of filtering the outfits proposed by the generation AI and selecting the one that best suits the user's preferences and the latest trends" is a function that selects the outfit that best suits the user's preferences and the latest trends from among the multiple outfit ideas created by the generation AI.

[0622] The "means for generating virtual try-on data" is a function for matching the selected outfit with the user's body type information and generating virtual try-on data that can be visually confirmed.

[0623] The "means for providing a virtual try-on function" is a function that allows a user to use a terminal to access virtual try-on data and visually check suggested outfits.

[0624] "Means for providing users with the ability to purchase, rent, or purchase suggested items from a flea market" is a feature that provides users with the option to purchase, rent, or purchase suggested items from a flea market.

[0625] "Means for processing payment" refers to the function that allows the server to process the payment required to purchase or rent the item selected by the user based on the payment information entered.

[0626] "Means for arranging delivery" refers to arranging delivery of items that have been purchased or rented, and in the case of flea markets, this is a function that supports communication between sellers and buyers and the delivery process.

[0627] This invention is a system for proposing optimal fashion coordination to a user. The system collects basic information about the user and information about items they own, analyzes this information, and then proposes coordination based on a generative AI model. It then provides a virtual try-on function, allowing the user to purchase, rent, or buy the proposed items from a flea market. A specific embodiment of the system is shown below.

[0628] Collection of User Information

[0629] After launching the application using a device such as a smartphone or PC, users enter their basic information. Input items include age, gender, height, weight, preferred fashion style, favorite color, and event information. For example, if you are a 30-year-old woman whose preferred style is "business casual" and favorite color is "navy," you would enter this information.

[0630] Users can also register information about clothes and accessories they already own by taking photos or manually entering them. For example, they can upload information about a navy skirt, a white shirt, and black heels to their device.

[0631] Analysis of information

[0632] The device sends the collected user basic information and information about items in their possession to the server. The server stores this information in a database and assigns each user a unique ID. The server performs an initial analysis based on the received information to understand the user's preferences and trends.

[0633] Learning product data

[0634] The server periodically collects all product information (category, size, color, style, price, etc.) from the fashion site and stores it in a database. The server inputs the collected product data into the generation AI and updates the generation AI model. This allows the generation AI to understand the latest fashion trends and propose appropriate outfits.

[0635] Generating outfit suggestions

[0636] The server inputs the analyzed user information and learned product data into the AI, which then proposes the optimal outfit. For example, it generates a combination of "navy skirt, white shirt, and black heels." The server then selects from the multiple outfit suggestions it has generated the one that best suits the user's preferences and the latest trends.

[0637] Providing virtual try-on functionality

[0638] The server generates virtual try-on data for the selected outfit and matches it with the user's body type. The user can then use the virtual try-on function on their device to visually check how the suggested outfit will suit them. For example, they can simulate how a navy blazer and white blouse would look.

[0639] Product purchases, rentals, and flea markets

[0640] The user browses the suggested items on their device and selects whether to buy, rent, or purchase from a flea market. Based on the option selected by the user, payment information is entered and the server processes the payment. Once the purchase or rental procedure is complete, the server arranges delivery of the item. In the case of a flea market, the server supports communication between the seller and buyer and the delivery procedure.

[0641] Specific examples

[0642] As a concrete example, let's say the user is a 30-year-old woman who likes business casual clothing and owns a navy skirt, a white shirt, and black heels. The system uses this information to suggest the best outfits. It also uses the virtual try-on feature to visually check how a navy blazer and a white blouse look.

[0643] Example prompt sentence:

[0644] "I'm a 30-year-old woman who likes business casual. I have a navy skirt, a white shirt, and black heels."

[0645] "I'd like to try on a virtual navy blazer and white blouse combination."

[0646] As described above, this system suggests the most suitable fashion items to users and makes it easy to purchase or rent them. This also enables fashion site operators to increase sales through personalized suggestions.

[0647] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0648] System program processing flow

[0649] Step 1:

[0650] Enter your user profile

[0651] Specific description:

[0652] The user starts the application and enters their profile information (age, gender, height, weight, preferred fashion style, preferred color, event information, etc.). For example, if a user is a 30-year-old woman whose preferred style is "business casual" and whose preferred color is "navy," they enter this information into the device.

[0653] Input and Output:

[0654] Input: User profile information

[0655] Output: User profile information is saved on the device

[0656] Step 2:

[0657] Registering on-hand item information

[0658] Specific description:

[0659] Users can register information about clothes and accessories they already own by taking photos or manually entering them, such as a navy skirt, a white shirt, and black heels, and uploading them to their device.

[0660] Input and Output:

[0661] Input: Information about items on hand

[0662] Output: Information about items in your possession is saved on the device.

[0663] Step 3:

[0664] Sending user information

[0665] Specific description:

[0666] The device sends the collected user information and item information to the server, which stores the information in a database and assigns a unique ID to each user.

[0667] Input and Output:

[0668] Input: User information and item information stored on the device

[0669] Output: User information and item information stored on the server

[0670] Step 4:

[0671] User information analysis

[0672] Specific description:

[0673] The server performs an initial analysis based on the received user information to understand the user's basic preferences and trends. For example, if the user prefers business casual attire, this tendency will be tracked.

[0674] Input and Output:

[0675] Input: User information stored in the database

[0676] Output: Analysis results of user preferences and trend information

[0677] Step 5:

[0678] Collecting product information

[0679] Specific description:

[0680] The server collects all product information from the fashion site and stores it in a database, including information such as category, size, color, style, and price.

[0681] Input and Output:

[0682] Input: Product information from a fashion website

[0683] Output: Product information stored in the database

[0684] Step 6:

[0685] Generative AI training

[0686] Specific description:

[0687] The server inputs the collected product data into the generation AI and updates the model, allowing the generation AI to understand the latest fashion trends and propose outfits.

[0688] Input and Output:

[0689] Input: Product information stored in the database

[0690] Output: A generative AI model that learns the latest fashion trends

[0691] Step 7:

[0692] Generating outfit suggestions

[0693] Specific description:

[0694] The server inputs the analyzed user information and learned product data into the AI, which then generates the optimal outfit. For example, it generates a combination of a navy skirt, a white shirt, and black heels.

[0695] Input and Output:

[0696] Input: User information, product information

[0697] Output: Generated outfit suggestions

[0698] Step 8:

[0699] Filtering outfit suggestions

[0700] Specific description:

[0701] The server selects from the multiple coordinated outfit suggestions generated the one that best suits the user's preferences and the latest trends.

[0702] Input and Output:

[0703] Input: Generated outfit suggestions

[0704] Output: Filtered optimal outfit suggestions

[0705] Step 9:

[0706] Generate virtual try-on data

[0707] Specific description:

[0708] The server generates virtual try-on data for the selected outfit and matches it with the user's body type information, allowing the user to visually check the suggested outfit.

[0709] Input and Output:

[0710] Input: Filtered outfit suggestions, user's body type information

[0711] Output: Generated virtual fitting data

[0712] Step 10:

[0713] Providing virtual try-on functionality

[0714] Specific description:

[0715] Users can use the virtual try-on feature on their device to see how suggested outfits will look on them, for example, simulating how a navy blazer and white blouse would look.

[0716] Input and Output:

[0717] Input: Virtual try-on data

[0718] Output: Visual confirmation through virtual try-on

[0719] Step 11:

[0720] Product selection and payment

[0721] Specific description:

[0722] The user browses the suggested items on the terminal and selects whether to buy, rent, or purchase from the flea market. After making a selection, the user enters payment information, and the server processes the payment.

[0723] Input and Output:

[0724] Input: Selected items, payment information

[0725] Output: Payment completion notification

[0726] Step 12:

[0727] Delivery arrangements

[0728] Specific description:

[0729] The server arranges delivery of purchased or rented items. In the case of a flea market, it supports communication between sellers and buyers and handles delivery procedures.

[0730] Input and Output:

[0731] Input: Payment completion notification, delivery information

[0732] Output: Delivery arrangement completion notification

[0733] This series of programs allows users to easily find the perfect fashion item to purchase or rent, and the virtual try-on feature allows users to see how it will look in real life.

[0734] (Application example 1)

[0735] 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."

[0736] Conventional fashion coordination systems have been unable to adequately address users' specific needs and preferences, and few of them have a virtual try-on function, making it difficult for users to easily find suitable fashion items at home. Another issue is the limited options for purchasing or renting various clothing items. Furthermore, few systems offer real-time virtual try-on functionality, which tends to discourage users from making purchases.

[0737] 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.

[0738] In this invention, the server includes means for collecting basic user information, means for collecting information on the user's owned items, means for analyzing the collected user information to understand the user's preferences and trends, means for training a generation AI to learn product data, means for the generation AI to suggest outfits based on the user information and product data, means for providing a virtual try-on function, means for offering the purchase, rental, or flea market purchase of suggested items in a virtual store, means for trying on items in a virtual space in real time using a head-mounted display, and means for arranging delivery of purchased or rented items. This allows users to easily try on fashion items virtually from the comfort of their own home and receive optimal outfit suggestions. Furthermore, the increased options for purchasing and renting products provide a more satisfying shopping experience.

[0739] "Means for collecting basic user information" refers to a method of providing an interface for users to enter profile information such as their age, gender, height, weight, preferred fashion style, favorite colors, and event information, and then incorporating this information into the system.

[0740] The "means for collecting information on items owned by the user" refers to a method by which the user registers information on the clothes and accessories that he or she owns by taking photographs or manually entering the information.

[0741] "Means for analyzing collected user information and understanding user preferences and trends" refers to technology that analyzes collected basic information about users and information about items they own, and identifies their preferences and current fashion trends.

[0742] "Method of having the generative AI learn product data" refers to a method of collecting all product information on a fashion site, inputting that data into the generative AI, and updating the model.

[0743] "Means for generative AI to suggest coordination based on user information and product data" refers to a method in which generative AI uses analyzed user information and learned product data to provide optimal fashion coordination.

[0744] The "means for providing a virtual try-on function" is a technology that allows a user to try on suggested fashion items in a virtual space and visually check them.

[0745] "Means for offering suggested items for purchase, rental, or purchase from a flea market within a virtual store" is a function that allows a user to choose to purchase, rent, or trade suggested items at a flea market.

[0746] "Means for trying on clothes in a virtual space in real time using a head-mounted display" is a technology that allows users to try on and experience fashion items in a virtual space in real time using a head-mounted display.

[0747] "Means for arranging delivery of purchased or rented products" refers to the procedures for delivering the products purchased or rented by the user to the specified address.

[0748] The system for implementing this invention mainly uses a server, a user terminal, and a head-mounted display (HMD). A specific form of the system is shown below.

[0749] System Configuration

[0750] Hardware and software used:

[0751] Server: General cloud computing service (e.g., Amazon Web Services EC2)

[0752] Database: Relational database system (e.g. Amazon RDS)

[0753] Generative AI models: advanced natural language generation systems (e.g., OpenAI GPT-4)

[0754] User device: Smartphone or personal computer

[0755] Virtual try-on engine: Advanced 3D engine (e.g. Unity 3D)

[0756] Head-mounted displays: commonly used VR devices (e.g., Oculus Rift or HTC Vive)

[0757] Program Overview

[0758] 1. User Information Collection:

[0759] The user uses the terminal to input profile information such as age, sex, height, weight, preferred fashion style, preferred colors, and event information.

[0760] Profile information is sent from the user's device to the server and stored in a database (Amazon RDS).

[0761] 2. Registering your inventory:

[0762] The user uses the device's camera to take photos of the clothes and accessories they own and registers them.

[0763] Using image recognition technology (e.g., Amazon Rekognition), item information is classified and stored in a database.

[0764] 3. Information analysis and product data learning:

[0765] The server analyzes the collected user information to understand user preferences and trends.

[0766] The latest item data is collected by scraping from fashion sites and trained on a generative AI (e.g., GPT-4).

[0767] 4. Coordination proposal generation:

[0768] The generative AI uses analyzed user information and the latest product data to generate optimal coordination suggestions.

[0769] Suggested outfits are filtered based on user preferences and the latest trends.

[0770] 5. Virtual try-on feature:

[0771] The user wears a head-mounted display and tries on the suggested items in a virtual space.

[0772] Using Unity 3D, you can try on your avatar in real time and visually check the fit.

[0773] 6. Product Purchases, Rentals, and Flea Markets:

[0774] The user can choose to buy, rent, or purchase the suggested items from a flea market.

[0775] Once the selected items are purchased, payment information is entered and delivery arrangements are made.

[0776] Specific examples

[0777] Example 1: Prompt when user enters profile information:

[0778] "30 years old, female, height 160cm, weight 55kg, preferred style is business casual, preferred color is navy, event information is company presentation."

[0779] Example 2: Prompt for collecting fashion item data:

[0780] "Collect the latest business casual fashion items and learn about categories, sizes, colors, styles, and pricing information."

[0781] In this way, users can easily find suitable fashion items at home, virtually try them on in real time, and enjoy a wide variety of choices, increasing user satisfaction.

[0782] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0783] Step 1: Collect user information

[0784] The user uses a device to enter profile information such as age, gender, height, weight, preferred fashion style, favorite colors, and event information. The entered information is sent from the device to the server and stored in a database. The input data is sent in JSON format, received by the server, and stored in the database. As an output, a record of the user information is added to the database.

[0785] Step 2: Register your inventory information

[0786] The user uses the device's camera to take a photo of the clothes or accessories they own and registers it. The image file and manually entered details are sent to the server. The server uses image recognition technology to identify the item and store the information in a database. The input data is the image file and a description, and the output is a record of the item information added to the database.

[0787] Step 3: Information analysis and product data learning

[0788] The server analyzes the collected user information and information on items in hand to understand the user's preferences and trends. The server then scrapes and collects the latest item data from fashion sites and trains the generative AI model. The input data is user information and item data, and the output is an analysis of the user's preferences and trends and an updated AI model.

[0789] Step 4: Generate outfit suggestions

[0790] The server uses a generative AI model to generate optimal outfit suggestions based on the analyzed user information and product data. The generated outfits are filtered based on user preferences and the latest trends. The input data are the analysis results and product data, and the output is a list of suggested outfits.

[0791] Step 5: Providing virtual try-on functionality

[0792] The user wears a head-mounted display and tries on the suggested items in a virtual space. The server uses the Unity 3D engine to have an avatar try on the items in real time, allowing the user to visually confirm them. The input data is the suggested outfit, and the output is a virtual try-on scene that is displayed on the user's HMD.

[0793] Step 6: Buying, renting, and going to the flea market

[0794] The user can choose to purchase, rent, or buy from a flea market of the suggested items. The selected item progresses through the purchase process by entering payment information, and the server arranges delivery. The input data is the user's selection and payment information, and the output is a purchase confirmation and notification of delivery arrangements.

[0795] 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.

[0796] The present invention combines an emotion engine with a system that proposes optimal fashion coordination to a user, and specific embodiments thereof are described below.

[0797] 1. Collection of User Information

[0798] A user starts the application and enters profile information (age, sex, height, weight, preferred fashion style, preferred colors, event information, etc.).

[0799] A user inputs their basic information into the application using a device (such as a smartphone or PC). For example, if a user is a 30-year-old woman whose preferred style is "business casual" and whose preferred color is "navy blue," the user inputs this information.

[0800] The user registers information about the items they have on hand.

[0801] Additionally, users can register information about clothes and accessories they already own by taking photos or manually entering them, such as uploading a navy skirt, a white shirt, and black heels.

[0802] 2. Analysis and storage of information

[0803] The terminal transmits user information and on-hand item information to the server.

[0804] The collected user basic information and information on items in hand is sent from the device to the server, which then stores this information in a database and assigns each user a unique ID.

[0805] The server analyzes the user data.

[0806] The server performs an initial analysis of the received user information to understand basic fashion styles and trends, thereby clarifying the user's preferences and current trends.

[0807] 3. Product Data Learning

[0808] The server collects all product information (category, size, color, style, price, etc.) from the fashion site.

[0809] The server collects all product information on the fashion site and stores it in a database.

[0810] The server trains the AI ​​to learn the product data.

[0811] The collected product data is input into the generative AI, which then updates its model based on this information, allowing the AI ​​to understand the latest fashion trends and suggest appropriate outfits.

[0812] 4. Coordination proposal generation and optimization

[0813] The server generates AI based on user information and product data to suggest outfits.

[0814] The server inputs the analyzed user information and learned product data into the generation AI to generate the optimal coordination.

[0815] The server filters multiple coordination proposals.

[0816] From the multiple coordination suggestions generated by the AI, the server selects the one that best suits the user's preferences and the latest trends.

[0817] 5. Emotion Recognition by Emotion Engine

[0818] As users visually check the virtual try-on feature, an emotion engine analyzes the user's current emotional state.

[0819] When a user uses the virtual try-on function on their device to visually check the suggested outfits, the emotion engine recognizes the user's emotional state based on their facial expressions, tone of voice, input actions, etc.

[0820] The server optimizes coordination suggestions based on the results of the emotion engine.

[0821] Based on the user's emotional state obtained by the emotion engine, the server reevaluates the coordination suggestions and, if necessary, changes the content or order of the suggestions.

[0822] 6. Purchasing, renting, and flea markets

[0823] The user decides on the suggested product options.

[0824] The user can browse the suggested items on the terminal and choose to buy, rent, or purchase from the flea market.

[0825] The terminal inputs payment information, and the server processes the payment.

[0826] The user enters payment information based on the option selected, and the server processes the payment.

[0827] The server arranges delivery.

[0828] The server will arrange delivery for items for which purchase or rental procedures have been completed. In the case of flea markets, the server will support communication between sellers and buyers and handle delivery procedures.

[0829] Specific examples

[0830] For example, suppose a user owns a "navy skirt, white blouse, and black heels" and is currently looking for a "business casual outfit." The user registers this information and uses the virtual try-on feature. If the emotion engine identifies positive emotions, such as joy or relief, while trying on the navy blazer and white blouse combination, further relevant suggestions may be made based on this information. For example, other accessories or small items that might be suitable for the user may be suggested. In this way, the emotion engine further personalizes the user's experience, potentially increasing their motivation to purchase.

[0831] This system, based on a series of processing steps, allows users to easily find the perfect fashion item, and the introduction of an emotion engine makes it possible to provide a more personalized experience, which in turn helps fashion site operators increase their sales.

[0832] The processing flow will be explained below.

[0833] Step 1:

[0834] The user starts the application on the terminal and enters profile information (age, sex, height, weight, preferred fashion style, preferred colors, event information, etc.).

[0835] Step 2:

[0836] The user uses a terminal to register information about clothes and accessories that they already own by taking photos or manually entering the information.

[0837] Step 3:

[0838] The terminal transmits the user's basic information and information about items in hand to the server.

[0839] Step 4:

[0840] The server stores the received user information and on-hand item information in a database and assigns a unique ID to each user.

[0841] Step 5:

[0842] The server performs an initial analysis of user data to determine basic fashion styles and trends.

[0843] Step 6:

[0844] The server collects all product information (category, size, color, style, price, etc.) from the fashion site.

[0845] Step 7:

[0846] The server inputs the collected product data into the generation AI, which then updates the model based on this information.

[0847] Step 8:

[0848] The server inputs analyzed user information and learned product data into the generation AI to generate the optimal outfit.

[0849] Step 9:

[0850] From the multiple coordination suggestions generated by the AI, the server selects the one that best suits the user's preferences and the latest trends.

[0851] Step 10:

[0852] The server generates virtual try-on data for the selected outfit and matches it with the user's body type information.

[0853] Step 11:

[0854] The user can use the virtual try-on function on the device to visually check the suggested outfits.

[0855] Step 12:

[0856] During virtual try-on, the emotion engine recognizes the user's emotional state based on facial expressions, tone of voice, input actions, etc.

[0857] Step 13:

[0858] The server optimizes the content and order of coordinated suggestions based on the user's emotional state obtained by the emotion engine.

[0859] Step 14:

[0860] The user browses the suggested items on the device and chooses to buy, rent, or purchase from a flea market.

[0861] Step 15:

[0862] The terminal inputs payment information based on the selection, and the server processes the payment.

[0863] Step 16:

[0864] The server will arrange delivery for items for which purchase or rental procedures have been completed. In the case of flea markets, it will support communication between sellers and buyers and delivery procedures.

[0865] This series of processing steps allows users to easily find the perfect fashion item, and the introduction of an emotion engine makes it possible to provide a more personalized experience. Fashion site operators can also increase their sales.

[0866] Example 2

[0867] 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."

[0868] Modern fashion suggestion systems offer coordinated outfit suggestions that take into account user preferences and trends, but these suggestions ignore the user's emotional state, which means they fail to provide sufficient satisfaction. Furthermore, there is a lack of integrated methods for providing choices between purchasing, renting, and flea market items.

[0869] 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.

[0870] In this invention, the server includes means for collecting basic information about the user, means for collecting information about items the user owns, means for analyzing the collected user information and understanding the user's preferences and trends, means for training a generation AI to learn product data, means for the generation AI to suggest outfits based on the user information and product data, means for providing a virtual try-on function, means for analyzing the user's emotions using an emotion engine when the user is trying on the items virtually, means for optimizing the outfit suggestions based on the user's emotional state, and means for offering the user the option to purchase, rent, or buy the suggested items from a flea market. This enables personalized outfit suggestions that take the user's emotional state into consideration, thereby improving user satisfaction and purchasing motivation.

[0871] "Basic user information" refers to information about a person, such as the user's age, sex, height, weight, preferred fashion style and color, and event information.

[0872] "Information about items in possession" refers to information about clothes and accessories that the user already owns, and specifically refers to data collected through photographs or manual input.

[0873] A "database" is a system that stores collected basic information about users and information about items they own, and manages it in a way that allows it to be searched and updated as needed.

[0874] "Collection means" refers to the method or device used to obtain basic information about a user and information about items held by that user, and specifically includes smartphones and personal computers.

[0875] "Analysis means" refers to the methods and technologies used to analyze collected user information and understand user preferences and trends, and specifically includes data analysis software and algorithms.

[0876] "Generative AI" is an artificial intelligence technology that trains models based on collected data and makes coordination suggestions, and specifically includes natural language processing models and machine learning models.

[0877] "Coordination suggestions" refer to fashion combinations created by the generation AI based on user information and product data.

[0878] The "virtual try-on function" is a function that allows users to try on outfits suggested digitally, and specifically includes technologies using AR (augmented reality) and VR (virtual reality).

[0879] An "emotion engine" is a technology that recognizes a user's emotional state by analyzing their facial expressions, tone of voice, input behavior, etc.

[0880] "Optimizing based on emotional state" refers to reevaluating the suggested outfits based on the acquired emotional data of the user and modifying them as necessary.

[0881] "Buy, rent, buy from flea market" means that the user can choose to buy the suggested fashion item, rent it for short-term use, or buy it second-hand.

[0882] The present invention combines an emotion engine with a system that proposes optimal fashion coordination to a user, and specific embodiments thereof are described below.

[0883] Collection of User Information

[0884] A user launches the application using a device (smartphone or PC). There, they enter their profile information (age, gender, height, weight, preferred fashion style and color, event information, etc.). For example, a 30-year-old woman might enter that she likes "business casual" style and "navy." In addition, the user can register information about clothes and accessories they already own by taking photos or manually entering them. Specifically, they might register a navy skirt, a white shirt, and black heels.

[0885] Analyzing and storing information

[0886] The device sends the collected user information and information about the items in their possession to the server, which stores this information in a database and assigns each user a unique ID. The server then performs an initial analysis of the received user information and uses data analysis software (e.g., Python's Pandas library) to identify user preferences and trends.

[0887] Learning product data

[0888] The server uses a web scraping tool (e.g., Beautiful Soup or Selenium) to collect all product information (e.g., category, size, color, style, price) from fashion websites and stores it in a database. The collected product data is input into a generative AI model (e.g., a GPT or Transformer-based model) to update the model so that the AI ​​can understand the latest fashion trends.

[0889] Coordination proposal generation and optimization

[0890] The server inputs prompts into the AI ​​based on the analyzed user information and learned product data to generate optimal outfit suggestions. For example, a prompt such as "Please suggest a business casual outfit that goes well with a navy skirt" can be used. From the multiple outfit suggestions generated by the AI, the server selects the one that best suits the user's preferences and the latest trends.

[0891] Emotion recognition by emotion engine

[0892] When a user uses the virtual try-on function on their device to visually check the suggested outfits, an emotion engine recognizes the user's emotional state based on their facial expressions, tone of voice, input actions, etc. (For example, Face++ or Microsoft Azure's Face API). The server analyzes the user's emotional state using the emotion engine, reevaluates the outfit suggestions based on that, and adjusts the content and order of the suggestions as necessary.

[0893] Product purchases, rentals, and flea markets

[0894] The user browses the proposed items on the device and selects whether to buy, rent, or purchase from the flea market. Based on the selected option, payment information is entered and the server processes the payment (e.g., Stripe or PayPal API). For purchased or rented items, the server also arranges delivery. In the case of the flea market, the server supports communication between the seller and buyer and the delivery process.

[0895] Specific examples

[0896] For example, suppose a user owns a navy skirt, a white blouse, and black heels and is currently looking for a business casual look. After registering this information, the user uses the virtual try-on feature. If the emotion engine identifies positive emotions, such as joy or relief, while trying on the navy blazer and white blouse combination, further relevant suggestions are made based on this. For example, other accessories or small items that would suit the user may be suggested. This further personalizes the user's experience and increases their motivation to purchase.

[0897] Examples of specific prompts include:

[0898] Please suggest some business casual outfits that would go well with a navy skirt.

[0899] I'm a 30-year-old woman, 160cm tall, 55kg, and my preferred fashion style is business casual. What outfits would you recommend?

[0900] This system allows users to easily find the perfect fashion item, and the introduction of an emotion engine can provide a more personalized experience.

[0901] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0902] Step 1:

[0903] The user uses the terminal to launch the application and enters profile information.

[0904] Input: User's age, gender, height, weight, preferred fashion style, favorite color, event information, etc.

[0905] Output: Basic user information data stored on the device.

[0906] Specific operation: The user launches the application, enters the required information into the input form on the screen, and clicks the submit button.

[0907] Step 2:

[0908] The user uses the terminal to register information about items on hand.

[0909] Input: Photos of clothes and accessories owned by the user, manual input information.

[0910] Output: On-hand item information data saved on the device.

[0911] What happens: Use the camera feature within the application to take photos of the items, manually enter the details of each item, and click the save button.

[0912] Step 3:

[0913] The terminal transmits the collected user information and on-hand item information to the server.

[0914] Input: User's basic information data and on-hand item information data stored on the device.

[0915] Output: User information and item information data sent to the server.

[0916] Specific operation: When the user clicks the information transmission button, the terminal encrypts the data and sends it to the server.

[0917] Step 4:

[0918] The server stores the received user information and on-hand item information in a database and performs an initial analysis.

[0919] Input: User information and item information data sent to the server.

[0920] Output: User information and item information data stored in the database, as well as analysis results.

[0921] Specific operation: The server stores the data in a database and uses data analysis software (e.g., Python's Pandas library) to extract user preferences and trends.

[0922] Step 5:

[0923] The server collects all product information on the fashion site.

[0924] Input: Fashion site URL and structure information.

[0925] Output: Product information data stored in a database.

[0926] What it does: The server uses a web scraping tool (such as Beautiful Soup or Selenium) to collect product information such as category, size, color, style, and price from across fashion sites and stores it in a database.

[0927] Step 6:

[0928] The product data collected by the server is trained into a generative AI model.

[0929] Input: Product information data stored in the database.

[0930] Output: An updated generative AI model.

[0931] Specific operation: The server inputs product data into a generative AI model (e.g., a GPT or Transformer-based model) and trains the model.

[0932] Step 7:

[0933] The server generates an AI model based on user information and product data to suggest outfits.

[0934] Input: Analyzed user information and trained product data.

[0935] Output: Coordination suggestions generated by the generative AI model.

[0936] Specific operation: The server inputs a prompt into the generated AI model, specifically, a prompt such as "Please suggest a business casual outfit that would go well with a navy skirt," and the AI ​​generates the optimal outfit.

[0937] Step 8:

[0938] The server filters multiple outfit suggestions and selects the one that best suits the user's preferences and the latest trends.

[0939] Input: Multiple outfit suggestions generated by the generative AI model.

[0940] Output: Optimal outfit suggestions after filtering.

[0941] Specific operation: The generated multiple coordination suggestions are scored using the user's preferences and trend data, and the coordination with the highest score is selected.

[0942] Step 9:

[0943] The user can use the virtual try-on function on the device to visually check the suggested outfits.

[0944] Input: Filtered optimal outfit suggestions.

[0945] Output: Visual feedback of the virtual try-on.

[0946] Specific operation: The user uses the device's camera and display to virtually try on clothes using AR (augmented reality) or VR (virtual reality) technology and check the suggested outfits.

[0947] Step 10:

[0948] The server uses an emotion engine to analyze the user's emotions and optimizes the coordination proposals.

[0949] Input: User's facial expressions, tone of voice, and input behavior data during virtual try-on.

[0950] Output: Optimized outfit suggestions based on emotion recognition results.

[0951] Specific operation: The emotion engine (for example, Face++ or Microsoft Azure's Face API) recognizes the user's emotional state in real time, and the server analyzes that data to reevaluate and revise the coordination suggestions.

[0952] Step 11:

[0953] The user browses the suggested items and chooses to buy, rent, or purchase from the flea market.

[0954] Input: Optimized coordination proposals.

[0955] Output: The purchase option selected by the user.

[0956] Specific operation: The user checks the coordination suggestions on the device screen, refers to detailed information about each item, and then selects whether to purchase, rent, or go to the flea market.

[0957] Step 12:

[0958] The terminal inputs payment information, and the server processes the payment.

[0959] Input: Your payment information (credit card information, PayPal information, etc.) and the purchase option you selected.

[0960] Output: Completed payment transaction.

[0961] Specific operation: The user enters payment information, the server receives it, and processes it through the payment process (e.g., Stripe or PayPal API).

[0962] Step 13:

[0963] The server arranges delivery.

[0964] Input: Completed payment processing and shipping information.

[0965] Output: Shipping process completed.

[0966] Specific operation: The server coordinates with delivery services (e.g., FedEx or DHL) to arrange for delivery of purchased or rented items. In the case of a flea market, it supports communication between sellers and buyers and the delivery process.

[0967] (Application example 2)

[0968] 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."

[0969] Conventional fashion coordination suggestion systems can make suggestions that take into account the user's basic information and the items they own, but it is difficult to optimize coordination suggestions by reflecting the user's emotional state in real time. As a result, it is difficult to make suggestions that truly satisfy the user, and there is a lack of improvement in increasing purchasing motivation and personalization of the experience.

[0970] 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.

[0971] In this invention, the server includes means for collecting basic information about the user, means for collecting information about items the user owns, means for analyzing the collected user information and understanding the user's preferences and trends, means for having a generating AI learn product data, means for the generating AI to suggest outfits based on the user information and product data, means for providing a virtual try-on function, means for analyzing the user's emotional state, means for optimizing the outfit suggestions based on the emotional state, and means for offering the suggested items to the user for purchase, rental, or purchase from a flea market. This makes it possible to analyze the user's emotional state and optimize the outfit suggestions in real time based on the analysis.

[0972] The "means for collecting basic information about a user" refers to a device or system for collecting basic information about a user, such as age, sex, height, weight, preferred fashion style, preferred colors, and event information.

[0973] The "means for collecting information on items owned by the user" refers to a device or system for collecting information on clothes and accessories already owned by the user by taking photographs or manually entering the information.

[0974] "Means for analyzing collected user information and understanding user preferences and trends" refers to a device or system that analyzes collected basic information and information on items owned by a user to understand the user's preferences and current fashion trends.

[0975] A "means for training a generating AI on product data" is a device or system that collects all product information (category, size, color, style, price, etc.) from a fashion site and inputs it into the generating AI, thereby training the generating AI.

[0976] "Means for a generation AI to suggest coordination based on user information and product data" refers to a device or system that enables a generation AI to generate optimal coordination based on analyzed user information and learned product data.

[0977] The "means for providing a virtual try-on function" is a device or system for providing a function that allows a user to virtually try on clothes.

[0978] The "means for analyzing the user's emotional state" is a device or system for recognizing the user's current emotional state based on the user's facial expression, tone of voice, input behavior, and the like.

[0979] The "means for optimizing coordination suggestions based on emotional state" refers to a device or system for reevaluating and optimizing coordination suggestions made by the generation AI based on the user's emotional state obtained by the emotion engine.

[0980] "Means for offering users the option to purchase, rent, or purchase suggested products from a flea market" refers to a device or system that offers users the option to purchase, rent, or purchase suggested products from a flea market, and that handles payment and delivery arrangements.

[0981] To realize this invention, hardware such as smart glasses and a server and software such as Python, OpenCV, and Keras are used.

[0982] The server collects and stores basic information about the user and the items they own. Specifically, the user enters their age, gender, height, weight, preferred fashion style, favorite colors, and event information through the smart glasses interface. They also register their items by taking photos or manually entering them. This information is sent to the server for initial analysis and stored in a database.

[0983] Next, product data is collected and trained by the generative AI. The server collects all product information from the fashion site and trains the generative AI model based on that information. This generative AI model generates optimal outfits using user information and product data as input.

[0984] When the user then uses the virtual try-on function through the smart glasses, the emotion engine recognizes the user's emotional state from their facial expressions and tone of voice. The server reevaluates and optimizes the outfit suggestions based on this emotional state. The resuggested outfits are displayed on the smart glasses in real time, and the user can choose to buy, rent, or purchase from a flea market.

[0985] For example, consider the suggestions displayed when a user tries on a navy skirt and a white blouse through smart glasses. If the emotion engine recognizes the user's sense of security, it can suggest additional related products, such as black heels and silver accessories, based on that emotion.

[0986] Below are some specific examples of input prompt sentences for the generative AI model.

[0987] The user is a 30-year-old woman who prefers a business casual style and likes the color navy. She is attending an event and has a navy skirt and a white blouse. Now that she has tried these items on, she feels comfortable wearing them. Based on this information, please suggest a suitable outfit.

[0988] This invention makes it possible to analyze a user's emotional state in real time and suggest optimal outfits based on that analysis, thereby increasing the user's purchasing motivation and providing a more personalized shopping experience.

[0989] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0990] Step 1:

[0991] The user inputs basic information through the smart glasses interface.

[0992] Input: Age, gender, height, weight, preferred fashion style, preferred color, event information

[0993] How it works: The user interacts with the smart glasses and provides the required information using text input or menu selections.

[0994] Output: Dataset of basic information entered

[0995] Step 2:

[0996] The user registers information about the items they have on hand.

[0997] Input: Information about the items you own (e.g., navy skirt, white blouse)

[0998] How it works: The user takes a picture of an item with the smart glasses' camera and manually enters the item's details (color, type, etc.).

[0999] Output: A dataset of registered items on hand

[1000] Step 3:

[1001] The server stores user information and item information in a database.

[1002] Input: User basic information dataset, on-hand item information dataset

[1003] How it works: The device sends the collected data to a server, which stores the information in a database.

[1004] Output: User information and items stored in the database

[1005] Step 4:

[1006] The server collects all product information on the fashion site.

[1007] Input: Product information (category, size, color, style, price, etc.) obtained from fashion site APIs or web pages

[1008] How it works: The server collects information using automated scripts and API calls.

[1009] Output: A dataset of collected product information

[1010] Step 5:

[1011] The server trains the generative AI model on product data.

[1012] Input: Product Information Dataset

[1013] How it works: The server provides product data as input to a generative AI model, updating the model to learn the latest trends.

[1014] Output: An updated generative AI model

[1015] Step 6:

[1016] The user uses the virtual try-on feature.

[1017] Input: Virtual try-on image data of the proposed item

[1018] How it works: The user tries on the suggested outfit through the smart glasses and visually checks it.

[1019] Output: facial expressions and movement data of the user while trying on the clothes

[1020] Step 7:

[1021] The server analyzes the user's emotional state.

[1022] Input: facial expressions and movement data of the user while trying on clothes

[1023] How it works: Facial images and audio data captured by the smart glasses' camera are sent to the emotion engine to recognize the user's emotional state.

[1024] Output: User's emotional state data (e.g., joy, relief, dissatisfaction, etc.)

[1025] Step 8:

[1026] The server optimizes coordination suggestions based on the emotional state.

[1027] Input: User's emotional state data, initial outfit suggestions from a generative AI model

[1028] How it works: The server re-evaluates the outfit based on the emotion data and recreates the suggestions that best fit the user's emotions using a generative AI model.

[1029] Output: Optimized outfit suggestion data

[1030] Step 9:

[1031] It offers users suggested products to buy, rent, or purchase from a flea market.

[1032] Input: Optimized outfit suggestion data

[1033] How it works: Presents users with options to buy, rent, or purchase from a flea market through the smart glasses interface, and then processes payment and shipping for selected items.

[1034] Output: User purchases, rentals, and completed purchases from the flea market

[1035] Through this series of processing steps, users receive suggested fashion coordinations that reflect their emotional state in real time, and can choose to purchase, rent, or buy from a flea market.Furthermore, as a specific example, the following prompt sentence is provided for the generative AI model.

[1036] The user is a 30-year-old woman who prefers a business casual style and likes the color navy. She is attending an event and has a navy skirt and a white blouse. Now that she has tried these items on, she feels comfortable wearing them. Based on this information, please suggest a suitable outfit.

[1037] 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.

[1038] 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.

[1039] 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.

[1040] [Third embodiment]

[1041] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1042] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1043] 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).

[1044] 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.

[1045] 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.

[1046] 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).

[1047] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for 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.

[1048] 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.

[1049] 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.

[1050] 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.

[1051] 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.

[1052] 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."

[1053] The present invention is a system for proposing optimal fashion coordination to a user, and specific embodiments thereof will be described below.

[1054] 1. Collection of User Information

[1055] A user starts the application and enters profile information (age, sex, height, weight, preferred fashion style, preferred colors, event information, etc.).

[1056] A user uses a device (such as a smartphone or PC) to enter their basic information into the application. For example, if a user is a 30-year-old woman whose preferred style is "business casual" and whose preferred color is "navy blue," they would enter this information.

[1057] The user registers information about the items they have on hand.

[1058] Additionally, users can register information about clothes and accessories they already own by taking photos or manually entering them, such as uploading a navy skirt, a white shirt, and black heels.

[1059] 2. Analysis of information

[1060] The terminal transmits user information and on-hand item information to the server.

[1061] The collected user basic information and information on items in hand is sent from the device to the server, which stores this information in a database and assigns each user a unique ID.

[1062] The server analyzes the user data.

[1063] The server performs an initial analysis of the received user information to understand basic fashion styles and trends. This analysis reveals the user's preferences and trends in detail.

[1064] 3. Learning product data

[1065] The server collects all product information on the fashion site.

[1066] The server collects all product information (category, size, color, style, price, etc.) on the fashion site and stores it in a database.

[1067] The server trains the AI ​​to learn the product data.

[1068] The collected product data is input into the generative AI, which then updates its model based on this information, allowing the AI ​​to understand the latest fashion trends and suggest appropriate outfits.

[1069] 4. Coordination Proposal Generation

[1070] The server generates AI based on user information and product data to suggest outfits.

[1071] The server inputs the analyzed user information and learned product data into the generation AI, which then generates the optimal outfit.

[1072] The server filters multiple coordination proposals.

[1073] From the multiple coordination suggestions generated by the AI, the server selects the one that best suits the user's preferences and the latest trends.

[1074] 5. Virtual try-on feature

[1075] The server generates virtual try-on data for the selected outfit.

[1076] The server generates virtual try-on data for the selected outfit and matches it with the user's body type information.

[1077] Users can visually check the product using the virtual try-on function.

[1078] Users can use the virtual try-on feature on their device to visually see how suggested outfits will look on them, simulating how a navy blazer and white blouse would look, for example.

[1079] 6. Purchasing, renting, and flea markets

[1080] The user decides on the suggested product options.

[1081] The user can browse the suggested items on the terminal and choose to buy, rent, or purchase from the flea market.

[1082] The terminal inputs payment information, and the server processes the payment.

[1083] The user enters payment information based on the option selected, and the server processes the payment.

[1084] The server arranges delivery.

[1085] The server will arrange delivery for items for which purchase or rental procedures have been completed. In the case of flea markets, the server will support communication between sellers and buyers and handle delivery procedures.

[1086] This series of program processes allows users to easily find the perfect fashion item, and fashion site operators can increase sales through personalized suggestions.

[1087] The processing flow will be explained below.

[1088] Step 1:

[1089] The user starts the application on the terminal and enters profile information (age, sex, height, weight, preferred fashion style, preferred colors, event information, etc.).

[1090] Step 2:

[1091] The user uses a terminal to register information about clothes and accessories that they already own by taking photos or manually entering the information.

[1092] Step 3:

[1093] The terminal transmits the user's basic information and information about items in hand to the server.

[1094] Step 4:

[1095] The server stores the received user information and on-hand item information in a database and assigns a unique ID to each user.

[1096] Step 5:

[1097] The server performs an initial analysis of user data to determine basic fashion styles and trends.

[1098] Step 6:

[1099] The server collects all product information (category, size, color, style, price, etc.) from the fashion site.

[1100] Step 7:

[1101] The server inputs the collected product data into the generation AI, which then updates the model based on this information.

[1102] Step 8:

[1103] The server inputs analyzed user information and learned product data into the generation AI to generate the optimal outfit.

[1104] Step 9:

[1105] From the multiple coordination suggestions generated by the AI, the server selects the one that best suits the user's preferences and the latest trends.

[1106] Step 10:

[1107] The server generates virtual try-on data for the selected outfit and matches it with the user's body type information.

[1108] Step 11:

[1109] The user can use the virtual try-on function on the device to visually check the suggested outfits.

[1110] Step 12:

[1111] The user browses the suggested items on the device and chooses to buy, rent, or purchase from a flea market.

[1112] Step 13:

[1113] The terminal inputs payment information based on the selection, and the server processes the payment.

[1114] Step 14:

[1115] The server will arrange delivery for items for which purchase or rental procedures have been completed. In the case of flea markets, it will support communication between sellers and buyers and delivery procedures.

[1116] This series of processing steps allows users to easily find the perfect fashion item, and fashion site operators to increase sales.

[1117] Example 1

[1118] 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."

[1119] Previous fashion coordination suggestion systems lacked the ability to provide personalized suggestions based on user preferences and trends, and users had limited means to visually confirm the suggested outfits. Furthermore, the procedures and delivery arrangements for purchasing the suggested items were cumbersome. This made it difficult for users to find the perfect fashion items, and prevented fashion site operators from fully increasing their sales.

[1120] 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.

[1121] In this invention, the server includes means for collecting basic information about the user, means for collecting information about items the user owns, means for transmitting the collected user information, means for analyzing the collected user information and understanding the user's preferences and trends, means for collecting product data, means for training a generation AI to learn the product data, means for the generation AI to suggest outfits based on the user information and the product data, means for filtering the outfits suggested by the generation AI and selecting those that best suit the user's preferences and the latest trends, means for generating virtual try-on data, means for providing a virtual try-on function, means for offering the user the option to purchase, rent, or purchase suggested items from a flea market, means for processing payments, and means for arranging delivery. This allows users to easily find the perfect fashion item, and fashion site operators can increase sales through personalized suggestions.

[1122] The "means for collecting basic information about the user" is a function for acquiring personal information about the user, such as age, sex, height, weight, preferred fashion style, preferred colors, and event information.

[1123] The "means for collecting information on items owned by the user" is a function for collecting information on clothes and accessories that the user already owns by taking photographs or manually entering the information.

[1124] The "means for transmitting collected user information" is a function for transmitting the user's basic information and on-hand item information collected by the terminal to the server.

[1125] "Means of analyzing collected user information and understanding user preferences and trends" refers to a function that allows the server to analyze information received from users and understand their preferences and current fashion trends.

[1126] "Means for collecting product data" is a function that allows the server to obtain all product information on the fashion site and store it in a database.

[1127] "Means for training the generative AI on product data" refers to a function that inputs collected product data into the generative AI, allowing the AI ​​to learn the latest fashion trends.

[1128] "A means for the generation AI to suggest coordination based on user information and product data" is a function that allows the generation AI to analyze user information and product data and suggest the optimal fashion coordination.

[1129] "Means of filtering the outfits proposed by the generation AI and selecting the one that best suits the user's preferences and the latest trends" is a function that selects the outfit that best suits the user's preferences and the latest trends from among the multiple outfit ideas created by the generation AI.

[1130] The "means for generating virtual try-on data" is a function for matching the selected outfit with the user's body type information and generating virtual try-on data that can be visually confirmed.

[1131] The "means for providing a virtual try-on function" is a function that allows a user to use a terminal to access virtual try-on data and visually check suggested outfits.

[1132] "Means for providing users with the ability to purchase, rent, or purchase suggested items from a flea market" is a feature that provides users with the option to purchase, rent, or purchase suggested items from a flea market.

[1133] "Means for processing payment" refers to the function that allows the server to process the payment required to purchase or rent the item selected by the user based on the payment information entered.

[1134] "Means for arranging delivery" refers to arranging delivery of items that have been purchased or rented, and in the case of flea markets, this is a function that supports communication between sellers and buyers and delivery procedures.

[1135] This invention is a system for proposing optimal fashion coordination to a user. The system collects basic information about the user and information about items they own, analyzes this information, and then proposes coordination based on a generative AI model. It then provides a virtual try-on function, allowing the user to purchase, rent, or buy the proposed items from a flea market. A specific embodiment of the system is shown below.

[1136] Collection of User Information

[1137] After launching the application using a device such as a smartphone or PC, users enter their basic information. Input items include age, gender, height, weight, preferred fashion style, favorite color, and event information. For example, if you are a 30-year-old woman whose preferred style is "business casual" and favorite color is "navy," you would enter this information.

[1138] Users can also register information about clothes and accessories they already own by taking photos or manually entering them. For example, they can upload information such as a navy skirt, a white shirt, and black heels to their device.

[1139] Analysis of information

[1140] The device sends the collected user basic information and information about items in their possession to the server. The server stores this information in a database and assigns each user a unique ID. The server performs an initial analysis based on the received information to understand the user's preferences and trends.

[1141] Learning product data

[1142] The server periodically collects all product information (category, size, color, style, price, etc.) from the fashion site and stores it in a database. The server inputs the collected product data into the generation AI and updates the generation AI model. This allows the generation AI to understand the latest fashion trends and propose appropriate outfits.

[1143] Generating outfit suggestions

[1144] The server inputs the analyzed user information and learned product data into the AI, which then proposes the optimal outfit. For example, it generates a combination of "navy skirt, white shirt, and black heels." The server then selects from the multiple outfit suggestions it has generated the one that best suits the user's preferences and the latest trends.

[1145] Virtual try-on function available

[1146] The server generates virtual try-on data for the selected outfit and matches it with the user's body type. The user can then use the virtual try-on function on their device to visually check how the suggested outfit will suit them. For example, they can simulate how a navy blazer and white blouse would look.

[1147] Product purchases, rentals, and flea markets

[1148] The user browses the suggested items on their device and selects whether to buy, rent, or purchase from a flea market. Based on the option selected by the user, payment information is entered and the server processes the payment. Once the purchase or rental procedure is complete, the server arranges delivery of the item. In the case of a flea market, the server supports communication between the seller and buyer and the delivery procedure.

[1149] Specific examples

[1150] As a concrete example, let's say the user is a 30-year-old woman who likes business casual clothing and owns a navy skirt, a white shirt, and black heels. The system uses this information to suggest the best outfits. It also uses the virtual try-on feature to visually check how a navy blazer and a white blouse look.

[1151] Example prompt sentence:

[1152] "I'm a 30-year-old woman who likes business casual. I have a navy skirt, a white shirt, and black heels."

[1153] "I'd like to try on a virtual navy blazer and white blouse combination."

[1154] As described above, this system suggests the most suitable fashion items to users and makes it easy to purchase or rent them. This also enables fashion site operators to increase sales through personalized suggestions.

[1155] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1156] System program processing flow

[1157] Step 1:

[1158] Enter your user profile

[1159] Specific description:

[1160] The user starts the application and enters their profile information (age, gender, height, weight, preferred fashion style, preferred color, event information, etc.). For example, if a user is a 30-year-old woman whose preferred style is "business casual" and whose preferred color is "navy," they enter this information into the device.

[1161] Input and Output:

[1162] Input: User profile information

[1163] Output: User profile information is saved on the device

[1164] Step 2:

[1165] Registering on-hand item information

[1166] Specific description:

[1167] Users can register information about clothes and accessories they already own by taking photos or manually entering them, such as a navy skirt, a white shirt, and black heels, and uploading them to their device.

[1168] Input and Output:

[1169] Input: Information about items on hand

[1170] Output: Information about items in your possession is saved on the device.

[1171] Step 3:

[1172] Sending user information

[1173] Specific description:

[1174] The device sends the collected user information and item information to the server, which stores the information in a database and assigns a unique ID to each user.

[1175] Input and Output:

[1176] Input: User information and item information stored on the device

[1177] Output: User information and item information stored on the server

[1178] Step 4:

[1179] User information analysis

[1180] Specific description:

[1181] The server performs an initial analysis based on the received user information to understand the user's basic preferences and trends. For example, if the user prefers business casual attire, this tendency will be tracked.

[1182] Input and Output:

[1183] Input: User information stored in the database

[1184] Output: Analysis results of user preferences and trend information

[1185] Step 5:

[1186] Collecting product information

[1187] Specific description:

[1188] The server collects all product information from the fashion site and stores it in a database, including information such as category, size, color, style, and price.

[1189] Input and Output:

[1190] Input: Product information from a fashion website

[1191] Output: Product information stored in the database

[1192] Step 6:

[1193] Generative AI training

[1194] Specific description:

[1195] The server inputs the collected product data into the generation AI and updates the model, allowing the generation AI to understand the latest fashion trends and propose outfits.

[1196] Input and Output:

[1197] Input: Product information stored in the database

[1198] Output: A generative AI model that learns the latest fashion trends

[1199] Step 7:

[1200] Generating outfit suggestions

[1201] Specific description:

[1202] The server inputs the analyzed user information and learned product data into the AI, which then generates the optimal outfit. For example, it generates a combination of a navy skirt, a white shirt, and black heels.

[1203] Input and Output:

[1204] Input: User information, product information

[1205] Output: Generated outfit suggestions

[1206] Step 8:

[1207] Filtering outfit suggestions

[1208] Specific description:

[1209] The server selects from the multiple coordinated outfit suggestions generated the one that best suits the user's preferences and the latest trends.

[1210] Input and Output:

[1211] Input: Generated outfit suggestions

[1212] Output: Filtered optimal outfit suggestions

[1213] Step 9:

[1214] Generate virtual try-on data

[1215] Specific description:

[1216] The server generates virtual try-on data for the selected outfit and matches it with the user's body type information, allowing the user to visually check the suggested outfit.

[1217] Input and Output:

[1218] Input: Filtered outfit suggestions, user's body type information

[1219] Output: Generated virtual fitting data

[1220] Step 10:

[1221] Providing virtual try-on functionality

[1222] Specific description:

[1223] Users can use the virtual try-on feature on their device to see how suggested outfits will look on them, for example, simulating how a navy blazer and white blouse would look.

[1224] Input and Output:

[1225] Input: Virtual try-on data

[1226] Output: Visual confirmation through virtual try-on

[1227] Step 11:

[1228] Product selection and payment

[1229] Specific description:

[1230] The user browses the suggested items on the terminal and selects whether to buy, rent, or purchase from the flea market. After making a selection, the user enters payment information, and the server processes the payment.

[1231] Input and Output:

[1232] Input: Selected items, payment information

[1233] Output: Payment completion notification

[1234] Step 12:

[1235] Delivery arrangements

[1236] Specific description:

[1237] The server arranges delivery of purchased or rented items. In the case of a flea market, it supports communication between sellers and buyers and handles delivery procedures.

[1238] Input and Output:

[1239] Input: Payment completion notification, delivery information

[1240] Output: Delivery arrangement completion notification

[1241] This series of programs allows users to easily find the perfect fashion item to purchase or rent, and the virtual try-on feature allows users to see how it will look in real life.

[1242] (Application example 1)

[1243] 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."

[1244] Conventional fashion coordination systems have been unable to adequately address users' specific needs and preferences, and few of them have a virtual try-on function, making it difficult for users to easily find suitable fashion items at home. Another issue is the limited options for purchasing or renting various clothing items. Furthermore, few systems offer real-time virtual try-on functionality, which tends to discourage users from making purchases.

[1245] 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.

[1246] In this invention, the server includes means for collecting basic user information, means for collecting information on the user's owned items, means for analyzing the collected user information to understand the user's preferences and trends, means for training a generation AI to learn product data, means for the generation AI to suggest outfits based on the user information and product data, means for providing a virtual try-on function, means for offering the purchase, rental, or flea market purchase of suggested items in a virtual store, means for trying on items in a virtual space in real time using a head-mounted display, and means for arranging delivery of purchased or rented items. This allows users to easily try on fashion items virtually from the comfort of their own home and receive optimal outfit suggestions. Furthermore, the increased options for purchasing and renting products provide a more satisfying shopping experience.

[1247] "Means for collecting basic user information" refers to a method of providing an interface for users to enter profile information such as their age, gender, height, weight, preferred fashion style, favorite colors, and event information, and then incorporating this information into the system.

[1248] The "means for collecting information on items owned by the user" refers to a method by which the user registers information on the clothes and accessories that he or she owns by taking photographs or manually entering the information.

[1249] "Means for analyzing collected user information and understanding user preferences and trends" refers to technology that analyzes collected basic information about users and information about items they own, and identifies their preferences and current fashion trends.

[1250] "Method of having the generative AI learn product data" refers to a method of collecting all product information on a fashion site, inputting that data into the generative AI, and updating the model.

[1251] "Means for generative AI to suggest coordination based on user information and product data" refers to a method in which generative AI uses analyzed user information and learned product data to provide optimal fashion coordination.

[1252] The "means for providing a virtual try-on function" is a technology that allows a user to try on suggested fashion items in a virtual space and visually check them.

[1253] "Means for offering suggested items for purchase, rental, or purchase from a flea market within a virtual store" is a function that allows a user to choose to purchase, rent, or trade suggested items at a flea market.

[1254] "Means for trying on clothes in a virtual space in real time using a head-mounted display" is a technology that allows users to try on and experience fashion items in a virtual space in real time using a head-mounted display.

[1255] "Means for arranging delivery of purchased or rented products" refers to the procedures for delivering the products purchased or rented by the user to the specified address.

[1256] The system for implementing this invention mainly uses a server, a user terminal, and a head-mounted display (HMD). A specific form of the system is shown below.

[1257] System Configuration

[1258] Hardware and software used:

[1259] Server: General cloud computing service (e.g., Amazon Web Services EC2)

[1260] Database: Relational database system (e.g. Amazon RDS)

[1261] Generative AI models: advanced natural language generation systems (e.g., OpenAI GPT-4)

[1262] User device: Smartphone or personal computer

[1263] Virtual try-on engine: Advanced 3D engine (e.g. Unity 3D)

[1264] Head-mounted displays: commonly used VR devices (e.g., Oculus Rift or HTC Vive)

[1265] Program Overview

[1266] 1. User Information Collection:

[1267] The user uses the terminal to input profile information such as age, sex, height, weight, preferred fashion style, preferred colors, and event information.

[1268] Profile information is sent from the user's device to the server and stored in a database (Amazon RDS).

[1269] 2. Registering your inventory:

[1270] The user uses the device's camera to take photos of the clothes and accessories they own and registers them.

[1271] Using image recognition technology (e.g., Amazon Rekognition), item information is classified and stored in a database.

[1272] 3. Information analysis and product data learning:

[1273] The server analyzes the collected user information to understand user preferences and trends.

[1274] The latest item data is collected by scraping from fashion sites and trained on a generative AI (e.g., GPT-4).

[1275] 4. Coordination proposal generation:

[1276] The generative AI uses analyzed user information and the latest product data to generate optimal coordination suggestions.

[1277] Suggested outfits are filtered based on user preferences and the latest trends.

[1278] 5. Virtual try-on feature:

[1279] The user wears a head-mounted display and tries on the suggested items in a virtual space.

[1280] Using Unity 3D, you can try on your avatar in real time and visually check the fit.

[1281] 6. Product Purchases, Rentals, and Flea Markets:

[1282] The user can choose to buy, rent, or purchase the suggested items from a flea market.

[1283] Once the selected items are purchased, payment information is entered and delivery arrangements are made.

[1284] Specific examples

[1285] Example 1: Prompt when user enters profile information:

[1286] "30 years old, female, height 160cm, weight 55kg, preferred style is business casual, preferred color is navy, event information is company presentation."

[1287] Example 2: Prompt for collecting fashion item data:

[1288] "Collect the latest business casual fashion items and learn about categories, sizes, colors, styles, and pricing information."

[1289] In this way, users can easily find suitable fashion items at home, virtually try them on in real time, and enjoy a wide variety of choices, increasing user satisfaction.

[1290] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1291] Step 1: Collect user information

[1292] The user uses a device to enter profile information such as age, gender, height, weight, preferred fashion style, favorite colors, and event information. The entered information is sent from the device to the server and stored in a database. The input data is sent in JSON format, received by the server, and stored in the database. As an output, a record of the user information is added to the database.

[1293] Step 2: Register your inventory information

[1294] The user uses the device's camera to take a photo of the clothes or accessories they own and registers it. The image file and manually entered details are sent to the server. The server uses image recognition technology to identify the item and store the information in a database. The input data is the image file and a description, and the output is a record of the item information added to the database.

[1295] Step 3: Information analysis and product data learning

[1296] The server analyzes the collected user information and information on items in hand to understand the user's preferences and trends. The server then scrapes and collects the latest item data from fashion sites and trains the generative AI model. The input data is user information and item data, and the output is an analysis of the user's preferences and trends and an updated AI model.

[1297] Step 4: Generate outfit suggestions

[1298] The server uses a generative AI model to generate optimal outfit suggestions based on the analyzed user information and product data. The generated outfits are filtered based on user preferences and the latest trends. The input data are the analysis results and product data, and the output is a list of suggested outfits.

[1299] Step 5: Providing virtual try-on functionality

[1300] The user wears a head-mounted display and tries on the suggested items in a virtual space. The server uses the Unity 3D engine to have an avatar try on the items in real time, allowing the user to visually confirm them. The input data is the suggested outfit, and the output is a virtual try-on scene that is displayed on the user's HMD.

[1301] Step 6: Buying, renting, and going to the flea market

[1302] The user can choose to purchase, rent, or buy from a flea market of the suggested items. The selected item progresses through the purchase process by entering payment information, and the server arranges delivery. The input data is the user's selection and payment information, and the output is a purchase confirmation and notification of delivery arrangements.

[1303] 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.

[1304] The present invention combines an emotion engine with a system that proposes optimal fashion coordination to a user, and specific embodiments thereof are described below.

[1305] 1. Collection of User Information

[1306] A user starts the application and enters profile information (age, sex, height, weight, preferred fashion style, preferred colors, event information, etc.).

[1307] A user inputs their basic information into the application using a device (such as a smartphone or PC). For example, if a user is a 30-year-old woman whose preferred style is "business casual" and whose preferred color is "navy blue," the user inputs this information.

[1308] The user registers information about the items they have on hand.

[1309] Additionally, users can register information about clothes and accessories they already own by taking photos or manually entering them, such as uploading a navy skirt, a white shirt, and black heels.

[1310] 2. Analysis and storage of information

[1311] The terminal transmits user information and on-hand item information to the server.

[1312] The collected user basic information and information on items in hand is sent from the device to the server, which then stores this information in a database and assigns each user a unique ID.

[1313] The server analyzes the user data.

[1314] The server performs an initial analysis of the received user information to understand basic fashion styles and trends, thereby clarifying the user's preferences and current trends.

[1315] 3. Product Data Learning

[1316] The server collects all product information (category, size, color, style, price, etc.) from the fashion site.

[1317] The server collects all product information on the fashion site and stores it in a database.

[1318] The server trains the AI ​​to learn the product data.

[1319] The collected product data is input into the generative AI, which then updates its model based on this information, allowing the AI ​​to understand the latest fashion trends and suggest appropriate outfits.

[1320] 4. Coordination proposal generation and optimization

[1321] The server generates AI based on user information and product data to suggest outfits.

[1322] The server inputs the analyzed user information and learned product data into the generation AI to generate the optimal coordination.

[1323] The server filters multiple coordination proposals.

[1324] From the multiple coordination suggestions generated by the AI, the server selects the one that best suits the user's preferences and the latest trends.

[1325] 5. Emotion Recognition by Emotion Engine

[1326] As users visually check the virtual try-on feature, an emotion engine analyzes the user's current emotional state.

[1327] When a user uses the virtual try-on function on their device to visually check the suggested outfits, the emotion engine recognizes the user's emotional state based on their facial expressions, tone of voice, input actions, etc.

[1328] The server optimizes coordination suggestions based on the results of the emotion engine.

[1329] Based on the user's emotional state obtained by the emotion engine, the server reevaluates the coordination suggestions and, if necessary, changes the content or order of the suggestions.

[1330] 6. Purchasing, renting, and flea markets

[1331] The user decides on the suggested product options.

[1332] The user can browse the suggested items on the terminal and choose to buy, rent, or purchase from the flea market.

[1333] The terminal inputs payment information, and the server processes the payment.

[1334] The user enters payment information based on the option selected, and the server processes the payment.

[1335] The server arranges delivery.

[1336] The server will arrange delivery for items for which purchase or rental procedures have been completed. In the case of flea markets, the server will support communication between sellers and buyers and handle delivery procedures.

[1337] Specific examples

[1338] For example, suppose a user owns a "navy skirt, white blouse, and black heels" and is currently looking for a "business casual outfit." The user registers this information and uses the virtual try-on feature. If the emotion engine identifies positive emotions, such as joy or relief, while trying on the navy blazer and white blouse combination, further relevant suggestions may be made based on this information. For example, other accessories or small items that might be suitable for the user may be suggested. In this way, the emotion engine further personalizes the user's experience, potentially increasing their motivation to purchase.

[1339] This system, based on a series of processing steps, allows users to easily find the perfect fashion item, and the introduction of an emotion engine makes it possible to provide a more personalized experience, which in turn helps fashion site operators increase their sales.

[1340] The processing flow will be explained below.

[1341] Step 1:

[1342] The user starts the application on the terminal and enters profile information (age, sex, height, weight, preferred fashion style, preferred colors, event information, etc.).

[1343] Step 2:

[1344] The user uses a terminal to register information about clothes and accessories that they already own by taking photos or manually entering the information.

[1345] Step 3:

[1346] The terminal transmits the user's basic information and information about items in hand to the server.

[1347] Step 4:

[1348] The server stores the received user information and on-hand item information in a database and assigns a unique ID to each user.

[1349] Step 5:

[1350] The server performs an initial analysis of user data to determine basic fashion styles and trends.

[1351] Step 6:

[1352] The server collects all product information (category, size, color, style, price, etc.) from the fashion site.

[1353] Step 7:

[1354] The server inputs the collected product data into the generation AI, which then updates the model based on this information.

[1355] Step 8:

[1356] The server inputs analyzed user information and learned product data into the generation AI to generate the optimal outfit.

[1357] Step 9:

[1358] From the multiple coordination suggestions generated by the AI, the server selects the one that best suits the user's preferences and the latest trends.

[1359] Step 10:

[1360] The server generates virtual try-on data for the selected outfit and matches it with the user's body type information.

[1361] Step 11:

[1362] The user can use the virtual try-on function on the device to visually check the suggested outfits.

[1363] Step 12:

[1364] During virtual try-on, the emotion engine recognizes the user's emotional state based on facial expressions, tone of voice, input actions, etc.

[1365] Step 13:

[1366] The server optimizes the content and order of coordinated suggestions based on the user's emotional state obtained by the emotion engine.

[1367] Step 14:

[1368] The user browses the suggested items on the device and chooses to buy, rent, or purchase from a flea market.

[1369] Step 15:

[1370] The terminal inputs payment information based on the selection, and the server processes the payment.

[1371] Step 16:

[1372] The server will arrange delivery for items for which purchase or rental procedures have been completed. In the case of flea markets, it will support communication between sellers and buyers and delivery procedures.

[1373] This series of processing steps allows users to easily find the perfect fashion item, and the introduction of an emotion engine makes it possible to provide a more personalized experience. Fashion site operators can also increase their sales.

[1374] Example 2

[1375] 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."

[1376] Modern fashion suggestion systems offer coordinated outfit suggestions that take into account user preferences and trends, but these suggestions ignore the user's emotional state, which means they fail to provide sufficient satisfaction. Furthermore, there is a lack of integrated methods for providing choices between purchasing, renting, and flea market items.

[1377] 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.

[1378] In this invention, the server includes means for collecting basic information about the user, means for collecting information about items the user owns, means for analyzing the collected user information and understanding the user's preferences and trends, means for training a generation AI to learn product data, means for the generation AI to suggest outfits based on the user information and product data, means for providing a virtual try-on function, means for analyzing the user's emotions using an emotion engine when the user is trying on the items virtually, means for optimizing the outfit suggestions based on the user's emotional state, and means for offering the user the option to purchase, rent, or buy the suggested items from a flea market. This enables personalized outfit suggestions that take the user's emotional state into consideration, thereby improving user satisfaction and purchasing motivation.

[1379] "Basic user information" refers to information about a person, such as the user's age, sex, height, weight, preferred fashion style and color, and event information.

[1380] "Information about items in possession" refers to information about clothes and accessories that the user already owns, and specifically refers to data collected through photographs or manual input.

[1381] A "database" is a system that stores collected basic information about users and information about items they own, and manages it in a way that allows it to be searched and updated as needed.

[1382] "Collection means" refers to the method or device used to obtain basic information about a user and information about items held by that user, and specifically includes smartphones and personal computers.

[1383] "Analysis means" refers to the methods and technologies used to analyze collected user information and understand user preferences and trends, and specifically includes data analysis software and algorithms.

[1384] "Generative AI" is an artificial intelligence technology that trains models based on collected data and makes coordination suggestions, and specifically includes natural language processing models and machine learning models.

[1385] "Coordination suggestions" refer to fashion combinations created by the generation AI based on user information and product data.

[1386] The "virtual try-on function" is a function that allows users to try on outfits suggested digitally, and specifically includes technologies using AR (augmented reality) and VR (virtual reality).

[1387] An "emotion engine" is a technology that recognizes a user's emotional state by analyzing their facial expressions, tone of voice, input behavior, etc.

[1388] "Optimizing based on emotional state" refers to reevaluating the suggested outfits based on the acquired emotional data of the user and modifying them as necessary.

[1389] "Buy, rent, buy from flea market" means that the user can choose to buy the suggested fashion item, rent it for short-term use, or buy it second-hand.

[1390] The present invention combines an emotion engine with a system that proposes optimal fashion coordination to a user, and specific embodiments thereof are described below.

[1391] Collection of User Information

[1392] A user launches the application using a device (smartphone or PC). There, they enter their profile information (age, gender, height, weight, preferred fashion style and color, event information, etc.). For example, a 30-year-old woman might enter that she likes "business casual" style and "navy." In addition, the user can register information about clothes and accessories they already own by taking photos or manually entering them. Specifically, they might register a navy skirt, a white shirt, and black heels.

[1393] Analyzing and storing information

[1394] The device sends the collected user information and information about the items in their possession to the server, which stores this information in a database and assigns each user a unique ID. The server then performs an initial analysis of the received user information and uses data analysis software (e.g., Python's Pandas library) to identify user preferences and trends.

[1395] Learning product data

[1396] The server uses a web scraping tool (e.g., Beautiful Soup or Selenium) to collect all product information (e.g., category, size, color, style, price) from fashion websites and stores it in a database. The collected product data is input into a generative AI model (e.g., a GPT or Transformer-based model) to update the model so that the AI ​​can understand the latest fashion trends.

[1397] Coordination proposal generation and optimization

[1398] The server inputs prompts into the AI ​​based on the analyzed user information and learned product data to generate optimal outfit suggestions. For example, a prompt such as "Please suggest a business casual outfit that goes well with a navy skirt" can be used. From the multiple outfit suggestions generated by the AI, the server selects the one that best suits the user's preferences and the latest trends.

[1399] Emotion recognition by emotion engine

[1400] When a user uses the virtual try-on function on their device to visually check the suggested outfits, an emotion engine recognizes the user's emotional state based on their facial expressions, tone of voice, input actions, etc. (For example, Face++ or Microsoft Azure's Face API). The server analyzes the user's emotional state using the emotion engine, reevaluates the outfit suggestions based on that, and adjusts the content and order of the suggestions as necessary.

[1401] Product purchases, rentals, and flea markets

[1402] The user browses the proposed items on the device and selects whether to buy, rent, or purchase from the flea market. Based on the selected option, payment information is entered and the server processes the payment (e.g., Stripe or PayPal API). For purchased or rented items, the server also arranges delivery. In the case of the flea market, the server supports communication between the seller and buyer and the delivery process.

[1403] Specific examples

[1404] For example, suppose a user owns a navy skirt, a white blouse, and black heels and is currently looking for a business casual look. After registering this information, the user uses the virtual try-on feature. If the emotion engine identifies positive emotions, such as joy or relief, while trying on the navy blazer and white blouse combination, further relevant suggestions are made based on this. For example, other accessories or small items that would suit the user may be suggested. This further personalizes the user's experience and increases their motivation to purchase.

[1405] Examples of specific prompts include:

[1406] Please suggest some business casual outfits that would go well with a navy skirt.

[1407] I'm a 30-year-old woman, 160cm tall, 55kg, and my preferred fashion style is business casual. What outfits would you recommend?

[1408] This system allows users to easily find the perfect fashion item, and the introduction of an emotion engine can provide a more personalized experience.

[1409] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1410] Step 1:

[1411] The user uses the terminal to launch the application and enters profile information.

[1412] Input: User's age, gender, height, weight, preferred fashion style, favorite color, event information, etc.

[1413] Output: Basic user information data stored on the device.

[1414] Specific operation: The user launches the application, enters the required information into the input form on the screen, and clicks the submit button.

[1415] Step 2:

[1416] The user uses the terminal to register information about items on hand.

[1417] Input: Photos of clothes and accessories owned by the user, manual input information.

[1418] Output: On-hand item information data saved on the device.

[1419] What happens: Use the camera feature within the application to take photos of the items, manually enter the details of each item, and click the save button.

[1420] Step 3:

[1421] The terminal transmits the collected user information and on-hand item information to the server.

[1422] Input: User's basic information data and on-hand item information data stored on the device.

[1423] Output: User information and item information data sent to the server.

[1424] Specific operation: When the user clicks the information transmission button, the terminal encrypts the data and sends it to the server.

[1425] Step 4:

[1426] The server stores the received user information and on-hand item information in a database and performs an initial analysis.

[1427] Input: User information and item information data sent to the server.

[1428] Output: User information and item information data stored in the database, as well as analysis results.

[1429] Specific operation: The server stores the data in a database and uses data analysis software (e.g., Python's Pandas library) to extract user preferences and trends.

[1430] Step 5:

[1431] The server collects all product information on the fashion site.

[1432] Input: Fashion site URL and structure information.

[1433] Output: Product information data stored in a database.

[1434] What it does: The server uses a web scraping tool (such as Beautiful Soup or Selenium) to collect product information such as category, size, color, style, and price from across fashion sites and stores it in a database.

[1435] Step 6:

[1436] The product data collected by the server is trained into a generative AI model.

[1437] Input: Product information data stored in the database.

[1438] Output: An updated generative AI model.

[1439] Specific operation: The server inputs product data into a generative AI model (e.g., a GPT or Transformer-based model) and trains the model.

[1440] Step 7:

[1441] The server generates an AI model based on user information and product data to suggest outfits.

[1442] Input: Analyzed user information and trained product data.

[1443] Output: Coordination suggestions generated by the generative AI model.

[1444] Specific operation: The server inputs a prompt into the generated AI model, specifically, a prompt such as "Please suggest a business casual outfit that would go well with a navy skirt," and the AI ​​generates the optimal outfit.

[1445] Step 8:

[1446] The server filters multiple outfit suggestions and selects the one that best suits the user's preferences and the latest trends.

[1447] Input: Multiple outfit suggestions generated by the generative AI model.

[1448] Output: Optimal outfit suggestions after filtering.

[1449] Specific operation: The generated multiple coordination suggestions are scored using the user's preferences and trend data, and the coordination with the highest score is selected.

[1450] Step 9:

[1451] The user can use the virtual try-on function on the device to visually check the suggested outfits.

[1452] Input: Filtered optimal outfit suggestions.

[1453] Output: Visual feedback of the virtual try-on.

[1454] Specific operation: The user uses the device's camera and display to virtually try on clothes using AR (augmented reality) or VR (virtual reality) technology and check the suggested outfits.

[1455] Step 10:

[1456] The server uses an emotion engine to analyze the user's emotions and optimizes the coordination proposals.

[1457] Input: User's facial expressions, tone of voice, and input behavior data during virtual try-on.

[1458] Output: Optimized outfit suggestions based on emotion recognition results.

[1459] Specific operation: The emotion engine (for example, Face++ or Microsoft Azure's Face API) recognizes the user's emotional state in real time, and the server analyzes that data to reevaluate and revise the coordination suggestions.

[1460] Step 11:

[1461] The user browses the suggested items and chooses to buy, rent, or purchase from the flea market.

[1462] Input: Optimized coordination proposals.

[1463] Output: The purchase option selected by the user.

[1464] Specific operation: The user checks the coordination suggestions on the device screen, refers to detailed information about each item, and then selects whether to purchase, rent, or go to the flea market.

[1465] Step 12:

[1466] The terminal inputs payment information, and the server processes the payment.

[1467] Input: Your payment information (credit card information, PayPal information, etc.) and the purchase option you selected.

[1468] Output: Completed payment transaction.

[1469] Specific operation: The user enters payment information, the server receives it, and processes it through the payment process (e.g., Stripe or PayPal API).

[1470] Step 13:

[1471] The server arranges delivery.

[1472] Input: Completed payment processing and shipping information.

[1473] Output: Shipping process completed.

[1474] Specific operation: The server coordinates with delivery services (e.g., FedEx or DHL) to arrange for delivery of purchased or rented items. In the case of a flea market, it supports communication between sellers and buyers and the delivery process.

[1475] (Application example 2)

[1476] 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."

[1477] Conventional fashion coordination suggestion systems can make suggestions that take into account the user's basic information and the items they own, but it is difficult to optimize coordination suggestions by reflecting the user's emotional state in real time. As a result, it is difficult to make suggestions that truly satisfy the user, and there is a lack of improvement in increasing purchasing motivation and personalization of the experience.

[1478] 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.

[1479] In this invention, the server includes means for collecting basic information about the user, means for collecting information about items the user owns, means for analyzing the collected user information and understanding the user's preferences and trends, means for having a generating AI learn product data, means for the generating AI to suggest outfits based on the user information and product data, means for providing a virtual try-on function, means for analyzing the user's emotional state, means for optimizing the outfit suggestions based on the emotional state, and means for offering the suggested items to the user for purchase, rental, or purchase from a flea market. This makes it possible to analyze the user's emotional state and optimize the outfit suggestions in real time based on the analysis.

[1480] The "means for collecting basic information about a user" refers to a device or system for collecting basic information about a user, such as age, sex, height, weight, preferred fashion style, preferred colors, and event information.

[1481] The "means for collecting information on items owned by the user" refers to a device or system for collecting information on clothes and accessories already owned by the user by taking photographs or manually entering the information.

[1482] "Means for analyzing collected user information and understanding user preferences and trends" refers to a device or system that analyzes collected basic information and information on items owned by a user to understand the user's preferences and current fashion trends.

[1483] A "means for training a generating AI on product data" is a device or system that collects all product information (category, size, color, style, price, etc.) from a fashion site and inputs it into the generating AI, thereby training the generating AI.

[1484] "Means for a generation AI to suggest coordination based on user information and product data" refers to a device or system that enables a generation AI to generate optimal coordination based on analyzed user information and learned product data.

[1485] The "means for providing a virtual try-on function" is a device or system for providing a function that allows a user to virtually try on clothes.

[1486] The "means for analyzing the user's emotional state" is a device or system for recognizing the user's current emotional state based on the user's facial expression, tone of voice, input behavior, and the like.

[1487] The "means for optimizing coordination suggestions based on emotional state" refers to a device or system for reevaluating and optimizing coordination suggestions made by the generation AI based on the user's emotional state obtained by the emotion engine.

[1488] "Means for offering users the option to purchase, rent, or purchase suggested products from a flea market" refers to a device or system that offers users the option to purchase, rent, or purchase suggested products from a flea market, and that handles payment and delivery arrangements.

[1489] To realize this invention, hardware such as smart glasses and a server and software such as Python, OpenCV, and Keras are used.

[1490] The server collects and stores basic information about the user and the items they own. Specifically, the user enters their age, gender, height, weight, preferred fashion style, favorite colors, and event information through the smart glasses interface. They also register their items by taking photos or manually entering them. This information is sent to the server for initial analysis and stored in a database.

[1491] Next, product data is collected and trained by the generative AI. The server collects all product information from the fashion site and trains the generative AI model based on that information. This generative AI model generates optimal outfits using user information and product data as input.

[1492] When the user then uses the virtual try-on function through the smart glasses, the emotion engine recognizes the user's emotional state from their facial expressions and tone of voice. The server reevaluates and optimizes the outfit suggestions based on this emotional state. The resuggested outfits are displayed on the smart glasses in real time, and the user can choose to buy, rent, or purchase from a flea market.

[1493] For example, consider the suggestions displayed when a user tries on a navy skirt and a white blouse through smart glasses. If the emotion engine recognizes the user's sense of security, it can suggest additional related products, such as black heels and silver accessories, based on that emotion.

[1494] Below are some specific examples of input prompt sentences for the generative AI model.

[1495] The user is a 30-year-old woman who prefers a business casual style and likes the color navy. She is attending an event and has a navy skirt and a white blouse. Now that she has tried these items on, she feels comfortable wearing them. Based on this information, please suggest a suitable outfit.

[1496] This invention makes it possible to analyze a user's emotional state in real time and suggest optimal outfits based on that analysis, thereby increasing the user's purchasing motivation and providing a more personalized shopping experience.

[1497] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1498] Step 1:

[1499] The user inputs basic information through the smart glasses interface.

[1500] Input: Age, gender, height, weight, preferred fashion style, preferred color, event information

[1501] How it works: The user interacts with the smart glasses and provides the required information using text input or menu selections.

[1502] Output: Dataset of basic information entered

[1503] Step 2:

[1504] The user registers information about the items they have on hand.

[1505] Input: Information about the items you own (e.g., navy skirt, white blouse)

[1506] How it works: The user takes a picture of an item with the smart glasses' camera and manually enters the item's details (color, type, etc.).

[1507] Output: A dataset of registered items on hand

[1508] Step 3:

[1509] The server stores user information and item information in a database.

[1510] Input: User basic information dataset, on-hand item information dataset

[1511] How it works: The device sends the collected data to a server, which stores the information in a database.

[1512] Output: User information and items stored in the database

[1513] Step 4:

[1514] The server collects all product information on the fashion site.

[1515] Input: Product information (category, size, color, style, price, etc.) obtained from fashion site APIs or web pages

[1516] How it works: The server collects information using automated scripts and API calls.

[1517] Output: A dataset of collected product information

[1518] Step 5:

[1519] The server trains the generative AI model on product data.

[1520] Input: Product Information Dataset

[1521] How it works: The server provides product data as input to a generative AI model, updating the model to learn the latest trends.

[1522] Output: An updated generative AI model

[1523] Step 6:

[1524] The user uses the virtual try-on feature.

[1525] Input: Virtual try-on image data of the proposed item

[1526] How it works: The user tries on the suggested outfit through the smart glasses and visually checks it.

[1527] Output: facial expressions and movement data of the user while trying on the clothes

[1528] Step 7:

[1529] The server analyzes the user's emotional state.

[1530] Input: facial expressions and movement data of the user while trying on clothes

[1531] How it works: Facial images and audio data captured by the smart glasses' camera are sent to the emotion engine to recognize the user's emotional state.

[1532] Output: User's emotional state data (e.g., joy, relief, dissatisfaction, etc.)

[1533] Step 8:

[1534] The server optimizes coordination suggestions based on the emotional state.

[1535] Input: User's emotional state data, initial outfit suggestions from a generative AI model

[1536] How it works: The server re-evaluates the outfit based on the emotion data and recreates the suggestions that best fit the user's emotions using a generative AI model.

[1537] Output: Optimized outfit suggestion data

[1538] Step 9:

[1539] It offers users suggested products to buy, rent, or purchase from a flea market.

[1540] Input: Optimized outfit suggestion data

[1541] How it works: Presents users with options to buy, rent, or purchase from a flea market through the smart glasses interface, and then processes payment and shipping for selected items.

[1542] Output: User purchases, rentals, and completed purchases from the flea market

[1543] Through this series of processing steps, users receive suggested fashion coordinations that reflect their emotional state in real time, and can choose to purchase, rent, or buy from a flea market.Furthermore, as a specific example, the following prompt sentence is provided for the generative AI model.

[1544] The user is a 30-year-old woman who prefers a business casual style and likes the color navy. She is attending an event and has a navy skirt and a white blouse. Now that she has tried these items on, she feels comfortable wearing them. Based on this information, please suggest a suitable outfit.

[1545] 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.

[1546] 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.

[1547] 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.

[1548] [Fourth embodiment]

[1549] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1550] 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.

[1551] 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).

[1552] 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.

[1553] 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.

[1554] 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).

[1555] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for 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.

[1556] 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.

[1557] 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.

[1558] 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.

[1559] 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.

[1560] 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.

[1561] 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."

[1562] The present invention is a system for proposing optimal fashion coordination to a user, and specific embodiments thereof will be described below.

[1563] 1. Collection of User Information

[1564] A user starts the application and enters profile information (age, sex, height, weight, preferred fashion style, preferred colors, event information, etc.).

[1565] A user uses a device (such as a smartphone or PC) to enter their basic information into the application. For example, if a user is a 30-year-old woman whose preferred style is "business casual" and whose preferred color is "navy blue," they would enter this information.

[1566] The user registers information about the items they have on hand.

[1567] Additionally, users can register information about clothes and accessories they already own by taking photos or manually entering them, such as uploading a navy skirt, a white shirt, and black heels.

[1568] 2. Analysis of information

[1569] The terminal transmits user information and on-hand item information to the server.

[1570] The collected user basic information and information on items in hand is sent from the device to the server, which stores this information in a database and assigns each user a unique ID.

[1571] The server analyzes the user data.

[1572] The server performs an initial analysis of the received user information to understand basic fashion styles and trends. This analysis reveals the user's preferences and trends in detail.

[1573] 3. Learning product data

[1574] The server collects all product information on the fashion site.

[1575] The server collects all product information (category, size, color, style, price, etc.) on the fashion site and stores it in a database.

[1576] The server trains the AI ​​to learn the product data.

[1577] The collected product data is input into the generative AI, which then updates its model based on this information, allowing the AI ​​to understand the latest fashion trends and suggest appropriate outfits.

[1578] 4. Coordination Proposal Generation

[1579] The server generates AI based on user information and product data to suggest outfits.

[1580] The server inputs the analyzed user information and learned product data into the generation AI, which then generates the optimal outfit.

[1581] The server filters multiple coordination proposals.

[1582] From the multiple coordination suggestions generated by the AI, the server selects the one that best suits the user's preferences and the latest trends.

[1583] 5. Virtual try-on feature

[1584] The server generates virtual try-on data for the selected outfit.

[1585] The server generates virtual try-on data for the selected outfit and matches it with the user's body type information.

[1586] Users can visually check the product using the virtual try-on function.

[1587] Users can use the virtual try-on feature on their device to visually see how suggested outfits will look on them, simulating how a navy blazer and white blouse would look, for example.

[1588] 6. Purchasing, renting, and flea markets

[1589] The user decides on the suggested product options.

[1590] The user can browse the suggested items on the terminal and choose to buy, rent, or purchase from the flea market.

[1591] The terminal inputs payment information, and the server processes the payment.

[1592] The user enters payment information based on the option selected, and the server processes the payment.

[1593] The server arranges delivery.

[1594] The server will arrange delivery for items for which purchase or rental procedures have been completed. In the case of flea markets, the server will support communication between sellers and buyers and handle delivery procedures.

[1595] This series of program processes allows users to easily find the perfect fashion item, and fashion site operators can increase sales through personalized suggestions.

[1596] The processing flow will be explained below.

[1597] Step 1:

[1598] The user starts the application on the terminal and enters profile information (age, sex, height, weight, preferred fashion style, preferred colors, event information, etc.).

[1599] Step 2:

[1600] The user uses a terminal to register information about clothes and accessories that they already own by taking photos or manually entering the information.

[1601] Step 3:

[1602] The terminal transmits the user's basic information and information about items in hand to the server.

[1603] Step 4:

[1604] The server stores the received user information and on-hand item information in a database and assigns a unique ID to each user.

[1605] Step 5:

[1606] The server performs an initial analysis of user data to determine basic fashion styles and trends.

[1607] Step 6:

[1608] The server collects all product information (category, size, color, style, price, etc.) from the fashion site.

[1609] Step 7:

[1610] The server inputs the collected product data into the generation AI, which then updates the model based on this information.

[1611] Step 8:

[1612] The server inputs analyzed user information and learned product data into the generation AI to generate the optimal outfit.

[1613] Step 9:

[1614] From the multiple coordination suggestions generated by the AI, the server selects the one that best suits the user's preferences and the latest trends.

[1615] Step 10:

[1616] The server generates virtual try-on data for the selected outfit and matches it with the user's body type information.

[1617] Step 11:

[1618] The user can use the virtual try-on function on the device to visually check the suggested outfits.

[1619] Step 12:

[1620] The user browses the suggested items on the device and chooses to buy, rent, or purchase from a flea market.

[1621] Step 13:

[1622] The terminal inputs payment information based on the selection, and the server processes the payment.

[1623] Step 14:

[1624] The server will arrange delivery for items for which purchase or rental procedures have been completed. In the case of flea markets, it will support communication between sellers and buyers and delivery procedures.

[1625] This series of processing steps allows users to easily find the perfect fashion item, and fashion site operators to increase sales.

[1626] Example 1

[1627] 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."

[1628] Previous fashion coordination suggestion systems lacked the ability to provide personalized suggestions based on user preferences and trends, and users had limited means to visually confirm the suggested outfits. Furthermore, the procedures and delivery arrangements for purchasing the suggested items were cumbersome. This made it difficult for users to find the perfect fashion items, and prevented fashion site operators from fully increasing their sales.

[1629] 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.

[1630] In this invention, the server includes means for collecting basic information about the user, means for collecting information about items the user owns, means for transmitting the collected user information, means for analyzing the collected user information and understanding the user's preferences and trends, means for collecting product data, means for training a generation AI to learn the product data, means for the generation AI to suggest outfits based on the user information and the product data, means for filtering the outfits suggested by the generation AI and selecting those that best suit the user's preferences and the latest trends, means for generating virtual try-on data, means for providing a virtual try-on function, means for offering the user the option to purchase, rent, or purchase suggested items from a flea market, means for processing payments, and means for arranging delivery. This allows users to easily find the perfect fashion item, and fashion site operators can increase sales through personalized suggestions.

[1631] The "means for collecting basic information about the user" is a function for acquiring personal information about the user, such as age, sex, height, weight, preferred fashion style, preferred colors, and event information.

[1632] The "means for collecting information on items owned by the user" is a function for collecting information on clothes and accessories that the user already owns by taking photographs or manually entering the information.

[1633] The "means for transmitting collected user information" is a function for transmitting the user's basic information and on-hand item information collected by the terminal to the server.

[1634] "Means of analyzing collected user information and understanding user preferences and trends" refers to a function that allows the server to analyze information received from users and understand their preferences and current fashion trends.

[1635] "Means for collecting product data" is a function that allows the server to obtain all product information on the fashion site and store it in a database.

[1636] "Means for training the generative AI on product data" refers to a function that inputs collected product data into the generative AI, allowing the AI ​​to learn the latest fashion trends.

[1637] "A means for the generation AI to suggest coordination based on user information and product data" is a function that allows the generation AI to analyze user information and product data and suggest the optimal fashion coordination.

[1638] "Means of filtering the outfits proposed by the generation AI and selecting the one that best suits the user's preferences and the latest trends" is a function that selects the outfit that best suits the user's preferences and the latest trends from among the multiple outfit ideas created by the generation AI.

[1639] The "means for generating virtual try-on data" is a function for matching the selected outfit with the user's body type information and generating virtual try-on data that can be visually confirmed.

[1640] The "means for providing a virtual try-on function" is a function that allows a user to use a terminal to access virtual try-on data and visually check suggested outfits.

[1641] "Means for providing users with the ability to purchase, rent, or purchase suggested items from a flea market" is a feature that provides users with the option to purchase, rent, or purchase suggested items from a flea market.

[1642] "Means for processing payment" refers to the function that allows the server to process the payment required to purchase or rent the item selected by the user based on the payment information entered.

[1643] "Means for arranging delivery" refers to arranging delivery of items that have been purchased or rented, and in the case of flea markets, this is a function that supports communication between sellers and buyers and delivery procedures.

[1644] This invention is a system for proposing optimal fashion coordination to a user. The system collects basic information about the user and information about items they own, analyzes this information, and then proposes coordination based on a generative AI model. It then provides a virtual try-on function, allowing the user to purchase, rent, or buy the proposed items from a flea market. A specific embodiment of the system is shown below.

[1645] Collection of User Information

[1646] After launching the application using a device such as a smartphone or PC, users enter their basic information. Input items include age, gender, height, weight, preferred fashion style, favorite color, and event information. For example, if you are a 30-year-old woman whose preferred style is "business casual" and favorite color is "navy," you would enter this information.

[1647] Users can also register information about clothes and accessories they already own by taking photos or manually entering them. For example, they can upload information such as a navy skirt, a white shirt, and black heels to their device.

[1648] Analysis of information

[1649] The device sends the collected user basic information and information about items in their possession to the server. The server stores this information in a database and assigns each user a unique ID. The server performs an initial analysis based on the received information to understand the user's preferences and trends.

[1650] Learning product data

[1651] The server periodically collects all product information (category, size, color, style, price, etc.) from the fashion site and stores it in a database. The server inputs the collected product data into the generation AI and updates the generation AI model. This allows the generation AI to understand the latest fashion trends and propose appropriate outfits.

[1652] Generating outfit suggestions

[1653] The server inputs the analyzed user information and learned product data into the AI, which then proposes the optimal outfit. For example, it generates a combination of "navy skirt, white shirt, and black heels." The server then selects from the multiple outfit suggestions it has generated the one that best suits the user's preferences and the latest trends.

[1654] Virtual try-on function available

[1655] The server generates virtual try-on data for the selected outfit and matches it with the user's body type. The user can then use the virtual try-on function on their device to visually check how the suggested outfit will suit them. For example, they can simulate how a navy blazer and white blouse would look.

[1656] Product purchases, rentals, and flea markets

[1657] The user browses the suggested items on their device and selects whether to buy, rent, or purchase from a flea market. Based on the option selected by the user, payment information is entered and the server processes the payment. Once the purchase or rental procedure is complete, the server arranges delivery of the item. In the case of a flea market, the server supports communication between the seller and buyer and the delivery procedure.

[1658] Specific examples

[1659] As a concrete example, let's say the user is a 30-year-old woman who likes business casual clothing and owns a navy skirt, a white shirt, and black heels. The system uses this information to suggest the best outfits. It also uses the virtual try-on feature to visually check how a navy blazer and a white blouse look.

[1660] Example prompt sentence:

[1661] "I'm a 30-year-old woman who likes business casual. I have a navy skirt, a white shirt, and black heels."

[1662] "I'd like to try on a virtual navy blazer and white blouse combination."

[1663] As described above, this system suggests the most suitable fashion items to users and makes it easy to purchase or rent them. This also enables fashion site operators to increase sales through personalized suggestions.

[1664] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1665] System program processing flow

[1666] Step 1:

[1667] Enter your user profile

[1668] Specific description:

[1669] The user starts the application and enters their profile information (age, gender, height, weight, preferred fashion style, preferred color, event information, etc.). For example, if a user is a 30-year-old woman whose preferred style is "business casual" and whose preferred color is "navy," they enter this information into the device.

[1670] Input and Output:

[1671] Input: User profile information

[1672] Output: User profile information is saved on the device

[1673] Step 2:

[1674] Registering on-hand item information

[1675] Specific description:

[1676] Users can register information about clothes and accessories they already own by taking photos or manually entering them, such as a navy skirt, a white shirt, and black heels, and uploading them to their device.

[1677] Input and Output:

[1678] Input: Information about items on hand

[1679] Output: Information about items in your possession is saved on the device.

[1680] Step 3:

[1681] Sending user information

[1682] Specific description:

[1683] The device sends the collected user information and item information to the server, which stores the information in a database and assigns a unique ID to each user.

[1684] Input and Output:

[1685] Input: User information and item information stored on the device

[1686] Output: User information and item information stored on the server

[1687] Step 4:

[1688] User information analysis

[1689] Specific description:

[1690] The server performs an initial analysis based on the received user information to understand the user's basic preferences and trends. For example, if the user prefers business casual attire, this tendency will be tracked.

[1691] Input and Output:

[1692] Input: User information stored in the database

[1693] Output: Analysis results of user preferences and trend information

[1694] Step 5:

[1695] Collecting product information

[1696] Specific description:

[1697] The server collects all product information from the fashion site and stores it in a database, including information such as category, size, color, style, and price.

[1698] Input and Output:

[1699] Input: Product information from a fashion website

[1700] Output: Product information stored in the database

[1701] Step 6:

[1702] Generative AI training

[1703] Specific description:

[1704] The server inputs the collected product data into the generation AI and updates the model, allowing the generation AI to understand the latest fashion trends and propose outfits.

[1705] Input and Output:

[1706] Input: Product information stored in the database

[1707] Output: A generative AI model that learns the latest fashion trends

[1708] Step 7:

[1709] Generating outfit suggestions

[1710] Specific description:

[1711] The server inputs the analyzed user information and learned product data into the AI, which then generates the optimal outfit. For example, it generates a combination of a navy skirt, a white shirt, and black heels.

[1712] Input and Output:

[1713] Input: User information, product information

[1714] Output: Generated outfit suggestions

[1715] Step 8:

[1716] Filtering outfit suggestions

[1717] Specific description:

[1718] The server selects from the multiple coordinated outfit suggestions generated the one that best suits the user's preferences and the latest trends.

[1719] Input and Output:

[1720] Input: Generated outfit suggestions

[1721] Output: Filtered optimal outfit suggestions

[1722] Step 9:

[1723] Generate virtual try-on data

[1724] Specific description:

[1725] The server generates virtual try-on data for the selected outfit and matches it with the user's body type information, allowing the user to visually check the suggested outfit.

[1726] Input and Output:

[1727] Input: Filtered outfit suggestions, user's body type information

[1728] Output: Generated virtual fitting data

[1729] Step 10:

[1730] Virtual try-on function available

[1731] Specific description:

[1732] Users can use the virtual try-on feature on their device to see how suggested outfits will look on them, for example, simulating how a navy blazer and white blouse would look.

[1733] Input and Output:

[1734] Input: Virtual try-on data

[1735] Output: Visual confirmation through virtual try-on

[1736] Step 11:

[1737] Product selection and payment

[1738] Specific description:

[1739] The user browses the suggested items on the terminal and selects whether to buy, rent, or purchase from the flea market. After making a selection, the user enters payment information, and the server processes the payment.

[1740] Input and Output:

[1741] Input: Selected items, payment information

[1742] Output: Payment completion notification

[1743] Step 12:

[1744] Delivery arrangements

[1745] Specific description:

[1746] The server arranges delivery of purchased or rented items. In the case of a flea market, it supports communication between sellers and buyers and handles delivery procedures.

[1747] Input and Output:

[1748] Input: Payment completion notification, delivery information

[1749] Output: Delivery arrangement completion notification

[1750] This series of programs allows users to easily find the perfect fashion item to purchase or rent, and the virtual try-on feature allows users to see how it will look in real life.

[1751] (Application example 1)

[1752] 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."

[1753] Conventional fashion coordination systems have been unable to adequately address users' specific needs and preferences, and few of them have a virtual try-on function, making it difficult for users to easily find suitable fashion items at home. Another issue is the limited options for purchasing or renting various clothing items. Furthermore, few systems offer real-time virtual try-on functionality, which tends to discourage users from making purchases.

[1754] 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.

[1755] In this invention, the server includes means for collecting basic user information, means for collecting information on the user's owned items, means for analyzing the collected user information to understand the user's preferences and trends, means for training a generation AI to learn product data, means for the generation AI to suggest outfits based on the user information and product data, means for providing a virtual try-on function, means for offering the purchase, rental, or flea market purchase of suggested items in a virtual store, means for trying on items in a virtual space in real time using a head-mounted display, and means for arranging delivery of purchased or rented items. This allows users to easily try on fashion items virtually from the comfort of their own home and receive optimal outfit suggestions. Furthermore, the increased options for purchasing and renting products provide a more satisfying shopping experience.

[1756] "Means for collecting basic user information" refers to a method of providing an interface for users to enter profile information such as their age, gender, height, weight, preferred fashion style, favorite colors, and event information, and then incorporating this information into the system.

[1757] The "means for collecting information on items owned by the user" refers to a method by which the user registers information on the clothes and accessories that he or she owns by taking photographs or manually entering the information.

[1758] "Means for analyzing collected user information and understanding user preferences and trends" refers to technology that analyzes collected basic information about users and information about items they own, and identifies their preferences and current fashion trends.

[1759] "Method of having the generative AI learn product data" refers to a method of collecting all product information on a fashion site, inputting that data into the generative AI, and updating the model.

[1760] "Means for generative AI to suggest coordination based on user information and product data" refers to a method in which generative AI uses analyzed user information and learned product data to provide optimal fashion coordination.

[1761] The "means for providing a virtual try-on function" is a technology that allows a user to try on suggested fashion items in a virtual space and visually check them.

[1762] "Means for offering suggested items for purchase, rental, or purchase from a flea market within a virtual store" is a function that allows a user to choose to purchase, rent, or trade suggested items at a flea market.

[1763] "Means for trying on clothes in a virtual space in real time using a head-mounted display" is a technology that allows users to try on and experience fashion items in a virtual space in real time using a head-mounted display.

[1764] "Means for arranging delivery of purchased or rented products" refers to the procedures for delivering the products purchased or rented by the user to the specified address.

[1765] The system for implementing this invention mainly uses a server, a user terminal, and a head-mounted display (HMD). A specific form of the system is shown below.

[1766] System Configuration

[1767] Hardware and software used:

[1768] Server: General cloud computing service (e.g., Amazon Web Services EC2)

[1769] Database: Relational database system (e.g. Amazon RDS)

[1770] Generative AI models: advanced natural language generation systems (e.g., OpenAI GPT-4)

[1771] User device: Smartphone or personal computer

[1772] Virtual try-on engine: Advanced 3D engine (e.g. Unity 3D)

[1773] Head-mounted displays: commonly used VR devices (e.g., Oculus Rift or HTC Vive)

[1774] Program Overview

[1775] 1. User Information Collection:

[1776] The user uses the terminal to input profile information such as age, sex, height, weight, preferred fashion style, preferred colors, and event information.

[1777] Profile information is sent from the user's device to the server and stored in a database (Amazon RDS).

[1778] 2. Registering your inventory:

[1779] The user uses the device's camera to take photos of the clothes and accessories they own and registers them.

[1780] Using image recognition technology (e.g., Amazon Rekognition), item information is classified and stored in a database.

[1781] 3. Information analysis and product data learning:

[1782] The server analyzes the collected user information to understand user preferences and trends.

[1783] The latest item data is collected by scraping from fashion sites and trained on a generative AI (e.g., GPT-4).

[1784] 4. Coordination proposal generation:

[1785] The generative AI uses analyzed user information and the latest product data to generate optimal coordination suggestions.

[1786] Suggested outfits are filtered based on user preferences and the latest trends.

[1787] 5. Virtual try-on feature:

[1788] The user wears a head-mounted display and tries on the suggested items in a virtual space.

[1789] Using Unity 3D, you can try on your avatar in real time and visually check the clothes.

[1790] 6. Product Purchases, Rentals, and Flea Markets:

[1791] The user can choose to buy, rent, or purchase the suggested items from a flea market.

[1792] Once the selected items are purchased, payment information is entered and delivery arrangements are made.

[1793] Specific examples

[1794] Example 1: Prompt when user enters profile information:

[1795] "30 years old, female, height 160cm, weight 55kg, preferred style is business casual, preferred color is navy, event information is company presentation."

[1796] Example 2: Prompt for collecting fashion item data:

[1797] "Collect the latest business casual fashion items and learn about categories, sizes, colors, styles, and pricing information."

[1798] In this way, users can easily find suitable fashion items at home, virtually try them on in real time, and enjoy a wide variety of choices, increasing user satisfaction.

[1799] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1800] Step 1: Collect user information

[1801] The user uses a device to enter profile information such as age, gender, height, weight, preferred fashion style, favorite colors, and event information. The entered information is sent from the device to the server and stored in a database. The input data is sent in JSON format, received by the server, and stored in the database. As an output, a record of the user information is added to the database.

[1802] Step 2: Register your inventory information

[1803] The user uses the device's camera to take a photo of the clothes or accessories they own and registers it. The image file and manually entered details are sent to the server. The server uses image recognition technology to identify the item and store the information in a database. The input data is the image file and a description, and the output is a record of the item information added to the database.

[1804] Step 3: Information analysis and product data learning

[1805] The server analyzes the collected user information and information on items in hand to understand the user's preferences and trends. The server then scrapes and collects the latest item data from fashion sites and trains the generative AI model. The input data is user information and item data, and the output is an analysis of the user's preferences and trends and an updated AI model.

[1806] Step 4: Generate outfit suggestions

[1807] The server uses a generative AI model to generate optimal outfit suggestions based on the analyzed user information and product data. The generated outfits are filtered based on user preferences and the latest trends. The input data are the analysis results and product data, and the output is a list of suggested outfits.

[1808] Step 5: Providing virtual try-on functionality

[1809] The user wears a head-mounted display and tries on the suggested items in a virtual space. The server uses the Unity 3D engine to have an avatar try on the items in real time, allowing the user to visually confirm them. The input data is the suggested outfit, and the output is a virtual try-on scene that is displayed on the user's HMD.

[1810] Step 6: Buying, renting, and going to the flea market

[1811] The user can choose to purchase, rent, or buy from a flea market of the suggested items. The selected item progresses through the purchase process by entering payment information, and the server arranges delivery. The input data is the user's selection and payment information, and the output is a purchase confirmation and notification of delivery arrangements.

[1812] 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.

[1813] The present invention combines an emotion engine with a system that proposes optimal fashion coordination to a user, and specific embodiments thereof are described below.

[1814] 1. Collection of User Information

[1815] A user starts the application and enters profile information (age, sex, height, weight, preferred fashion style, preferred colors, event information, etc.).

[1816] A user inputs their basic information into the application using a device (such as a smartphone or PC). For example, if a user is a 30-year-old woman whose preferred style is "business casual" and whose preferred color is "navy blue," the user inputs this information.

[1817] The user registers information about the items they have on hand.

[1818] Additionally, users can register information about clothes and accessories they already own by taking photos or manually entering them, such as uploading a navy skirt, a white shirt, and black heels.

[1819] 2. Analysis and storage of information

[1820] The terminal transmits user information and on-hand item information to the server.

[1821] The collected user basic information and information on items in hand is sent from the device to the server, which then stores this information in a database and assigns each user a unique ID.

[1822] The server analyzes the user data.

[1823] The server performs an initial analysis of the received user information to understand basic fashion styles and trends, thereby clarifying the user's preferences and current trends.

[1824] 3. Learning product data

[1825] The server collects all product information (category, size, color, style, price, etc.) from the fashion site.

[1826] The server collects all product information on the fashion site and stores it in a database.

[1827] The server trains the AI ​​to learn the product data.

[1828] The collected product data is input into the generative AI, which then updates its model based on this information, allowing the AI ​​to understand the latest fashion trends and suggest appropriate outfits.

[1829] 4. Coordination proposal generation and optimization

[1830] The server generates AI based on user information and product data to suggest outfits.

[1831] The server inputs the analyzed user information and learned product data into the generation AI to generate the optimal coordination.

[1832] The server filters multiple coordination proposals.

[1833] From the multiple coordination suggestions generated by the AI, the server selects the one that best suits the user's preferences and the latest trends.

[1834] 5. Emotion Recognition by Emotion Engine

[1835] As users visually check the virtual try-on feature, an emotion engine analyzes the user's current emotional state.

[1836] When a user uses the virtual try-on function on their device to visually check the suggested outfits, the emotion engine recognizes the user's emotional state based on their facial expressions, tone of voice, input actions, etc.

[1837] The server optimizes coordination suggestions based on the results of the emotion engine.

[1838] Based on the user's emotional state obtained by the emotion engine, the server reevaluates the coordination suggestions and, if necessary, changes the content or order of the suggestions.

[1839] 6. Purchasing, renting, and flea markets

[1840] The user decides on the suggested product options.

[1841] The user can browse the suggested items on the terminal and choose to buy, rent, or purchase from the flea market.

[1842] The terminal inputs payment information, and the server processes the payment.

[1843] The user enters payment information based on the option selected, and the server processes the payment.

[1844] The server arranges delivery.

[1845] The server will arrange delivery for items for which purchase or rental procedures have been completed. In the case of flea markets, the server will support communication between sellers and buyers and handle delivery procedures.

[1846] Specific examples

[1847] For example, suppose a user owns a "navy skirt, white blouse, and black heels" and is currently looking for a "business casual outfit." The user registers this information and uses the virtual try-on feature. If the emotion engine identifies positive emotions, such as joy or relief, while trying on the navy blazer and white blouse combination, further relevant suggestions may be made based on this information. For example, other accessories or small items that might be suitable for the user may be suggested. In this way, the emotion engine further personalizes the user's experience, potentially increasing their motivation to purchase.

[1848] This system, based on a series of processing steps, allows users to easily find the perfect fashion item, and the introduction of an emotion engine makes it possible to provide a more personalized experience, which in turn helps fashion site operators increase their sales.

[1849] The processing flow will be explained below.

[1850] Step 1:

[1851] The user starts the application on the terminal and enters profile information (age, sex, height, weight, preferred fashion style, preferred colors, event information, etc.).

[1852] Step 2:

[1853] The user uses a terminal to register information about clothes and accessories that they already own by taking photos or manually entering the information.

[1854] Step 3:

[1855] The terminal transmits the user's basic information and information about items in hand to the server.

[1856] Step 4:

[1857] The server stores the received user information and on-hand item information in a database and assigns a unique ID to each user.

[1858] Step 5:

[1859] The server performs an initial analysis of user data to determine basic fashion styles and trends.

[1860] Step 6:

[1861] The server collects all product information (category, size, color, style, price, etc.) from the fashion site.

[1862] Step 7:

[1863] The server inputs the collected product data into the generation AI, which then updates the model based on this information.

[1864] Step 8:

[1865] The server inputs analyzed user information and learned product data into the generation AI to generate the optimal outfit.

[1866] Step 9:

[1867] From the multiple coordination suggestions generated by the AI, the server selects the one that best suits the user's preferences and the latest trends.

[1868] Step 10:

[1869] The server generates virtual try-on data for the selected outfit and matches it with the user's body type information.

[1870] Step 11:

[1871] The user can use the virtual try-on function on the device to visually check the suggested outfits.

[1872] Step 12:

[1873] During virtual try-on, the emotion engine recognizes the user's emotional state based on facial expressions, tone of voice, input actions, etc.

[1874] Step 13:

[1875] The server optimizes the content and order of coordinated suggestions based on the user's emotional state obtained by the emotion engine.

[1876] Step 14:

[1877] The user browses the suggested items on the device and chooses to buy, rent, or purchase from a flea market.

[1878] Step 15:

[1879] The terminal inputs payment information based on the selection, and the server processes the payment.

[1880] Step 16:

[1881] The server will arrange delivery for items for which purchase or rental procedures have been completed. In the case of flea markets, it will support communication between sellers and buyers and delivery procedures.

[1882] This series of processing steps allows users to easily find the perfect fashion item, and the introduction of an emotion engine makes it possible to provide a more personalized experience. Fashion site operators can also increase their sales.

[1883] Example 2

[1884] 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."

[1885] Modern fashion suggestion systems offer coordinated outfit suggestions that take into account user preferences and trends, but these suggestions ignore the user's emotional state, which means they fail to provide sufficient satisfaction. Furthermore, there is a lack of integrated methods for providing choices between purchasing, renting, and flea market items.

[1886] 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.

[1887] In this invention, the server includes means for collecting basic information about the user, means for collecting information about items the user owns, means for analyzing the collected user information and understanding the user's preferences and trends, means for training a generation AI to learn product data, means for the generation AI to suggest outfits based on the user information and product data, means for providing a virtual try-on function, means for analyzing the user's emotions using an emotion engine when the user is trying on the items virtually, means for optimizing the outfit suggestions based on the user's emotional state, and means for offering the user the option to purchase, rent, or buy the suggested items from a flea market. This enables personalized outfit suggestions that take the user's emotional state into consideration, thereby improving user satisfaction and purchasing motivation.

[1888] "Basic user information" refers to information about a person, such as the user's age, sex, height, weight, preferred fashion style and color, and event information.

[1889] "Information about items in possession" refers to information about clothes and accessories that the user already owns, and specifically refers to data collected through photographs or manual input.

[1890] A "database" is a system that stores collected basic information about users and information about items they own, and manages it in a way that allows it to be searched and updated as needed.

[1891] "Collection means" refers to the method or device used to obtain basic information about a user and information about items held by that user, and specifically includes smartphones and personal computers.

[1892] "Analysis means" refers to the methods and technologies used to analyze collected user information and understand user preferences and trends, and specifically includes data analysis software and algorithms.

[1893] "Generative AI" is an artificial intelligence technology that trains models based on collected data and makes coordination suggestions, and specifically includes natural language processing models and machine learning models.

[1894] "Coordination suggestions" refer to fashion combinations created by the generation AI based on user information and product data.

[1895] The "virtual try-on function" is a function that allows users to try on outfits suggested digitally, and specifically includes technologies using AR (augmented reality) and VR (virtual reality).

[1896] An "emotion engine" is a technology that recognizes a user's emotional state by analyzing their facial expressions, tone of voice, input behavior, etc.

[1897] "Optimizing based on emotional state" refers to reevaluating the suggested outfits based on the acquired emotional data of the user and modifying them as necessary.

[1898] "Buy, rent, buy from flea market" means that the user can choose to buy the suggested fashion item, rent it for short-term use, or buy it second-hand.

[1899] The present invention combines an emotion engine with a system that proposes optimal fashion coordination to a user, and specific embodiments thereof are described below.

[1900] Collection of User Information

[1901] A user launches the application using a device (smartphone or PC). There, they enter their profile information (age, gender, height, weight, preferred fashion style and color, event information, etc.). For example, a 30-year-old woman might enter that she likes "business casual" style and "navy." In addition, the user can register information about clothes and accessories they already own by taking photos or manually entering them. Specifically, they might register a navy skirt, a white shirt, and black heels.

[1902] Analyzing and storing information

[1903] The device sends the collected user information and information about the items in their possession to the server, which stores this information in a database and assigns each user a unique ID. The server then performs an initial analysis of the received user information and uses data analysis software (e.g., Python's Pandas library) to identify user preferences and trends.

[1904] Learning product data

[1905] The server uses a web scraping tool (e.g., Beautiful Soup or Selenium) to collect all product information (e.g., category, size, color, style, price) from fashion websites and stores it in a database. The collected product data is input into a generative AI model (e.g., a GPT or Transformer-based model) to update the model so that the AI ​​can understand the latest fashion trends.

[1906] Coordination proposal generation and optimization

[1907] The server inputs prompts into the AI ​​based on the analyzed user information and learned product data to generate optimal outfit suggestions. For example, a prompt such as "Please suggest a business casual outfit that goes well with a navy skirt" can be used. From the multiple outfit suggestions generated by the AI, the server selects the one that best suits the user's preferences and the latest trends.

[1908] Emotion recognition by emotion engine

[1909] When a user uses the virtual try-on function on their device to visually check the suggested outfits, an emotion engine recognizes the user's emotional state based on their facial expressions, tone of voice, input actions, etc. (For example, Face++ or Microsoft Azure's Face API). The server analyzes the user's emotional state using the emotion engine, reevaluates the outfit suggestions based on that, and adjusts the content and order of the suggestions as necessary.

[1910] Product purchases, rentals, and flea markets

[1911] The user browses the proposed items on the device and selects whether to buy, rent, or purchase from the flea market. Based on the selected option, payment information is entered and the server processes the payment (e.g., Stripe or PayPal API). For purchased or rented items, the server also arranges delivery. In the case of the flea market, the server supports communication between the seller and buyer and the delivery process.

[1912] Specific examples

[1913] For example, suppose a user owns a navy skirt, a white blouse, and black heels and is currently looking for a business casual look. After registering this information, the user uses the virtual try-on feature. If the emotion engine identifies positive emotions, such as joy or relief, while trying on the navy blazer and white blouse combination, further relevant suggestions are made based on this. For example, other accessories or small items that would suit the user may be suggested. This further personalizes the user's experience and increases their motivation to purchase.

[1914] Examples of specific prompts include:

[1915] Please suggest some business casual outfits that would go well with a navy skirt.

[1916] I'm a 30-year-old woman, 160cm tall, 55kg, and my preferred fashion style is business casual. What outfits would you recommend?

[1917] This system allows users to easily find the perfect fashion item, and the introduction of an emotion engine can provide a more personalized experience.

[1918] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1919] Step 1:

[1920] The user uses the terminal to launch the application and enters profile information.

[1921] Input: User's age, gender, height, weight, preferred fashion style, favorite color, event information, etc.

[1922] Output: Basic user information data stored on the device.

[1923] Specific operation: The user launches the application, enters the required information into the input form on the screen, and clicks the submit button.

[1924] Step 2:

[1925] The user uses the terminal to register information about items on hand.

[1926] Input: Photos of clothes and accessories owned by the user, manual input information.

[1927] Output: On-hand item information data saved on the device.

[1928] What happens: Use the camera feature within the application to take photos of the items, manually enter the details of each item, and click the save button.

[1929] Step 3:

[1930] The terminal transmits the collected user information and on-hand item information to the server.

[1931] Input: User's basic information data and on-hand item information data stored on the device.

[1932] Output: User information and item information data sent to the server.

[1933] Specific operation: When the user clicks the information transmission button, the terminal encrypts the data and sends it to the server.

[1934] Step 4:

[1935] The server stores the received user information and on-hand item information in a database and performs an initial analysis.

[1936] Input: User information and item information data sent to the server.

[1937] Output: User information and item information data stored in the database, as well as analysis results.

[1938] Specific operation: The server stores the data in a database and uses data analysis software (e.g., Python's Pandas library) to extract user preferences and trends.

[1939] Step 5:

[1940] The server collects all product information on the fashion site.

[1941] Input: Fashion site URL and structure information.

[1942] Output: Product information data stored in a database.

[1943] What it does: The server uses a web scraping tool (such as Beautiful Soup or Selenium) to collect product information such as category, size, color, style, and price from across fashion sites and stores it in a database.

[1944] Step 6:

[1945] The product data collected by the server is trained into a generative AI model.

[1946] Input: Product information data stored in the database.

[1947] Output: An updated generative AI model.

[1948] Specific operation: The server inputs product data into a generative AI model (e.g., a GPT or Transformer-based model) and trains the model.

[1949] Step 7:

[1950] The server generates an AI model based on user information and product data to suggest outfits.

[1951] Input: Analyzed user information and trained product data.

[1952] Output: Coordination suggestions generated by the generative AI model.

[1953] Specific operation: The server inputs a prompt into the generated AI model, specifically, a prompt such as "Please suggest a business casual outfit that would go well with a navy skirt," and the AI ​​generates the optimal outfit.

[1954] Step 8:

[1955] The server filters multiple outfit suggestions and selects the one that best suits the user's preferences and the latest trends.

[1956] Input: Multiple outfit suggestions generated by the generative AI model.

[1957] Output: Optimal outfit suggestions after filtering.

[1958] Specific operation: The generated multiple coordination suggestions are scored using the user's preferences and trend data, and the coordination with the highest score is selected.

[1959] Step 9:

[1960] The user can use the virtual try-on function on the device to visually check the suggested outfits.

[1961] Input: Filtered optimal outfit suggestions.

[1962] Output: Visual feedback of the virtual try-on.

[1963] Specific operation: The user uses the device's camera and display to virtually try on clothes using AR (augmented reality) or VR (virtual reality) technology and check the suggested outfits.

[1964] Step 10:

[1965] The server uses an emotion engine to analyze the user's emotions and optimizes the coordination proposals.

[1966] Input: User's facial expressions, tone of voice, and input behavior data during virtual try-on.

[1967] Output: Optimized outfit suggestions based on emotion recognition results.

[1968] Specific operation: The emotion engine (for example, Face++ or Microsoft Azure's Face API) recognizes the user's emotional state in real time, and the server analyzes that data to reevaluate and revise the coordination suggestions.

[1969] Step 11:

[1970] The user browses the suggested items and chooses to buy, rent, or purchase from the flea market.

[1971] Input: Optimized coordination proposals.

[1972] Output: The purchase option selected by the user.

[1973] Specific operation: The user checks the coordination suggestions on the device screen, refers to detailed information about each item, and then selects whether to purchase, rent, or go to the flea market.

[1974] Step 12:

[1975] The terminal inputs payment information, and the server processes the payment.

[1976] Input: Your payment information (credit card information, PayPal information, etc.) and the purchase option you selected.

[1977] Output: Completed payment transaction.

[1978] Specific operation: The user enters payment information, the server receives it, and processes it through the payment process (e.g., Stripe or PayPal API).

[1979] Step 13:

[1980] The server arranges delivery.

[1981] Input: Completed payment processing and shipping information.

[1982] Output: Shipping process completed.

[1983] Specific operation: The server coordinates with delivery services (e.g., FedEx or DHL) to arrange for delivery of purchased or rented items. In the case of a flea market, it supports communication between sellers and buyers and the delivery process.

[1984] (Application example 2)

[1985] 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."

[1986] Conventional fashion coordination suggestion systems can make suggestions that take into account the user's basic information and the items they own, but it is difficult to optimize coordination suggestions by reflecting the user's emotional state in real time. As a result, it is difficult to make suggestions that truly satisfy the user, and there is a lack of improvement in increasing purchasing motivation and personalization of the experience.

[1987] 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.

[1988] In this invention, the server includes means for collecting basic information about the user, means for collecting information about items the user owns, means for analyzing the collected user information and understanding the user's preferences and trends, means for having a generating AI learn product data, means for the generating AI to suggest outfits based on the user information and product data, means for providing a virtual try-on function, means for analyzing the user's emotional state, means for optimizing the outfit suggestions based on the emotional state, and means for offering the suggested items to the user for purchase, rental, or purchase from a flea market. This makes it possible to analyze the user's emotional state and optimize the outfit suggestions in real time based on the analysis.

[1989] The "means for collecting basic information about a user" refers to a device or system for collecting basic information about a user, such as age, sex, height, weight, preferred fashion style, preferred colors, and event information.

[1990] The "means for collecting information on items owned by the user" refers to a device or system for collecting information on clothes and accessories already owned by the user by taking photographs or manually entering the information.

[1991] "Means for analyzing collected user information and understanding user preferences and trends" refers to a device or system that analyzes collected basic information and information on items owned by a user to understand the user's preferences and current fashion trends.

[1992] A "means for training a generating AI on product data" is a device or system that collects all product information (category, size, color, style, price, etc.) from a fashion site and inputs it into the generating AI, thereby training the generating AI.

[1993] "Means for a generation AI to suggest coordination based on user information and product data" refers to a device or system that enables a generation AI to generate optimal coordination based on analyzed user information and learned product data.

[1994] The "means for providing a virtual try-on function" is a device or system for providing a function that allows a user to virtually try on clothes.

[1995] The "means for analyzing the user's emotional state" is a device or system for recognizing the user's current emotional state based on the user's facial expression, tone of voice, input behavior, and the like.

[1996] The "means for optimizing coordination suggestions based on emotional state" refers to a device or system for reevaluating and optimizing coordination suggestions made by the generation AI based on the user's emotional state obtained by the emotion engine.

[1997] "Means for offering users the option to purchase, rent, or purchase suggested products from a flea market" refers to a device or system that offers users the option to purchase, rent, or purchase suggested products from a flea market, and that handles payment and delivery arrangements.

[1998] To realize this invention, hardware such as smart glasses and a server and software such as Python, OpenCV, and Keras are used.

[1999] The server collects and stores basic information about the user and the items they own. Specifically, the user enters their age, gender, height, weight, preferred fashion style, favorite colors, and event information through the smart glasses interface. They also register their items by taking photos or manually entering them. This information is sent to the server for initial analysis and stored in a database.

[2000] Next, product data is collected and trained by the generative AI. The server collects all product information from the fashion site and trains the generative AI model based on that information. This generative AI model generates optimal outfits using user information and product data as input.

[2001] When the user then uses the virtual try-on function through the smart glasses, the emotion engine recognizes the user's emotional state from their facial expressions and tone of voice. The server reevaluates and optimizes the outfit suggestions based on this emotional state. The resuggested outfits are displayed on the smart glasses in real time, and the user can choose to buy, rent, or purchase from a flea market.

[2002] For example, consider the suggestions displayed when a user tries on a navy skirt and a white blouse through smart glasses. If the emotion engine recognizes the user's sense of security, it can suggest additional related products, such as black heels and silver accessories, based on that emotion.

[2003] Below are some specific examples of input prompts for the generative AI model.

[2004] The user is a 30-year-old woman who prefers a business casual style and likes the color navy. She is attending an event and has a navy skirt and a white blouse. Now that she has tried these items on, she feels comfortable wearing them. Based on this information, please suggest a suitable outfit.

[2005] This invention makes it possible to analyze a user's emotional state in real time and suggest optimal outfits based on that analysis, thereby increasing the user's purchasing motivation and providing a more personalized shopping experience.

[2006] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2007] Step 1:

[2008] The user inputs basic information through the smart glasses interface.

[2009] Input: Age, gender, height, weight, preferred fashion style, preferred color, event information

[2010] How it works: The user interacts with the smart glasses and provides the required information using text input or menu selections.

[2011] Output: Dataset of basic information entered

[2012] Step 2:

[2013] The user registers information about the items they have on hand.

[2014] Input: Information about the items you own (e.g., navy skirt, white blouse)

[2015] How it works: The user takes a picture of an item with the smart glasses' camera and manually enters the item's details (color, type, etc.).

[2016] Output: A dataset of registered items on hand

[2017] Step 3:

[2018] The server stores user information and item information in a database.

[2019] Input: User basic information dataset, on-hand item information dataset

[2020] How it works: The device sends the collected data to a server, which stores the information in a database.

[2021] Output: User information and items stored in the database

[2022] Step 4:

[2023] The server collects all product information on the fashion site.

[2024] Input: Product information (category, size, color, style, price, etc.) obtained from fashion site APIs or web pages

[2025] How it works: The server collects information using automated scripts and API calls.

[2026] Output: A dataset of collected product information

[2027] Step 5:

[2028] The server trains the generative AI model on product data.

[2029] Input: Product Information Dataset

[2030] How it works: The server provides product data as input to a generative AI model, updating the model to learn the latest trends.

[2031] Output: An updated generative AI model

[2032] Step 6:

[2033] The user uses the virtual try-on feature.

[2034] Input: Virtual try-on image data of the proposed item

[2035] How it works: The user tries on the suggested outfit through the smart glasses and visually checks it.

[2036] Output: facial expressions and movement data of the user while trying on the clothes

[2037] Step 7:

[2038] The server analyzes the user's emotional state.

[2039] Input: facial expressions and movement data of the user while trying on clothes

[2040] How it works: Facial images and audio data captured by the smart glasses' camera are sent to the emotion engine to recognize the user's emotional state.

[2041] Output: User's emotional state data (e.g., joy, relief, dissatisfaction, etc.)

[2042] Step 8:

[2043] The server optimizes coordination suggestions based on the emotional state.

[2044] Input: User's emotional state data, initial outfit suggestions from a generative AI model

[2045] How it works: The server re-evaluates the outfit based on the emotion data and recreates the suggestions that best fit the user's emotions using a generative AI model.

[2046] Output: Optimized outfit suggestion data

[2047] Step 9:

[2048] It offers users suggested products to buy, rent, or purchase from a flea market.

[2049] Input: Optimized outfit suggestion data

[2050] How it works: Presents users with options to buy, rent, or purchase from a flea market through the smart glasses interface, and then processes payment and shipping for selected items.

[2051] Output: User purchases, rentals, and completed purchases from the flea market

[2052] Through this series of processing steps, users receive suggested fashion coordinations that reflect their emotional state in real time, and can choose to purchase, rent, or buy from a flea market.Furthermore, as a specific example, the following prompt sentence is provided for the generative AI model.

[2053] The user is a 30-year-old woman who prefers a business casual style and likes the color navy. She is attending an event and has a navy skirt and a white blouse. Now that she has tried these items on, she feels comfortable wearing them. Based on this information, please suggest a suitable outfit.

[2054] 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.

[2055] 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.

[2056] 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.

[2057] 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.

[2058] 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.

[2059] 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.

[2060] 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).

[2061] 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.

[2062] 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."

[2063] 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.

[2064] 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 ...

Claims

1. a means for collecting basic information about the user; A means for collecting information on items held by a user; A means of analyzing collected user information to understand user preferences and trends; A means to train product data generation AI, A means for AI to suggest outfits based on user information and product data, a means for providing a virtual try-on feature; A system including a means for providing users with suggested items to purchase, rent, or purchase from a flea market.

2. The system according to claim 1 , further comprising means for storing the collected user basic information and on-hand item information in a database.

3. The system according to claim 1, further comprising means for filtering the outfits suggested by the generating AI and selecting those that best suit the user's preferences and the latest trends.

Images