System

Abstract

A system is provided.SOLUTION: The system includes a means for receiving an image of clothes photographed by a user, a means for extracting feature data such as a kind, a color, and a pattern of clothes from the received image, a means for storing the extracted feature data in a database for each user, a means for receiving rental desired conditions designated by the user, a means for generating optimum coordination based on the stored feature data of clothes of the user and feature data of rental clothes, a means for presenting the generated coordination to the user, and a means for providing rental clothes based on selection of 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] Today's busy consumers often struggle with how to combine their existing clothes with new clothes they will purchase or rent. Furthermore, they have limited time and energy to try out multiple outfit combinations. Therefore, there is a demand for a system that efficiently coordinates outfits that combine existing clothes with newly rented outfits. Conventional systems have not fully realized such automated outfit suggestions, and technology to improve user convenience is needed. [Means for solving the problem]

[0005] The present invention provides a means for receiving images of clothing photographed by a user and extracting feature data, such as the type, color, and pattern of the clothing, from the received images. The extracted feature data is stored in a database for each user, and includes a means for receiving rental preferences specified by the user and generating an optimal outfit based on the stored feature data of the user's clothing and the feature data of rental clothing. The system also includes a means for presenting the generated outfit to the user and providing rental clothing based on the user's selection. The system also includes a means for extracting fabric texture and style information from the received images and a means for using an AI algorithm to evaluate the compatibility of the user's existing clothing with potential rental clothing. In this way, the present invention can provide outfits that efficiently combine the user's existing clothing with newly rented clothing, greatly improving user convenience.

[0006] A "user" refers to an individual who uses the system and interacts with it by uploading images of clothes, selecting outfits, and so on.

[0007] An "image" is a digital representation of visual information taken with a device such as a smartphone or PC, or uploaded from an existing file.

[0008] "Receiving" is the process by which the system server obtains data sent by the user over the network.

[0009] "Clothes" refers to clothing in general and includes a variety of items such as shirts, pants, dresses, and jackets.

[0010] "Type" refers to the basic category of clothing, examples being shirts, pants, dresses, etc.

[0011] "Color" refers to the visual characteristics of clothing, such as hue, brightness, and saturation.

[0012] "Pattern" refers to the repeating design or texture of clothing, and includes solid colors, stripes, checks, etc.

[0013] "Feature data" is information about clothing extracted from an image, and includes multiple attribute data such as type, color, pattern, texture, and style.

[0014] A "database" is an information system for efficiently storing, searching, and managing data managed for each user.

[0015] "Desired rental conditions" is setting information that indicates requirements such as the category, situation, and season of the clothes that the user wants to rent.

[0016] The "optimal coordination" is a suggestion that, when combining clothes that the user owns with clothes that can be rented, best matches the user's desires and is visually appropriate.

[0017] An "AI algorithm" is an automated processing method that uses artificial intelligence technology to analyze data and evaluate and select combinations of clothing you own and rental clothing.

[0018] "Presentation" is the process of visually displaying the coordinates generated by the system to the user.

[0019] "Providing" refers to an operation that includes a series of processes leading up to actually delivering the rental clothing selected by the user to the user. [Brief explanation of the drawings]

[0020] [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

[0021] 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.

[0022] First, the terms used in the following description will be explained.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 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.

[0031] 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).

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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."

[0041] The system of the present invention provides coordinated outfits that efficiently combine the user's existing clothes with newly rented clothes. This system is composed of the following elements: a means for the user to upload images of the clothes, a means for performing image analysis on the server, a means for storing and managing the extracted feature data, a means for receiving the user's desired rental conditions and generating an optimal outfit, and a means for presenting the generated outfit to the user and providing the rental clothes.

[0042] User procedure flow

[0043] First, users use their smartphone or PC to take a photo of their clothes and upload it to the system. Once the upload is complete, users can enter the desired rental clothing criteria, such as "casual summer clothes."

[0044] Server Processing

[0045] Based on this, the server performs the following processing.

[0046] 1. Receiving and saving images

[0047] The server receives the images of the clothes uploaded by the user and temporarily stores them in a database.

[0048] 2. Image Analysis

[0049] The server runs an AI algorithm for image analysis to extract feature data such as the type of clothing (e.g., shirt, pants), color (e.g., white, black, red), and pattern (e.g., solid, striped), as well as fabric texture and style information (e.g., casual, formal).

[0050] 3. Saving feature data

[0051] The extracted feature data is associated with the user ID and stored in a database, creating a database of clothing for each user.

[0052] 4. Receiving and analyzing rental requirements

[0053] The server receives rental requirements specified by the user, including clothing category (e.g., shirt, dress), occasion (e.g., casual, formal), and season (e.g., summer, winter).

[0054] 5. Generating optimal coordination

[0055] The server compares the data on the customer's clothing with the data on rental clothing and uses AI to generate optimal outfit suggestions, taking into account criteria such as color compatibility, style matching, and seasonality.

[0056] 6. Coordination Presentation

[0057] The server presents the generated coordinates to the user and allows the user to select one. Notification methods include push notifications and emails.

[0058] Specific examples

[0059] For example, suppose a user uploads an image of a white T-shirt and requests a casual rental item suitable for summer wear. The server stores the characteristics of the white T-shirt and suggests the following outfits along with the desired rental conditions:

[0060] White T-shirt (own) + Jeans shorts (rental)

[0061] White T-shirt (own) + Cargo shorts (rental)

[0062] The user checks the suggested outfits, selects their favorite combination, and confirms the rental. The server receives this order and proceeds with the delivery of the rental clothes.

[0063] In this way, the system of the present invention can efficiently combine the user's existing clothes with newly rented clothes to provide optimal coordination, thereby expanding the user's fashion choices and greatly improving convenience.

[0064] The processing flow will be explained below.

[0065] Step 1:

[0066] Users use their smartphone or PC to take pictures of their own clothes and then upload the images using the "Register Owned Clothes" function within the application.

[0067] Step 2:

[0068] The server receives the uploaded images and temporarily stores them in a database.

[0069] Step 3:

[0070] The server runs an AI algorithm for image analysis to extract characteristic data such as the type of clothing (e.g., shirt, pants), color (e.g., white, black, red), and pattern (e.g., solid, striped), as well as fabric texture and style information (e.g., casual, formal).

[0071] Step 4:

[0072] The server associates the extracted feature data with the user ID and stores it in a database, thereby creating a clothing database for each user.

[0073] Step 5:

[0074] The user enters the rental requirements (e.g., casual summer clothing) into the application.

[0075] Step 6:

[0076] The server receives rental requirements from the user, including clothing category (e.g., shirt, dress), occasion (e.g., casual, formal), and season (e.g., summer, winter).

[0077] Step 7:

[0078] The server retrieves the user's clothing data from the database and runs an AI algorithm to compare it with the rental clothing database, thereby evaluating combinations of the user's clothing and potential rental items.

[0079] Step 8:

[0080] The server uses AI algorithms to generate optimal outfit suggestions, which include evaluations of color compatibility, style matching, and seasonal suitability.

[0081] Step 9:

[0082] The server generates a plurality of coordinate candidates and presents them to the user.

[0083] Step 10:

[0084] Using the terminal application, the user visually checks the presented coordination candidates and selects the combination they like.

[0085] Step 11:

[0086] Based on the outfit the user selects, they "add" the clothes to rent to their cart and finally confirm the rental order.

[0087] Step 12:

[0088] The server receives the user's order information and starts the delivery procedure for the rental clothes.

[0089] By using the above steps, the system of the present invention efficiently combines the clothes the user owns with the clothes to be rented, providing optimal coordination. Furthermore, by allowing the user to easily select clothes and complete the rental procedure, convenience is greatly improved.

[0090] Example 1

[0091] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0092] Conventional fashion coordination systems have made it difficult for users to effectively combine their existing clothes with newly rented clothes. Furthermore, they lacked a mechanism for automatically suggesting optimal outfits based on the user's existing clothes and desired rental conditions. This not only resulted in low convenience for users, but also made it difficult to achieve a highly satisfying outfit. Therefore, there is a demand for a system that allows users to enjoy coordinating outfits in a more efficient and satisfying way.

[0093] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0094] In this invention, the server

[0095] means for receiving an image of clothing taken by a user;

[0096] A means for extracting feature data such as type, color, and pattern of clothing from the received image;

[0097] A means for storing the extracted feature data in a database for each user;

[0098] means for receiving desired rental conditions specified by a user;

[0099] A means for generating an optimal outfit based on the stored feature data of the user's clothes and the feature data of the rental clothes;

[0100] means for presenting the generated coordinates to a user;

[0101] A means for providing rental clothing based on a user's selection;

[0102] means for notifying a user of the generated coordinates by a notification means;

[0103] This allows users to efficiently combine their own clothes with rental clothes to create the perfect outfit.

[0104] "User" refers to an individual who uses this system to coordinate their own clothing.

[0105] "Server" refers to a device that receives images uploaded by users, analyzes the images, stores the data, and generates and provides coordinates.

[0106] "Image" refers to visual data of clothing photographed by a user and stored in digital format.

[0107] "Feature data" refers to the type, color, pattern, and fabric texture and style information of clothing extracted from the received image.

[0108] "Database" refers to an information storage system for saving and managing clothing characteristic data for each user.

[0109] "Rental Desired Conditions" refers to the conditions such as the category, situation, and season of the clothing the user desires to rent.

[0110] "Coordination" refers to a fashion proposal that combines the user's own clothes with rental clothes.

[0111] "Notification means" refers to a method for notifying the user of the created coordination, and includes push notification and email.

[0112] This invention is a system that provides coordinated outfits that efficiently combine a user's existing clothes with newly rented clothes. This system includes the following elements: a means for the user to upload images of the clothes, a means for performing image analysis on a server, a means for storing and managing extracted feature data, a means for receiving the user's desired rental conditions and generating an optimal outfit, and a means for presenting the generated outfit to the user and providing the rental clothes.

[0113] First, the user uses their smartphone or PC (terminal) to take a picture of the clothes they own and upload it to the system. Specifically, the user takes a picture of the clothes using a camera app and uploads the image to the system through a dedicated web or mobile application. At that time, the user enters the conditions for the clothes they want to rent (for example, "casual summer clothes"). This process is carried out via an HTTP request.

[0114] The server receives the uploaded images and temporarily stores them in a database. The database used can be a relational database such as MySQL (registered trademark) or PostgreSQL. The received image data is stored in a temporary storage folder, and image metadata (upload date and time, user ID, etc.) is also recorded in the database.

[0115] The server then runs an AI algorithm for image analysis (such as TENSORFLOW® or PyTorch) to extract feature data such as clothing type (e.g., shirt, pants), color (e.g., white, black), pattern (e.g., solid, striped), fabric texture, and style information (e.g., casual, formal). This process provides specific information about the user's clothing.

[0116] The extracted feature data is associated with the user ID and stored in a database. This creates a clothing database for each user. Next, the server receives the rental requirements specified by the user (e.g. clothing category, occasion, season). The desired requirements are also received via an HTTP request.

[0117] The server uses this data to generate optimal outfit suggestions using an AI algorithm. Evaluation criteria include color compatibility, style matching, and seasonality. The generated outfit suggestions are displayed on the user's interface. Notifications are sent via push notifications and email.

[0118] As a concrete example, consider the case where a user uploads an image of a white T-shirt and requests casual rental clothing suitable for summer wear. For example, the server can save the characteristic data of the white T-shirt and compare it with the rental requirements to suggest the following outfits:

[0119] White T-shirt (own) + Jeans shorts (rental)

[0120] White T-shirt (own) + Cargo shorts (rental)

[0121] The user checks the suggested outfits and selects the combination they want. The server then receives the order and begins the process of shipping the rental clothes.

[0122] As described above, the system of the present invention can efficiently combine the user's existing clothes with newly rented clothes to provide optimal coordination, thereby expanding the range of fashion choices available to the user and greatly improving convenience.

[0123] Example prompt sentence:

[0124] "I'd like to upload an image of a white T-shirt to the system and request casual rental clothing for summer wear. I'd like you to suggest items that coordinate well with the shirts, pants, and other items I already have."

[0125] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0126] Step 1:

[0127] Upload an image and enter conditions

[0128] Users use their smartphones or PCs to take pictures of their clothes and upload them to the system. After this is complete, users enter the conditions for the clothes they want to rent (e.g., "casual summer clothes").

[0129] Input: Clothing image data, desired rental conditions

[0130] Output: Upload image data to the system, send rental requirements

[0131] Specific behavior:

[0132] Use the camera app to take a picture of the outfit.

[0133] Open your web browser or mobile app and log in.

[0134] Click the image upload button, select the image you have taken, and upload it.

[0135] Enter your desired rental conditions (e.g., "casual summer clothing") in the text box and submit.

[0136] Step 2:

[0137] Receiving and saving images

[0138] The server receives the images of the clothes uploaded by the user and temporarily stores them in a database.

[0139] Input: Image data sent by the user

[0140] Output: Image files saved in a temporary folder, metadata recorded in a database

[0141] Specific behavior:

[0142] The server receives the image data via an HTTP request.

[0143] The received image is saved in a temporary folder.

[0144] Record image metadata (upload date and time, user ID, etc.) in a database.

[0145] Step 3:

[0146] Feature extraction through image analysis

[0147] The server runs AI algorithms for image analysis to extract information about the type of clothing, color, pattern, and fabric texture and style.

[0148] Input: Saved image data

[0149] Output: Extracted feature data (type, color, pattern, texture, style information)

[0150] Specific behavior:

[0151] Calls an image analysis engine (such as TensorFlow) to process the uploaded image.

[0152] Analyze the type (shirt, pants, etc.), color (white, black, etc.), and pattern (solid, striped).

[0153] AI algorithm determines style (casual, formal).

[0154] Step 4:

[0155] Feature data storage

[0156] The server associates the extracted feature data with the user ID and stores it in a database.

[0157] Input: extracted feature data, user ID

[0158] Output: Feature data stored in a per-user clothing database

[0159] Specific behavior:

[0160] The extracted feature data is inserted into a database.

[0161] Link feature data with user ID.

[0162] Step 5:

[0163] Receiving rental requirements

[0164] The server receives the rental requirements entered by the user, including information such as clothing category, occasion, and season.

[0165] Input: Rental requirements submitted by the user

[0166] Output: The received rental requirements are stored on the server.

[0167] Specific behavior:

[0168] Receives form data from the user via an HTTP request.

[0169] The received data is analyzed, the user's desired conditions are identified, and the results are stored in a database.

[0170] Step 6:

[0171] Optimal coordination generation

[0172] The server compares data on existing clothing with rental clothing data and uses AI to generate optimal outfit suggestions.

[0173] Input: User's clothing characteristics, rental requirements

[0174] Output: A list of optimal outfit candidates

[0175] Specific behavior:

[0176] The user's clothing data is obtained from the database.

[0177] The clothes are compared with a database of rental clothing and evaluated using an AI algorithm.

[0178] Several coordination candidates are generated and their evaluation scores are calculated.

[0179] Step 7:

[0180] Coordination presentation and selection for users

[0181] The server presents the generated coordinates to the user, allowing the user to make a selection.

[0182] Input: Best coordinate candidates

[0183] Output: Coordination candidates presented to the user, and the user's choice

[0184] Specific behavior:

[0185] Coordination candidates are displayed on the user interface.

[0186] Notify users via push notification or email.

[0187] The user clicks the select button to confirm the coordinates.

[0188] Step 8:

[0189] Rental clothing shipping procedures

[0190] The server then processes the delivery of the rental clothing coordinated by the user, and if necessary, shares the shipping information with the delivery company.

[0191] Input: Rental clothing selected by the user

[0192] Output: Rental clothing shipping instructions, delivery notification to user

[0193] Specific behavior:

[0194] Check the availability of the selected rental clothing.

[0195] Get the user's shipping information and generate a shipping label.

[0196] Information is shared with departments and services responsible for delivery procedures.

[0197] (Application example 1)

[0198] 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."

[0199] Conventional coordination systems have the problem that it is difficult for users to efficiently combine their existing clothes with the clothes available in stores when they visit a physical store. Furthermore, they do not provide sufficient support for users to select clothes in the store using a smartphone or smart glasses, and lack functionality to improve the shopping experience in physical stores.

[0200] 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.

[0201] In this invention, the server includes means for receiving images of clothes photographed by a user, means for extracting characteristic data such as the type, color, and pattern of the clothes from the received images, means for storing the extracted characteristic data in a database for each user, means for receiving desired rental conditions specified by the user, means for generating an optimal outfit based on the stored characteristic data of the user's clothes and the characteristic data of rental clothes, means for using a smartphone, smart glasses, or interactive kiosk to present the optimal outfit to the user in the store, and means for providing rental or sales clothes based on the user's selection. This allows users to easily find an optimal outfit that efficiently combines clothes they own with clothes in the store in a physical store.

[0202] A "user" is an individual who uses the system to coordinate and rent clothes.

[0203] "Photographing" refers to the act of capturing an image of clothing using a device such as a smartphone or smart glasses.

[0204] "Clothing images" are photographic data of clothes taken by the user.

[0205] The "receiving means" is a function that allows the server to receive image data of clothes sent by the user.

[0206] "Clothing type" is a clothing category such as shirts, pants, dresses, etc.

[0207] "Color" refers to the specific color information that clothing possesses.

[0208] A "pattern" is a design or figure found in clothing designs.

[0209] "Feature data" is specific information such as the type, color, and pattern of clothing extracted through image analysis.

[0210] The "database" is a digital information management system for storing extracted feature data for each user.

[0211] "Rental requirements" are requirements such as a specific clothing category or style specified by the user.

[0212] "Rental clothing" refers to clothing that is available for rental to users.

[0213] The "optimal coordination" refers to the combination of the user's own clothes with rental or sales clothes that best harmonizes in terms of color, style, etc.

[0214] "In-store" refers to the interior space of the actual store that the user visits.

[0215] A "smartphone" is a mobile phone with internet connectivity and the ability to run advanced applications.

[0216] "Smart glasses" are wearable devices that have the shape of regular glasses but can display information and perform other functions.

[0217] An "interactive kiosk" is a device that allows users to obtain information and perform operations using an operable display device such as a touch panel.

[0218] "Sales clothing" refers to clothing sold to users in a store.

[0219] The following describes the system configuration and operation procedure as an embodiment of the present invention. The system includes a server that receives and analyzes images of clothes taken by a user, a smartphone, smart glasses, and an interactive kiosk that present optimal outfits to the user.

[0220] System Configuration

[0221] 1. Server:

[0222] Image receiving function: Receives images of clothes uploaded by users.

[0223] Image analysis function: Uses libraries such as TensorFlow and OpenCV to extract feature data such as clothing type, color, and pattern from images.

[0224] Database management: The extracted feature data is stored in a database for each user.

[0225] Recommendation engine: Generates optimal coordination based on the user's desired rental conditions.

[0226] 2. User Device:

[0227] Smartphone: Used to take and upload images and check outfits.

[0228] Smart glasses: Used by users to check the best outfits in real time while walking around the store.

[0229] Interactive Kiosk: Enables in-store operation for suggesting and selecting outfits.

[0230] Program processing

[0231] 1. Image reception:

[0232] The server receives the images of the clothes sent from the user's device and temporarily stores them in a database, using a high-speed Internet connection to send and receive the images.

[0233] 2. Image Analysis:

[0234] The received images are analyzed on the server using TensorFlow and OpenCV to extract information such as the type of clothing (e.g., shirt, pants), color (e.g., white, black, red), pattern (e.g., solid, striped), texture, and style information.

[0235] 3. Save feature data:

[0236] The extracted feature data is associated with the user ID and stored in a database, which creates a clothing database for each user and is used to suggest future outfits.

[0237] 4. Coordinate generation:

[0238] After the user enters their desired rental requirements, the server compares the stored data of clothing on hand with the data of clothing candidates for rental and generates the optimal outfit using an AI algorithm (e.g., cosine similarity calculation).

[0239] 5. Proposal and Selection:

[0240] The optimal outfits are presented to the user via a smartphone, smart glasses, or interactive kiosk, and the process of providing rental or sales clothes based on the outfits selected by the user proceeds.

[0241] Specific examples

[0242] User behavior example:

[0243] A user takes a photo of a white T-shirt with their smartphone and uploads it to the system. They then enter their desired casual summer clothing rental requirements. Based on this information, the server recommends jeans shorts that go perfectly with the white T-shirt. The user can instantly view the jeans shorts while walking around the store through the smart glasses.

[0244] Example prompt sentence:

[0245] prompt:

[0246] User ID: example_user_01

[0247] Clothing characteristics: White T-shirt, casual, summer

[0248] In-store clothing data: Jeans shorts, casual, summer

[0249] How to use generative AI models:

[0250] 1. Input the feature data of the user's white T-shirt into the AI.

[0251] 2. Compare with the characteristic data of jean shorts in stock at the store.

[0252] 3. Optimal coordination is suggested using cosine similarity.

[0253] Example response:

[0254] Select a pair of jean shorts that match the color of the user's T-shirt.

[0255] Selection results:

[0256] White T-shirt + Jean shorts

[0257] In this way, a system is provided that enables a user to easily find an optimal outfit that efficiently combines clothes that the user owns with clothes in the store in a real store.

[0258] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0259] Step 1:

[0260] The user uploads a photo of the clothes they have taken. The information entered here is the user ID and the image file of the clothes. The uploaded image data is sent from the device to the server.

[0261] Step 2:

[0262] The image received by the server is temporarily stored in a database. The output of this process is the completion of saving the uploaded image data. Specifically, the image received by the server is saved in a specified directory and linked to the corresponding user ID.

[0263] Step 3:

[0264] The server retrieves the stored image data and performs image analysis. The input is the image data stored in the database. TensorFlow and OpenCV are used for the analysis to extract feature data such as the type of clothing, color, pattern, fabric texture, and style information. The output of this process is the extracted feature data. Specifically, an AI model is executed to extract clothing features from the image.

[0265] Step 4:

[0266] The extracted feature data is saved in a database for each user. The input is the feature data extracted in step 3 and the user ID. The output of this process is a database with updated feature data for each user. Specifically, the feature data is associated with the user ID and inserted into the database.

[0267] Step 5:

[0268] The user inputs the desired rental conditions, such as clothing category, occasion, season, etc. The desired rental conditions are sent from the terminal to the server.

[0269] Step 6:

[0270] The server compares the stored data of clothing items on hand with the data of clothing items that can be rented based on the desired rental conditions. The inputs are the desired rental conditions, the user's characteristic data, and the data of the clothing items that can be rented. An optimal outfit is generated using an AI algorithm (e.g., cosine similarity calculation). The output of this process is the optimal outfit candidate. Specifically, an AI model is executed to find the optimal combination.

[0271] Step 7:

[0272] The optimal outfit is presented to the user. The input is the outfit candidates generated in step 6. The output is outfit information displayed on the user's smartphone, smart glasses, or interactive kiosk. Specifically, the outfit information is displayed via push notification or within the application.

[0273] Step 8:

[0274] The user selects a suggested outfit. The input information is the outfit selected by the user. The selection information is sent from the terminal to the server.

[0275] Step 9:

[0276] Based on the selection, the system carries out procedures to provide the clothes for rental or sale. The input is the outfit and rental conditions selected by the user. The output of this process is the delivery of the rental clothes or the completion of the sales procedure. Specifically, delivery arrangements and purchase procedures are automatically carried out by the server.

[0277] 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.

[0278] The system of the present invention provides coordinated outfits that efficiently combine the user's existing clothes with newly rented clothes, and by combining it with an emotion engine that recognizes the user's emotions, it realizes more personalized suggestions. The details of the system are described below.

[0279] User procedure flow

[0280] Users take pictures of their clothes using their smartphones or PCs and upload them using the app's "Register Your Own Clothes" function. Once the upload is complete, users can enter the desired rental clothing specifications (e.g., casual summer clothes).

[0281] Server Processing

[0282] Based on this, the server performs the following processing.

[0283] Receiving and saving images

[0284] The server receives the images of the clothes uploaded by the user and temporarily stores them in a database.

[0285] Image analysis

[0286] The server runs an AI algorithm for image analysis to extract characteristic data such as the type of clothing (e.g., shirt, pants), color (e.g., white, black, red), and pattern (e.g., solid, striped), as well as the texture of the fabric and style information (e.g., casual, formal).

[0287] Feature data storage

[0288] The server associates the extracted feature data with the user ID and stores it in a database, thereby creating a clothing database for each user.

[0289] Receiving and analyzing rental requirements

[0290] Once customers input their desired rental requirements, the server receives them and runs an AI algorithm to match their existing clothing data with the rental clothing data, using criteria such as color compatibility, style matching, and seasonal suitability.

[0291] Coordinate generation and presentation

[0292] The server generates optimal outfit suggestions and presents multiple options to the user. The outfit suggestions are displayed in the device's application via push notification or email.

[0293] Incorporating an emotion engine

[0294] Furthermore, the system incorporates an emotion engine to perform the following processes:

[0295] Emotion Recognition and Analysis

[0296] The device captures the user's facial expressions and voice in response to the presented outfit, and the emotion engine analyzes them to collect the user's emotional data. The emotion engine then sends the analysis results to the server.

[0297] Saving and reflecting emotional data

[0298] The server stores the emotion data in a database and reflects this data the next time a coordinated outfit is generated, suggesting a more appropriate outfit based on the user's preferences and feedback.

[0299] Specific examples

[0300] For example, suppose a user uploads an image of a white T-shirt and requests a casual rental item suitable for summer wear. In this case, the server saves the characteristics of the white T-shirt and suggests the following outfits along with the desired rental conditions:

[0301] White T-shirt (own) + Jeans shorts (rental)

[0302] White T-shirt (own) + Cargo shorts (rental)

[0303] The user reviews the suggested outfit, and the emotion engine analyzes the user's preferences from their facial expressions and tone of voice. For example, if the user smiles or sounds satisfied, this is saved as positive feedback. The next time the system suggests an outfit, this positive feedback will be reflected, making the suggestion more in line with the user's preferences.

[0304] In this way, the system of the present invention can efficiently combine the user's existing clothes with new clothes to rent, and further make suggestions that take the user's emotions into consideration, thereby expanding the range of fashion choices available to the user and greatly improving convenience.

[0305] The processing flow will be explained below.

[0306] Step 1:

[0307] Users use their smartphone or PC to take pictures of their clothes and then upload the images using the "Register clothes you own" function within the application.

[0308] Step 2:

[0309] The server receives the uploaded images and temporarily stores them in a database.

[0310] Step 3:

[0311] The server runs an AI algorithm for image analysis to extract characteristic data such as the type of clothing (shirt, pants, etc.), color (white, black, red, etc.), and pattern (solid, striped, etc.), as well as the texture of the fabric and style information (casual, formal, etc.).

[0312] Step 4:

[0313] The server associates the extracted feature data with the user ID and stores it in a database, thereby creating a clothing database for each user.

[0314] Step 5:

[0315] The user enters the rental requirements (e.g., casual summer clothing) into the application.

[0316] Step 6:

[0317] The server receives rental requirements from the user, including clothing category (e.g., shirt, dress), occasion (e.g., casual, formal), and season (e.g., summer, winter).

[0318] Step 7:

[0319] The server retrieves the user's clothing data from the database and runs an AI algorithm to compare it with the rental clothing database, thereby evaluating combinations of the user's clothing and potential rental items.

[0320] Step 8:

[0321] The server uses AI algorithms to generate optimal outfit suggestions, which include evaluations of color compatibility, style matching, and seasonal suitability.

[0322] Step 9:

[0323] The server generates a plurality of coordinate candidates and presents them to the user.

[0324] Step 10:

[0325] Using the terminal application, the user visually checks the presented coordination candidates and selects the combination they like.

[0326] Step 11:

[0327] The device captures the user's facial expressions and voice, and the emotion engine analyzes the data to collect the user's emotional data.

[0328] Step 12:

[0329] The server receives the analysis results from the emotion engine and stores them in a database.

[0330] Step 13:

[0331] Based on the outfit the user selects, they "add" the clothes to rent to their cart and finally confirm the rental order.

[0332] Step 14:

[0333] The server receives the user's order information and starts the delivery procedure for the rental clothes.

[0334] Step 15:

[0335] From the next time onwards, the server will adjust the evaluation criteria of the AI ​​algorithm based on the collected emotional data and suggest outfits that better match the user's preferences. For example, if positive feedback is received from a smile or a satisfied voice, similar outfits will be suggested based on that information.

[0336] Through the above steps, the system of the present invention can efficiently combine the user's existing clothes with new rental clothes, and further make suggestions that take the user's emotions into consideration, thereby expanding the range of fashion choices available to the user and greatly improving convenience.

[0337] Example 2

[0338] 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."

[0339] In conventional fashion coordination systems, it is difficult for users to efficiently combine clothes they own with newly rented clothes, and they also have the problem of not being able to provide suggestions that fully take into account the user's preferences and emotions. The present invention aims to solve these problems and provide appropriate fashion coordination that is personalized for the user.

[0340] 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.

[0341] In this invention, the server includes means for receiving images of clothes photographed by a user, means for extracting characteristic data such as the type, color, and pattern of the clothes from the received images, means for saving the extracted characteristic data in a database for each user, means for receiving desired rental conditions specified by the user, means for generating an optimal outfit based on the saved characteristic data of the user's clothes and the characteristic data of rental clothes, means for presenting the generated outfit to the user, means for providing rental clothes based on the user's selection, means for capturing the user's facial expressions and voice and analyzing emotional data, and means for saving the analyzed emotional data in a database and reflecting it when generating the next outfit. This makes it possible to efficiently combine the user's own clothes with new rental clothes and to make more personalized suggestions that reflect the user's emotions and preferences.

[0342] A "user" is someone who wishes to coordinate or rent clothes using this system.

[0343] "Means for receiving images of clothes in hand" refers to the function that allows users to upload images of clothes taken with their smartphone or PC to the server.

[0344] "Feature data" refers to data about clothing characteristics extracted through image analysis, such as type of clothing, color, pattern, fabric texture, and style information.

[0345] A "database" is an information accumulation system for storing extracted feature data, user information, emotional data, etc.

[0346] "Desired rental conditions" refers to information that allows a user to specify the conditions for the clothes they wish to rent (for example, casual summer clothes).

[0347] "Coordination" means suggesting styling by combining clothes you already own with rented clothes.

[0348] An "artificial intelligence model" is an algorithm or machine learning model used to evaluate the compatibility of clothing.

[0349] "Emotion data" refers to data related to emotions obtained by analyzing the user's facial expressions and voice.

[0350] "Means for analyzing" refers to technology for processing a user's emotional data in real time and determining the type and degree of emotion.

[0351] The "server" is a central computer system that stores and processes user data, image analysis, coordinate generation, and emotion data.

[0352] A "terminal" refers to a device such as a smartphone or PC operated by a user.

[0353] "Capture" refers to capturing the user's facial expressions and voice through a camera or microphone.

[0354] "Means for reflecting the next coordinated outfit when generating the next coordinated outfit" refers to a function for taking the user's preferences and emotions into consideration when proposing the next coordinated outfit based on the saved emotion data.

[0355] The system of the present invention provides coordinated outfits that efficiently combine the user's existing clothes with newly rented clothes, and by combining it with an emotion engine that recognizes the user's emotions, it realizes more personalized suggestions. Detailed embodiments of this system are described below.

[0356] System configuration

[0357] This system consists of the following main components:

[0358] 1. Server

[0359] 2. Terminal

[0360] 3. Database

[0361] 4. Emotion Engine

[0362] Hardware and software used

[0363] The server plays a central role in image analysis, data storage, and coordinate generation. Specifically, it uses the following software and services:

[0364] Image analysis uses Google (registered trademark) Cloud Vision API and Amazon Rekognition.

[0365] Amazon RDS and MySQL are used as databases.

[0366] Coordination generation uses machine learning libraries such as TensorFlow and PyTorch.

[0367] The terminals are devices operated by users, such as smartphones and PCs, that take and upload images and capture emotions.

[0368] The emotion engine is a component that captures and analyzes the user's facial expressions and voice. Specifically, it uses Microsoft® Azure® Face API and IBM Watson® Tone Analyzer.

[0369] System operation procedures

[0370] The system operation procedure will be explained below with specific examples.

[0371] 1. User uploads clothing images

[0372] Users can take pictures of their clothes using their smartphones or PCs and upload them using the application's "Register clothes" function by selecting the image file and clicking the upload button.

[0373] 2. Receiving and saving images

[0374] The server receives image files uploaded by users and temporarily stores the image data in cloud storage such as Amazon S3.

[0375] 3. Image Analysis

[0376] The server uses the Google Cloud Vision API to analyze the images and extract information about the type, color, pattern, texture, and style of the clothing, thereby obtaining feature data such as the type of shirt or pants, color (white or black), and pattern (solid or striped).

[0377] 4. Saving feature data

[0378] The server associates the extracted feature data with the user ID and stores it in Amazon RDS. The stored data includes the clothing ID, type, color, pattern, texture, style, etc.

[0379] 5. Enter your desired rental conditions

[0380] The user enters the desired rental clothing requirements (e.g., casual summer clothing) into a form within the application and submits it.

[0381] 6. Analysis of desired rental conditions

[0382] The server receives the user's desired rental conditions via an HTTP POST request, compares them with the user's clothing data, and selects the most suitable rental clothing.

[0383] 7. Coordinate Generation

[0384] The server generates combination candidates for clothes that you own and rent, and creates the most suitable outfit that meets your requirements.

[0385] 8. Coordination Presentation

[0386] The server presents the generated outfit suggestions to the user via push notification or email, and the user can check the outfits within the application.

[0387] 9. Capturing Emotions

[0388] The device captures the user's facial expressions and voice using a camera and microphone and analyzes them in real time. For example, if the user smiles or sounds satisfied, this is analyzed by the emotion engine as positive feedback and the results are sent to the server.

[0389] 10. Saving and Reflecting Emotional Data

[0390] The server stores the emotion data in a database and reflects it in the next outfit suggestions, thereby learning the user's preferences and realizing more personalized outfit suggestions.

[0391] Examples of specific examples and prompts

[0392] For example, if a user uploads an image of a white T-shirt and requests "casual rental clothing suitable for summer," the server will save the characteristics of the white T-shirt, compare them with the rental requirements, and suggest the following outfits:

[0393] White T-shirt (own) + Jeans shorts (rental)

[0394] White T-shirt (own) + Cargo shorts (rental)

[0395] Based on this suggestion, the user checks the suggested outfit, and the emotion engine analyzes their preferences from their facial expressions and tone of voice. If they smile or sound satisfied, this is saved as positive feedback and will be reflected in the next suggestion. An example of a prompt is, "Please suggest some casual summer clothes to wear on my next trip. I'd like to combine it with a white T-shirt I have."

[0396] The above is a detailed embodiment of the system of the present invention, which allows users to efficiently combine existing clothes with new rental clothes and receive personalized suggestions that take emotions into account.

[0397] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0398] Processing step details

[0399] Step 1:

[0400] Users upload images of their clothing.

[0401] Specifically, the user takes a photo of the clothes with their smartphone or PC, selects the image file using the "Register clothes in stock" function in the application, and clicks the upload button. The input for this process is the image file selected by the user, and the output is a notification that the image file has been uploaded.

[0402] Step 2:

[0403] The server receives and stores the images.

[0404] Specifically, the server receives image data of the clothes in hand via an HTTP POST request and temporarily stores it in cloud storage (e.g., Amazon S3). The input of this process is the uploaded image file, and the output is the URL of the image stored in the storage.

[0405] Step 3:

[0406] The server performs the image analysis.

[0407] Specifically, the server calls the Google Cloud Vision API and analyzes the received image. At this time, it extracts the type of clothing (e.g., shirt, pants), color, pattern (e.g., solid, striped), fabric texture, and style information (e.g., casual, formal). The input for this process is the image URL from storage, and the output is feature data (type, color, pattern, texture, style).

[0408] Step 4:

[0409] The server stores the feature data.

[0410] Specifically, the server associates the extracted feature data with the user ID and stores it in a database (e.g., Amazon RDS). The input to this process is the feature data and the user ID, and the output is the record ID stored in the database.

[0411] Step 5:

[0412] The user inputs the desired rental conditions.

[0413] Specifically, the user enters the desired rental clothing requirements (e.g., casual summer clothing) into a form within the application and clicks the submit button. The input for this process is the text data of the desired rental requirements entered by the user, and the output is a notification that the requirements have been submitted.

[0414] Step 6:

[0415] The server receives and analyzes the rental request conditions.

[0416] Specifically, the server receives the desired rental conditions via an HTTP POST request and executes an AI model to evaluate the optimal combination of the desired rental clothing with the clothes the customer owns based on the conditions. The input to this process is the text data of the desired rental conditions, and the output is pairing candidate data.

[0417] Step 7:

[0418] The server generates the coordinates.

[0419] Specifically, the server generates candidate combinations of clothing items owned and rented, and creates the most suitable outfit for the given conditions. Evaluation criteria include color compatibility, style matching, and seasonal suitability. The input to this process is pairing candidate data and evaluation criteria data, and the output is a list of outfit candidates.

[0420] Step 8:

[0421] The server presents the coordinates to the user.

[0422] Specifically, the server presents the coordinated outfit candidates it has generated to the user. The presentation method is push notification or email, and the user can check the outfits within the application. The input for this process is a list of coordinated outfit candidates, and the output is a notification that the presentation has been completed.

[0423] Step 9:

[0424] The device captures the user's emotions.

[0425] Specifically, when a user checks their outfit, the device's camera captures their facial expression in real time and records their voice with a microphone. The input to this process is the user's facial expression image and voice data, and the output is the captured emotional data.

[0426] Step 10:

[0427] The device transmits the emotion data to the server.

[0428] Specifically, the device sends the captured emotion data to the server via an HTTP POST request. The input of this process is the emotion data, and the output is a notification that the data has been sent.

[0429] Step 11:

[0430] The server stores and reflects the emotional data.

[0431] Specifically, the server stores the received emotion data in a database, and the next time it proposes a coordinated outfit, it reflects the user's preferences based on this data. The input for this process is the emotion data and the user ID, and the output is the record ID stored in the database.

[0432] The above are the specific processing steps of this system.

[0433] (Application example 2)

[0434] 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."

[0435] In today's clothing rental services, it is difficult for users to efficiently combine their existing clothes with newly rented clothes. It is also difficult to reflect the user's emotions and preferences in the actual outfit suggestions. This makes it difficult to provide optimal outfit suggestions for the user, potentially reducing satisfaction. While conventional technologies have partially achieved evaluation of clothing characteristics and appropriate combinations, they have yet to achieve personalized outfit suggestions that take the user's emotions into account. Technology to solve these issues is needed.

[0436] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving images of clothes photographed by the user, means for extracting feature data such as the type, color, and pattern of the clothes from the received images, means for saving the extracted feature data in a database for each user, means for receiving desired rental conditions specified by the user, means for generating an optimal outfit based on the saved feature data of the user's clothes and the feature data of rental clothes, means for presenting the generated outfit to the user, means for providing rental clothes based on the user's selection, means for recognizing and analyzing the user's emotions, and means for saving the analyzed emotion data in a database and reflecting it when generating the next outfit. This makes it possible to propose personalized outfits that reflect the user's emotions and preferences.

[0437] definition statement

[0438] "User" means an individual or legal entity that uses the Service.

[0439] "Clothing images" are digital images of clothing owned by the user.

[0440] "Emotion data" is data relating to emotions analyzed from the user's facial expressions and voice.

[0441] "Feature data" is information such as the type, color, and pattern of clothing extracted through image analysis.

[0442] "Rental Desired Conditions" refers to conditions such as the style and season of the clothing desired by the user.

[0443] "Coordination" is a styling suggestion that combines clothes you already own with rented clothes.

[0444] The "emotion engine" is a system that analyzes the user's facial expressions and voice to generate emotional data.

[0445] The "database" is a system for storing data on the characteristics and emotions of users' clothing.

[0446] An "AI algorithm" is a method that uses artificial intelligence to analyze data and generate optimal coordination.

[0447] "Owned clothes" refers to clothes that the user already owns.

[0448] "Rental clothing" refers to clothing that a user wishes to rent.

[0449] MODE FOR CARRYING OUT THE INVENTION

[0450] This invention is a system that uses images of clothes owned by a user to suggest optimal outfits for rental clothes, and further reflects the user's emotional data to provide more personalized outfits. This section describes specific methods for implementing the invention.

[0451] System Configuration

[0452] The system mainly consists of the following components:

[0453] 1. User device (smartphone, PC, etc.)

[0454] 2. Server

[0455] 3. Database

[0456] 4. Emotion Engine

[0457] 5. AI Algorithms

[0458] Processing flow

[0459] First, the user takes a photo of their clothes using a smartphone or PC, and the image is uploaded to the server via a dedicated application.

[0460] Image analysis of hand-held clothing

[0461] The server analyzes the images of the clothes received from the user. This analysis uses the image processing libraries OpenCV and TensorFlow. Feature data such as the type, color, and pattern of the clothes are extracted from the images. The server also analyzes the texture and style of the fabric, and stores this data in a database for each user.

[0462] Receiving rental requirements

[0463] Users input their desired clothing rental style, season, and other criteria into the application, which is then sent to the server and compared with the data on their existing clothing.

[0464] Coordinate generation

[0465] The server uses the stored characteristic data of the user's clothes and the characteristic data of the rental clothes to generate the optimal outfit using an AI algorithm, which takes into account factors such as color compatibility, style matching, and seasonal suitability.

[0466] Coordination suggestions

[0467] The generated coordinates are sent to the user's terminal, where the user can check the proposed coordinates.

[0468] Emotion data analysis and storage

[0469] The user reacts to the proposed outfits with facial expressions and voice. This reaction is captured by the device's camera and microphone and analyzed by the emotion engine. The emotional data resulting from this analysis is then sent back to the server and stored in a database.

[0470] Reflecting feedback

[0471] The saved emotion data is reflected the next time an outfit is created, allowing the system to suggest more appropriate outfits based on the user's preferences and feedback.

[0472] Specific examples

[0473] For example, suppose a user uploads an image of a white T-shirt and requests to rent casual summer clothing. In this case, the server analyzes the feature data of the white T-shirt and suggests jeans shorts or cargo shorts as suitable rental clothing. If the user responds with a smile or a satisfied voice, that emotional data is saved as positive feedback. The next time outfit suggestions are made, this positive feedback will be reflected, and suggestions that better match the user's preferences will be made.

[0474] Prompt Sentence Examples

[0475] "To suggest the next outfit, please generate a casual summer outfit by analyzing an image of a white T-shirt and the user's emotional feedback. Please consider the compatibility between the user's existing clothes and the rental clothes, and emphasize matching colors and styles. Also, please prioritize reflecting the user's positive emotional feedback."

[0476] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0477] Processing Steps

[0478] Step 1:

[0479] Users take pictures of their clothes and upload them through the application.

[0480] Specific operation: The user takes a picture of their clothes using the smartphone camera and uploads the picture using the "Register clothes" function in the application.

[0481] Input: A photograph of the clothing.

[0482] Output: Uploaded clothes images are sent to the server.

[0483] Step 2:

[0484] The server analyzes the received image and extracts feature data.

[0485] How it works: The server uses OpenCV and TensorFlow to analyze the image and extract feature data such as clothing type, color, pattern, fabric texture, and style information.

[0486] Input: Uploaded clothing image.

[0487] Data processing: Image analysis is used to extract clothing characteristic data (type, color, pattern, texture, and style information).

[0488] Output: Extracted feature data.

[0489] Step 3:

[0490] The server stores the extracted feature data in a database.

[0491] Specific operation: The server associates the extracted feature data with the user ID and stores it in a database.

[0492] Input: extracted feature data, user ID.

[0493] Data processing: Associating feature data with user ID.

[0494] Output: Feature data stored in a database.

[0495] Step 4:

[0496] The user inputs the desired rental conditions and transmits them to the server.

[0497] Specific operation: The user enters the desired rental clothing requirements (style, season, etc.) through the application and sends them to the server.

[0498] Input: The rental requirements entered by the user.

[0499] Output: Rental preferences sent to the server.

[0500] Step 5:

[0501] The server compares the characteristic data of the clothes you own with the data of the rental clothes and generates the optimal outfit.

[0502] Specific operation: The server uses an AI algorithm to compare the stored characteristic data of the clothes you own with the characteristic data of the rental clothes and generate the optimal combination.

[0503] Input: Characteristic data of your clothes, desired rental conditions.

[0504] Data calculation: AI algorithms match and generate optimal coordinates.

[0505] Output: Optimal coordinates.

[0506] Step 6:

[0507] The generated coordinates are presented on the user terminal.

[0508] Specific operation: The server displays the generated coordinates on the user's device via push notification or email.

[0509] Input: Optimal coordinates.

[0510] Output: Coordinates displayed on the user's terminal.

[0511] Step 7:

[0512] Capture user responses and analyze emotional data.

[0513] Specific operation: The user checks the suggested outfit, and their facial expressions and voice are captured using the device's camera and microphone, which are then analyzed by the emotion engine.

[0514] Input: Captured facial expressions and voice.

[0515] Data computation: Emotion data analysis using emotion engines.

[0516] Output: Parsed emotion data.

[0517] Step 8:

[0518] The emotional data is stored in a database and reflected in the next coordination generation.

[0519] Specific operation: The server saves the analyzed emotion data in a database and reflects it the next time a coordinate is generated.

[0520] Input: Parsed emotion data.

[0521] Data processing: Emotion data is saved and reflected in the next coordinate generation.

[0522] Output: Emotion data stored in the database, next outfit suggestions.

[0523] 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.

[0524] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0525] 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.

[0526] [Second embodiment]

[0527] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0528] 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.

[0529] 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).

[0530] 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.

[0531] 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.

[0532] 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).

[0533] 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.

[0534] 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.

[0535] 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.

[0536] 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.

[0537] 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.

[0538] 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."

[0539] The system of the present invention provides coordinated outfits that efficiently combine the user's existing clothes with newly rented clothes. This system is composed of the following elements: a means for the user to upload images of the clothes, a means for performing image analysis on the server, a means for storing and managing the extracted feature data, a means for receiving the user's desired rental conditions and generating an optimal outfit, and a means for presenting the generated outfit to the user and providing the rental clothes.

[0540] User procedure flow

[0541] First, users use their smartphone or PC to take a photo of their clothes and upload it to the system. Once the upload is complete, users can enter the desired rental clothing criteria, such as "casual summer clothes."

[0542] Server Processing

[0543] Based on this, the server performs the following processing.

[0544] 1. Receiving and saving images

[0545] The server receives the images of the clothes uploaded by the user and temporarily stores them in a database.

[0546] 2. Image Analysis

[0547] The server runs an AI algorithm for image analysis to extract feature data such as the type of clothing (e.g., shirt, pants), color (e.g., white, black, red), and pattern (e.g., solid, striped), as well as fabric texture and style information (e.g., casual, formal).

[0548] 3. Saving feature data

[0549] The extracted feature data is associated with the user ID and stored in a database, creating a database of clothing for each user.

[0550] 4. Receiving and analyzing rental requirements

[0551] The server receives rental requirements specified by the user, including clothing category (e.g., shirt, dress), occasion (e.g., casual, formal), and season (e.g., summer, winter).

[0552] 5. Generating optimal coordination

[0553] The server compares the data on the customer's clothing with the data on rental clothing and uses AI to generate optimal outfit suggestions, taking into account criteria such as color compatibility, style matching, and seasonality.

[0554] 6. Coordination Presentation

[0555] The server presents the generated coordinates to the user and allows the user to select one. Notification methods include push notifications and emails.

[0556] Specific examples

[0557] For example, suppose a user uploads an image of a white T-shirt and requests a casual rental item suitable for summer wear. The server stores the characteristics of the white T-shirt and suggests the following outfits along with the desired rental conditions:

[0558] White T-shirt (own) + Jeans shorts (rental)

[0559] White T-shirt (own) + Cargo shorts (rental)

[0560] The user checks the suggested outfits, selects their favorite combination, and confirms the rental. The server receives this order and proceeds with the delivery of the rental clothes.

[0561] In this way, the system of the present invention can efficiently combine the user's existing clothes with newly rented clothes to provide optimal coordination, thereby expanding the user's fashion choices and greatly improving convenience.

[0562] The processing flow will be explained below.

[0563] Step 1:

[0564] Users use their smartphone or PC to take pictures of their own clothes and then upload the images using the "Register Owned Clothes" function within the application.

[0565] Step 2:

[0566] The server receives the uploaded images and temporarily stores them in a database.

[0567] Step 3:

[0568] The server runs an AI algorithm for image analysis to extract characteristic data such as the type of clothing (e.g., shirt, pants), color (e.g., white, black, red), and pattern (e.g., solid, striped), as well as fabric texture and style information (e.g., casual, formal).

[0569] Step 4:

[0570] The server associates the extracted feature data with the user ID and stores it in a database, thereby creating a clothing database for each user.

[0571] Step 5:

[0572] The user enters the rental requirements (e.g., casual summer clothing) into the application.

[0573] Step 6:

[0574] The server receives rental requirements from the user, including clothing category (e.g., shirt, dress), occasion (e.g., casual, formal), and season (e.g., summer, winter).

[0575] Step 7:

[0576] The server retrieves the user's clothing data from the database and runs an AI algorithm to compare it with the rental clothing database, thereby evaluating combinations of the user's clothing and potential rental items.

[0577] Step 8:

[0578] The server uses AI algorithms to generate optimal outfit suggestions, which include evaluations of color compatibility, style matching, and seasonal suitability.

[0579] Step 9:

[0580] The server generates a plurality of coordinate candidates and presents them to the user.

[0581] Step 10:

[0582] Using the terminal application, the user visually checks the presented coordination candidates and selects the combination they like.

[0583] Step 11:

[0584] Based on the outfit the user selects, they "add" the clothes to rent to their cart and finally confirm the rental order.

[0585] Step 12:

[0586] The server receives the user's order information and starts the delivery procedure for the rental clothes.

[0587] By using the above steps, the system of the present invention efficiently combines the clothes the user owns with the clothes to be rented, providing optimal coordination. Furthermore, by allowing the user to easily select clothes and complete the rental procedure, convenience is greatly improved.

[0588] Example 1

[0589] 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."

[0590] Conventional fashion coordination systems have made it difficult for users to effectively combine their existing clothes with newly rented clothes. Furthermore, they lacked a mechanism for automatically suggesting optimal outfits based on the user's existing clothes and desired rental conditions. This not only resulted in low convenience for users, but also made it difficult to achieve a highly satisfying outfit. Therefore, there is a demand for a system that allows users to enjoy coordinating outfits in a more efficient and satisfying way.

[0591] 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.

[0592] In this invention, the server

[0593] means for receiving an image of clothing taken by a user;

[0594] A means for extracting feature data such as type, color, and pattern of clothing from the received image;

[0595] A means for storing the extracted feature data in a database for each user;

[0596] means for receiving desired rental conditions specified by a user;

[0597] A means for generating an optimal outfit based on the stored feature data of the user's clothes and the feature data of the rental clothes;

[0598] means for presenting the generated coordinates to a user;

[0599] A means for providing rental clothing based on a user's selection;

[0600] means for notifying a user of the generated coordinates by a notification means;

[0601] This allows users to efficiently combine their own clothes with rental clothes to create the perfect outfit.

[0602] "User" refers to an individual who uses this system to coordinate their own clothing.

[0603] "Server" refers to a device that receives images uploaded by users, analyzes the images, stores the data, and generates and provides coordinates.

[0604] "Image" refers to visual data of clothing photographed by a user and stored in digital format.

[0605] "Feature data" refers to the type, color, pattern, and fabric texture and style information of clothing extracted from the received image.

[0606] "Database" refers to an information storage system for saving and managing clothing characteristic data for each user.

[0607] "Rental Desired Conditions" refers to the conditions such as the category, situation, and season of the clothing the user desires to rent.

[0608] "Coordination" refers to a fashion proposal that combines the user's own clothes with rental clothes.

[0609] "Notification means" refers to a method for notifying the user of the created coordination, and includes push notification and email.

[0610] This invention is a system that provides coordinated outfits that efficiently combine a user's existing clothes with newly rented clothes. This system includes the following elements: a means for the user to upload images of the clothes, a means for performing image analysis on a server, a means for storing and managing extracted feature data, a means for receiving the user's desired rental conditions and generating an optimal outfit, and a means for presenting the generated outfit to the user and providing the rental clothes.

[0611] First, the user uses their smartphone or PC (terminal) to take a picture of the clothes they own and upload it to the system. Specifically, the user takes a picture of the clothes using a camera app and uploads the image to the system through a dedicated web or mobile application. At that time, the user enters the conditions for the clothes they want to rent (for example, "casual summer clothes"). This process is carried out via an HTTP request.

[0612] The server receives the uploaded images and temporarily stores them in a database. The database used can be a relational database such as MySQL or PostgreSQL. The received image data is stored in a temporary storage folder, and image metadata (upload date and time, user ID, etc.) is also recorded in the database.

[0613] The server then runs an AI algorithm (such as TensorFlow or PyTorch) for image analysis to extract feature data such as clothing type (e.g., shirt, pants), color (e.g., white, black), pattern (e.g., solid, striped), fabric texture, and style information (e.g., casual, formal). This process provides specific information about the user's clothing.

[0614] The extracted feature data is associated with the user ID and stored in a database. This creates a clothing database for each user. Next, the server receives the rental requirements specified by the user (e.g. clothing category, occasion, season). The desired requirements are also received via an HTTP request.

[0615] The server uses this data to generate optimal outfit suggestions using an AI algorithm. Evaluation criteria include color compatibility, style matching, and seasonality. The generated outfit suggestions are displayed on the user's interface. Notifications are sent via push notifications and email.

[0616] As a concrete example, consider the case where a user uploads an image of a white T-shirt and requests casual rental clothing suitable for summer wear. For example, the server can save the characteristic data of the white T-shirt and compare it with the rental requirements to suggest the following outfits:

[0617] White T-shirt (own) + Jeans shorts (rental)

[0618] White T-shirt (own) + Cargo shorts (rental)

[0619] The user checks the suggested outfits and selects the combination they want. The server then receives the order and begins the process of shipping the rental clothes.

[0620] As described above, the system of the present invention can efficiently combine the user's existing clothes with newly rented clothes to provide optimal coordination, thereby expanding the range of fashion choices available to the user and greatly improving convenience.

[0621] Example prompt sentence:

[0622] "I'd like to upload an image of a white T-shirt to the system and request casual rental clothing for summer wear. I'd like you to suggest items that coordinate well with the shirts, pants, and other items I already have."

[0623] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0624] Step 1:

[0625] Upload an image and enter conditions

[0626] Users use their smartphones or PCs to take pictures of their clothes and upload them to the system. After this is complete, users enter the conditions for the clothes they want to rent (e.g., "casual summer clothes").

[0627] Input: Clothing image data, desired rental conditions

[0628] Output: Upload image data to the system, send rental requirements

[0629] Specific behavior:

[0630] Use the camera app to take a picture of the outfit.

[0631] Open your web browser or mobile app and log in.

[0632] Click the image upload button, select the image you have taken, and upload it.

[0633] Enter your desired rental conditions (e.g., "casual summer clothing") in the text box and submit.

[0634] Step 2:

[0635] Receiving and saving images

[0636] The server receives the images of the clothes uploaded by the user and temporarily stores them in a database.

[0637] Input: Image data sent by the user

[0638] Output: Image files saved in a temporary folder, metadata recorded in a database

[0639] Specific behavior:

[0640] The server receives the image data via an HTTP request.

[0641] The received image is saved in a temporary folder.

[0642] Record image metadata (upload date and time, user ID, etc.) in a database.

[0643] Step 3:

[0644] Feature extraction through image analysis

[0645] The server runs AI algorithms for image analysis to extract information about the type of clothing, color, pattern, and fabric texture and style.

[0646] Input: Saved image data

[0647] Output: Extracted feature data (type, color, pattern, texture, style information)

[0648] Specific behavior:

[0649] Calls an image analysis engine (such as TensorFlow) to process the uploaded image.

[0650] Analyze the type (shirt, pants, etc.), color (white, black, etc.), and pattern (solid, striped).

[0651] AI algorithm determines style (casual, formal).

[0652] Step 4:

[0653] Feature data storage

[0654] The server associates the extracted feature data with the user ID and stores it in a database.

[0655] Input: extracted feature data, user ID

[0656] Output: Feature data stored in a per-user clothing database

[0657] Specific behavior:

[0658] The extracted feature data is inserted into a database.

[0659] Link feature data with user ID.

[0660] Step 5:

[0661] Receiving rental requirements

[0662] The server receives the rental requirements entered by the user, including information such as clothing category, occasion, and season.

[0663] Input: Rental requirements submitted by the user

[0664] Output: The received rental requirements are stored on the server.

[0665] Specific behavior:

[0666] Receives form data from the user via an HTTP request.

[0667] The received data is analyzed, the user's desired conditions are identified, and the results are stored in a database.

[0668] Step 6:

[0669] Optimal coordination generation

[0670] The server compares data on existing clothing with rental clothing data and uses AI to generate optimal outfit suggestions.

[0671] Input: User's clothing characteristics, rental requirements

[0672] Output: A list of optimal outfit candidates

[0673] Specific behavior:

[0674] The user's clothing data is obtained from the database.

[0675] The clothes are compared with a database of rental clothing and evaluated using an AI algorithm.

[0676] Several coordination candidates are generated and their evaluation scores are calculated.

[0677] Step 7:

[0678] Coordination presentation and selection for users

[0679] The server presents the generated coordinates to the user, allowing the user to make a selection.

[0680] Input: Best coordinate candidates

[0681] Output: Coordination candidates presented to the user, and the user's choice

[0682] Specific behavior:

[0683] Coordination candidates are displayed on the user interface.

[0684] Notify users via push notification or email.

[0685] The user clicks the select button to confirm the coordinates.

[0686] Step 8:

[0687] Rental clothing shipping procedures

[0688] The server then processes the delivery of the rental clothing coordinated by the user, and if necessary, shares the shipping information with the delivery company.

[0689] Input: Rental clothing selected by the user

[0690] Output: Rental clothing shipping instructions, delivery notification to user

[0691] Specific behavior:

[0692] Check the availability of the selected rental clothing.

[0693] Get the user's shipping information and generate a shipping label.

[0694] Information is shared with departments and services responsible for delivery procedures.

[0695] (Application example 1)

[0696] 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."

[0697] Conventional coordination systems have the problem that it is difficult for users to efficiently combine their existing clothes with the clothes available in stores when they visit a physical store. Furthermore, they do not provide sufficient support for users to select clothes in the store using a smartphone or smart glasses, and lack functionality to improve the shopping experience in physical stores.

[0698] 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.

[0699] In this invention, the server includes means for receiving images of clothes photographed by a user, means for extracting characteristic data such as the type, color, and pattern of the clothes from the received images, means for storing the extracted characteristic data in a database for each user, means for receiving desired rental conditions specified by the user, means for generating an optimal outfit based on the stored characteristic data of the user's clothes and the characteristic data of rental clothes, means for using a smartphone, smart glasses, or interactive kiosk to present the optimal outfit to the user in the store, and means for providing rental or sales clothes based on the user's selection. This allows users to easily find an optimal outfit that efficiently combines clothes they own with clothes in the store in a physical store.

[0700] A "user" is an individual who uses the system to coordinate and rent clothes.

[0701] "Photographing" refers to the act of capturing an image of clothing using a device such as a smartphone or smart glasses.

[0702] "Clothing images" are photographic data of clothes taken by the user.

[0703] The "receiving means" is a function that allows the server to receive image data of clothes sent by the user.

[0704] "Clothing type" is a clothing category such as shirts, pants, dresses, etc.

[0705] "Color" refers to the specific color information that clothing possesses.

[0706] A "pattern" is a design or figure found in clothing designs.

[0707] "Feature data" is specific information such as the type, color, and pattern of clothing extracted through image analysis.

[0708] The "database" is a digital information management system for storing extracted feature data for each user.

[0709] "Rental requirements" are requirements such as a specific clothing category or style specified by the user.

[0710] "Rental clothing" refers to clothing that is available for rental to users.

[0711] The "optimal coordination" refers to the combination of the user's own clothes with rental or sales clothes that best harmonizes in terms of color, style, etc.

[0712] "In-store" refers to the interior space of the actual store that the user visits.

[0713] A "smartphone" is a mobile phone with internet connectivity and the ability to run advanced applications.

[0714] "Smart glasses" are wearable devices that have the shape of regular glasses but can display information and perform other functions.

[0715] An "interactive kiosk" is a device that allows users to obtain information and perform operations using an operable display device such as a touch panel.

[0716] "Sales clothing" refers to clothing sold to users in a store.

[0717] The following describes the system configuration and operation procedure as an embodiment of the present invention. The system includes a server that receives and analyzes images of clothes taken by a user, a smartphone, smart glasses, and an interactive kiosk that present optimal outfits to the user.

[0718] System Configuration

[0719] 1. Server:

[0720] Image receiving function: Receives images of clothes uploaded by users.

[0721] Image analysis function: Uses libraries such as TensorFlow and OpenCV to extract feature data such as clothing type, color, and pattern from images.

[0722] Database management: The extracted feature data is stored in a database for each user.

[0723] Recommendation engine: Generates optimal coordination based on the user's desired rental conditions.

[0724] 2. User Device:

[0725] Smartphone: Used to take and upload images and check outfits.

[0726] Smart glasses: Used by users to check the best outfits in real time while walking around the store.

[0727] Interactive Kiosk: Enables in-store operation for suggesting and selecting outfits.

[0728] Program processing

[0729] 1. Image reception:

[0730] The server receives the images of the clothes sent from the user's device and temporarily stores them in a database, using a high-speed Internet connection to send and receive the images.

[0731] 2. Image Analysis:

[0732] The received images are analyzed on the server using TensorFlow and OpenCV to extract information such as the type of clothing (e.g., shirt, pants), color (e.g., white, black, red), pattern (e.g., solid, striped), texture, and style information.

[0733] 3. Save feature data:

[0734] The extracted feature data is associated with the user ID and stored in a database, which creates a clothing database for each user and is used to suggest future outfits.

[0735] 4. Coordinate generation:

[0736] After the user enters their desired rental requirements, the server compares the stored data of clothing on hand with the data of clothing candidates for rental and generates the optimal outfit using an AI algorithm (e.g., cosine similarity calculation).

[0737] 5. Proposal and Selection:

[0738] The optimal outfits are presented to the user via a smartphone, smart glasses, or interactive kiosk, and the process of providing rental or sales clothes based on the outfits selected by the user proceeds.

[0739] Specific examples

[0740] User behavior example:

[0741] A user takes a photo of a white T-shirt with their smartphone and uploads it to the system. They then enter their desired casual summer clothing rental requirements. Based on this information, the server recommends jeans shorts that go perfectly with the white T-shirt. The user can instantly view the jeans shorts while walking around the store through the smart glasses.

[0742] Example prompt sentence:

[0743] prompt:

[0744] User ID: example_user_01

[0745] Clothing characteristics: White T-shirt, casual, summer

[0746] In-store clothing data: Jeans shorts, casual, summer

[0747] How to use generative AI models:

[0748] 1. Input the feature data of the user's white T-shirt into the AI.

[0749] 2. Compare with the characteristic data of jean shorts in stock at the store.

[0750] 3. Optimal coordination is suggested using cosine similarity.

[0751] Example response:

[0752] Select a pair of jean shorts that match the color of the user's T-shirt.

[0753] Selection results:

[0754] White T-shirt + Jean shorts

[0755] In this way, a system is provided that enables a user to easily find an optimal outfit that efficiently combines clothes that the user owns with clothes in the store in a real store.

[0756] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0757] Step 1:

[0758] The user uploads a photo of the clothes they have taken. The information entered here is the user ID and the image file of the clothes. The uploaded image data is sent from the device to the server.

[0759] Step 2:

[0760] The image received by the server is temporarily stored in a database. The output of this process is the completion of saving the uploaded image data. Specifically, the image received by the server is saved in a specified directory and linked to the corresponding user ID.

[0761] Step 3:

[0762] The server retrieves the stored image data and performs image analysis. The input is the image data stored in the database. TensorFlow and OpenCV are used for the analysis to extract feature data such as the type of clothing, color, pattern, fabric texture, and style information. The output of this process is the extracted feature data. Specifically, an AI model is executed to extract clothing features from the image.

[0763] Step 4:

[0764] The extracted feature data is saved in a database for each user. The input is the feature data extracted in step 3 and the user ID. The output of this process is a database with updated feature data for each user. Specifically, the feature data is associated with the user ID and inserted into the database.

[0765] Step 5:

[0766] The user inputs the desired rental conditions, such as clothing category, occasion, season, etc. The desired rental conditions are sent from the terminal to the server.

[0767] Step 6:

[0768] The server compares the stored data of clothing items on hand with the data of clothing items that can be rented based on the desired rental conditions. The inputs are the desired rental conditions, the user's characteristic data, and the data of the clothing items that can be rented. An optimal outfit is generated using an AI algorithm (e.g., cosine similarity calculation). The output of this process is the optimal outfit candidate. Specifically, an AI model is executed to find the optimal combination.

[0769] Step 7:

[0770] The optimal outfit is presented to the user. The input is the outfit candidates generated in step 6. The output is outfit information displayed on the user's smartphone, smart glasses, or interactive kiosk. Specifically, the outfit information is displayed via push notification or within the application.

[0771] Step 8:

[0772] The user selects a suggested outfit. The input information is the outfit selected by the user. The selection information is sent from the terminal to the server.

[0773] Step 9:

[0774] Based on the selection, the system carries out procedures to provide the clothes for rental or sale. The input is the outfit and rental conditions selected by the user. The output of this process is the delivery of the rental clothes or the completion of the sales procedure. Specifically, delivery arrangements and purchase procedures are automatically carried out by the server.

[0775] 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.

[0776] The system of the present invention provides coordinated outfits that efficiently combine the user's existing clothes with newly rented clothes, and by combining it with an emotion engine that recognizes the user's emotions, it realizes more personalized suggestions. The details of the system are described below.

[0777] User procedure flow

[0778] Users take pictures of their clothes using their smartphones or PCs and upload them using the app's "Register Your Own Clothes" function. Once the upload is complete, users can enter the desired rental clothing specifications (e.g., casual summer clothes).

[0779] Server Processing

[0780] Based on this, the server performs the following processing.

[0781] Receiving and saving images

[0782] The server receives the images of the clothes uploaded by the user and temporarily stores them in a database.

[0783] Image analysis

[0784] The server runs an AI algorithm for image analysis to extract characteristic data such as the type of clothing (e.g., shirt, pants), color (e.g., white, black, red), and pattern (e.g., solid, striped), as well as the texture of the fabric and style information (e.g., casual, formal).

[0785] Feature data storage

[0786] The server associates the extracted feature data with the user ID and stores it in a database, thereby creating a clothing database for each user.

[0787] Receiving and analyzing rental requirements

[0788] Once customers input their desired rental requirements, the server receives them and runs an AI algorithm to match their existing clothing data with the rental clothing data, using criteria such as color compatibility, style matching, and seasonal suitability.

[0789] Coordinate generation and presentation

[0790] The server generates optimal outfit suggestions and presents multiple options to the user. The outfit suggestions are displayed in the device's application via push notification or email.

[0791] Incorporating an emotion engine

[0792] Furthermore, the system incorporates an emotion engine to perform the following processes:

[0793] Emotion Recognition and Analysis

[0794] The device captures the user's facial expressions and voice in response to the presented outfit, and the emotion engine analyzes them to collect the user's emotional data. The emotion engine then sends the analysis results to the server.

[0795] Saving and reflecting emotional data

[0796] The server stores the emotion data in a database and reflects this data the next time a coordinated outfit is generated, suggesting a more appropriate outfit based on the user's preferences and feedback.

[0797] Specific examples

[0798] For example, suppose a user uploads an image of a white T-shirt and requests a casual rental item suitable for summer wear. In this case, the server saves the characteristics of the white T-shirt and suggests the following outfits along with the desired rental conditions:

[0799] White T-shirt (own) + Jeans shorts (rental)

[0800] White T-shirt (own) + Cargo shorts (rental)

[0801] The user reviews the suggested outfit, and the emotion engine analyzes the user's preferences from their facial expressions and tone of voice. For example, if the user smiles or sounds satisfied, this is saved as positive feedback. The next time the system suggests an outfit, this positive feedback will be reflected, making the suggestion more in line with the user's preferences.

[0802] In this way, the system of the present invention can efficiently combine the user's existing clothes with new clothes to rent, and further make suggestions that take the user's emotions into consideration, thereby expanding the range of fashion choices available to the user and greatly improving convenience.

[0803] The processing flow will be explained below.

[0804] Step 1:

[0805] Users use their smartphone or PC to take pictures of their clothes and then upload the images using the "Register clothes you own" function within the application.

[0806] Step 2:

[0807] The server receives the uploaded images and temporarily stores them in a database.

[0808] Step 3:

[0809] The server runs an AI algorithm for image analysis to extract characteristic data such as the type of clothing (shirt, pants, etc.), color (white, black, red, etc.), and pattern (solid, striped, etc.), as well as the texture of the fabric and style information (casual, formal, etc.).

[0810] Step 4:

[0811] The server associates the extracted feature data with the user ID and stores it in a database, thereby creating a clothing database for each user.

[0812] Step 5:

[0813] The user enters the rental requirements (e.g., casual summer clothing) into the application.

[0814] Step 6:

[0815] The server receives rental requirements from the user, including clothing category (e.g., shirt, dress), occasion (e.g., casual, formal), and season (e.g., summer, winter).

[0816] Step 7:

[0817] The server retrieves the user's clothing data from the database and runs an AI algorithm to compare it with the rental clothing database, thereby evaluating combinations of the user's clothing and potential rental items.

[0818] Step 8:

[0819] The server uses AI algorithms to generate optimal outfit suggestions, which include evaluations of color compatibility, style matching, and seasonal suitability.

[0820] Step 9:

[0821] The server generates a plurality of coordinate candidates and presents them to the user.

[0822] Step 10:

[0823] Using the terminal application, the user visually checks the presented coordination candidates and selects the combination they like.

[0824] Step 11:

[0825] The device captures the user's facial expressions and voice, and the emotion engine analyzes the data to collect the user's emotional data.

[0826] Step 12:

[0827] The server receives the analysis results from the emotion engine and stores them in a database.

[0828] Step 13:

[0829] Based on the outfit the user selects, they "add" the clothes to rent to their cart and finally confirm the rental order.

[0830] Step 14:

[0831] The server receives the user's order information and starts the delivery procedure for the rental clothes.

[0832] Step 15:

[0833] From the next time onwards, the server will adjust the evaluation criteria of the AI ​​algorithm based on the collected emotional data and suggest outfits that better match the user's preferences. For example, if positive feedback is received from a smile or a satisfied voice, similar outfits will be suggested based on that information.

[0834] Through the above steps, the system of the present invention can efficiently combine the user's existing clothes with new rental clothes, and further make suggestions that take the user's emotions into consideration, thereby expanding the range of fashion choices available to the user and greatly improving convenience.

[0835] Example 2

[0836] 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."

[0837] In conventional fashion coordination systems, it is difficult for users to efficiently combine clothes they own with newly rented clothes, and they also have the problem of not being able to provide suggestions that fully take into account the user's preferences and emotions. The present invention aims to solve these problems and provide appropriate fashion coordination that is personalized for the user.

[0838] 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.

[0839] In this invention, the server includes means for receiving images of clothes photographed by a user, means for extracting characteristic data such as the type, color, and pattern of the clothes from the received images, means for saving the extracted characteristic data in a database for each user, means for receiving desired rental conditions specified by the user, means for generating an optimal outfit based on the saved characteristic data of the user's clothes and the characteristic data of rental clothes, means for presenting the generated outfit to the user, means for providing rental clothes based on the user's selection, means for capturing the user's facial expressions and voice and analyzing emotional data, and means for saving the analyzed emotional data in a database and reflecting it when generating the next outfit. This makes it possible to efficiently combine the user's own clothes with new rental clothes and to make more personalized suggestions that reflect the user's emotions and preferences.

[0840] A "user" is someone who wishes to coordinate or rent clothes using this system.

[0841] "Means for receiving images of clothes in hand" refers to the function that allows users to upload images of clothes taken with their smartphone or PC to the server.

[0842] "Feature data" refers to data about clothing characteristics extracted through image analysis, such as type of clothing, color, pattern, fabric texture, and style information.

[0843] A "database" is an information accumulation system for storing extracted feature data, user information, emotional data, etc.

[0844] "Desired rental conditions" refers to information that allows a user to specify the conditions for the clothes they wish to rent (for example, casual summer clothes).

[0845] "Coordination" means suggesting styling by combining clothes you already own with rented clothes.

[0846] An "artificial intelligence model" is an algorithm or machine learning model used to evaluate the compatibility of clothing.

[0847] "Emotion data" refers to data related to emotions obtained by analyzing the user's facial expressions and voice.

[0848] "Means for analyzing" refers to technology for processing a user's emotional data in real time and determining the type and degree of emotion.

[0849] The "server" is a central computer system that stores and processes user data, image analysis, coordinate generation, and emotion data.

[0850] A "terminal" refers to a device such as a smartphone or PC operated by a user.

[0851] "Capture" refers to capturing the user's facial expressions and voice through a camera or microphone.

[0852] "Means for reflecting the next coordinated outfit when generating the next coordinated outfit" refers to a function for taking the user's preferences and emotions into consideration when proposing the next coordinated outfit based on the saved emotion data.

[0853] The system of the present invention provides coordinated outfits that efficiently combine the user's existing clothes with newly rented clothes, and by combining it with an emotion engine that recognizes the user's emotions, it realizes more personalized suggestions. Detailed embodiments of this system are described below.

[0854] System configuration

[0855] This system consists of the following main components:

[0856] 1. Server

[0857] 2. Terminal

[0858] 3. Database

[0859] 4. Emotion Engine

[0860] Hardware and software used

[0861] The server plays a central role in image analysis, data storage, and coordinate generation. Specifically, it uses the following software and services:

[0862] Image analysis uses Google Cloud Vision API and Amazon Rekognition.

[0863] Amazon RDS and MySQL are used as databases.

[0864] Coordination generation uses machine learning libraries such as TensorFlow and PyTorch.

[0865] The terminals are devices operated by users, such as smartphones and PCs, that take and upload images and capture emotions.

[0866] The emotion engine is a component that captures and analyzes the user's facial expressions and voice, specifically using Microsoft Azure's Face API and IBM Watson's Tone Analyzer.

[0867] System operation procedures

[0868] The system operation procedure will be explained below with specific examples.

[0869] 1. User uploads clothing images

[0870] Users can take pictures of their clothes using their smartphones or PCs and upload them using the application's "Register clothes" function by selecting the image file and clicking the upload button.

[0871] 2. Receiving and saving images

[0872] The server receives image files uploaded by users and temporarily stores the image data in cloud storage such as Amazon S3.

[0873] 3. Image Analysis

[0874] The server uses the Google Cloud Vision API to analyze the images and extract information about the type, color, pattern, texture, and style of the clothing, thereby obtaining feature data such as the type of shirt or pants, color (white or black), and pattern (solid or striped).

[0875] 4. Saving feature data

[0876] The server associates the extracted feature data with the user ID and stores it in Amazon RDS. The stored data includes the clothing ID, type, color, pattern, texture, style, etc.

[0877] 5. Enter your desired rental conditions

[0878] The user enters the desired rental clothing requirements (e.g., casual summer clothing) into a form within the application and submits it.

[0879] 6. Analysis of desired rental conditions

[0880] The server receives the user's desired rental conditions via an HTTP POST request, compares them with the user's clothing data, and selects the most suitable rental clothing.

[0881] 7. Coordinate Generation

[0882] The server generates combination candidates for clothes that you own and rent, and creates the most suitable outfit that meets your requirements.

[0883] 8. Coordination Presentation

[0884] The server presents the generated outfit suggestions to the user via push notification or email, and the user can check the outfits within the application.

[0885] 9. Capturing Emotions

[0886] The device captures the user's facial expressions and voice using a camera and microphone and analyzes them in real time. For example, if the user smiles or sounds satisfied, this is analyzed by the emotion engine as positive feedback and the results are sent to the server.

[0887] 10. Saving and Reflecting Emotional Data

[0888] The server stores the emotion data in a database and reflects it in the next outfit suggestions, thereby learning the user's preferences and realizing more personalized outfit suggestions.

[0889] Examples of specific examples and prompts

[0890] For example, if a user uploads an image of a white T-shirt and requests "casual rental clothing suitable for summer," the server will save the characteristics of the white T-shirt, compare them with the rental requirements, and suggest the following outfits:

[0891] White T-shirt (own) + Jeans shorts (rental)

[0892] White T-shirt (own) + Cargo shorts (rental)

[0893] Based on this suggestion, the user checks the suggested outfit, and the emotion engine analyzes their preferences from their facial expressions and tone of voice. If they smile or sound satisfied, this is saved as positive feedback and will be reflected in the next suggestion. An example of a prompt is, "Please suggest some casual summer clothes to wear on my next trip. I'd like to combine it with a white T-shirt I have."

[0894] The above is a detailed embodiment of the system of the present invention, which allows users to efficiently combine existing clothes with new rental clothes and receive personalized suggestions that take emotions into account.

[0895] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0896] Processing step details

[0897] Step 1:

[0898] Users upload images of their clothing.

[0899] Specifically, the user takes a photo of the clothes with their smartphone or PC, selects the image file using the "Register clothes in stock" function in the application, and clicks the upload button. The input for this process is the image file selected by the user, and the output is a notification that the image file has been uploaded.

[0900] Step 2:

[0901] The server receives and stores the images.

[0902] Specifically, the server receives image data of the clothes in hand via an HTTP POST request and temporarily stores it in cloud storage (e.g., Amazon S3). The input of this process is the uploaded image file, and the output is the URL of the image stored in the storage.

[0903] Step 3:

[0904] The server performs the image analysis.

[0905] Specifically, the server calls the Google Cloud Vision API and analyzes the received image. At this time, it extracts the type of clothing (e.g., shirt, pants), color, pattern (e.g., solid, striped), fabric texture, and style information (e.g., casual, formal). The input for this process is the image URL from storage, and the output is feature data (type, color, pattern, texture, style).

[0906] Step 4:

[0907] The server stores the feature data.

[0908] Specifically, the server associates the extracted feature data with the user ID and stores it in a database (e.g., Amazon RDS). The input to this process is the feature data and the user ID, and the output is the record ID stored in the database.

[0909] Step 5:

[0910] The user inputs the desired rental conditions.

[0911] Specifically, the user enters the desired rental clothing requirements (e.g., casual summer clothing) into a form within the application and clicks the submit button. The input for this process is the text data of the desired rental requirements entered by the user, and the output is a notification that the requirements have been submitted.

[0912] Step 6:

[0913] The server receives and analyzes the rental request conditions.

[0914] Specifically, the server receives the desired rental conditions via an HTTP POST request and executes an AI model to evaluate the optimal combination of the desired rental clothing with the clothes the customer owns based on the conditions. The input to this process is the text data of the desired rental conditions, and the output is pairing candidate data.

[0915] Step 7:

[0916] The server generates the coordinates.

[0917] Specifically, the server generates candidate combinations of clothing items owned and rented, and creates the most suitable outfit for the given conditions. Evaluation criteria include color compatibility, style matching, and seasonal suitability. The input to this process is pairing candidate data and evaluation criteria data, and the output is a list of outfit candidates.

[0918] Step 8:

[0919] The server presents the coordinates to the user.

[0920] Specifically, the server presents the coordinated outfit candidates it has generated to the user. The presentation method is push notification or email, and the user can check the outfits within the application. The input for this process is a list of coordinated outfit candidates, and the output is a notification that the presentation has been completed.

[0921] Step 9:

[0922] The device captures the user's emotions.

[0923] Specifically, when a user checks their outfit, the device's camera captures their facial expression in real time and records their voice with a microphone. The input to this process is the user's facial expression image and voice data, and the output is the captured emotional data.

[0924] Step 10:

[0925] The device transmits the emotion data to the server.

[0926] Specifically, the device sends the captured emotion data to the server via an HTTP POST request. The input of this process is the emotion data, and the output is a notification that the data has been sent.

[0927] Step 11:

[0928] The server stores and reflects the emotional data.

[0929] Specifically, the server stores the received emotion data in a database, and the next time it proposes a coordinated outfit, it reflects the user's preferences based on this data. The input for this process is the emotion data and the user ID, and the output is the record ID stored in the database.

[0930] The above are the specific processing steps of this system.

[0931] (Application example 2)

[0932] 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."

[0933] In today's clothing rental services, it is difficult for users to efficiently combine their existing clothes with newly rented clothes. It is also difficult to reflect the user's emotions and preferences in the actual outfit suggestions. This makes it difficult to provide optimal outfit suggestions for the user, potentially reducing satisfaction. While conventional technologies have partially achieved evaluation of clothing characteristics and appropriate combinations, they have yet to achieve personalized outfit suggestions that take the user's emotions into account. Technology to solve these issues is needed.

[0934] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving images of clothes photographed by the user, means for extracting feature data such as the type, color, and pattern of the clothes from the received images, means for saving the extracted feature data in a database for each user, means for receiving desired rental conditions specified by the user, means for generating an optimal outfit based on the saved feature data of the user's clothes and the feature data of rental clothes, means for presenting the generated outfit to the user, means for providing rental clothes based on the user's selection, means for recognizing and analyzing the user's emotions, and means for saving the analyzed emotion data in a database and reflecting it when generating the next outfit. This makes it possible to propose personalized outfits that reflect the user's emotions and preferences.

[0935] definition statement

[0936] "User" means an individual or legal entity that uses the Service.

[0937] "Clothing images" are digital images of clothing owned by the user.

[0938] "Emotion data" is data relating to emotions analyzed from the user's facial expressions and voice.

[0939] "Feature data" is information such as the type, color, and pattern of clothing extracted through image analysis.

[0940] "Rental Desired Conditions" refers to conditions such as the style and season of the clothing desired by the user.

[0941] "Coordination" is a styling suggestion that combines clothes you already own with rented clothes.

[0942] The "emotion engine" is a system that analyzes the user's facial expressions and voice to generate emotional data.

[0943] The "database" is a system for storing data on the characteristics and emotions of users' clothing.

[0944] An "AI algorithm" is a method that uses artificial intelligence to analyze data and generate optimal coordination.

[0945] "Owned clothes" refers to clothes that the user already owns.

[0946] "Rental clothing" refers to clothing that a user wishes to rent.

[0947] MODE FOR CARRYING OUT THE INVENTION

[0948] This invention is a system that uses images of clothes owned by a user to suggest optimal outfits for rental clothes, and further reflects the user's emotional data to provide more personalized outfits. This section describes specific methods for implementing the invention.

[0949] System Configuration

[0950] The system mainly consists of the following components:

[0951] 1. User device (smartphone, PC, etc.)

[0952] 2. Server

[0953] 3. Database

[0954] 4. Emotion Engine

[0955] 5. AI Algorithms

[0956] Processing flow

[0957] First, the user takes a photo of their clothes using a smartphone or PC, and the image is uploaded to the server via a dedicated application.

[0958] Image analysis of hand-held clothing

[0959] The server analyzes the images of the clothes received from the user. This analysis uses the image processing libraries OpenCV and TensorFlow. Feature data such as the type, color, and pattern of the clothes are extracted from the images. The server also analyzes the texture and style of the fabric, and stores this data in a database for each user.

[0960] Receiving rental requirements

[0961] Users input their desired clothing rental style, season, and other criteria into the application, which is then sent to the server and compared with the data on their existing clothing.

[0962] Coordinate generation

[0963] The server uses the stored characteristic data of the user's clothes and the characteristic data of the rental clothes to generate the optimal outfit using an AI algorithm, which takes into account factors such as color compatibility, style matching, and seasonal suitability.

[0964] Coordination suggestions

[0965] The generated coordinates are sent to the user's terminal, where the user can check the proposed coordinates.

[0966] Emotion data analysis and storage

[0967] The user reacts to the proposed outfits with facial expressions and voice. This reaction is captured by the device's camera and microphone and analyzed by the emotion engine. The emotional data resulting from this analysis is then sent back to the server and stored in a database.

[0968] Reflecting feedback

[0969] The saved emotion data is reflected the next time an outfit is created, allowing the system to suggest more appropriate outfits based on the user's preferences and feedback.

[0970] Specific examples

[0971] For example, suppose a user uploads an image of a white T-shirt and requests to rent casual summer clothing. In this case, the server analyzes the feature data of the white T-shirt and suggests jeans shorts or cargo shorts as suitable rental clothing. If the user responds with a smile or a satisfied voice, that emotional data is saved as positive feedback. The next time outfit suggestions are made, this positive feedback will be reflected, and suggestions that better match the user's preferences will be made.

[0972] Prompt Sentence Examples

[0973] "To suggest the next outfit, please generate a casual summer outfit by analyzing an image of a white T-shirt and the user's emotional feedback. Please consider the compatibility between the user's existing clothes and the rental clothes, and emphasize matching colors and styles. Also, please prioritize reflecting the user's positive emotional feedback."

[0974] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0975] Processing Steps

[0976] Step 1:

[0977] Users take pictures of their clothes and upload them through the application.

[0978] Specific operation: The user takes a picture of their clothes using the smartphone camera and uploads the picture using the "Register clothes" function in the application.

[0979] Input: A photograph of the clothing.

[0980] Output: Uploaded clothes images are sent to the server.

[0981] Step 2:

[0982] The server analyzes the received image and extracts feature data.

[0983] How it works: The server uses OpenCV and TensorFlow to analyze the image and extract feature data such as clothing type, color, pattern, fabric texture, and style information.

[0984] Input: Uploaded clothing image.

[0985] Data processing: Image analysis is used to extract clothing characteristic data (type, color, pattern, texture, and style information).

[0986] Output: Extracted feature data.

[0987] Step 3:

[0988] The server stores the extracted feature data in a database.

[0989] Specific operation: The server associates the extracted feature data with the user ID and stores it in a database.

[0990] Input: extracted feature data, user ID.

[0991] Data processing: Associating feature data with user ID.

[0992] Output: Feature data stored in a database.

[0993] Step 4:

[0994] The user inputs the desired rental conditions and transmits them to the server.

[0995] Specific operation: The user enters the desired rental clothing requirements (style, season, etc.) through the application and sends them to the server.

[0996] Input: The rental requirements entered by the user.

[0997] Output: Rental preferences sent to the server.

[0998] Step 5:

[0999] The server compares the characteristic data of the clothes you own with the data of the rental clothes and generates the optimal outfit.

[1000] Specific operation: The server uses an AI algorithm to compare the stored characteristic data of the clothes you own with the characteristic data of the rental clothes and generate the optimal combination.

[1001] Input: Characteristic data of your clothes, desired rental conditions.

[1002] Data calculation: AI algorithms match and generate optimal coordinates.

[1003] Output: Optimal coordinates.

[1004] Step 6:

[1005] The generated coordinates are presented on the user terminal.

[1006] Specific operation: The server displays the generated coordinates on the user's device via push notification or email.

[1007] Input: Optimal coordinates.

[1008] Output: Coordinates displayed on the user's terminal.

[1009] Step 7:

[1010] Capture user responses and analyze emotional data.

[1011] Specific operation: The user checks the suggested outfit, and their facial expressions and voice are captured using the device's camera and microphone, which are then analyzed by the emotion engine.

[1012] Input: Captured facial expressions and voice.

[1013] Data computation: Emotion data analysis using emotion engines.

[1014] Output: Parsed emotion data.

[1015] Step 8:

[1016] The emotional data is stored in a database and reflected in the next coordination generation.

[1017] Specific operation: The server saves the analyzed emotion data in a database and reflects it the next time a coordinate is generated.

[1018] Input: Parsed emotion data.

[1019] Data processing: Emotion data is saved and reflected in the next coordinate generation.

[1020] Output: Emotion data stored in the database, next outfit suggestions.

[1021] 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.

[1022] 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.

[1023] 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.

[1024] [Third embodiment]

[1025] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1026] 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.

[1027] 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).

[1028] 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.

[1029] 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.

[1030] 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).

[1031] 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.

[1032] 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.

[1033] 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.

[1034] 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.

[1035] 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.

[1036] 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."

[1037] The system of the present invention provides coordinated outfits that efficiently combine the user's existing clothes with newly rented clothes. This system is composed of the following elements: a means for the user to upload images of the clothes, a means for performing image analysis on the server, a means for storing and managing the extracted feature data, a means for receiving the user's desired rental conditions and generating an optimal outfit, and a means for presenting the generated outfit to the user and providing the rental clothes.

[1038] User procedure flow

[1039] First, users use their smartphone or PC to take a photo of their clothes and upload it to the system. Once the upload is complete, users can enter the desired rental clothing criteria, such as "casual summer clothes."

[1040] Server Processing

[1041] Based on this, the server performs the following processing.

[1042] 1. Receiving and saving images

[1043] The server receives the images of the clothes uploaded by the user and temporarily stores them in a database.

[1044] 2. Image Analysis

[1045] The server runs an AI algorithm for image analysis to extract feature data such as the type of clothing (e.g., shirt, pants), color (e.g., white, black, red), and pattern (e.g., solid, striped), as well as fabric texture and style information (e.g., casual, formal).

[1046] 3. Saving feature data

[1047] The extracted feature data is associated with the user ID and stored in a database, creating a database of clothing for each user.

[1048] 4. Receiving and analyzing rental requirements

[1049] The server receives rental requirements specified by the user, including clothing category (e.g., shirt, dress), occasion (e.g., casual, formal), and season (e.g., summer, winter).

[1050] 5. Generating optimal coordination

[1051] The server compares the data on the customer's clothing with the data on rental clothing and uses AI to generate optimal outfit suggestions, taking into account criteria such as color compatibility, style matching, and seasonality.

[1052] 6. Coordination Presentation

[1053] The server presents the generated coordinates to the user and allows the user to select one. Notification methods include push notifications and emails.

[1054] Specific examples

[1055] For example, suppose a user uploads an image of a white T-shirt and requests a casual rental item suitable for summer wear. The server stores the characteristics of the white T-shirt and suggests the following outfits along with the desired rental conditions:

[1056] White T-shirt (own) + Jeans shorts (rental)

[1057] White T-shirt (own) + Cargo shorts (rental)

[1058] The user checks the suggested outfits, selects their favorite combination, and confirms the rental. The server receives this order and proceeds with the delivery of the rental clothes.

[1059] In this way, the system of the present invention can efficiently combine the user's existing clothes with newly rented clothes to provide optimal coordination, thereby expanding the user's fashion choices and greatly improving convenience.

[1060] The processing flow will be explained below.

[1061] Step 1:

[1062] Users use their smartphone or PC to take pictures of their own clothes and then upload the images using the "Register Owned Clothes" function within the application.

[1063] Step 2:

[1064] The server receives the uploaded images and temporarily stores them in a database.

[1065] Step 3:

[1066] The server runs an AI algorithm for image analysis to extract characteristic data such as the type of clothing (e.g., shirt, pants), color (e.g., white, black, red), and pattern (e.g., solid, striped), as well as fabric texture and style information (e.g., casual, formal).

[1067] Step 4:

[1068] The server associates the extracted feature data with the user ID and stores it in a database, thereby creating a clothing database for each user.

[1069] Step 5:

[1070] The user enters the rental requirements (e.g., casual summer clothing) into the application.

[1071] Step 6:

[1072] The server receives rental requirements from the user, including clothing category (e.g., shirt, dress), occasion (e.g., casual, formal), and season (e.g., summer, winter).

[1073] Step 7:

[1074] The server retrieves the user's clothing data from the database and runs an AI algorithm to compare it with the rental clothing database, thereby evaluating combinations of the user's clothing and potential rental items.

[1075] Step 8:

[1076] The server uses AI algorithms to generate optimal outfit suggestions, which include evaluations of color compatibility, style matching, and seasonal suitability.

[1077] Step 9:

[1078] The server generates a plurality of coordinate candidates and presents them to the user.

[1079] Step 10:

[1080] Using the terminal application, the user visually checks the presented coordination candidates and selects the combination they like.

[1081] Step 11:

[1082] Based on the outfit the user selects, they "add" the clothes to rent to their cart and finally confirm the rental order.

[1083] Step 12:

[1084] The server receives the user's order information and starts the delivery procedure for the rental clothes.

[1085] By using the above steps, the system of the present invention efficiently combines the clothes the user owns with the clothes to be rented, providing optimal coordination. Furthermore, by allowing the user to easily select clothes and complete the rental procedure, convenience is greatly improved.

[1086] Example 1

[1087] 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."

[1088] Conventional fashion coordination systems have made it difficult for users to effectively combine their existing clothes with newly rented clothes. Furthermore, they lacked a mechanism for automatically suggesting optimal outfits based on the user's existing clothes and desired rental conditions. This not only resulted in low convenience for users, but also made it difficult to achieve a highly satisfying outfit. Therefore, there is a demand for a system that allows users to enjoy coordinating outfits in a more efficient and satisfying way.

[1089] 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.

[1090] In this invention, the server

[1091] means for receiving an image of clothing taken by a user;

[1092] A means for extracting feature data such as type, color, and pattern of clothing from the received image;

[1093] A means for storing the extracted feature data in a database for each user;

[1094] means for receiving desired rental conditions specified by a user;

[1095] A means for generating an optimal outfit based on the stored feature data of the user's clothes and the feature data of the rental clothes;

[1096] means for presenting the generated coordinates to a user;

[1097] A means for providing rental clothing based on a user's selection;

[1098] means for notifying a user of the generated coordinates by a notification means;

[1099] This allows users to efficiently combine their own clothes with rental clothes to create the perfect outfit.

[1100] "User" refers to an individual who uses this system to coordinate their own clothing.

[1101] "Server" refers to a device that receives images uploaded by users, analyzes the images, stores the data, and generates and provides coordinates.

[1102] "Image" refers to visual data of clothing photographed by a user and stored in digital format.

[1103] "Feature data" refers to the type, color, pattern, and fabric texture and style information of clothing extracted from the received image.

[1104] "Database" refers to an information storage system for saving and managing clothing characteristic data for each user.

[1105] "Rental Desired Conditions" refers to the conditions such as the category, situation, and season of the clothing the user desires to rent.

[1106] "Coordination" refers to a fashion proposal that combines the user's own clothes with rental clothes.

[1107] "Notification means" refers to a method for notifying the user of the created coordination, and includes push notification and email.

[1108] This invention is a system that provides coordinated outfits that efficiently combine a user's existing clothes with newly rented clothes. This system includes the following elements: a means for the user to upload images of the clothes, a means for performing image analysis on a server, a means for storing and managing extracted feature data, a means for receiving the user's desired rental conditions and generating an optimal outfit, and a means for presenting the generated outfit to the user and providing the rental clothes.

[1109] First, the user uses their smartphone or PC (terminal) to take a picture of the clothes they own and upload it to the system. Specifically, the user takes a picture of the clothes using a camera app and uploads the image to the system through a dedicated web or mobile application. At that time, the user enters the conditions for the clothes they want to rent (for example, "casual summer clothes"). This process is carried out via an HTTP request.

[1110] The server receives the uploaded images and temporarily stores them in a database. The database used can be a relational database such as MySQL or PostgreSQL. The received image data is stored in a temporary storage folder, and image metadata (upload date and time, user ID, etc.) is also recorded in the database.

[1111] The server then runs an AI algorithm (such as TensorFlow or PyTorch) for image analysis to extract feature data such as clothing type (e.g., shirt, pants), color (e.g., white, black), pattern (e.g., solid, striped), fabric texture, and style information (e.g., casual, formal). This process provides specific information about the user's clothing.

[1112] The extracted feature data is associated with the user ID and stored in a database. This creates a clothing database for each user. Next, the server receives the rental requirements specified by the user (e.g. clothing category, occasion, season). The desired requirements are also received via an HTTP request.

[1113] The server uses this data to generate optimal outfit suggestions using an AI algorithm. Evaluation criteria include color compatibility, style matching, and seasonality. The generated outfit suggestions are displayed on the user's interface. Notifications are sent via push notifications and email.

[1114] As a concrete example, consider the case where a user uploads an image of a white T-shirt and requests casual rental clothing suitable for summer wear. For example, the server can save the characteristic data of the white T-shirt and compare it with the rental requirements to suggest the following outfits:

[1115] White T-shirt (own) + Jeans shorts (rental)

[1116] White T-shirt (own) + Cargo shorts (rental)

[1117] The user checks the suggested outfits and selects the combination they want. The server then receives the order and begins the process of shipping the rental clothes.

[1118] As described above, the system of the present invention can efficiently combine the user's existing clothes with newly rented clothes to provide optimal coordination, thereby expanding the range of fashion choices available to the user and greatly improving convenience.

[1119] Example prompt sentence:

[1120] "I'd like to upload an image of a white T-shirt to the system and request casual rental clothing for summer wear. I'd like you to suggest items that coordinate well with the shirts, pants, and other items I already have."

[1121] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1122] Step 1:

[1123] Upload an image and enter conditions

[1124] Users use their smartphones or PCs to take pictures of their clothes and upload them to the system. After this is complete, users enter the conditions for the clothes they want to rent (e.g., "casual summer clothes").

[1125] Input: Clothing image data, desired rental conditions

[1126] Output: Upload image data to the system, send rental requirements

[1127] Specific behavior:

[1128] Use the camera app to take a picture of the outfit.

[1129] Open your web browser or mobile app and log in.

[1130] Click the image upload button, select the image you have taken, and upload it.

[1131] Enter your desired rental conditions (e.g., "casual summer clothing") in the text box and submit.

[1132] Step 2:

[1133] Receiving and saving images

[1134] The server receives the images of the clothes uploaded by the user and temporarily stores them in a database.

[1135] Input: Image data sent by the user

[1136] Output: Image files saved in a temporary folder, metadata recorded in a database

[1137] Specific behavior:

[1138] The server receives the image data via an HTTP request.

[1139] The received image is saved in a temporary folder.

[1140] Record image metadata (upload date and time, user ID, etc.) in a database.

[1141] Step 3:

[1142] Feature extraction through image analysis

[1143] The server runs AI algorithms for image analysis to extract information about the type of clothing, color, pattern, and fabric texture and style.

[1144] Input: Saved image data

[1145] Output: Extracted feature data (type, color, pattern, texture, style information)

[1146] Specific behavior:

[1147] Calls an image analysis engine (such as TensorFlow) to process the uploaded image.

[1148] Analyze the type (shirt, pants, etc.), color (white, black, etc.), and pattern (solid, striped).

[1149] AI algorithm determines style (casual, formal).

[1150] Step 4:

[1151] Feature data storage

[1152] The server associates the extracted feature data with the user ID and stores it in a database.

[1153] Input: extracted feature data, user ID

[1154] Output: Feature data stored in a per-user clothing database

[1155] Specific behavior:

[1156] The extracted feature data is inserted into a database.

[1157] Link feature data with user ID.

[1158] Step 5:

[1159] Receiving rental requirements

[1160] The server receives the rental requirements entered by the user, including information such as clothing category, occasion, and season.

[1161] Input: Rental requirements submitted by the user

[1162] Output: The received rental requirements are stored on the server.

[1163] Specific behavior:

[1164] Receives form data from the user via an HTTP request.

[1165] The received data is analyzed, the user's desired conditions are identified, and the results are stored in a database.

[1166] Step 6:

[1167] Optimal coordination generation

[1168] The server compares data on existing clothing with rental clothing data and uses AI to generate optimal outfit suggestions.

[1169] Input: User's clothing characteristics, rental requirements

[1170] Output: A list of optimal outfit candidates

[1171] Specific behavior:

[1172] The user's clothing data is obtained from the database.

[1173] The clothes are compared with a database of rental clothing and evaluated using an AI algorithm.

[1174] Several coordination candidates are generated and their evaluation scores are calculated.

[1175] Step 7:

[1176] Coordination presentation and selection for users

[1177] The server presents the generated coordinates to the user, allowing the user to make a selection.

[1178] Input: Best coordinate candidates

[1179] Output: Coordination candidates presented to the user, and the user's choice

[1180] Specific behavior:

[1181] Coordination candidates are displayed on the user interface.

[1182] Notify users via push notification or email.

[1183] The user clicks the select button to confirm the coordinates.

[1184] Step 8:

[1185] Rental clothing shipping procedures

[1186] The server then processes the delivery of the rental clothing coordinated by the user, and if necessary, shares the shipping information with the delivery company.

[1187] Input: Rental clothing selected by the user

[1188] Output: Rental clothing shipping instructions, delivery notification to user

[1189] Specific behavior:

[1190] Check the availability of the selected rental clothing.

[1191] Get the user's shipping information and generate a shipping label.

[1192] Information is shared with departments and services responsible for delivery procedures.

[1193] (Application example 1)

[1194] 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."

[1195] Conventional coordination systems have the problem that it is difficult for users to efficiently combine their existing clothes with the clothes available in stores when they visit a physical store. Furthermore, they do not provide sufficient support for users to select clothes in the store using a smartphone or smart glasses, and lack functionality to improve the shopping experience in physical stores.

[1196] 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.

[1197] In this invention, the server includes means for receiving images of clothes photographed by a user, means for extracting characteristic data such as the type, color, and pattern of the clothes from the received images, means for storing the extracted characteristic data in a database for each user, means for receiving desired rental conditions specified by the user, means for generating an optimal outfit based on the stored characteristic data of the user's clothes and the characteristic data of rental clothes, means for using a smartphone, smart glasses, or interactive kiosk to present the optimal outfit to the user in the store, and means for providing rental or sales clothes based on the user's selection. This allows users to easily find an optimal outfit that efficiently combines clothes they own with clothes in the store in a physical store.

[1198] A "user" is an individual who uses the system to coordinate and rent clothes.

[1199] "Photographing" refers to the act of capturing an image of clothing using a device such as a smartphone or smart glasses.

[1200] "Clothing images" are photographic data of clothes taken by the user.

[1201] The "receiving means" is a function that allows the server to receive image data of clothes sent by the user.

[1202] "Clothing type" is a clothing category such as shirts, pants, dresses, etc.

[1203] "Color" refers to the specific color information that clothing possesses.

[1204] A "pattern" is a design or figure found in clothing designs.

[1205] "Feature data" is specific information such as the type, color, and pattern of clothing extracted through image analysis.

[1206] The "database" is a digital information management system for storing extracted feature data for each user.

[1207] "Rental requirements" are requirements such as a specific clothing category or style specified by the user.

[1208] "Rental clothing" refers to clothing that is available for rental to users.

[1209] The "optimal coordination" refers to the combination of the user's own clothes with rental or sales clothes that best harmonizes in terms of color, style, etc.

[1210] "In-store" refers to the interior space of the actual store that the user visits.

[1211] A "smartphone" is a mobile phone with internet connectivity and the ability to run advanced applications.

[1212] "Smart glasses" are wearable devices that have the shape of regular glasses but can display information and perform other functions.

[1213] An "interactive kiosk" is a device that allows users to obtain information and perform operations using an operable display device such as a touch panel.

[1214] "Sales clothing" refers to clothing sold to users in a store.

[1215] The following describes the system configuration and operation procedure as an embodiment of the present invention. The system includes a server that receives and analyzes images of clothes taken by a user, a smartphone, smart glasses, and an interactive kiosk that present optimal outfits to the user.

[1216] System Configuration

[1217] 1. Server:

[1218] Image receiving function: Receives images of clothes uploaded by users.

[1219] Image analysis function: Uses libraries such as TensorFlow and OpenCV to extract feature data such as clothing type, color, and pattern from images.

[1220] Database management: The extracted feature data is stored in a database for each user.

[1221] Recommendation engine: Generates optimal coordination based on the user's desired rental conditions.

[1222] 2. User Device:

[1223] Smartphone: Used to take and upload images and check outfits.

[1224] Smart glasses: Used by users to check the best outfits in real time while walking around the store.

[1225] Interactive Kiosk: Enables in-store operation for suggesting and selecting outfits.

[1226] Program processing

[1227] 1. Image reception:

[1228] The server receives the images of the clothes sent from the user's device and temporarily stores them in a database, using a high-speed Internet connection to send and receive the images.

[1229] 2. Image Analysis:

[1230] The received images are analyzed on the server using TensorFlow and OpenCV to extract information such as the type of clothing (e.g., shirt, pants), color (e.g., white, black, red), pattern (e.g., solid, striped), texture, and style information.

[1231] 3. Save feature data:

[1232] The extracted feature data is associated with the user ID and stored in a database, which creates a clothing database for each user and is used to suggest future outfits.

[1233] 4. Coordinate generation:

[1234] After the user enters their desired rental requirements, the server compares the stored data of clothing on hand with the data of clothing candidates for rental and generates the optimal outfit using an AI algorithm (e.g., cosine similarity calculation).

[1235] 5. Proposal and Selection:

[1236] The optimal outfits are presented to the user via a smartphone, smart glasses, or interactive kiosk, and the process of providing rental or sales clothes based on the outfits selected by the user proceeds.

[1237] Specific examples

[1238] User behavior example:

[1239] A user takes a photo of a white T-shirt with their smartphone and uploads it to the system. They then enter their desired casual summer clothing rental requirements. Based on this information, the server recommends jeans shorts that go perfectly with the white T-shirt. The user can instantly view the jeans shorts while walking around the store through the smart glasses.

[1240] Example prompt sentence:

[1241] prompt:

[1242] User ID: example_user_01

[1243] Clothing characteristics: White T-shirt, casual, summer

[1244] In-store clothing data: Jeans shorts, casual, summer

[1245] How to use generative AI models:

[1246] 1. Input the feature data of the user's white T-shirt into the AI.

[1247] 2. Compare with the characteristic data of jean shorts in stock at the store.

[1248] 3. Optimal coordination is suggested using cosine similarity.

[1249] Example response:

[1250] Select a pair of jean shorts that match the color of the user's T-shirt.

[1251] Selection results:

[1252] White T-shirt + Jean shorts

[1253] In this way, a system is provided that enables a user to easily find an optimal outfit that efficiently combines clothes that the user owns with clothes in the store in a real store.

[1254] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1255] Step 1:

[1256] The user uploads a photo of the clothes they have taken. The information entered here is the user ID and the image file of the clothes. The uploaded image data is sent from the device to the server.

[1257] Step 2:

[1258] The image received by the server is temporarily stored in a database. The output of this process is the completion of saving the uploaded image data. Specifically, the image received by the server is saved in a specified directory and linked to the corresponding user ID.

[1259] Step 3:

[1260] The server retrieves the stored image data and performs image analysis. The input is the image data stored in the database. TensorFlow and OpenCV are used for the analysis to extract feature data such as the type of clothing, color, pattern, fabric texture, and style information. The output of this process is the extracted feature data. Specifically, an AI model is executed to extract clothing features from the image.

[1261] Step 4:

[1262] The extracted feature data is saved in a database for each user. The input is the feature data extracted in step 3 and the user ID. The output of this process is a database with updated feature data for each user. Specifically, the feature data is associated with the user ID and inserted into the database.

[1263] Step 5:

[1264] The user inputs the desired rental conditions, such as clothing category, occasion, season, etc. The desired rental conditions are sent from the terminal to the server.

[1265] Step 6:

[1266] The server compares the stored data of clothing items on hand with the data of clothing items that can be rented based on the desired rental conditions. The inputs are the desired rental conditions, the user's characteristic data, and the data of the clothing items that can be rented. An optimal outfit is generated using an AI algorithm (e.g., cosine similarity calculation). The output of this process is the optimal outfit candidate. Specifically, an AI model is executed to find the optimal combination.

[1267] Step 7:

[1268] The optimal outfit is presented to the user. The input is the outfit candidates generated in step 6. The output is outfit information displayed on the user's smartphone, smart glasses, or interactive kiosk. Specifically, the outfit information is displayed via push notification or within the application.

[1269] Step 8:

[1270] The user selects a suggested outfit. The input information is the outfit selected by the user. The selection information is sent from the terminal to the server.

[1271] Step 9:

[1272] Based on the selection, the system carries out procedures to provide the clothes for rental or sale. The input is the outfit and rental conditions selected by the user. The output of this process is the delivery of the rental clothes or the completion of the sales procedure. Specifically, delivery arrangements and purchase procedures are automatically carried out by the server.

[1273] 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.

[1274] The system of the present invention provides coordinated outfits that efficiently combine the user's existing clothes with newly rented clothes, and by combining it with an emotion engine that recognizes the user's emotions, it realizes more personalized suggestions. The details of the system are described below.

[1275] User procedure flow

[1276] Users take pictures of their clothes using their smartphones or PCs and upload them using the app's "Register Your Own Clothes" function. Once the upload is complete, users can enter the desired rental clothing specifications (e.g., casual summer clothes).

[1277] Server Processing

[1278] Based on this, the server performs the following processing.

[1279] Receiving and saving images

[1280] The server receives the images of the clothes uploaded by the user and temporarily stores them in a database.

[1281] Image analysis

[1282] The server runs an AI algorithm for image analysis to extract characteristic data such as the type of clothing (e.g., shirt, pants), color (e.g., white, black, red), and pattern (e.g., solid, striped), as well as the texture of the fabric and style information (e.g., casual, formal).

[1283] Feature data storage

[1284] The server associates the extracted feature data with the user ID and stores it in a database, thereby creating a clothing database for each user.

[1285] Receiving and analyzing rental requirements

[1286] Once customers input their desired rental requirements, the server receives them and runs an AI algorithm to match their existing clothing data with the rental clothing data, using criteria such as color compatibility, style matching, and seasonal suitability.

[1287] Coordinate generation and presentation

[1288] The server generates optimal outfit suggestions and presents multiple options to the user. The outfit suggestions are displayed in the device's application via push notification or email.

[1289] Incorporating an emotion engine

[1290] Furthermore, the system incorporates an emotion engine to perform the following processes:

[1291] Emotion Recognition and Analysis

[1292] The device captures the user's facial expressions and voice in response to the presented outfit, and the emotion engine analyzes them to collect the user's emotional data. The emotion engine then sends the analysis results to the server.

[1293] Saving and reflecting emotional data

[1294] The server stores the emotion data in a database and reflects this data the next time a coordinated outfit is generated, suggesting a more appropriate outfit based on the user's preferences and feedback.

[1295] Specific examples

[1296] For example, suppose a user uploads an image of a white T-shirt and requests a casual rental item suitable for summer wear. In this case, the server saves the characteristics of the white T-shirt and suggests the following outfits along with the desired rental conditions:

[1297] White T-shirt (own) + Jeans shorts (rental)

[1298] White T-shirt (own) + Cargo shorts (rental)

[1299] The user reviews the suggested outfit, and the emotion engine analyzes the user's preferences from their facial expressions and tone of voice. For example, if the user smiles or sounds satisfied, this is saved as positive feedback. The next time the system suggests an outfit, this positive feedback will be reflected, making the suggestion more in line with the user's preferences.

[1300] In this way, the system of the present invention can efficiently combine the user's existing clothes with new clothes to rent, and further make suggestions that take the user's emotions into consideration, thereby expanding the range of fashion choices available to the user and greatly improving convenience.

[1301] The processing flow will be explained below.

[1302] Step 1:

[1303] Users use their smartphone or PC to take pictures of their clothes and then upload the images using the "Register clothes you own" function within the application.

[1304] Step 2:

[1305] The server receives the uploaded images and temporarily stores them in a database.

[1306] Step 3:

[1307] The server runs an AI algorithm for image analysis to extract characteristic data such as the type of clothing (shirt, pants, etc.), color (white, black, red, etc.), and pattern (solid, striped, etc.), as well as the texture of the fabric and style information (casual, formal, etc.).

[1308] Step 4:

[1309] The server associates the extracted feature data with the user ID and stores it in a database, thereby creating a clothing database for each user.

[1310] Step 5:

[1311] The user enters the rental requirements (e.g., casual summer clothing) into the application.

[1312] Step 6:

[1313] The server receives rental requirements from the user, including clothing category (e.g., shirt, dress), occasion (e.g., casual, formal), and season (e.g., summer, winter).

[1314] Step 7:

[1315] The server retrieves the user's clothing data from the database and runs an AI algorithm to compare it with the rental clothing database, thereby evaluating combinations of the user's clothing and potential rental items.

[1316] Step 8:

[1317] The server uses AI algorithms to generate optimal outfit suggestions, which include evaluations of color compatibility, style matching, and seasonal suitability.

[1318] Step 9:

[1319] The server generates a plurality of coordinate candidates and presents them to the user.

[1320] Step 10:

[1321] Using the terminal application, the user visually checks the presented coordination candidates and selects the combination they like.

[1322] Step 11:

[1323] The device captures the user's facial expressions and voice, and the emotion engine analyzes the data to collect the user's emotional data.

[1324] Step 12:

[1325] The server receives the analysis results from the emotion engine and stores them in a database.

[1326] Step 13:

[1327] Based on the outfit the user selects, they "add" the clothes to rent to their cart and finally confirm the rental order.

[1328] Step 14:

[1329] The server receives the user's order information and starts the delivery procedure for the rental clothes.

[1330] Step 15:

[1331] From the next time onwards, the server will adjust the evaluation criteria of the AI ​​algorithm based on the collected emotional data and suggest outfits that better match the user's preferences. For example, if positive feedback is received from a smile or a satisfied voice, similar outfits will be suggested based on that information.

[1332] Through the above steps, the system of the present invention can efficiently combine the user's existing clothes with new rental clothes, and further make suggestions that take the user's emotions into consideration, thereby expanding the range of fashion choices available to the user and greatly improving convenience.

[1333] Example 2

[1334] 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."

[1335] In conventional fashion coordination systems, it is difficult for users to efficiently combine clothes they own with newly rented clothes, and they also have the problem of not being able to provide suggestions that fully take into account the user's preferences and emotions. The present invention aims to solve these problems and provide appropriate fashion coordination that is personalized for the user.

[1336] 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.

[1337] In this invention, the server includes means for receiving images of clothes photographed by a user, means for extracting characteristic data such as the type, color, and pattern of the clothes from the received images, means for saving the extracted characteristic data in a database for each user, means for receiving desired rental conditions specified by the user, means for generating an optimal outfit based on the saved characteristic data of the user's clothes and the characteristic data of rental clothes, means for presenting the generated outfit to the user, means for providing rental clothes based on the user's selection, means for capturing the user's facial expressions and voice and analyzing emotional data, and means for saving the analyzed emotional data in a database and reflecting it when generating the next outfit. This makes it possible to efficiently combine the user's own clothes with new rental clothes and to make more personalized suggestions that reflect the user's emotions and preferences.

[1338] A "user" is someone who wishes to coordinate or rent clothes using this system.

[1339] "Means for receiving images of clothes in hand" refers to the function that allows users to upload images of clothes taken with their smartphone or PC to the server.

[1340] "Feature data" refers to data about clothing characteristics extracted through image analysis, such as type of clothing, color, pattern, fabric texture, and style information.

[1341] A "database" is an information accumulation system for storing extracted feature data, user information, emotional data, etc.

[1342] "Desired rental conditions" refers to information that allows a user to specify the conditions for the clothes they wish to rent (for example, casual summer clothes).

[1343] "Coordination" means suggesting styling by combining clothes you already own with rented clothes.

[1344] An "artificial intelligence model" is an algorithm or machine learning model used to evaluate the compatibility of clothing.

[1345] "Emotion data" refers to data related to emotions obtained by analyzing the user's facial expressions and voice.

[1346] "Means for analyzing" refers to technology for processing a user's emotional data in real time and determining the type and degree of emotion.

[1347] The "server" is a central computer system that stores and processes user data, image analysis, coordinate generation, and emotion data.

[1348] A "terminal" refers to a device such as a smartphone or PC operated by a user.

[1349] "Capture" refers to capturing the user's facial expressions and voice through a camera or microphone.

[1350] "Means for reflecting the next coordinated outfit when generating the next coordinated outfit" refers to a function for taking the user's preferences and emotions into consideration when proposing the next coordinated outfit based on the saved emotion data.

[1351] The system of the present invention provides coordinated outfits that efficiently combine the user's existing clothes with newly rented clothes, and by combining it with an emotion engine that recognizes the user's emotions, it realizes more personalized suggestions. Detailed embodiments of this system are described below.

[1352] System configuration

[1353] This system consists of the following main components:

[1354] 1. Server

[1355] 2. Terminal

[1356] 3. Database

[1357] 4. Emotion Engine

[1358] Hardware and software used

[1359] The server plays a central role in image analysis, data storage, and coordinate generation. Specifically, it uses the following software and services:

[1360] Image analysis uses Google Cloud Vision API and Amazon Rekognition.

[1361] Amazon RDS and MySQL are used as databases.

[1362] Coordination generation uses machine learning libraries such as TensorFlow and PyTorch.

[1363] The terminals are devices operated by users, such as smartphones and PCs, that take and upload images and capture emotions.

[1364] The emotion engine is a component that captures and analyzes the user's facial expressions and voice, specifically using Microsoft Azure's Face API and IBM Watson's Tone Analyzer.

[1365] System operation procedures

[1366] The system operation procedure will be explained below with specific examples.

[1367] 1. User uploads clothing images

[1368] Users can take pictures of their clothes using their smartphones or PCs and upload them using the application's "Register clothes" function by selecting the image file and clicking the upload button.

[1369] 2. Receiving and saving images

[1370] The server receives image files uploaded by users and temporarily stores the image data in cloud storage such as Amazon S3.

[1371] 3. Image Analysis

[1372] The server uses the Google Cloud Vision API to analyze the images and extract information about the type, color, pattern, texture, and style of the clothing, thereby obtaining feature data such as the type of shirt or pants, color (white or black), and pattern (solid or striped).

[1373] 4. Saving feature data

[1374] The server associates the extracted feature data with the user ID and stores it in Amazon RDS. The stored data includes the clothing ID, type, color, pattern, texture, style, etc.

[1375] 5. Enter your desired rental conditions

[1376] The user enters the desired rental clothing requirements (e.g., casual summer clothing) into a form within the application and submits it.

[1377] 6. Analysis of desired rental conditions

[1378] The server receives the user's desired rental conditions via an HTTP POST request, compares them with the user's clothing data, and selects the most suitable rental clothing.

[1379] 7. Coordinate Generation

[1380] The server generates combination candidates for clothes that you own and rent, and creates the most suitable outfit that meets your requirements.

[1381] 8. Coordination Presentation

[1382] The server presents the generated outfit suggestions to the user via push notification or email, and the user can check the outfits within the application.

[1383] 9. Capturing Emotions

[1384] The device captures the user's facial expressions and voice using a camera and microphone and analyzes them in real time. For example, if the user smiles or sounds satisfied, this is analyzed by the emotion engine as positive feedback and the results are sent to the server.

[1385] 10. Saving and Reflecting Emotional Data

[1386] The server stores the emotion data in a database and reflects it in the next outfit suggestions, thereby learning the user's preferences and realizing more personalized outfit suggestions.

[1387] Examples of specific examples and prompts

[1388] For example, if a user uploads an image of a white T-shirt and requests "casual rental clothing suitable for summer," the server will save the characteristics of the white T-shirt, compare them with the rental requirements, and suggest the following outfits:

[1389] White T-shirt (own) + Jeans shorts (rental)

[1390] White T-shirt (own) + Cargo shorts (rental)

[1391] Based on this suggestion, the user checks the suggested outfit, and the emotion engine analyzes their preferences from their facial expressions and tone of voice. If they smile or sound satisfied, this is saved as positive feedback and will be reflected in the next suggestion. An example of a prompt is, "Please suggest some casual summer clothes to wear on my next trip. I'd like to combine it with a white T-shirt I have."

[1392] The above is a detailed embodiment of the system of the present invention, which allows users to efficiently combine existing clothes with new rental clothes and receive personalized suggestions that take emotions into account.

[1393] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1394] Processing step details

[1395] Step 1:

[1396] Users upload images of their clothing.

[1397] Specifically, the user takes a photo of the clothes with their smartphone or PC, selects the image file using the "Register clothes in stock" function in the application, and clicks the upload button. The input for this process is the image file selected by the user, and the output is a notification that the image file has been uploaded.

[1398] Step 2:

[1399] The server receives and stores the images.

[1400] Specifically, the server receives image data of the clothes in hand via an HTTP POST request and temporarily stores it in cloud storage (e.g., Amazon S3). The input of this process is the uploaded image file, and the output is the URL of the image stored in the storage.

[1401] Step 3:

[1402] The server performs the image analysis.

[1403] Specifically, the server calls the Google Cloud Vision API and analyzes the received image. At this time, it extracts the type of clothing (e.g., shirt, pants), color, pattern (e.g., solid, striped), fabric texture, and style information (e.g., casual, formal). The input for this process is the image URL from storage, and the output is feature data (type, color, pattern, texture, style).

[1404] Step 4:

[1405] The server stores the feature data.

[1406] Specifically, the server associates the extracted feature data with the user ID and stores it in a database (e.g., Amazon RDS). The input to this process is the feature data and the user ID, and the output is the record ID stored in the database.

[1407] Step 5:

[1408] The user inputs the desired rental conditions.

[1409] Specifically, the user enters the desired rental clothing requirements (e.g., casual summer clothing) into a form within the application and clicks the submit button. The input for this process is the text data of the desired rental requirements entered by the user, and the output is a notification that the requirements have been submitted.

[1410] Step 6:

[1411] The server receives and analyzes the rental request conditions.

[1412] Specifically, the server receives the desired rental conditions via an HTTP POST request and executes an AI model to evaluate the optimal combination of the desired rental clothing with the clothes the customer owns based on the conditions. The input to this process is the text data of the desired rental conditions, and the output is pairing candidate data.

[1413] Step 7:

[1414] The server generates the coordinates.

[1415] Specifically, the server generates candidate combinations of clothing items owned and rented, and creates the most suitable outfit for the given conditions. Evaluation criteria include color compatibility, style matching, and seasonal suitability. The input to this process is pairing candidate data and evaluation criteria data, and the output is a list of outfit candidates.

[1416] Step 8:

[1417] The server presents the coordinates to the user.

[1418] Specifically, the server presents the coordinated outfit candidates it has generated to the user. The presentation method is push notification or email, and the user can check the outfits within the application. The input for this process is a list of coordinated outfit candidates, and the output is a notification that the presentation has been completed.

[1419] Step 9:

[1420] The device captures the user's emotions.

[1421] Specifically, when a user checks their outfit, the device's camera captures their facial expression in real time and records their voice with a microphone. The input to this process is the user's facial expression image and voice data, and the output is the captured emotional data.

[1422] Step 10:

[1423] The device transmits the emotion data to the server.

[1424] Specifically, the device sends the captured emotion data to the server via an HTTP POST request. The input of this process is the emotion data, and the output is a notification that the data has been sent.

[1425] Step 11:

[1426] The server stores and reflects the emotional data.

[1427] Specifically, the server stores the received emotion data in a database, and the next time it proposes a coordinated outfit, it reflects the user's preferences based on this data. The input for this process is the emotion data and the user ID, and the output is the record ID stored in the database.

[1428] The above are the specific processing steps of this system.

[1429] (Application example 2)

[1430] 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."

[1431] In today's clothing rental services, it is difficult for users to efficiently combine their existing clothes with newly rented clothes. It is also difficult to reflect the user's emotions and preferences in the actual outfit suggestions. This makes it difficult to provide optimal outfit suggestions for the user, potentially reducing satisfaction. While conventional technologies have partially achieved evaluation of clothing characteristics and appropriate combinations, they have yet to achieve personalized outfit suggestions that take the user's emotions into account. Technology to solve these issues is needed.

[1432] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving images of clothes photographed by the user, means for extracting feature data such as the type, color, and pattern of the clothes from the received images, means for saving the extracted feature data in a database for each user, means for receiving desired rental conditions specified by the user, means for generating an optimal outfit based on the saved feature data of the user's clothes and the feature data of rental clothes, means for presenting the generated outfit to the user, means for providing rental clothes based on the user's selection, means for recognizing and analyzing the user's emotions, and means for saving the analyzed emotion data in a database and reflecting it when generating the next outfit. This makes it possible to propose personalized outfits that reflect the user's emotions and preferences.

[1433] definition statement

[1434] "User" means an individual or legal entity that uses the Service.

[1435] "Clothing images" are digital images of clothing owned by the user.

[1436] "Emotion data" is data relating to emotions analyzed from the user's facial expressions and voice.

[1437] "Feature data" is information such as the type, color, and pattern of clothing extracted through image analysis.

[1438] "Rental Desired Conditions" refers to conditions such as the style and season of the clothing desired by the user.

[1439] "Coordination" is a styling suggestion that combines clothes you already own with rented clothes.

[1440] The "emotion engine" is a system that analyzes the user's facial expressions and voice to generate emotional data.

[1441] The "database" is a system for storing data on the characteristics and emotions of users' clothing.

[1442] An "AI algorithm" is a method that uses artificial intelligence to analyze data and generate optimal coordination.

[1443] "Owned clothes" refers to clothes that the user already owns.

[1444] "Rental clothing" refers to clothing that a user wishes to rent.

[1445] MODE FOR CARRYING OUT THE INVENTION

[1446] This invention is a system that uses images of clothes owned by a user to suggest optimal outfits for rental clothes, and further reflects the user's emotional data to provide more personalized outfits. This section describes specific methods for implementing the invention.

[1447] System Configuration

[1448] The system mainly consists of the following components:

[1449] 1. User device (smartphone, PC, etc.)

[1450] 2. Server

[1451] 3. Database

[1452] 4. Emotion Engine

[1453] 5. AI Algorithms

[1454] Processing flow

[1455] First, the user takes a photo of their clothes using a smartphone or PC, and the image is uploaded to the server via a dedicated application.

[1456] Image analysis of hand-held clothing

[1457] The server analyzes the images of the clothes received from the user. This analysis uses the image processing libraries OpenCV and TensorFlow. Feature data such as the type, color, and pattern of the clothes are extracted from the images. The server also analyzes the texture and style of the fabric, and stores this data in a database for each user.

[1458] Receiving rental requirements

[1459] Users input their desired clothing rental style, season, and other criteria into the application, which is then sent to the server and compared with the data on their existing clothing.

[1460] Coordinate generation

[1461] The server uses the stored characteristic data of the user's clothes and the characteristic data of the rental clothes to generate the optimal outfit using an AI algorithm, which takes into account factors such as color compatibility, style matching, and seasonal suitability.

[1462] Coordination suggestions

[1463] The generated coordinates are sent to the user's terminal, where the user can check the proposed coordinates.

[1464] Emotion data analysis and storage

[1465] The user reacts to the proposed outfits with facial expressions and voice. This reaction is captured by the device's camera and microphone and analyzed by the emotion engine. The emotional data resulting from this analysis is then sent back to the server and stored in a database.

[1466] Reflecting feedback

[1467] The saved emotion data is reflected the next time an outfit is created, allowing the system to suggest more appropriate outfits based on the user's preferences and feedback.

[1468] Specific examples

[1469] For example, suppose a user uploads an image of a white T-shirt and requests to rent casual summer clothing. In this case, the server analyzes the feature data of the white T-shirt and suggests jeans shorts or cargo shorts as suitable rental clothing. If the user responds with a smile or a satisfied voice, that emotional data is saved as positive feedback. The next time outfit suggestions are made, this positive feedback will be reflected, and suggestions that better match the user's preferences will be made.

[1470] Prompt Sentence Examples

[1471] "To suggest the next outfit, please generate a casual summer outfit by analyzing an image of a white T-shirt and the user's emotional feedback. Please consider the compatibility between the user's existing clothes and the rental clothes, and emphasize matching colors and styles. Also, please prioritize reflecting the user's positive emotional feedback."

[1472] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1473] Processing Steps

[1474] Step 1:

[1475] Users take pictures of their clothes and upload them through the application.

[1476] Specific operation: The user takes a picture of their clothes using the smartphone camera and uploads the picture using the "Register clothes" function in the application.

[1477] Input: A photograph of the clothing.

[1478] Output: Uploaded clothes images are sent to the server.

[1479] Step 2:

[1480] The server analyzes the received image and extracts feature data.

[1481] How it works: The server uses OpenCV and TensorFlow to analyze the image and extract feature data such as clothing type, color, pattern, fabric texture, and style information.

[1482] Input: Uploaded clothing image.

[1483] Data processing: Image analysis is used to extract clothing characteristic data (type, color, pattern, texture, and style information).

[1484] Output: Extracted feature data.

[1485] Step 3:

[1486] The server stores the extracted feature data in a database.

[1487] Specific operation: The server associates the extracted feature data with the user ID and stores it in a database.

[1488] Input: extracted feature data, user ID.

[1489] Data processing: Associating feature data with user ID.

[1490] Output: Feature data stored in a database.

[1491] Step 4:

[1492] The user inputs the desired rental conditions and transmits them to the server.

[1493] Specific operation: The user enters the desired rental clothing requirements (style, season, etc.) through the application and sends them to the server.

[1494] Input: The rental requirements entered by the user.

[1495] Output: Rental preferences sent to the server.

[1496] Step 5:

[1497] The server compares the characteristic data of the clothes you own with the data of the rental clothes and generates the optimal outfit.

[1498] Specific operation: The server uses an AI algorithm to compare the stored characteristic data of the clothes you own with the characteristic data of the rental clothes and generate the optimal combination.

[1499] Input: Characteristic data of your clothes, desired rental conditions.

[1500] Data calculation: AI algorithms match and generate optimal coordinates.

[1501] Output: Optimal coordinates.

[1502] Step 6:

[1503] The generated coordinates are presented on the user terminal.

[1504] Specific operation: The server displays the generated coordinates on the user's device via push notification or email.

[1505] Input: Optimal coordinates.

[1506] Output: Coordinates displayed on the user's terminal.

[1507] Step 7:

[1508] Capture user responses and analyze emotional data.

[1509] Specific operation: The user checks the suggested outfit, and their facial expressions and voice are captured using the device's camera and microphone, which are then analyzed by the emotion engine.

[1510] Input: Captured facial expressions and voice.

[1511] Data computation: Emotion data analysis using emotion engines.

[1512] Output: Parsed emotion data.

[1513] Step 8:

[1514] The emotional data is stored in a database and reflected in the next coordination generation.

[1515] Specific operation: The server saves the analyzed emotion data in a database and reflects it the next time a coordinate is generated.

[1516] Input: Parsed emotion data.

[1517] Data processing: Emotion data is saved and reflected in the next coordinate generation.

[1518] Output: Emotion data stored in the database, next outfit suggestions.

[1519] 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.

[1520] 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.

[1521] 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.

[1522] [Fourth embodiment]

[1523] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1524] 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.

[1525] 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).

[1526] 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.

[1527] 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.

[1528] 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).

[1529] 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.

[1530] 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.

[1531] 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.

[1532] 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.

[1533] 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.

[1534] 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.

[1535] 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."

[1536] The system of the present invention provides coordinated outfits that efficiently combine the user's existing clothes with newly rented clothes. This system is composed of the following elements: a means for the user to upload images of the clothes, a means for performing image analysis on the server, a means for storing and managing the extracted feature data, a means for receiving the user's desired rental conditions and generating an optimal outfit, and a means for presenting the generated outfit to the user and providing the rental clothes.

[1537] User procedure flow

[1538] First, users use their smartphone or PC to take a photo of their clothes and upload it to the system. Once the upload is complete, users can enter the desired rental clothing criteria, such as "casual summer clothes."

[1539] Server Processing

[1540] Based on this, the server performs the following processing.

[1541] 1. Receiving and saving images

[1542] The server receives the images of the clothes uploaded by the user and temporarily stores them in a database.

[1543] 2. Image Analysis

[1544] The server runs an AI algorithm for image analysis to extract feature data such as the type of clothing (e.g., shirt, pants), color (e.g., white, black, red), and pattern (e.g., solid, striped), as well as fabric texture and style information (e.g., casual, formal).

[1545] 3. Saving feature data

[1546] The extracted feature data is associated with the user ID and stored in a database, creating a database of clothing for each user.

[1547] 4. Receiving and analyzing rental requirements

[1548] The server receives rental requirements specified by the user, including clothing category (e.g., shirt, dress), occasion (e.g., casual, formal), and season (e.g., summer, winter).

[1549] 5. Generating optimal coordination

[1550] The server compares the data on the customer's clothing with the data on rental clothing and uses AI to generate optimal outfit suggestions, taking into account criteria such as color compatibility, style matching, and seasonality.

[1551] 6. Coordination Presentation

[1552] The server presents the generated coordinates to the user and allows the user to select one. Notification methods include push notifications and emails.

[1553] Specific examples

[1554] For example, suppose a user uploads an image of a white T-shirt and requests a casual rental item suitable for summer wear. The server stores the characteristics of the white T-shirt and suggests the following outfits along with the desired rental conditions:

[1555] White T-shirt (own) + Jeans shorts (rental)

[1556] White T-shirt (own) + Cargo shorts (rental)

[1557] The user checks the suggested outfits, selects their favorite combination, and confirms the rental. The server receives this order and proceeds with the delivery of the rental clothes.

[1558] In this way, the system of the present invention can efficiently combine the user's existing clothes with newly rented clothes to provide optimal coordination, thereby expanding the user's fashion choices and greatly improving convenience.

[1559] The processing flow will be explained below.

[1560] Step 1:

[1561] Users use their smartphone or PC to take pictures of their own clothes and then upload the images using the "Register Owned Clothes" function within the application.

[1562] Step 2:

[1563] The server receives the uploaded images and temporarily stores them in a database.

[1564] Step 3:

[1565] The server runs an AI algorithm for image analysis to extract characteristic data such as the type of clothing (e.g., shirt, pants), color (e.g., white, black, red), and pattern (e.g., solid, striped), as well as fabric texture and style information (e.g., casual, formal).

[1566] Step 4:

[1567] The server associates the extracted feature data with the user ID and stores it in a database, thereby creating a clothing database for each user.

[1568] Step 5:

[1569] The user enters the rental requirements (e.g., casual summer clothing) into the application.

[1570] Step 6:

[1571] The server receives rental requirements from the user, including clothing category (e.g., shirt, dress), occasion (e.g., casual, formal), and season (e.g., summer, winter).

[1572] Step 7:

[1573] The server retrieves the user's clothing data from the database and runs an AI algorithm to compare it with the rental clothing database, thereby evaluating combinations of the user's clothing and potential rental items.

[1574] Step 8:

[1575] The server uses AI algorithms to generate optimal outfit suggestions, which include evaluations of color compatibility, style matching, and seasonal suitability.

[1576] Step 9:

[1577] The server generates a plurality of coordinate candidates and presents them to the user.

[1578] Step 10:

[1579] Using the terminal application, the user visually checks the presented coordination candidates and selects the combination they like.

[1580] Step 11:

[1581] Based on the outfit the user selects, they "add" the clothes to rent to their cart and finally confirm the rental order.

[1582] Step 12:

[1583] The server receives the user's order information and starts the delivery procedure for the rental clothes.

[1584] By using the above steps, the system of the present invention efficiently combines the clothes the user owns with the clothes to be rented, providing optimal coordination. Furthermore, by allowing the user to easily select clothes and complete the rental procedure, convenience is greatly improved.

[1585] Example 1

[1586] 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."

[1587] Conventional fashion coordination systems have made it difficult for users to effectively combine their existing clothes with newly rented clothes. Furthermore, they lacked a mechanism for automatically suggesting optimal outfits based on the user's existing clothes and desired rental conditions. This not only resulted in low convenience for users, but also made it difficult to achieve a highly satisfying outfit. Therefore, there is a demand for a system that allows users to enjoy coordinating outfits in a more efficient and satisfying way.

[1588] 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.

[1589] In this invention, the server

[1590] means for receiving an image of clothing taken by a user;

[1591] A means for extracting feature data such as type, color, and pattern of clothing from the received image;

[1592] A means for storing the extracted feature data in a database for each user;

[1593] means for receiving desired rental conditions specified by a user;

[1594] A means for generating an optimal outfit based on the stored feature data of the user's clothes and the feature data of the rental clothes;

[1595] means for presenting the generated coordinates to a user;

[1596] A means for providing rental clothing based on a user's selection;

[1597] means for notifying a user of the generated coordinates by a notification means;

[1598] This allows users to efficiently combine their own clothes with rental clothes to create the perfect outfit.

[1599] "User" refers to an individual who uses this system to coordinate their own clothing.

[1600] "Server" refers to a device that receives images uploaded by users, analyzes the images, stores the data, and generates and provides coordinates.

[1601] "Image" refers to visual data of clothing photographed by a user and stored in digital format.

[1602] "Feature data" refers to the type, color, pattern, and fabric texture and style information of clothing extracted from the received image.

[1603] "Database" refers to an information storage system for saving and managing clothing characteristic data for each user.

[1604] "Rental Desired Conditions" refers to the conditions such as the category, situation, and season of the clothing the user desires to rent.

[1605] "Coordination" refers to a fashion proposal that combines the user's own clothes with rental clothes.

[1606] "Notification means" refers to a method for notifying the user of the created coordination, and includes push notification and email.

[1607] This invention is a system that provides coordinated outfits that efficiently combine a user's existing clothes with newly rented clothes. This system includes the following elements: a means for the user to upload images of the clothes, a means for performing image analysis on a server, a means for storing and managing extracted feature data, a means for receiving the user's desired rental conditions and generating an optimal outfit, and a means for presenting the generated outfit to the user and providing the rental clothes.

[1608] First, the user uses their smartphone or PC (terminal) to take a picture of the clothes they own and upload it to the system. Specifically, the user takes a picture of the clothes using a camera app and uploads the image to the system through a dedicated web or mobile application. At that time, the user enters the conditions for the clothes they want to rent (for example, "casual summer clothes"). This process is carried out via an HTTP request.

[1609] The server receives the uploaded images and temporarily stores them in a database. The database used can be a relational database such as MySQL or PostgreSQL. The received image data is stored in a temporary storage folder, and image metadata (upload date and time, user ID, etc.) is also recorded in the database.

[1610] The server then runs an AI algorithm (such as TensorFlow or PyTorch) for image analysis to extract feature data such as clothing type (e.g., shirt, pants), color (e.g., white, black), pattern (e.g., solid, striped), fabric texture, and style information (e.g., casual, formal). This process provides specific information about the user's clothing.

[1611] The extracted feature data is associated with the user ID and stored in a database. This creates a clothing database for each user. Next, the server receives the rental requirements specified by the user (e.g. clothing category, occasion, season). The desired requirements are also received via an HTTP request.

[1612] The server uses this data to generate optimal outfit suggestions using an AI algorithm. Evaluation criteria include color compatibility, style matching, and seasonality. The generated outfit suggestions are displayed on the user's interface. Notifications are sent via push notifications and email.

[1613] As a concrete example, consider the case where a user uploads an image of a white T-shirt and requests casual rental clothing suitable for summer wear. For example, the server can save the characteristic data of the white T-shirt and compare it with the rental requirements to suggest the following outfits:

[1614] White T-shirt (own) + Jeans shorts (rental)

[1615] White T-shirt (own) + Cargo shorts (rental)

[1616] The user checks the suggested outfits and selects the combination they want. The server then receives the order and begins the process of shipping the rental clothes.

[1617] As described above, the system of the present invention can efficiently combine the user's existing clothes with newly rented clothes to provide optimal coordination, thereby expanding the range of fashion choices available to the user and greatly improving convenience.

[1618] Example prompt sentence:

[1619] "I'd like to upload an image of a white T-shirt to the system and request casual rental clothing for summer wear. I'd like you to suggest items that coordinate well with the shirts, pants, and other items I already have."

[1620] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1621] Step 1:

[1622] Upload an image and enter conditions

[1623] Users use their smartphones or PCs to take pictures of their clothes and upload them to the system. After this is complete, users enter the conditions for the clothes they want to rent (e.g., "casual summer clothes").

[1624] Input: Clothing image data, desired rental conditions

[1625] Output: Upload image data to the system, send rental requirements

[1626] Specific behavior:

[1627] Use the camera app to take a picture of the outfit.

[1628] Open your web browser or mobile app and log in.

[1629] Click the image upload button, select the image you have taken, and upload it.

[1630] Enter your desired rental conditions (e.g., "casual summer clothing") in the text box and submit.

[1631] Step 2:

[1632] Receiving and saving images

[1633] The server receives the images of the clothes uploaded by the user and temporarily stores them in a database.

[1634] Input: Image data sent by the user

[1635] Output: Image files saved in a temporary folder, metadata recorded in a database

[1636] Specific behavior:

[1637] The server receives the image data via an HTTP request.

[1638] The received image is saved in a temporary folder.

[1639] Record image metadata (upload date and time, user ID, etc.) in a database.

[1640] Step 3:

[1641] Feature extraction through image analysis

[1642] The server runs AI algorithms for image analysis to extract information about the type of clothing, color, pattern, and fabric texture and style.

[1643] Input: Saved image data

[1644] Output: Extracted feature data (type, color, pattern, texture, style information)

[1645] Specific behavior:

[1646] Calls an image analysis engine (such as TensorFlow) to process the uploaded image.

[1647] Analyze the type (shirt, pants, etc.), color (white, black, etc.), and pattern (solid, striped).

[1648] AI algorithm determines style (casual, formal).

[1649] Step 4:

[1650] Feature data storage

[1651] The server associates the extracted feature data with the user ID and stores it in a database.

[1652] Input: extracted feature data, user ID

[1653] Output: Feature data stored in a per-user clothing database

[1654] Specific behavior:

[1655] The extracted feature data is inserted into a database.

[1656] Link feature data with user ID.

[1657] Step 5:

[1658] Receiving rental requirements

[1659] The server receives the rental requirements entered by the user, including information such as clothing category, occasion, and season.

[1660] Input: Rental requirements submitted by the user

[1661] Output: The received rental requirements are stored on the server.

[1662] Specific behavior:

[1663] Receives form data from the user via an HTTP request.

[1664] The received data is analyzed, the user's desired conditions are identified, and the results are stored in a database.

[1665] Step 6:

[1666] Optimal coordination generation

[1667] The server compares data on existing clothing with rental clothing data and uses AI to generate optimal outfit suggestions.

[1668] Input: User's clothing characteristics, rental requirements

[1669] Output: A list of optimal outfit candidates

[1670] Specific behavior:

[1671] The user's clothing data is obtained from the database.

[1672] The clothes are compared with a database of rental clothing and evaluated using an AI algorithm.

[1673] Several coordination candidates are generated and their evaluation scores are calculated.

[1674] Step 7:

[1675] Coordination presentation and selection for users

[1676] The server presents the generated coordinates to the user, allowing the user to make a selection.

[1677] Input: Best coordinate candidates

[1678] Output: Coordination candidates presented to the user, and the user's choice

[1679] Specific behavior:

[1680] Coordination candidates are displayed on the user interface.

[1681] Notify users via push notification or email.

[1682] The user clicks the select button to confirm the coordinates.

[1683] Step 8:

[1684] Rental clothing shipping procedures

[1685] The server then processes the delivery of the rental clothing coordinated by the user, and if necessary, shares the shipping information with the delivery company.

[1686] Input: Rental clothing selected by the user

[1687] Output: Rental clothing shipping instructions, delivery notification to user

[1688] Specific behavior:

[1689] Check the availability of the selected rental clothing.

[1690] Get the user's shipping information and generate a shipping label.

[1691] Information is shared with departments and services responsible for delivery procedures.

[1692] (Application example 1)

[1693] 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."

[1694] Conventional coordination systems have the problem that it is difficult for users to efficiently combine their existing clothes with the clothes available in stores when they visit a physical store. Furthermore, they do not provide sufficient support for users to select clothes in the store using a smartphone or smart glasses, and lack functionality to improve the shopping experience in physical stores.

[1695] 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.

[1696] In this invention, the server includes means for receiving images of clothes photographed by a user, means for extracting characteristic data such as the type, color, and pattern of the clothes from the received images, means for storing the extracted characteristic data in a database for each user, means for receiving desired rental conditions specified by the user, means for generating an optimal outfit based on the stored characteristic data of the user's clothes and the characteristic data of rental clothes, means for using a smartphone, smart glasses, or interactive kiosk to present the optimal outfit to the user in the store, and means for providing rental or sales clothes based on the user's selection. This allows users to easily find an optimal outfit that efficiently combines clothes they own with clothes in the store in a physical store.

[1697] A "user" is an individual who uses the system to coordinate and rent clothes.

[1698] "Photographing" refers to the act of capturing an image of clothing using a device such as a smartphone or smart glasses.

[1699] "Clothing images" are photographic data of clothes taken by the user.

[1700] The "receiving means" is a function that allows the server to receive image data of clothes sent by the user.

[1701] "Clothing type" is a clothing category such as shirts, pants, dresses, etc.

[1702] "Color" refers to the specific color information that clothing possesses.

[1703] A "pattern" is a design or figure found in clothing designs.

[1704] "Feature data" is specific information such as the type, color, and pattern of clothing extracted through image analysis.

[1705] The "database" is a digital information management system for storing extracted feature data for each user.

[1706] "Rental requirements" are requirements such as a specific clothing category or style specified by the user.

[1707] "Rental clothing" refers to clothing that is available for rental to users.

[1708] The "optimal coordination" refers to the combination of the user's own clothes with rental or sales clothes that best harmonizes in terms of color, style, etc.

[1709] "In-store" refers to the interior space of the actual store that the user visits.

[1710] A "smartphone" is a mobile phone with internet connectivity and the ability to run advanced applications.

[1711] "Smart glasses" are wearable devices that have the shape of regular glasses but can display information and perform other functions.

[1712] An "interactive kiosk" is a device that allows users to obtain information and perform operations using an operable display device such as a touch panel.

[1713] "Sales clothing" refers to clothing sold to users in a store.

[1714] The following describes the system configuration and operation procedure as an embodiment of the present invention. The system includes a server that receives and analyzes images of clothes taken by a user, a smartphone, smart glasses, and an interactive kiosk that present optimal outfits to the user.

[1715] System Configuration

[1716] 1. Server:

[1717] Image receiving function: Receives images of clothes uploaded by users.

[1718] Image analysis function: Uses libraries such as TensorFlow and OpenCV to extract feature data such as clothing type, color, and pattern from images.

[1719] Database management: The extracted feature data is stored in a database for each user.

[1720] Recommendation engine: Generates optimal coordination based on the user's desired rental conditions.

[1721] 2. User Device:

[1722] Smartphone: Used to take and upload images and check outfits.

[1723] Smart glasses: Used by users to check the best outfits in real time while walking around the store.

[1724] Interactive Kiosk: Enables in-store operation for suggesting and selecting outfits.

[1725] Program processing

[1726] 1. Image reception:

[1727] The server receives the images of the clothes sent from the user's device and temporarily stores them in a database, using a high-speed Internet connection to send and receive the images.

[1728] 2. Image Analysis:

[1729] The received images are analyzed on the server using TensorFlow and OpenCV to extract information such as the type of clothing (e.g., shirt, pants), color (e.g., white, black, red), pattern (e.g., solid, striped), texture, and style information.

[1730] 3. Save feature data:

[1731] The extracted feature data is associated with the user ID and stored in a database, which creates a clothing database for each user and is used to suggest future outfits.

[1732] 4. Coordinate generation:

[1733] After the user enters their desired rental requirements, the server compares the stored data of clothing on hand with the data of clothing candidates for rental and generates the optimal outfit using an AI algorithm (e.g., cosine similarity calculation).

[1734] 5. Proposal and Selection:

[1735] The optimal outfits are presented to the user via a smartphone, smart glasses, or interactive kiosk, and the process of providing rental or sales clothes based on the outfits selected by the user proceeds.

[1736] Specific examples

[1737] User behavior example:

[1738] A user takes a photo of a white T-shirt with their smartphone and uploads it to the system. They then enter their desired casual summer clothing rental requirements. Based on this information, the server recommends jeans shorts that go perfectly with the white T-shirt. The user can instantly view the jeans shorts while walking around the store through the smart glasses.

[1739] Example prompt sentence:

[1740] prompt:

[1741] User ID: example_user_01

[1742] Clothing characteristics: White T-shirt, casual, summer

[1743] In-store clothing data: Jeans shorts, casual, summer

[1744] How to use generative AI models:

[1745] 1. Input the feature data of the user's white T-shirt into the AI.

[1746] 2. Compare with the characteristic data of jean shorts in stock at the store.

[1747] 3. Optimal coordination is suggested using cosine similarity.

[1748] Example response:

[1749] Select a pair of jean shorts that match the color of the user's T-shirt.

[1750] Selection results:

[1751] White T-shirt + Jean shorts

[1752] In this way, a system is provided that enables a user to easily find an optimal outfit that efficiently combines clothes that the user owns with clothes in the store in a real store.

[1753] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1754] Step 1:

[1755] The user uploads a photo of the clothes they have taken. The information entered here is the user ID and the image file of the clothes. The uploaded image data is sent from the device to the server.

[1756] Step 2:

[1757] The image received by the server is temporarily stored in a database. The output of this process is the completion of saving the uploaded image data. Specifically, the image received by the server is saved in a specified directory and linked to the corresponding user ID.

[1758] Step 3:

[1759] The server retrieves the stored image data and performs image analysis. The input is the image data stored in the database. TensorFlow and OpenCV are used for the analysis to extract feature data such as the type of clothing, color, pattern, fabric texture, and style information. The output of this process is the extracted feature data. Specifically, an AI model is executed to extract clothing features from the image.

[1760] Step 4:

[1761] The extracted feature data is saved in a database for each user. The input is the feature data extracted in step 3 and the user ID. The output of this process is a database with updated feature data for each user. Specifically, the feature data is associated with the user ID and inserted into the database.

[1762] Step 5:

[1763] The user inputs the desired rental conditions, such as clothing category, occasion, season, etc. The desired rental conditions are sent from the terminal to the server.

[1764] Step 6:

[1765] The server compares the stored data of clothing items on hand with the data of clothing items that can be rented based on the desired rental conditions. The inputs are the desired rental conditions, the user's characteristic data, and the data of the clothing items that can be rented. An optimal outfit is generated using an AI algorithm (e.g., cosine similarity calculation). The output of this process is the optimal outfit candidate. Specifically, an AI model is executed to find the optimal combination.

[1766] Step 7:

[1767] The optimal outfit is presented to the user. The input is the outfit candidates generated in step 6. The output is outfit information displayed on the user's smartphone, smart glasses, or interactive kiosk. Specifically, the outfit information is displayed via push notification or within the application.

[1768] Step 8:

[1769] The user selects a suggested outfit. The input information is the outfit selected by the user. The selection information is sent from the terminal to the server.

[1770] Step 9:

[1771] Based on the selection, the system carries out procedures to provide the clothes for rental or sale. The input is the outfit and rental conditions selected by the user. The output of this process is the delivery of the rental clothes or the completion of the sales procedure. Specifically, delivery arrangements and purchase procedures are automatically carried out by the server.

[1772] 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.

[1773] The system of the present invention provides coordinated outfits that efficiently combine the user's existing clothes with newly rented clothes, and by combining it with an emotion engine that recognizes the user's emotions, it realizes more personalized suggestions. The details of the system are described below.

[1774] User procedure flow

[1775] Users take pictures of their clothes using their smartphones or PCs and upload them using the app's "Register Your Own Clothes" function. Once the upload is complete, users can enter the desired rental clothing specifications (e.g., casual summer clothes).

[1776] Server Processing

[1777] Based on this, the server performs the following processing.

[1778] Receiving and saving images

[1779] The server receives the images of the clothes uploaded by the user and temporarily stores them in a database.

[1780] Image analysis

[1781] The server runs an AI algorithm for image analysis to extract characteristic data such as the type of clothing (e.g., shirt, pants), color (e.g., white, black, red), and pattern (e.g., solid, striped), as well as the texture of the fabric and style information (e.g., casual, formal).

[1782] Feature data storage

[1783] The server associates the extracted feature data with the user ID and stores it in a database, thereby creating a clothing database for each user.

[1784] Receiving and analyzing rental requirements

[1785] Once customers input their desired rental requirements, the server receives them and runs an AI algorithm to match their existing clothing data with the rental clothing data, using criteria such as color compatibility, style matching, and seasonal suitability.

[1786] Coordinate generation and presentation

[1787] The server generates optimal outfit suggestions and presents multiple options to the user. The outfit suggestions are displayed in the device's application via push notification or email.

[1788] Incorporating an emotion engine

[1789] Furthermore, the system incorporates an emotion engine to perform the following processes:

[1790] Emotion Recognition and Analysis

[1791] The device captures the user's facial expressions and voice in response to the presented outfit, and the emotion engine analyzes them to collect the user's emotional data. The emotion engine then sends the analysis results to the server.

[1792] Saving and reflecting emotional data

[1793] The server stores the emotion data in a database and reflects this data the next time a coordinated outfit is generated, suggesting a more appropriate outfit based on the user's preferences and feedback.

[1794] Specific examples

[1795] For example, suppose a user uploads an image of a white T-shirt and requests a casual rental item suitable for summer wear. In this case, the server saves the characteristics of the white T-shirt and suggests the following outfits along with the desired rental conditions:

[1796] White T-shirt (own) + Jeans shorts (rental)

[1797] White T-shirt (own) + Cargo shorts (rental)

[1798] The user reviews the suggested outfit, and the emotion engine analyzes the user's preferences from their facial expressions and tone of voice. For example, if the user smiles or sounds satisfied, this is saved as positive feedback. The next time the system suggests an outfit, this positive feedback will be reflected, making the suggestion more in line with the user's preferences.

[1799] In this way, the system of the present invention can efficiently combine the user's existing clothes with new clothes to rent, and further make suggestions that take the user's emotions into consideration, thereby expanding the range of fashion choices available to the user and greatly improving convenience.

[1800] The processing flow will be explained below.

[1801] Step 1:

[1802] Users use their smartphone or PC to take pictures of their clothes and then upload the images using the "Register clothes you own" function within the application.

[1803] Step 2:

[1804] The server receives the uploaded images and temporarily stores them in a database.

[1805] Step 3:

[1806] The server runs an AI algorithm for image analysis to extract characteristic data such as the type of clothing (shirt, pants, etc.), color (white, black, red, etc.), and pattern (solid, striped, etc.), as well as the texture of the fabric and style information (casual, formal, etc.).

[1807] Step 4:

[1808] The server associates the extracted feature data with the user ID and stores it in a database, thereby creating a clothing database for each user.

[1809] Step 5:

[1810] The user enters the rental requirements (e.g., casual summer clothing) into the application.

[1811] Step 6:

[1812] The server receives rental requirements from the user, including clothing category (e.g., shirt, dress), occasion (e.g., casual, formal), and season (e.g., summer, winter).

[1813] Step 7:

[1814] The server retrieves the user's clothing data from the database and runs an AI algorithm to compare it with the rental clothing database, thereby evaluating combinations of the user's clothing and potential rental items.

[1815] Step 8:

[1816] The server uses AI algorithms to generate optimal outfit suggestions, which include evaluations of color compatibility, style matching, and seasonal suitability.

[1817] Step 9:

[1818] The server generates a plurality of coordinate candidates and presents them to the user.

[1819] Step 10:

[1820] Using the terminal application, the user visually checks the presented coordination candidates and selects the combination they like.

[1821] Step 11:

[1822] The device captures the user's facial expressions and voice, and the emotion engine analyzes the data to collect the user's emotional data.

[1823] Step 12:

[1824] The server receives the analysis results from the emotion engine and stores them in a database.

[1825] Step 13:

[1826] Based on the outfit the user selects, they "add" the clothes to rent to their cart and finally confirm the rental order.

[1827] Step 14:

[1828] The server receives the user's order information and starts the delivery procedure for the rental clothes.

[1829] Step 15:

[1830] From the next time onwards, the server will adjust the evaluation criteria of the AI ​​algorithm based on the collected emotional data and suggest outfits that better match the user's preferences. For example, if positive feedback is received from a smile or a satisfied voice, similar outfits will be suggested based on that information.

[1831] Through the above steps, the system of the present invention can efficiently combine the user's existing clothes with new rental clothes, and further make suggestions that take the user's emotions into consideration, thereby expanding the range of fashion choices available to the user and greatly improving convenience.

[1832] Example 2

[1833] 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."

[1834] In conventional fashion coordination systems, it is difficult for users to efficiently combine clothes they own with newly rented clothes, and they also have the problem of not being able to provide suggestions that fully take into account the user's preferences and emotions. The present invention aims to solve these problems and provide appropriate fashion coordination that is personalized for the user.

[1835] 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.

[1836] In this invention, the server includes means for receiving images of clothes photographed by a user, means for extracting characteristic data such as the type, color, and pattern of the clothes from the received images, means for saving the extracted characteristic data in a database for each user, means for receiving desired rental conditions specified by the user, means for generating an optimal outfit based on the saved characteristic data of the user's clothes and the characteristic data of rental clothes, means for presenting the generated outfit to the user, means for providing rental clothes based on the user's selection, means for capturing the user's facial expressions and voice and analyzing emotional data, and means for saving the analyzed emotional data in a database and reflecting it when generating the next outfit. This makes it possible to efficiently combine the user's own clothes with new rental clothes and to make more personalized suggestions that reflect the user's emotions and preferences.

[1837] A "user" is someone who wishes to coordinate or rent clothes using this system.

[1838] "Means for receiving images of clothes in hand" refers to the function that allows users to upload images of clothes taken with their smartphone or PC to the server.

[1839] "Feature data" refers to data about clothing characteristics extracted through image analysis, such as type of clothing, color, pattern, fabric texture, and style information.

[1840] A "database" is an information accumulation system for storing extracted feature data, user information, emotional data, etc.

[1841] "Desired rental conditions" refers to information that allows a user to specify the conditions for the clothes they wish to rent (for example, casual summer clothes).

[1842] "Coordination" means suggesting styling by combining clothes you already own with rented clothes.

[1843] An "artificial intelligence model" is an algorithm or machine learning model used to evaluate the compatibility of clothing.

[1844] "Emotion data" refers to data related to emotions obtained by analyzing the user's facial expressions and voice.

[1845] "Means for analyzing" refers to technology for processing a user's emotional data in real time and determining the type and degree of emotion.

[1846] The "server" is a central computer system that stores and processes user data, image analysis, coordinate generation, and emotion data.

[1847] A "terminal" refers to a device such as a smartphone or PC operated by a user.

[1848] "Capture" refers to capturing the user's facial expressions and voice through a camera or microphone.

[1849] "Means for reflecting the next coordinated outfit when generating the next coordinated outfit" refers to a function for taking the user's preferences and emotions into consideration when proposing the next coordinated outfit based on the saved emotion data.

[1850] The system of the present invention provides coordinated outfits that efficiently combine the user's existing clothes with newly rented clothes, and by combining it with an emotion engine that recognizes the user's emotions, it realizes more personalized suggestions. Detailed embodiments of this system are described below.

[1851] System configuration

[1852] This system consists of the following main components:

[1853] 1. Server

[1854] 2. Terminal

[1855] 3. Database

[1856] 4. Emotion Engine

[1857] Hardware and software used

[1858] The server plays a central role in image analysis, data storage, and coordinate generation. Specifically, it uses the following software and services:

[1859] Image analysis uses Google Cloud Vision API and Amazon Rekognition.

[1860] Amazon RDS and MySQL are used as databases.

[1861] Coordination generation uses machine learning libraries such as TensorFlow and PyTorch.

[1862] The terminals are devices operated by users, such as smartphones and PCs, that take and upload images and capture emotions.

[1863] The emotion engine is a component that captures and analyzes the user's facial expressions and voice, specifically using Microsoft Azure's Face API and IBM Watson's Tone Analyzer.

[1864] System operation procedures

[1865] The system operation procedure will be explained below with specific examples.

[1866] 1. User uploads clothing images

[1867] Users can take pictures of their clothes using their smartphones or PCs and upload them using the application's "Register clothes" function by selecting the image file and clicking the upload button.

[1868] 2. Receiving and saving images

[1869] The server receives image files uploaded by users and temporarily stores the image data in cloud storage such as Amazon S3.

[1870] 3. Image Analysis

[1871] The server uses the Google Cloud Vision API to analyze the images and extract information about the type, color, pattern, texture, and style of the clothing, thereby obtaining feature data such as the type of shirt or pants, color (white or black), and pattern (solid or striped).

[1872] 4. Saving feature data

[1873] The server associates the extracted feature data with the user ID and stores it in Amazon RDS. The stored data includes the clothing ID, type, color, pattern, texture, style, etc.

[1874] 5. Enter your desired rental conditions

[1875] The user enters the desired rental clothing requirements (e.g., casual summer clothing) into a form within the application and submits it.

[1876] 6. Analysis of desired rental conditions

[1877] The server receives the user's desired rental conditions via an HTTP POST request, compares them with the user's clothing data, and selects the most suitable rental clothing.

[1878] 7. Coordinate Generation

[1879] The server generates combination candidates for clothes that you own and rent, and creates the most suitable outfit that meets your requirements.

[1880] 8. Coordination Presentation

[1881] The server presents the generated outfit suggestions to the user via push notification or email, and the user can check the outfits within the application.

[1882] 9. Capturing Emotions

[1883] The device captures the user's facial expressions and voice using a camera and microphone and analyzes them in real time. For example, if the user smiles or sounds satisfied, this is analyzed by the emotion engine as positive feedback and the results are sent to the server.

[1884] 10. Saving and Reflecting Emotional Data

[1885] The server stores the emotion data in a database and reflects it in the next outfit suggestions, thereby learning the user's preferences and realizing more personalized outfit suggestions.

[1886] Examples of specific examples and prompts

[1887] For example, if a user uploads an image of a white T-shirt and requests "casual rental clothing suitable for summer," the server will save the characteristics of the white T-shirt, compare them with the rental requirements, and suggest the following outfits:

[1888] White T-shirt (own) + Jeans shorts (rental)

[1889] White T-shirt (own) + Cargo shorts (rental)

[1890] Based on this suggestion, the user checks the suggested outfit, and the emotion engine analyzes their preferences from their facial expressions and tone of voice. If they smile or sound satisfied, this is saved as positive feedback and will be reflected in the next suggestion. An example of a prompt is, "Please suggest some casual summer clothes to wear on my next trip. I'd like to combine it with a white T-shirt I have."

[1891] The above is a detailed embodiment of the system of the present invention, which allows users to efficiently combine existing clothes with new rental clothes and receive personalized suggestions that take emotions into account.

[1892] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1893] Processing step details

[1894] Step 1:

[1895] Users upload images of their clothing.

[1896] Specifically, the user takes a photo of the clothes with their smartphone or PC, selects the image file using the "Register clothes in stock" function in the application, and clicks the upload button. The input for this process is the image file selected by the user, and the output is a notification that the image file has been uploaded.

[1897] Step 2:

[1898] The server receives and stores the images.

[1899] Specifically, the server receives image data of the clothes in hand via an HTTP POST request and temporarily stores it in cloud storage (e.g., Amazon S3). The input of this process is the uploaded image file, and the output is the URL of the image stored in the storage.

[1900] Step 3:

[1901] The server performs the image analysis.

[1902] Specifically, the server calls the Google Cloud Vision API and analyzes the received image. At this time, it extracts the type of clothing (e.g., shirt, pants), color, pattern (e.g., solid, striped), fabric texture, and style information (e.g., casual, formal). The input for this process is the image URL from storage, and the output is feature data (type, color, pattern, texture, style).

[1903] Step 4:

[1904] The server stores the feature data.

[1905] Specifically, the server associates the extracted feature data with the user ID and stores it in a database (e.g., Amazon RDS). The input to this process is the feature data and the user ID, and the output is the record ID stored in the database.

[1906] Step 5:

[1907] The user inputs the desired rental conditions.

[1908] Specifically, the user enters the desired rental clothing requirements (e.g., casual summer clothing) into a form within the application and clicks the submit button. The input for this process is the text data of the desired rental requirements entered by the user, and the output is a notification that the requirements have been submitted.

[1909] Step 6:

[1910] The server receives and analyzes the rental request conditions.

[1911] Specifically, the server receives the desired rental conditions via an HTTP POST request and executes an AI model to evaluate the optimal combination of the desired rental clothing with the clothes the customer owns based on the conditions. The input to this process is the text data of the desired rental conditions, and the output is pairing candidate data.

[1912] Step 7:

[1913] The server generates the coordinates.

[1914] Specifically, the server generates candidate combinations of clothing items owned and rented, and creates the most suitable outfit for the given conditions. Evaluation criteria include color compatibility, style matching, and seasonal suitability. The input to this process is pairing candidate data and evaluation criteria data, and the output is a list of outfit candidates.

[1915] Step 8:

[1916] The server presents the coordinates to the user.

[1917] Specifically, the server presents the coordinated outfit candidates it has generated to the user. The presentation method is push notification or email, and the user can check the outfits within the application. The input for this process is a list of coordinated outfit candidates, and the output is a notification that the presentation has been completed.

[1918] Step 9:

[1919] The device captures the user's emotions.

[1920] Specifically, when a user checks their outfit, the device's camera captures their facial expression in real time and records their voice with a microphone. The input to this process is the user's facial expression image and voice data, and the output is the captured emotional data.

[1921] Step 10:

[1922] The device transmits the emotion data to the server.

[1923] Specifically, the device sends the captured emotion data to the server via an HTTP POST request. The input of this process is the emotion data, and the output is a notification that the data has been sent.

[1924] Step 11:

[1925] The server stores and reflects the emotional data.

[1926] Specifically, the server stores the received emotion data in a database, and the next time it proposes a coordinated outfit, it reflects the user's preferences based on this data. The input for this process is the emotion data and the user ID, and the output is the record ID stored in the database.

[1927] The above are the specific processing steps of this system.

[1928] (Application example 2)

[1929] 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."

[1930] In today's clothing rental services, it is difficult for users to efficiently combine their existing clothes with newly rented clothes. It is also difficult to reflect the user's emotions and preferences in the actual outfit suggestions. This makes it difficult to provide optimal outfit suggestions for the user, potentially reducing satisfaction. While conventional technologies have partially achieved evaluation of clothing characteristics and appropriate combinations, they have yet to achieve personalized outfit suggestions that take the user's emotions into account. Technology to solve these issues is needed.

[1931] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving images of clothes photographed by the user, means for extracting feature data such as the type, color, and pattern of the clothes from the received images, means for saving the extracted feature data in a database for each user, means for receiving desired rental conditions specified by the user, means for generating an optimal outfit based on the saved feature data of the user's clothes and the feature data of rental clothes, means for presenting the generated outfit to the user, means for providing rental clothes based on the user's selection, means for recognizing and analyzing the user's emotions, and means for saving the analyzed emotion data in a database and reflecting it when generating the next outfit. This makes it possible to propose personalized outfits that reflect the user's emotions and preferences.

[1932] definition statement

[1933] "User" means an individual or legal entity that uses the Service.

[1934] "Clothing images" are digital images of clothing owned by the user.

[1935] "Emotion data" is data relating to emotions analyzed from the user's facial expressions and voice.

[1936] "Feature data" is information such as the type, color, and pattern of clothing extracted through image analysis.

[1937] "Rental Desired Conditions" refers to conditions such as the style and season of the clothing desired by the user.

[1938] "Coordination" is a styling suggestion that combines clothes you already own with rented clothes.

[1939] The "emotion engine" is a system that analyzes the user's facial expressions and voice to generate emotional data.

[1940] The "database" is a system for storing data on the characteristics and emotions of users' clothing.

[1941] An "AI algorithm" is a method that uses artificial intelligence to analyze data and generate optimal coordination.

[1942] "Owned clothes" refers to clothes that the user already owns.

[1943] "Rental clothing" refers to clothing that a user wishes to rent.

[1944] MODE FOR CARRYING OUT THE INVENTION

[1945] This invention is a system that uses images of clothes owned by a user to suggest optimal outfits for rental clothes, and further reflects the user's emotional data to provide more personalized outfits. This section describes specific methods for implementing the invention.

[1946] System Configuration

[1947] The system mainly consists of the following components:

[1948] 1. User device (smartphone, PC, etc.)

[1949] 2. Server

[1950] 3. Database

[1951] 4. Emotion Engine

[1952] 5. AI Algorithms

[1953] Processing flow

[1954] First, the user takes a photo of their clothes using a smartphone or PC, and the image is uploaded to the server via a dedicated application.

[1955] Image analysis of hand-held clothing

[1956] The server analyzes the images of the clothes received from the user. This analysis uses the image processing libraries OpenCV and TensorFlow. Feature data such as the type, color, and pattern of the clothes are extracted from the images. The server also analyzes the texture and style of the fabric, and stores this data in a database for each user.

[1957] Receiving rental requirements

[1958] Users input their desired clothing rental style, season, and other criteria into the application, which is then sent to the server and compared with the data on their existing clothing.

[1959] Coordinate generation

[1960] The server uses the stored characteristic data of the user's clothes and the characteristic data of the rental clothes to generate the optimal outfit using an AI algorithm, which takes into account factors such as color compatibility, style matching, and seasonal suitability.

[1961] Coordination suggestions

[1962] The generated coordinates are sent to the user's terminal, where the user can check the proposed coordinates.

[1963] Emotion data analysis and storage

[1964] The user reacts to the proposed outfits with facial expressions and voice. This reaction is captured by the device's camera and microphone and analyzed by the emotion engine. The emotional data resulting from this analysis is then sent back to the server and stored in a database.

[1965] Reflecting feedback

[1966] The saved emotion data is reflected the next time an outfit is created, allowing the system to suggest more appropriate outfits based on the user's preferences and feedback.

[1967] Specific examples

[1968] For example, suppose a user uploads an image of a white T-shirt and requests to rent casual summer clothing. In this case, the server analyzes the feature data of the white T-shirt and suggests jeans shorts or cargo shorts as suitable rental clothing. If the user responds with a smile or a satisfied voice, that emotional data is saved as positive feedback. The next time outfit suggestions are made, this positive feedback will be reflected, and suggestions that better match the user's preferences will be made.

[1969] Prompt Sentence Examples

[1970] "To suggest the next outfit, please generate a casual summer outfit by analyzing an image of a white T-shirt and the user's emotional feedback. Please consider the compatibility between the user's existing clothes and the rental clothes, and emphasize matching colors and styles. Also, please prioritize reflecting the user's positive emotional feedback."

[1971] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1972] Processing Steps

[1973] Step 1:

[1974] Users take pictures of their clothes and upload them through the application.

[1975] Specific operation: The user takes a picture of their clothes using the smartphone camera and uploads the picture using the "Register clothes" function in the application.

[1976] Input: A photograph of the clothing.

[1977] Output: Uploaded clothes images are sent to the server.

[1978] Step 2:

[1979] The server analyzes the received image and extracts feature data.

[1980] How it works: The server uses OpenCV and TensorFlow to analyze the image and extract feature data such as clothing type, color, pattern, fabric texture, and style information.

[1981] Input: Uploaded clothing image.

[1982] Data processing: Image analysis is used to extract clothing characteristic data (type, color, pattern, texture, and style information).

[1983] Output: Extracted feature data.

[1984] Step 3:

[1985] The server stores the extracted feature data in a database.

[1986] Specific operation: The server associates the extracted feature data with the user ID and stores it in a database.

[1987] Input: extracted feature data, user ID.

[1988] Data processing: Associating feature data with user ID.

[1989] Output: Feature data stored in a database.

[1990] Step 4:

[1991] The user inputs the desired rental conditions and transmits them to the server.

[1992] Specific operation: The user enters the desired rental clothing requirements (style, season, etc.) through the application and sends them to the server.

[1993] Input: The rental requirements entered by the user.

[1994] Output: Rental preferences sent to the server.

[1995] Step 5:

[1996] The server compares the characteristic data of the clothes you own with the data of the rental clothes and generates the optimal outfit.

[1997] Specific operation: The server uses an AI algorithm to compare the stored characteristic data of the clothes you own with the characteristic data of the rental clothes and generate the optimal combination.

[1998] Input: Characteristic data of your clothes, desired rental conditions.

[1999] Data calculation: AI algorithms match and generate optimal coordinates.

[2000] Output: Optimal coordinates.

[2001] Step 6:

[2002] The generated coordinates are presented on the user terminal.

[2003] Specific operation: The server displays the generated coordinates on the user's device via push notification or email.

[2004] Input: Optimal coordinates.

[2005] Output: Coordinates displayed on the user's terminal.

[2006] Step 7:

[2007] Capture user responses and analyze emotional data.

[2008] Specific operation: The user checks the suggested outfit, and their facial expressions and voice are captured using the device's camera and microphone, which are then analyzed by the emotion engine.

[2009] Input: Captured facial expressions and voice.

[2010] Data computation: Emotion data analysis using emotion engines.

[2011] Output: Parsed emotion data.

[2012] Step 8:

[2013] The emotional data is stored in a database and reflected in the next coordination generation.

[2014] Specific operation: The server saves the analyzed emotion data in a database and reflects it the next time a coordinate is generated.

[2015] Input: Parsed emotion data.

[2016] Data processing: Emotion data is saved and reflected in the next coordinate generation.

[2017] Output: Emotion data stored in the database, next outfit suggestions.

[2018] 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.

[2019] 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.

[2020] 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.

[2021] 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.

[2022] 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.

[2023] 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.

[2024] 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).

[2025] 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.

[2026] 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."

[2027] 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.

[2028] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[2029] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[2030] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[2031] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[2032] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[2033] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[2034] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[2035] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[2036] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[2037] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[2038] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[2039] The following is further disclosed regarding the above embodiment.

[2040] (Claim 1)

[2041] means for receiving an image of clothing taken by a user;

[2042] A means for extracting feature data such as type, color, and pattern of clothing from the received image;

[2043] A means for storing the extracted feature data in a database for each user;

[2044] means for receiving desired rental conditions specified by a user;

[2045] A means for generating an optimal outfit based on the stored characteristic data of the user's clothes and the characteristic data of the rental clothes;

[2046] means for presenting the generated coordinates to a user;

[2047] A means for providing rental clothing based on a user's selection;

[2048] A system including:

[2049] (Claim 2)

[2050] 10. The system of claim 1, further comprising means for extracting fabric texture and style information from the received image.

[2051] (Claim 3)

[2052] 10. The system of claim 1, further comprising means for using an AI algorithm to evaluate the compatibility of a user's existing clothing with potential rental clothing.

[2053] "Example 1"

[2054] (Claim 1)

[2055] means for receiving an image of clothing taken by a user;

[2056] A means for extracting feature data such as type, color, and pattern of clothing from the received image;

[2057] A means for storing the extracted feature data in a database for each user;

[2058] means for receiving desired rental conditions specified by a user;

[2059] A means for generating an optimal outfit based on the stored feature data of the user's clothes and the feature data of the rental clothes;

[2060] means for presenting the generated coordinates to a user;

[2061] A means for providing rental clothing based on a user's selection;

[2062] means for notifying a user of the generated coordinates by a notification means;

[2063] A system including:

[2064] (Claim 2)

[2065] 10. The system of claim 1, further comprising means for extracting fabric texture and style information from the received image.

[2066] (Claim 3)

[2067] 10. The system of claim 1, further comprising means for using an AI algorithm to evaluate the compatibility of a user's existing clothing with potential rental clothing.

[2068] "Application Example 1"

[2069] (Claim 1)

[2070] means for receiving an image of clothing taken by a user;

[2071] A means for extracting feature data such as type, color, and pattern of clothing from the received image;

[2072] A means for storing the extracted feature data in a database for each user;

[2073] means for receiving desired rental conditions specified by a user;

[2074] A means for generating an optimal outfit based on the stored feature data of the user's clothes and the feature data of the rental clothes;

[2075] a means for using a smartphone, smart glasses, or an interactive kiosk to present the optimal outfit to the user in-store;

[2076] A means for providing rental or sales clothing based on the user's selection;

[2077] A system including:

[2078] (Claim 2)

[2079] 10. The system of claim 1, further comprising means for extracting fabric texture and style information from the received image.

[2080] (Claim 3)

[2081] 10. The system of claim 1, further comprising means for using an AI algorithm to evaluate the compatibility of a user's clothing with clothing in the store.

[2082] "Example 2: Combining Emotion Engines"

[2083] (Claim 1)

[2084] means for receiving an image of clothing taken by a user;

[2085] A means for extracting feature data such as type, color, and pattern of clothing from the received image;

[2086] A means for storing the extracted feature data in a database for each user;

[2087] means for receiving desired rental conditions specified by a user;

[2088] A means for generating an optimal outfit based on the stored feature data of the user's clothes and the feature data of the rental clothes;

[2089] means for presenting the generated coordinates to a user;

[2090] A means for providing rental clothing based on a user's selection;

[2091] A means for capturing a user's facial expressions and voice and analyzing the emotional data;

[2092] A means for storing the analyzed emotion data in a database and reflecting it when generating the next coordinate;

[2093] A system including:

[2094] (Claim 2)

[2095] 10. The system of claim 1, further comprising means for extracting fabric texture and style information from the received image.

[2096] (Claim 3)

[2097] 10. The system of claim 1, further comprising means for using an artificial intelligence model to evaluate the compatibility of a user's existing clothing with potential rental clothing.

[2098] "Application example 2 when combining emotion engines"

[2099] (Claim 1)

[2100] means for receiving an image of clothing taken by a user;

[2101] A means for extracting feature data such as type, color, and pattern of clothing from the received image;

[2102] A means for storing the extracted feature data in a database for each user;

[2103] means for receiving desired rental conditions specified by a user;

[2104] A means for generating an optimal outfit based on the stored feature data of the user's clothes and the feature data of the rental clothes;

[2105] means for presenting the generated coordinates to a user;

[2106] A means for providing rental clothing based on a user's selection;

[2107] means for recognizing and analyzing user emotions;

[2108] A means for saving the analyzed emotion data in a database and reflecting it when generating the next outfit;

[2109] A system including:

[2110] (Claim 2)

[2111] 10. The system of claim 1, further comprising means for extracting fabric texture and style information from the received image.

[2112] (Claim 3)

[2113] 10. The system of claim 1, further comprising means for using an AI algorithm to evaluate the compatibility of a user's existing clothing with potential rental clothing. [Explanation of symbols]

[2114] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving an image of clothing taken by a user; A means for extracting feature data such as type, color, and pattern of clothing from the received image; A means for storing the extracted feature data in a database for each user; means for receiving desired rental conditions specified by a user; A means for generating an optimal outfit based on the stored characteristic data of the user's clothes and the characteristic data of the rental clothes; means for presenting the generated coordinates to a user; A means for providing rental clothing based on a user's selection; A system including:

2. The system of claim 1 further comprising means for extracting fabric texture and style information from the received image.

3. 10. The system of claim 1, further comprising means for using an AI algorithm to evaluate the compatibility of a user's existing clothing with potential rental clothing.

Images