System

Abstract

A system is provided.SOLUTION: Means for receiving an image of clothing photographed by a user, means for generating three dimensional data of the clothing from the received image, means for classifying the generated three dimensional data by attributes such as color and shape, means for storing the classified clothing data in a database, means for proposing coordination in consideration of season, weather, temperature, and trend information on the basis of the stored clothing data, means for notifying the user of the proposed coordination, means for recording a use situation of the clothing of the user, and means for specifying clothing with a low use frequency from the recorded use information, A system comprising: means for suggesting recycling or resale; means for cooperating with a plurality of shopping sites to enable a user to purchase new clothing in bulk; and means for matching a user with a professional coordinator.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] The present invention relates to a system for efficiently managing a user's clothing and suggesting outfits based on that clothing. Conventional technologies have made it difficult for users to understand their clothing and coordinate it appropriately, and managing infrequently worn clothing and tracking trends can be particularly cumbersome. Furthermore, there are limitations in the ability to select and purchase new clothing, and even in connecting users with professional outfit designers. [Means for solving the problem]

[0005] The present invention provides a means for receiving images of clothing photographed by a user, generating three-dimensional data of the clothing from the received images, classifying the generated three-dimensional data by attributes such as color and shape, and storing the classified clothing data in a database. It also includes a means for suggesting outfits based on the stored clothing data, taking into account season, weather, temperature, and trend information. It also includes a means for notifying the user of the suggested outfits, a means for recording the user's clothing usage, a means for identifying infrequently worn clothing from the recorded usage information and suggesting recycling or resale, a means for linking with multiple shopping sites to allow users to purchase new clothing in bulk, and a means for matching users with professional outfitters. In this way, it becomes possible to centrally manage, coordinate, purchase, and resell the clothing a user owns, and collaborate with professional outfitters.

[0006] A "user" is someone who uses this system to manage their own clothing and receive coordination suggestions.

[0007] "Device" refers to electronic devices used by users, such as smartphones, tablets, and PCs.

[0008] A "server" is a computer system that receives, analyzes, and stores data sent from terminals and manages the processing of the entire system.

[0009] "Clothing" refers to clothing items owned by a user and managed by this system.

[0010] "Image" refers to photographic data of clothing that a user takes with their device and uploads to the server.

[0011] "Three-dimensional data" is data containing three-dimensional information about clothing that is generated by the server from an image.

[0012] "Attributes" refer to specific characteristics of clothing, such as color, shape, and style.

[0013] A "database" is an information system in which classified clothing data is stored.

[0014] "Coordination" refers to the style or combination proposed by combining multiple pieces of clothing.

[0015] "Season, weather, and temperature" refers to external environmental information that is taken into consideration when suggesting outfits.

[0016] "Trend information" refers to information about trends and the latest styles in the fashion industry.

[0017] "Recycling or reselling" refers to the distribution process of gently used clothing for sale to other users.

[0018] "Shopping Site" refers to an online sales platform where users can purchase new clothes.

[0019] A "coordinator" is a professional who provides fashion advice and suggests coordination ideas.

[0020] "Matching" refers to the process of matching users with appropriate coordinators. [Brief explanation of the drawings]

[0021] [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

[0022] 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.

[0023] First, the terms used in the following description will be explained.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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."

[0029] [First embodiment]

[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0031] 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.

[0032] 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).

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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."

[0042] This invention is a system for efficiently managing a user's clothing and suggesting outfits based on that clothing. The system starts when the user takes a photo of the clothing with their device and uploads the image to a server. The server generates three-dimensional data from the received image and classifies it by attributes such as color and shape. The classified data is then stored in a database.

[0043] The user launches a dedicated application and takes a photo of the garment. The device has the function to upload the captured image to a server. The server analyzes the received image and generates 3D data based on the analysis results. This 3D data is categorized by attributes such as color, shape, and style, and the categorized data is stored in a database.

[0044] Based on the stored data, the server takes into account external information such as the season, weather, temperature, and trend information to suggest the most suitable outfit for the user. This suggestion is sent to the user's device, and the user can confirm the received outfit suggestion.

[0045] Furthermore, based on the user's own recorded wearing information, the server will accumulate information on clothing usage and analyze frequency of use. If clothing that has been used infrequently is identified, the server will also provide suggestions to the user on how to recycle or resell this clothing.

[0046] As a specific example, a user takes a photo of a white shirt and uploads the image from their device to a server. The server generates three-dimensional data of a white long-sleeved shirt from the received image and stores that data in a database. Later, if the weather is sunny and the temperature is 23 degrees, the server will use that information to suggest coordinating the white shirt with casual chinos and notify the user's device. Data is also accumulated showing that the user wears the shirt once a week, and if the user wears the shirt infrequently, a notification is sent to the user's device suggesting that the shirt be put up for sale on a flea market site.

[0047] In addition, the system is linked to multiple shopping sites, so when a user wants to buy new clothes, they can enter their desired category and budget, and the server will search for and suggest the most suitable products and provide a purchase link.

[0048] The service also has a function that matches users with professional coordinators. When a user requests stylist advice for a special event, the server selects an appropriate coordinator and the user receives advice based on the request.

[0049] In this way, the present invention allows users to manage their clothing, suggest outfits, purchase, resell, and even collaborate with professional coordinators in a unified manner, allowing users to enjoy fashion efficiently and smartly.

[0050] The processing flow will be explained below.

[0051] Garment photography and upload process

[0052] Step 1:

[0053] The user launches a dedicated application on the device and selects the "photograph clothing" function.

[0054] Step 2:

[0055] The device's camera is activated, and the user points the camera at the clothing they want to photograph and takes a photo.

[0056] Step 3:

[0057] The device displays the captured image and prompts the user to confirm. The user confirms and selects "Save."

[0058] Step 4:

[0059] The device uploads the saved images to a dedicated server.

[0060] Step 5:

[0061] The server receives the uploaded images and stores them in a database.

[0062] 3D data generation and classification process

[0063] Step 1:

[0064] The server executes an algorithm to analyze the received image.

[0065] Step 2:

[0066] The server uses image analysis to identify specific attributes of the clothing (e.g., shirt, pants, etc.).

[0067] Step 3:

[0068] The server generates three-dimensional data from the images of the identified garments.

[0069] Step 4:

[0070] The server classifies the generated 3D data by attributes such as color, shape, and style.

[0071] Step 5:

[0072] The server stores the classified clothing data in a database.

[0073] Coordination proposal process

[0074] Step 1:

[0075] The server retrieves the stored clothing information from the user's clothing database.

[0076] Step 2:

[0077] The server retrieves season, weather, temperature, and trend information from an external API.

[0078] Step 3:

[0079] Based on the above information, the server generates the most suitable outfit for the user.

[0080] Step 4:

[0081] The server transmits the generated coordinate information to the user's terminal.

[0082] Step 5:

[0083] The terminal notifies the user of the received coordination proposal.

[0084] Accumulation process of clothing usage

[0085] Step 1:

[0086] The user inputs information about the clothes they are wearing today through the application.

[0087] Step 2:

[0088] The terminal transmits the input wearing information to the server.

[0089] Step 3:

[0090] The server stores the received wearing information in a database.

[0091] Step 4:

[0092] The server runs a counting algorithm to calculate how often each garment is used.

[0093] Step 5:

[0094] The server generates data to notify the user based on the frequency of use.

[0095] The process of proposing to open a store on a flea market site

[0096] Step 1:

[0097] The server analyzes the accumulated data on the frequency of use of clothing.

[0098] Step 2:

[0099] The server lists the least frequently used clothes for a specific period.

[0100] Step 3:

[0101] The server generates recycling or resale suggestion data for the listed garments.

[0102] Step 4:

[0103] The server transmits the generated proposal data to the user's terminal.

[0104] Step 5:

[0105] The terminal notifies the user of the received proposal.

[0106] Process for linking with shopping sites

[0107] Step 1:

[0108] The user inputs the category and budget of the item they wish to purchase through the application.

[0109] Step 2:

[0110] The terminal transmits the input purchase information to the server.

[0111] Step 3:

[0112] The server calls the APIs of multiple linked shopping sites and retrieves product information that matches the criteria.

[0113] Step 4:

[0114] The server generates the optimal purchase link based on the product information acquired.

[0115] Step 5:

[0116] The server sends the generated purchase link to the user's terminal.

[0117] Step 6:

[0118] The terminal presents the received purchase link to the user.

[0119] User and Coordinator Matching Process

[0120] Step 1:

[0121] A user sends a request from an application for advice from a coordinator.

[0122] Step 2:

[0123] The terminal sends the user's request to the server.

[0124] Step 3:

[0125] A matching algorithm is executed based on the coordinator list held by the server.

[0126] Step 4:

[0127] The server selects an appropriate coordinator and generates a matching result.

[0128] Step 5:

[0129] The server notifies the user of the matching results.

[0130] Step 6:

[0131] The terminal presents the received matching results to the user.

[0132] These are the specific processing steps of the system, which allows users to efficiently and smartly manage their clothes, get outfit suggestions, purchase new clothes, recycle and resell, and connect with professional outfit designers.

[0133] Example 1

[0134] 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."

[0135] Today's consumers tend to own a wide variety of clothing, and managing and coordinating them on a daily basis requires a great deal of time and effort. Infrequently worn clothes can easily end up forgotten in the closet, and finding the right items can be difficult when buying new ones. Furthermore, there are still challenges in getting professional advice for special events. A system that solves these problems and allows people to enjoy fashion efficiently and smartly is needed.

[0136] 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.

[0137] In this invention, the server includes means for receiving images of clothing photographed by a user, means for generating three-dimensional data of the clothing from the received images, means for classifying the generated three-dimensional data by attributes such as color and shape, means for saving the classified clothing data in a database, means for suggesting outfits based on the saved clothing data and taking into account season, weather, temperature, and trend information, means for notifying the user of the suggested outfits, means for recording the user's clothing usage, means for identifying infrequently used clothing from the recorded usage information and suggesting recycling or resale, means for linking with multiple purchasing sites to enable the user to purchase new clothing in bulk, means for matching the user with a professional outfitter, means for the user to input a desired category and budget for purchasing new clothing, means for acquiring weather information and temperature, and means for generating outfit suggestions using a generative AI model based on the conditions entered by the user. This allows the user to manage their clothing, get outfit suggestions, purchase, resell, and collaborate with professional outfitters in a unified manner.

[0138] "User" refers to an individual or group that uses the system to manage clothing and receive coordination suggestions.

[0139] A "terminal" refers to a device that a user owns and connects to the system for use, and specifically includes smartphones and tablets.

[0140] "Server" means a central computing device that processes, stores and presents data submitted by users.

[0141] The "means for receiving images" refers to a process or device that transfers the clothing image data sent from the terminal to the server.

[0142] "Means for generating three-dimensional data" refers to software or algorithms for generating a three-dimensional model of the garment from received image data.

[0143] "Means for classifying by attributes such as color, shape, etc." refers to the algorithm or software used to classify the generated 3D data into categories such as color, shape, style, etc.

[0144] "Means for storing in a database" refers to a data management system and storage for long-term storage of classified clothing data.

[0145] "Means for suggesting outfits" refers to processes or software that provide optimal outfits to users based on stored clothing data and external information.

[0146] "Means for notifying a user of a coordinated outfit" refers to a communication system and software for transmitting suggested coordinated outfit information to a user's terminal.

[0147] "Means for recording the usage of clothing" refers to an interface and data storage system for inputting and recording information about clothing worn by a user.

[0148] "Recycle or resale suggestion mechanism" refers to a process or notification system for suggesting to users to recycle or resell gently used clothing.

[0149] "Buying Site" refers to an online platform that sells clothing over the Internet and allows users to purchase them.

[0150] "Professional coordinator" refers to a person or organization who is a fashion professional and provides styling advice to users.

[0151] A "generative AI model" refers to a computer model that uses artificial intelligence technology to generate optimal outfits from text and images.

[0152] A "prompt" is text that is input into a generative AI model and is an instruction that the model uses to make coordination suggestions.

[0153] The present invention is a system for efficiently managing a user's clothing and suggesting outfits based on that clothing. This system starts when a user takes a photo of the clothing with their device and uploads the image to a server. The specific operation method of the system is described below.

[0154] Photographing and uploading clothing

[0155] First, the user takes a photo of the clothing using a device (such as a smartphone or tablet) with the dedicated application installed. It is recommended that the photo be taken in sufficient light so that the entire clothing is clearly visible. The user then presses the upload button in the application to send the image to the server. The protocol used for this transmission is an HTTP request.

[0156] Image analysis and 3D data generation

[0157] The server uses image analysis software (e.g., OpenCV or TensorFlow) to analyze the received images. The server extracts feature points from the images and generates three-dimensional data (3D models). Specifically, it creates a 3D model of the clothing using a deep learning model (e.g., YOLO, Mask R-CNN).

[0158] Data classification and storage

[0159] The server classifies the generated 3D data by attributes such as color, shape, and style. A machine learning algorithm (e.g., K-means clustering) is used for classification. The classified data is then stored in a database (e.g., MySQL or PostgreSQL), allowing for quick search and reference later.

[0160] Coordination suggestions

[0161] The server compares the stored clothing data with external information obtained from a weather API (e.g., OpenWeatherMap) to suggest optimal outfits. Using a generative AI model, it makes outfit suggestions based on the user's input criteria. The suggested outfits are sent to the user's device as push notifications.

[0162] As a concrete example, a user takes a photo of a white shirt and uploads the image from their device to a server. The server generates three-dimensional data of a white long-sleeved shirt from the received image and stores that data in a database. Later, if the weather is sunny and the temperature is 23 degrees, the server will use that information to suggest a combination of the white shirt and casual chinos and notify the user's device.

[0163] Usage management and recycling / resale suggestions

[0164] Users can record their clothing usage through the application (e.g., by entering the date of wear). The server analyzes the recorded data and uses Pandas and NumPy to calculate how often the clothing has been used. If the clothing is deemed to have been used infrequently, the server sends a notification to the user's device suggesting that the clothing be recycled or resold.

[0165] Linking with purchasing sites

[0166] When a user wants to buy new clothes, the system provides a way for them to input their desired category and budget by linking with multiple purchasing sites. The server then searches for the best products based on the input criteria and provides a link to purchase them.

[0167] Collaboration with professional coordinators

[0168] Users can request the advice of professional coordinators for special events, and the server will select an appropriate coordinator and provide advice according to the user's request.

[0169] Prompt Sentence Examples

[0170] "Please suggest a casual outfit using a white shirt. The weather is sunny and the temperature is 23 degrees."

[0171] In this way, the present invention provides a comprehensive system that makes users' lives more efficient and smarter by enabling them to manage their clothing, suggest outfits, purchase, resell, and even collaborate with professional coordinators in a unified manner.

[0172] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0173] Step 1:

[0174] The user takes a photo of the clothing using a device with a dedicated application installed. It is recommended that the photo be taken in sufficient light so that the entire clothing is clearly visible. This captured image is the data input to the next step. The device then sends the image data to the server. An HTTP request is used for transmission.

[0175] Input: Image data of clothing

[0176] Output: Image data sent to the server

[0177] Step 2:

[0178] The server processes the image data of the clothing received from the device. First, it analyzes the image using image analysis software (e.g., OpenCV, TensorFlow). At this time, the server extracts feature points from the image and generates three-dimensional data (3D model). The generated 3D model is input into the next step.

[0179] Input: Image data of clothing

[0180] Output: Analyzed 3D model

[0181] Step 3:

[0182] The server classifies the generated 3D data by attributes such as color, shape, and style using machine learning algorithms (e.g., K-means clustering), and stores the classified data in a database.

[0183] Input: 3D model

[0184] Output: Classified clothing data

[0185] Step 4:

[0186] The server then uses the classified clothing data to suggest outfits, taking into account the season, weather, temperature, and trend information. To do this, the server obtains relevant information from weather APIs (e.g., OpenWeatherMap) and other sources. It also uses a generative AI model to suggest outfits based on the user's input. The results are then sent to the user's device.

[0187] Input: Categorized clothing data, as well as information on seasons, weather, temperature, and trends

[0188] Output: Coordination suggestions

[0189] Step 5:

[0190] The server notifies the user of the proposed outfit. This notification is performed using a push notification system. The user receives the notification and can check the proposed outfit.

[0191] Input: Coordination suggestion

[0192] Output: Coordination suggestions notified to the user

[0193] Step 6:

[0194] Users record their clothing usage through a dedicated application (e.g., by entering the date of wear), and this data is sent to and stored on a server.

[0195] Input: Usage data

[0196] Output: Saved usage data

[0197] Step 7:

[0198] The server analyzes the frequency of clothing use from the recorded usage information. This analysis is performed using data processing libraries (e.g., Pandas, NumPy). When infrequently used clothing is identified, the server suggests recycling or reselling the clothing. This suggestion is sent to the user's device.

[0199] Input: Usage data

[0200] Output: Recycle or resell offer

[0201] Step 8:

[0202] When a user wants to buy new clothes, they input their desired category and budget through a dedicated application. The server connects with multiple purchasing sites, searches for the best products based on the input criteria, and provides a link to purchase them.

[0203] Input: desired category and budget

[0204] Output: Purchase link

[0205] Step 9:

[0206] Users can request professional coordinator advice for special events, and the server will select an appropriate coordinator and provide advice based on the request.

[0207] Input: Coordinator Request

[0208] Output: Coordination advice

[0209] (Application example 1)

[0210] 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."

[0211] In modern life, there is a great demand for systems that can efficiently manage the clothes a user owns and suggest outfits based on that clothing. However, conventional clothing management systems and outfit suggestion systems have difficulty responding flexibly to the usage and frequency of individual clothes and fluctuations in the external environment (season, weather, temperature). Furthermore, there is a lack of a means for easily connecting users with professional stylists. Therefore, the challenge is to provide a system that can optimally manage and utilize a user's clothing, comprehensively and efficiently suggest new clothing purchases and recycling of unwanted clothing.

[0212] 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.

[0213] In this invention, the server includes a means for receiving images of clothing photographed by the user, a means for generating three-dimensional data of the clothing from the received images, and a means for classifying the generated three-dimensional data by attributes such as color and shape. This allows the user to efficiently manage their clothing and provide optimal coordination and recycling suggestions that take external information into account. Furthermore, by collaborating with professional stylists, the system can provide more specialized advice to users. Furthermore, data can be stored and analyzed via a cloud server, allowing for the centralized management of clothing data photographed by users, resulting in a highly convenient system.

[0214] "Image receiving means" refers to a device or software for receiving image data of clothing photographed by a user.

[0215] "Three-dimensional data generation means" refers to technology or equipment for three-dimensionally reproducing the shape and size of clothing from received image data.

[0216] "Attribute classification means" refers to technology or equipment for classifying generated three-dimensional data by characteristics such as color, shape, and style.

[0217] "Database storage means" refers to a device or software for recording and storing classified clothing data, making it easy to search and use later.

[0218] The "coordination suggestion means" is a technology that suggests optimal clothing combinations based on stored data, taking into consideration external factors and user information.

[0219] "Notification means" refers to a device or software for notifying the user of suggested coordination and related information.

[0220] "Usage recording means" refers to technology or devices for recording data on how a user wears clothing.

[0221] "Recycling suggestion means" refers to technology or equipment that suggests recycling or reselling clothing that is rarely used or no longer needed.

[0222] "Electronic commerce site linking means" refers to technology or devices that link with multiple online shopping sites, allowing users to purchase new clothes all at once.

[0223] "Stylist matching means" refers to technology or devices that match users with professional fashion stylists and enable them to receive expert advice and outfit suggestions.

[0224] A "cloud server" is a data storage and processing function on a server that can be accessed via the Internet, and is used to centrally manage clothing data photographed by users.

[0225] "Image analysis" is a technology that analyzes received images of clothing and identifies their attributes, such as color and shape.

[0226] "Database storage" is the process of storing analyzed data so that it can be easily searched and used later.

[0227] A "professional stylist" is someone who has specialized knowledge and skills in fashion and provides users with advice on coordinating outfits.

[0228] The "chat function" is a function that allows users and professional stylists to exchange text information in real time.

[0229] The "video consulting function" allows users to consult and receive advice on coordination between themselves and professional stylists via video call.

[0230] This invention is a system for efficiently managing a user's clothing and suggesting outfits based on that clothing. The system starts when a user takes a photo of their clothing using a device such as a smartphone and uploads the image to a cloud server.

[0231] The server generates 3D data from the received images using image analysis technology and classifies the 3D data by attributes such as color and shape. This allows accurate clothing data to be stored in a database. Specifically, image analysis and classification algorithms using Python (e.g., OpenCV and TensorFlow) are used.

[0232] The server uses the stored data to suggest optimal outfits to users, taking into account external information such as the season, weather, temperature, and trend information. This involves using an API to obtain weather forecast information and current fashion trends. The suggestions are sent to the user's device, where the user can confirm the received outfit suggestions. The notification function is performed through a dedicated smartphone app (for example, an iOS or Android app).

[0233] Furthermore, based on the user's own recorded wearing information, the server accumulates information on the user's clothing usage and analyzes the frequency of use. If clothing that has been used infrequently is identified, the server will provide the user with suggestions for recycling or reselling the clothing. The system also links to multiple e-commerce sites and provides links to purchase new clothing.

[0234] Matching with professional stylists is also an important function of this system. Users can chat with stylists and conduct video consultations through a dedicated app. This function is achieved by combining a video calling system using WebRTC technology with a real-time chat app (such as Firebase Realtime Database or Socket.IO).

[0235] For example, suppose a user takes a photo of a white shirt and uploads the image from their device to a server. The server generates three-dimensional data of a white long-sleeved shirt from the received image and stores that data in a database. If the weather is sunny and the temperature is 23 degrees Celsius at a later date, the server will use that information to suggest coordinating the white shirt with casual chinos and notify the user's device. Data is also accumulated showing that the user wears the shirt once a week, and if the user wears the shirt infrequently, a notification is sent to the user's device suggesting that the shirt be put up for sale on a flea market site.

[0236] The stored data and the proposed algorithm are optimized based on user feedback, allowing for more appropriate outfit suggestions. For example, a generative AI model can be used to input prompts and update the algorithm based on user feedback.

[0237] An example of a prompt is:

[0238] "A user has uploaded an image of XXX. Please analyze this image and classify its color and shape attributes. Then, based on weather information, please suggest the best outfit for the user."

[0239] Examples include:

[0240] In this way, the present invention allows users to manage their clothing, suggest outfits, purchase, resell, and even collaborate with professional stylists in a unified manner, enabling users to enjoy fashion efficiently and smartly.

[0241] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0242] Step 1:

[0243] The user takes a photo of the clothes they own using the device. The user takes a photo of the clothes they own using the smartphone camera. This image becomes the input data for the next processing step.

[0244] Step 2:

[0245] The captured image is uploaded to the server. The device then sends the captured image over the Internet to a server on the cloud. The image received by the server becomes input data and is used for the next process.

[0246] Step 3:

[0247] The server performs image analysis. From the received images, the server generates 3D data of the clothing using a generative AI model. During this analysis process, data processing is performed to classify attributes such as color and shape. The generated 3D data becomes the input for the next step.

[0248] Step 4:

[0249] The 3D data is stored in a database. The server classifies the generated 3D data by attributes such as color and shape, and stores it in the database. This stored data is the data necessary for coordinating outfits.

[0250] Step 5:

[0251] Collecting external information. The server uses API to collect information on seasons, weather, temperature, and trends. This external information is used as input data for the outfit suggestion algorithm.

[0252] Step 6:

[0253] Generates coordination suggestions. The server generates optimal coordination suggestions for the user based on the collected external information and clothing data stored in the database. This suggestion algorithm is realized by a generative AI model on the server.

[0254] Step 7:

[0255] The server notifies the user of the coordination proposal. The server notifies the user of the coordination proposal via a dedicated application. The user confirms the proposal, which leads to the next step.

[0256] Step 8:

[0257] Records the wearing information. When a user wears clothes based on the coordination suggestions, the wearing information is recorded on the device. This data is sent to the server and added to the user's usage database.

[0258] Step 9:

[0259] Analyze frequency of use. The server analyzes the frequency of use of each piece of clothing based on the accumulated wearing information. Using this analysis data, identifying clothes that are used less frequently leads to the next step.

[0260] Step 10:

[0261] Generate recycling and resale suggestions: The server identifies clothes that are rarely used and generates recycling and resale suggestions to notify the user. These suggestions are sent to the user's device.

[0262] Step 11:

[0263] Suggesting new clothing items: The server connects with multiple e-commerce sites to suggest new clothing items based on the user's preferences and budget. Links to suggested items are also included, allowing the user to purchase them.

[0264] Step 12:

[0265] It allows users to connect with professional stylists through chat and video consultations with professional stylists via a dedicated app. This feature uses real-time chat and video calling technology.

[0266] Example prompt sentence:

[0267] "A user has uploaded an image of XXX. Please analyze this image and classify its color and shape attributes. Then, based on weather information, please suggest the best outfit for the user."

[0268] 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.

[0269] This invention is a system for efficiently managing a user's clothing and suggesting outfits based on that clothing. The system starts when the user takes a photo of the clothing with their device and uploads the image to a server. The server generates three-dimensional data from the received image and classifies it by attributes such as color and shape. The classified data is then stored in a database.

[0270] The user launches a dedicated application and takes a photo of the garment. The device has the function to upload the captured image to a server. The server analyzes the received image and generates 3D data based on the analysis results. This 3D data is categorized by attributes such as color, shape, and style, and the categorized data is stored in a database.

[0271] Based on the stored data, the server takes into account external information such as the season, weather, temperature, and trend information to suggest the most suitable outfit for the user. This suggestion is sent to the user's device, and the user can confirm the received outfit suggestion.

[0272] Furthermore, based on the user's own recorded wearing information, the server will accumulate information on clothing usage and analyze frequency of use. If clothing that has been used infrequently is identified, the server will also provide suggestions to the user on how to recycle or resell this clothing.

[0273] The system also incorporates an emotion engine for analyzing the user's emotions. When the user takes a photo of their face with their device, the server analyzes the image and recognizes the user's emotions. Based on the recognized emotions, the server adjusts the outfit suggestions. For example, if the user is feeling stressed, the server may suggest relaxing clothing.

[0274] Emotion analysis is also possible through voice input. When a user speaks to the application, the server analyzes the voice data and recognizes the emotion. Based on this, coordination suggestions can be made.

[0275] As a specific example, a user takes a photo of a white shirt and uploads the image from their device to a server. The server generates three-dimensional data of a white long-sleeved shirt from the received image and stores that data in a database. When the user then points their face toward the camera, the device sends the facial image to the server. The server recognizes from the facial image that the user is tired and suggests a white shirt and casual chinos as a relaxing outfit.

[0276] Furthermore, if a user says "I'm a little tired" through voice input, the server will analyze it and suggest a relaxing outfit to relieve fatigue. It is also possible to save the user's emotional history and reflect it in the next outfit suggestion. In this way, by making suggestions based on the user's emotional state, it is possible to provide a more personalized service.

[0277] This system is linked to multiple shopping sites, so when a user wants to buy new clothes, they can enter their desired category and budget, and the server will search for and suggest the most suitable products and provide a purchase link.

[0278] The service also has a function that matches users with professional coordinators. When a user requests stylist advice for a special event, the server selects an appropriate coordinator and the user receives advice based on the request.

[0279] In this way, the present invention allows users to manage their clothing, suggest outfits, purchase, resell, and even collaborate with professional fashion coordinators in a unified manner, allowing users to enjoy fashion efficiently and smartly. Furthermore, by taking into account the user's emotional state, more personalized suggestions can be made, improving user satisfaction.

[0280] The processing flow will be explained below.

[0281] Garment photography and upload process

[0282] Step 1:

[0283] The user launches a dedicated application on the device and selects the "photograph clothing" function.

[0284] Step 2:

[0285] The device's camera is activated, and the user points the camera at the clothing they want to photograph and takes a photo.

[0286] Step 3:

[0287] The device displays the captured image and prompts the user to confirm. The user confirms and selects "Save."

[0288] Step 4:

[0289] The device uploads the saved images to a dedicated server.

[0290] Step 5:

[0291] The server receives the uploaded images and stores them in a database.

[0292] 3D data generation and classification process

[0293] Step 1:

[0294] The server executes an algorithm to analyze the received image.

[0295] Step 2:

[0296] The server uses image analysis to identify specific attributes of the clothing (e.g., shirt, pants, etc.).

[0297] Step 3:

[0298] The server generates three-dimensional data from the images of the identified garments.

[0299] Step 4:

[0300] The server classifies the generated 3D data by attributes such as color, shape, and style.

[0301] Step 5:

[0302] The server stores the classified clothing data in a database.

[0303] Coordination proposal process

[0304] Step 1:

[0305] The server retrieves the stored clothing information from the user's clothing database.

[0306] Step 2:

[0307] The server retrieves season, weather, temperature, and trend information from an external API.

[0308] Step 3:

[0309] Based on the above information, the server generates the most suitable outfit for the user.

[0310] Step 4:

[0311] The server transmits the generated coordinate information to the user's terminal.

[0312] Step 5:

[0313] The terminal notifies the user of the received coordination proposal.

[0314] Accumulation process of clothing usage

[0315] Step 1:

[0316] The user inputs information about the clothes they are wearing today through the application.

[0317] Step 2:

[0318] The terminal transmits the input wearing information to the server.

[0319] Step 3:

[0320] The server stores the received wearing information in a database.

[0321] Step 4:

[0322] The server runs a counting algorithm to calculate how often each garment is used.

[0323] Step 5:

[0324] The server generates data to notify the user based on the frequency of use.

[0325] The process of proposing to open a store on a flea market site

[0326] Step 1:

[0327] The server analyzes the accumulated data on the frequency of use of clothing.

[0328] Step 2:

[0329] The server lists the least frequently used clothes for a specific period.

[0330] Step 3:

[0331] The server generates recycling or resale suggestion data for the listed garments.

[0332] Step 4:

[0333] The server transmits the generated proposal data to the user's terminal.

[0334] Step 5:

[0335] The terminal notifies the user of the received proposal.

[0336] Process for linking with shopping sites

[0337] Step 1:

[0338] The user inputs the category and budget of the item they wish to purchase through the application.

[0339] Step 2:

[0340] The terminal transmits the input purchase information to the server.

[0341] Step 3:

[0342] The server calls the APIs of multiple linked shopping sites and retrieves product information that matches the criteria.

[0343] Step 4:

[0344] The server generates the optimal purchase link based on the product information acquired.

[0345] Step 5:

[0346] The server sends the generated purchase link to the user's terminal.

[0347] Step 6:

[0348] The terminal presents the received purchase link to the user.

[0349] User and Coordinator Matching Process

[0350] Step 1:

[0351] A user sends a request from an application for advice from a coordinator.

[0352] Step 2:

[0353] The terminal sends the user's request to the server.

[0354] Step 3:

[0355] A matching algorithm is executed based on the coordinator list held by the server.

[0356] Step 4:

[0357] The server selects an appropriate coordinator and generates a matching result.

[0358] Step 5:

[0359] The server notifies the user of the matching results.

[0360] Step 6:

[0361] The terminal presents the received matching results to the user.

[0362] Processing process using emotion engine

[0363] Step 1:

[0364] The user inputs a face image or voice through the application.

[0365] Step 2:

[0366] The terminal transmits the captured face image or voice data to the server.

[0367] Step 3:

[0368] The server runs a sentiment analysis algorithm based on the data it receives.

[0369] Step 4:

[0370] The server adjusts the coordination proposal based on the user's emotions recognized.

[0371] Step 5:

[0372] The server transmits the adjusted coordinate information to the user's terminal.

[0373] Step 6:

[0374] The terminal notifies the user of the received coordination proposal.

[0375] Step 7:

[0376] The user inputs feedback on the proposed outfit.

[0377] Step 8:

[0378] The device sends the feedback to the server.

[0379] Step 9:

[0380] The server optimizes the proposed algorithm based on the feedback.

[0381] These are the processing steps of the present invention, which incorporates an emotion engine that recognizes the user's emotions. This allows users to efficiently and intelligently manage their clothes, get outfit suggestions, purchase new clothes, recycle and resell, and connect with professional coordinators. Personalized suggestions based on emotion recognition can further improve user satisfaction.

[0382] Example 2

[0383] 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."

[0384] Conventional methods for managing clothing and suggesting outfits are often cumbersome and time-consuming for users. Furthermore, outfit suggestions that take into account the user's emotional state, the season, weather conditions, and fashion trends are not adequately implemented. As a result, it is difficult for users to enjoy efficient and personalized fashion. Furthermore, the lack of functionality to suggest reuse or resale of infrequently used clothing results in insufficient utilization of clothing. Therefore, the present invention aims to provide a system that streamlines clothing management and suggests outfits, and can make suggestions that reflect the user's emotional state and external information.

[0385] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving images of clothes photographed by a user, means for generating three-dimensional data of the clothes from the received images, means for classifying the generated three-dimensional data by attributes such as color and shape, means for saving the classified clothing data in a database, means for proposing outfits based on the saved clothing data and taking into account seasons, weather conditions, temperature, and fashion information, means for notifying the user of the suggested outfits, means for recording the user's clothing usage, means for identifying infrequently used clothes from the recorded usage information and proposing reuse or resale, means for linking with multiple e-commerce sites to enable users to purchase new clothes in bulk, means for matching users with experts, means for receiving a user's facial image and analyzing emotions, means for adjusting the outfit suggestions based on the emotion analysis results, means for receiving voice input and analyzing the voice data to recognize emotions, and means for adjusting the outfit suggestions based on the emotion recognition results. This improves the efficiency of clothing management and enables personalized outfit suggestions that reflect the user's emotions and external information. It also encourages the reuse and resale of clothing that is used less frequently, optimizing the use of clothing.

[0386] A "user" is a customer who uses the system to manage their clothing and receive coordination suggestions.

[0387] "Clothing image" is photographic data of clothing taken by a user using a terminal.

[0388] "Three-dimensional data" is data that aggregates three-dimensional shapes and attribute information generated from images of clothing.

[0389] "Classification" is the process of organizing the generated 3D data by attributes such as color, shape, and style.

[0390] A "database" is an information management system for storing classified clothing data.

[0391] "Season, weather conditions, temperature, and fashion information" is external environmental information that is taken into consideration when suggesting outfits.

[0392] "Coordination suggestions" refers to presenting optimal clothing combinations to users based on stored clothing data and external information.

[0393] "Notification" is a means by which the server conveys information such as coordination suggestions to the user's terminal.

[0394] "Usage status" is information indicating how frequently the user uses each piece of clothing.

[0395] "Usage information" is data that records the date and number of times the user has used the clothing.

[0396] "Reuse or resale" refers to the offer to repurpose or sell gently used clothing.

[0397] An "e-commerce site" is an online marketplace where users can purchase new clothing.

[0398] An "expert" is a person with specialized knowledge of fashion who gives coordination advice to the user.

[0399] A "face image" is photographic data of a user's own face taken with a terminal.

[0400] "Emotion analysis" is the process of recognizing a user's emotional state from facial images and voice data.

[0401] "Voice input" refers to voice data that is input by the user speaking into the terminal.

[0402] "Emotion recognition" is the process of identifying a user's emotions from speech data.

[0403] The present invention relates to a system for efficiently managing clothing owned by a user and proposing outfit coordination based on the managed clothing. Hereinafter, an embodiment of the system will be described in detail.

[0404] Overall system configuration

[0405] The system's main components are a terminal, a server, and a database. It also utilizes various software and APIs to realize functions such as image analysis, data management, outfit suggestions, emotion analysis, voice recognition, and online shopping.

[0406] Hardware and software used

[0407] The device used is a smartphone or tablet equipped with a camera, which allows users to take pictures of their clothes and their own faces.

[0408] The server is a high-performance computer that runs an image analysis engine, a database management system, and an AI model (e.g., TensorFlow or OpenCV).

[0409] The database uses a relational database management system (RDBMS, such as MySQL or PostgreSQL).

[0410] Program processing flow

[0411] 1. Photographing and uploading the garment:

[0412] The user launches the dedicated application and takes a picture of the garment using the camera, after which the device uploads the image to the server.

[0413] 2. Image analysis and 3D data generation:

[0414] The server uses an image analysis engine to analyze the received images and generate 3D data of the clothing. Image processing libraries such as TensorFlow and OpenCV are used for image analysis.

[0415] 3. Data Storage and Classification:

[0416] The server classifies the 3D data generated based on the analysis results by attributes such as color, shape, and style, and stores the classified data in a database.

[0417] 4. Coordination suggestions:

[0418] The server obtains external information such as the season, weather conditions, temperature, and fashion trends, and suggests optimal outfits to users based on the saved 3D data. The server uses the OpenWeatherMap API to obtain external information. The suggested outfits are then sent to the user via their device.

[0419] 5. Clothing usage analysis:

[0420] When a user enters their clothing information into their application, the device sends that information to a server, which analyzes the frequency of use based on the accumulated data and suggests reuse or resale of infrequently worn clothing.

[0421] 6. Sentiment analysis and suggestion adjustment:

[0422] The user inputs their emotional state using images or voice. The captured facial image is uploaded from the device to a server, which then uses an emotion analysis engine to recognize the emotion. The voice input data is also sent to the server and converted to text using, for example, the Google Cloud Speech-to-Text API. The outfit suggestions are then adjusted based on the emotion recognition results.

[0423] 7. Collaboration with shopping sites:

[0424] When a user wants to buy new clothes, they input their request through the terminal, and the server retrieves data from multiple e-commerce sites and suggests the best products to the user, for example, using the Amazon Product Advertising API.

[0425] 8. Matching with a professional coordinator:

[0426] When a user requests advice from a stylist for a specific event, they send a special request, and the server selects the most suitable person from the registered coordinators and matches them with the user.

[0427] Specific examples

[0428] As a concrete use case, consider the following scenario:

[0429] The user takes a photo of a white shirt and uploads the image from their device to the server. The server analyzes the image, identifies it as a white shirt, generates three-dimensional data, and stores it in a database. If the user then feels tired, they can notify the server via their device using a facial image or voice. The server then performs emotion analysis and suggests relaxing outfits to soothe fatigue.

[0430] Prompt Sentence Examples

[0431] "You take a photo of a white shirt and upload it to the server. Then you use the camera to take a photo of your face and receive outfit suggestions based on your emotional state. If you're tired, we'll suggest outfits that will help you relax."

[0432] In this way, the present invention provides a system that improves the efficiency of managing the clothes owned by the user and suggesting outfits, allowing the user to enjoy fashion comfortably.

[0433] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0434] Step 1:

[0435] The user launches the dedicated application and takes a picture of the garment using the camera, at which point the camera application installed on the device captures a high-resolution image.

[0436] Input: A user-taken image of the clothing

[0437] Output: Image file of the clothing saved on the device

[0438] Step 2:

[0439] The device uploads the captured image of the clothing to a server, where it is securely transmitted using HTTPS.

[0440] Input: Image file of clothing saved on the device

[0441] Output: Images of the garment uploaded to the server

[0442] Step 3:

[0443] The server analyzes the received images and generates 3D data of the clothing. Specifically, it processes the images with a deep learning model using TensorFlow and OpenCV to extract the 3D shape.

[0444] Input: Images of clothing uploaded to the server

[0445] Output: 3D data of the generated garment

[0446] Step 4:

[0447] The server classifies the generated 3D data by attributes such as color, shape, and style, using machine learning algorithms.

[0448] Input: 3D data of the generated clothing

[0449] Output: Classified clothing data

[0450] Step 5:

[0451] The server stores the classified data in a database, which is then inserted into the database (e.g., MySQL or PostgreSQL) using SQL queries.

[0452] Input: Categorized clothing data

[0453] Output: Clothing data stored in a database

[0454] Step 6:

[0455] The server uses external APIs to obtain external information such as seasons, weather conditions, temperature, and trend information. Examples of APIs used include the OpenWeatherMap API.

[0456] Input: Request for external information obtained from API

[0457] Output: The external information obtained

[0458] Step 7:

[0459] The server runs an algorithm based on the stored data and external information to suggest the best outfits for the user. In this case, a generative AI model is used.

[0460] Input: Garment data and external information stored in the database

[0461] Output: Proposed coordinate data

[0462] Step 8:

[0463] The device receives coordination suggestions from the server and displays an interface to notify the user. Push notifications may also be used.

[0464] Input: Coordination proposal data sent from the server

[0465] Output: Coordination suggestions displayed to the user

[0466] Step 9:

[0467] The wearing information entered by the user is recorded on the terminal. Once the input is complete, the terminal sends the wearing information to the server.

[0468] Input: Wearing information entered by the user

[0469] Output: Wearing information sent to the server

[0470] Step 10:

[0471] The server analyzes the frequency of use based on the accumulated wearing information, and uses SQL to retrieve data from the database, aggregate and analyze it.

[0472] Input: Wearing information stored on the server

[0473] Output: Analysis results on frequency of use

[0474] Step 11:

[0475] The server identifies gently used clothing and makes suggestions for reuse or resale, which are then notified to the user.

[0476] Input: Analysis results on frequency of use

[0477] Output: Proposal data for reuse or resale

[0478] Step 12:

[0479] The user takes a picture of their face with the device, which then uploads the captured image to the server.

[0480] Input: A face image taken by the user

[0481] Output: Face image uploaded to the server

[0482] Step 13:

[0483] The server analyzes the facial image and recognizes the user's emotions. Image recognition is performed using OpenCV or deep learning models, for example.

[0484] Input: Face image uploaded to the server

[0485] Output: Recognized user emotion data

[0486] Step 14:

[0487] The server adjusts the outfit suggestions based on the emotion recognition results, selecting outfits that will alleviate emotions such as stress and fatigue.

[0488] Input: Recognized user emotion data

[0489] Output: Adjusted coordinate suggestion data

[0490] Step 15:

[0491] The user speaks to the application to provide voice input, and the device sends the voice data to the server.

[0492] Input: Voice data spoken by the user

[0493] Output: Audio data sent to the server

[0494] Step 16:

[0495] The server analyzes the voice data and recognizes the user's emotions. It converts the voice data into text using the Google Cloud Speech-to-Text API and then analyzes the emotions.

[0496] Input: Audio data sent to the server

[0497] Output: Translated speech data and recognized emotion data

[0498] Step 17:

[0499] The server adjusts the coordination suggestions based on the emotion recognition results, allowing suggestions to be tailored to the user's emotions.

[0500] Input: Recognized emotion data

[0501] Output: Adjusted coordinate suggestion data

[0502] Step 18:

[0503] The user inputs their desired clothing purchase, and the terminal sends the desired category and budget to the server.

[0504] Input: New purchase request (category and budget) entered by the user

[0505] Output: Purchase request data sent to the server

[0506] Step 19:

[0507] The server searches for product information from multiple e-commerce sites, using the Amazon Product Advertising API, etc.

[0508] Input: Purchase request data sent to the server

[0509] Output: Retrieved product information data

[0510] Step 20:

[0511] The server selects the most suitable product based on the search results and provides the user with a purchase link.

[0512] Input: Retrieved product information data

[0513] Output: Purchase link and product information provided to the user

[0514] Step 21:

[0515] The user requests advice from a stylist. The device sends the request to the server.

[0516] Input: A user-entered request for stylist advice

[0517] Output: Request data sent to the server

[0518] Step 22:

[0519] The server selects the most suitable coordinator based on the information of registered coordinators and matches it with the user.

[0520] Input: Coordinator information stored on the server and user request data

[0521] Output: Selected coordinator information and matching results

[0522] The above is a description of the specific operations and inputs and outputs for each processing step of the program of this system.

[0523] (Application example 2)

[0524] 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."

[0525] Traditionally, managing a user's clothing and suggesting outfits was often done manually, which was time-consuming and labor-intensive. Furthermore, outfit suggestions that took into account the user's emotions and external environment were rarely provided, making it difficult to increase user satisfaction. Furthermore, there were cases where infrequently worn clothing was not managed and collaboration with professional outfit coordinators was not fully implemented, preventing efficient clothing utilization.

[0526] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0527] In this invention, the server includes means for receiving images of clothing photographed by a user, means for generating three-dimensional data of the clothing from the received images, means for classifying the generated three-dimensional data by attributes such as color and shape, means for saving the classified clothing data in a database, means for suggesting outfits based on the saved clothing data and taking into account season, weather, temperature, and trend information, means for notifying the user of the suggested outfits, means for recording the user's clothing usage, means for identifying infrequently used clothing from the recorded usage information and suggesting recycling or resale, means for linking with multiple purchasing sites to enable the user to purchase new clothing in bulk, means for matching users with experts, means for receiving a user's facial image or voice input and analyzing emotions, and means for adjusting the outfit suggestions based on the analyzed emotions. This enables more accurate and personalized clothing management and outfit suggestions that take into account the user's emotions and external environment.

[0528] "User" refers to an individual who uses the system to manage clothing and receive coordination suggestions.

[0529] "Clothing image" refers to photographic data of specific clothing that a user takes and uploads to the system.

[0530] "Three-dimensional data" is three-dimensional data generated from an image and has attributes such as the color and shape of clothing.

[0531] "Database" means an information management system for storing classified garment data and other related information.

[0532] "Coordination suggestions" refers to suggestions to the user for appropriate clothing combinations based on stored clothing data and external information.

[0533] "Notification" refers to the act of sending and informing a user of suggested outfits and other information.

[0534] "Usage status" is information that records how much a user uses the clothing.

[0535] "Recycle or resell" is the act of offering to reuse gently used clothing.

[0536] "Shopping sites" are multiple online sales sites where users can purchase new clothing.

[0537] An "expert" is a professional with specialized knowledge about clothing coordination who provides advice to users.

[0538] "Emotion analysis" is a process that analyzes the user's facial image and voice input to recognize their current state of mind and emotions.

[0539] "Adjustment" refers to the act of optimizing the coordination suggestions to suit the user's emotional state based on the analyzed emotions.

[0540] The present invention provides a system for managing a user's clothing and for efficiently suggesting outfits based on that data. Hereinafter, an embodiment of the present invention will be described based on a specific operational example.

[0541] First, the user takes a picture of the clothing using their smartphone. The image is then uploaded to a server via the smartphone's application. The server then analyzes the received image using the Google Cloud Vision API and generates 3D data with attributes such as the color and shape of the clothing. This 3D data is then stored in a database such as MySQL.

[0542] Based on the stored data, the server takes into account the season, weather, temperature, and trend information to suggest appropriate outfits. These suggestions are provided to the user via the smartphone's notification function. In particular, when the user takes a facial image or enters voice input, the respective data is sent to the server, and emotions are analyzed using the Microsoft Azure Emotion API. Based on the analyzed emotions, the outfit suggestions are further adjusted.

[0543] For example, if a user takes a photo of a black jacket and uploads it to the application, the server generates three-dimensional data of the black jacket from the received image and stores it in a database. If the user then voice-inputs "It's cold today" into their smartphone, the server analyzes the voice data, recognizes that the user is feeling cold, and suggests corresponding outfits.

[0544] Furthermore, the server records the user's clothing usage and identifies infrequently worn clothing. The server then offers suggestions for recycling or reselling the identified clothing. The server also connects with multiple purchasing sites to offer shopping suggestions, allowing users to purchase desired new clothing all at once. For special events, the server matches users with experts to provide professional coordination advice.

[0545] Below are some example prompts for the generative AI model:

[0546] Example prompt sentence:

[0547] Please convert a photo of a black jacket taken by the user into 3D data using the image analysis API and save it in the user database. Also, please analyze the user's voice input "It's cold today" and suggest the warmest possible outfit.

[0548] Such a system allows users to manage their clothing and receive coordination suggestions in an efficient and personalized manner.

[0549] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0550] Step 1:

[0551] A user takes an image of the garment using a smartphone.

[0552] Input: Images of clothing

[0553] Output: Image data

[0554] The user uses the camera application on their smartphone to take a picture of the garment, and the captured image data is saved in the application.

[0555] Step 2:

[0556] The device uploads the captured image to the server.

[0557] Input: Saved image data

[0558] Output: Image data transferred to the server

[0559] The device (smartphone) uses an Internet connection to transfer the image data of the garment to the server. The data is transmitted via the HTTP protocol.

[0560] Step 3:

[0561] The server receives the image data and generates three-dimensional data using the Google Cloud Vision API.

[0562] Input: Image data

[0563] Output: 3D data

[0564] The server then sends the received image data to the Google Cloud Vision API, which analyzes attributes such as the color and shape of the clothing. Based on the results of this analysis, 3D data is generated.

[0565] Step 4:

[0566] The server classifies the generated 3D data by attributes such as color and shape and stores it in a MySQL database.

[0567] Input: 3D data

[0568] Output: Categorized database entries

[0569] The server classifies the 3D data by attributes such as color, shape, style, etc. The classified data is stored in a MySQL database.

[0570] Step 5:

[0571] The server generates coordination suggestions based on the stored data, taking into account the season, weather, temperature, and trend information.

[0572] Input: Stored clothing data, season, weather, temperature, trend information

[0573] Output: Coordination suggestions

[0574] The server uses the stored clothing data and external information (season, weather, temperature, trend information) to generate optimal coordination suggestions for the user.

[0575] Step 6:

[0576] The terminal notifies the user of the coordination proposal.

[0577] Input: Coordination suggestion

[0578] Output: User notification

[0579] The device will then send a push notification to the user informing them of the outfit suggestions received from the server, and the user can view the suggestions through their smartphone's notification function.

[0580] Step 7:

[0581] The user inputs a facial image or voice, and the device sends it to the server.

[0582] Input: Face image, voice input

[0583] Output: Facial image and audio data transferred to the server

[0584] Users use the smartphone's camera and microphone to input facial images and voice data, which are then sent to a server via an application.

[0585] Step 8:

[0586] The server analyzes facial images and voice data and recognizes the user's emotions using the Microsoft Azure Emotion API.

[0587] Input: face image, voice data

[0588] Output: Recognized emotion data

[0589] The server uses the Microsoft Azure Emotion API to analyze and recognize the user's emotional state from the facial images and voice data sent.

[0590] Step 9:

[0591] The server adjusts the coordination suggestions based on the analyzed emotional data.

[0592] Input: Emotion data, initial coordination proposal

[0593] Output: Tailored outfit suggestions

[0594] The server uses the analyzed emotion data to adjust the initial outfit suggestions depending on the user's emotions, for example, suggesting warm outfits if the user is feeling cold.

[0595] Step 10:

[0596] The server records the user's clothing usage, identifies less frequently used clothing, and suggests recycling or reselling it.

[0597] Input: Usage data

[0598] Output: Offer to recycle or resell

[0599] The server analyzes the user's usage frequency data and identifies clothes that are used less frequently, and based on that, makes suggestions to the user about recycling or reselling them.

[0600] 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.

[0601] 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.

[0602] 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.

[0603] [Second embodiment]

[0604] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0605] 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.

[0606] 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).

[0607] 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.

[0608] 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.

[0609] 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).

[0610] 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.

[0611] 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.

[0612] 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.

[0613] 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.

[0614] 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.

[0615] 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."

[0616] This invention is a system for efficiently managing a user's clothing and suggesting outfits based on that clothing. The system starts when the user takes a photo of the clothing with their device and uploads the image to a server. The server generates three-dimensional data from the received image and classifies it by attributes such as color and shape. The classified data is then stored in a database.

[0617] The user launches a dedicated application and takes a photo of the garment. The device has the function to upload the captured image to a server. The server analyzes the received image and generates 3D data based on the analysis results. This 3D data is categorized by attributes such as color, shape, and style, and the categorized data is stored in a database.

[0618] Based on the stored data, the server takes into account external information such as the season, weather, temperature, and trend information to suggest the most suitable outfit for the user. This suggestion is sent to the user's device, and the user can confirm the received outfit suggestion.

[0619] Furthermore, based on the user's own recorded wearing information, the server will accumulate information on clothing usage and analyze frequency of use. If clothing that has been used infrequently is identified, the server will also provide suggestions to the user on how to recycle or resell this clothing.

[0620] As a specific example, a user takes a photo of a white shirt and uploads the image from their device to a server. The server generates three-dimensional data of a white long-sleeved shirt from the received image and stores that data in a database. Later, if the weather is sunny and the temperature is 23 degrees, the server will use that information to suggest coordinating the white shirt with casual chinos and notify the user's device. Data is also accumulated showing that the user wears the shirt once a week, and if the user wears the shirt infrequently, a notification is sent to the user's device suggesting that the shirt be put up for sale on a flea market site.

[0621] In addition, the system is linked to multiple shopping sites, so when a user wants to buy new clothes, they can enter their desired category and budget, and the server will search for and suggest the most suitable products and provide a purchase link.

[0622] The service also has a function that matches users with professional coordinators. When a user requests stylist advice for a special event, the server selects an appropriate coordinator and the user receives advice based on the request.

[0623] In this way, the present invention allows users to manage their clothing, suggest outfits, purchase, resell, and even collaborate with professional coordinators in a unified manner, enabling users to enjoy fashion efficiently and smartly.

[0624] The processing flow will be explained below.

[0625] Garment photography and upload process

[0626] Step 1:

[0627] The user launches a dedicated application on the device and selects the "photograph clothing" function.

[0628] Step 2:

[0629] The device's camera is activated, and the user points the camera at the clothing they want to photograph and takes a photo.

[0630] Step 3:

[0631] The device displays the captured image and prompts the user to confirm. The user confirms and selects "Save."

[0632] Step 4:

[0633] The device uploads the saved images to a dedicated server.

[0634] Step 5:

[0635] The server receives the uploaded images and stores them in a database.

[0636] 3D data generation and classification process

[0637] Step 1:

[0638] The server executes an algorithm to analyze the received image.

[0639] Step 2:

[0640] The server uses image analysis to identify specific attributes of the clothing (e.g., shirt, pants, etc.).

[0641] Step 3:

[0642] The server generates three-dimensional data from the images of the identified garments.

[0643] Step 4:

[0644] The server classifies the generated 3D data by attributes such as color, shape, and style.

[0645] Step 5:

[0646] The server stores the classified clothing data in a database.

[0647] Coordination proposal process

[0648] Step 1:

[0649] The server retrieves the stored clothing information from the user's clothing database.

[0650] Step 2:

[0651] The server retrieves season, weather, temperature, and trend information from an external API.

[0652] Step 3:

[0653] Based on the above information, the server generates the most suitable outfit for the user.

[0654] Step 4:

[0655] The server transmits the generated coordinate information to the user's terminal.

[0656] Step 5:

[0657] The terminal notifies the user of the received coordination proposal.

[0658] Accumulation process of clothing usage

[0659] Step 1:

[0660] The user inputs information about the clothes they are wearing today through the application.

[0661] Step 2:

[0662] The terminal transmits the input wearing information to the server.

[0663] Step 3:

[0664] The server stores the received wearing information in a database.

[0665] Step 4:

[0666] The server runs a counting algorithm to calculate how often each garment is used.

[0667] Step 5:

[0668] The server generates data to notify the user based on the frequency of use.

[0669] The process of proposing to open a store on a flea market site

[0670] Step 1:

[0671] The server analyzes the accumulated data on the frequency of use of clothing.

[0672] Step 2:

[0673] The server lists the least frequently used clothes for a specific period.

[0674] Step 3:

[0675] The server generates recycling or resale suggestion data for the listed garments.

[0676] Step 4:

[0677] The server transmits the generated proposal data to the user's terminal.

[0678] Step 5:

[0679] The terminal notifies the user of the received proposal.

[0680] Process for linking with shopping sites

[0681] Step 1:

[0682] The user inputs the category and budget of the item they wish to purchase through the application.

[0683] Step 2:

[0684] The terminal transmits the input purchase information to the server.

[0685] Step 3:

[0686] The server calls the APIs of multiple linked shopping sites and retrieves product information that matches the criteria.

[0687] Step 4:

[0688] The server generates the optimal purchase link based on the product information acquired.

[0689] Step 5:

[0690] The server sends the generated purchase link to the user's terminal.

[0691] Step 6:

[0692] The terminal presents the received purchase link to the user.

[0693] User and Coordinator Matching Process

[0694] Step 1:

[0695] A user sends a request from an application for advice from a coordinator.

[0696] Step 2:

[0697] The terminal sends the user's request to the server.

[0698] Step 3:

[0699] A matching algorithm is executed based on the coordinator list held by the server.

[0700] Step 4:

[0701] The server selects an appropriate coordinator and generates a matching result.

[0702] Step 5:

[0703] The server notifies the user of the matching results.

[0704] Step 6:

[0705] The terminal presents the received matching results to the user.

[0706] These are the specific processing steps of the system, which allows users to efficiently and smartly manage their clothes, get outfit suggestions, purchase new clothes, recycle and resell, and connect with professional outfit designers.

[0707] Example 1

[0708] 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."

[0709] Today's consumers tend to own a wide variety of clothing, and managing and coordinating them on a daily basis requires a great deal of time and effort. Infrequently worn clothes can easily end up forgotten in the closet, and finding the right items can be difficult when buying new ones. Furthermore, there are still challenges in getting professional advice for special events. A system that solves these problems and allows people to enjoy fashion efficiently and smartly is needed.

[0710] 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.

[0711] In this invention, the server includes means for receiving images of clothing photographed by a user, means for generating three-dimensional data of the clothing from the received images, means for classifying the generated three-dimensional data by attributes such as color and shape, means for saving the classified clothing data in a database, means for suggesting outfits based on the saved clothing data and taking into account season, weather, temperature, and trend information, means for notifying the user of the suggested outfits, means for recording the user's clothing usage, means for identifying infrequently used clothing from the recorded usage information and suggesting recycling or resale, means for linking with multiple purchasing sites to enable the user to purchase new clothing in bulk, means for matching the user with a professional outfitter, means for the user to input a desired category and budget for purchasing new clothing, means for acquiring weather information and temperature, and means for generating outfit suggestions using a generative AI model based on the conditions entered by the user. This allows the user to manage their clothing, get outfit suggestions, purchase, resell, and collaborate with professional outfitters in a unified manner.

[0712] "User" refers to an individual or group that uses the system to manage clothing and receive coordination suggestions.

[0713] A "terminal" refers to a device that a user owns and connects to the system for use, and specifically includes smartphones and tablets.

[0714] "Server" means a central computing device that processes, stores and presents data submitted by users.

[0715] The "means for receiving images" refers to a process or device that transfers the clothing image data sent from the terminal to the server.

[0716] "Means for generating three-dimensional data" refers to software or algorithms for generating a three-dimensional model of the garment from received image data.

[0717] "Means for classifying by attributes such as color, shape, etc." refers to the algorithm or software used to classify the generated 3D data into categories such as color, shape, style, etc.

[0718] "Means for storing in a database" refers to a data management system and storage for long-term storage of classified clothing data.

[0719] "Means for suggesting outfits" refers to processes or software that provide optimal outfits to users based on stored clothing data and external information.

[0720] "Means for notifying a user of a coordinated outfit" refers to a communication system and software for transmitting suggested coordinated outfit information to a user's terminal.

[0721] "Means for recording the usage of clothing" refers to an interface and data storage system for inputting and recording information about clothing worn by a user.

[0722] "Recycle or resale suggestion mechanism" refers to a process or notification system for suggesting to users to recycle or resell gently used clothing.

[0723] "Buying Site" refers to an online platform that sells clothing over the Internet and allows users to purchase them.

[0724] "Professional coordinator" refers to a person or organization who is a fashion professional and provides styling advice to users.

[0725] A "generative AI model" refers to a computer model that uses artificial intelligence technology to generate optimal outfits from text and images.

[0726] A "prompt" is text that is input into a generative AI model and is an instruction that the model uses to make coordination suggestions.

[0727] The present invention is a system for efficiently managing a user's clothing and suggesting outfits based on that clothing. This system starts when a user takes a photo of the clothing with their device and uploads the image to a server. The specific operation method of the system is described below.

[0728] Photographing and uploading clothing

[0729] First, the user takes a photo of the clothing using a device (such as a smartphone or tablet) with the dedicated application installed. It is recommended that the photo be taken in sufficient light so that the entire clothing is clearly visible. The user then presses the upload button in the application to send the image to the server. The protocol used for this transmission is an HTTP request.

[0730] Image analysis and 3D data generation

[0731] The server uses image analysis software (e.g., OpenCV or TensorFlow) to analyze the received images. The server extracts feature points from the images and generates three-dimensional data (3D models). Specifically, it creates a 3D model of the clothing using a deep learning model (e.g., YOLO, Mask R-CNN).

[0732] Data classification and storage

[0733] The server classifies the generated 3D data by attributes such as color, shape, and style. A machine learning algorithm (e.g., K-means clustering) is used for classification. The classified data is then stored in a database (e.g., MySQL or PostgreSQL), allowing for quick search and reference later.

[0734] Coordination suggestions

[0735] The server compares the stored clothing data with external information obtained from a weather API (e.g., OpenWeatherMap) to suggest optimal outfits. Using a generative AI model, it makes outfit suggestions based on the user's input criteria. The suggested outfits are sent to the user's device as push notifications.

[0736] As a concrete example, a user takes a photo of a white shirt and uploads the image from their device to a server. The server generates three-dimensional data of a white long-sleeved shirt from the received image and stores that data in a database. Later, if the weather is sunny and the temperature is 23 degrees, the server will use that information to suggest a combination of the white shirt and casual chinos and notify the user's device.

[0737] Usage management and recycling / resale suggestions

[0738] Users can record their clothing usage through the application (e.g., by entering the date of wear). The server analyzes the recorded data and uses Pandas and NumPy to calculate how often the clothing has been used. If the clothing is deemed to have been used infrequently, the server sends a notification to the user's device suggesting that the clothing be recycled or resold.

[0739] Linking with purchasing sites

[0740] When a user wants to buy new clothes, the system provides a way for them to input their desired category and budget by linking with multiple purchasing sites. The server then searches for the best products based on the input criteria and provides a link to purchase them.

[0741] Collaboration with professional coordinators

[0742] Users can request the advice of professional coordinators for special events, and the server will select an appropriate coordinator and provide advice according to the user's request.

[0743] Prompt Sentence Examples

[0744] "Please suggest a casual outfit using a white shirt. The weather is sunny and the temperature is 23 degrees."

[0745] In this way, the present invention provides a comprehensive system that makes users' lives more efficient and smarter by enabling them to manage their clothing, suggest outfits, purchase, resell, and even collaborate with professional coordinators in a unified manner.

[0746] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0747] Step 1:

[0748] The user takes a photo of the clothing using a device with a dedicated application installed. It is recommended that the photo be taken in sufficient light so that the entire clothing is clearly visible. This captured image is the data input to the next step. The device then sends the image data to the server. An HTTP request is used for transmission.

[0749] Input: Image data of clothing

[0750] Output: Image data sent to the server

[0751] Step 2:

[0752] The server processes the image data of the clothing received from the device. First, it analyzes the image using image analysis software (e.g., OpenCV, TensorFlow). At this time, the server extracts feature points from the image and generates three-dimensional data (3D model). The generated 3D model is input into the next step.

[0753] Input: Image data of clothing

[0754] Output: Analyzed 3D model

[0755] Step 3:

[0756] The server classifies the generated 3D data by attributes such as color, shape, and style using machine learning algorithms (e.g., K-means clustering), and stores the classified data in a database.

[0757] Input: 3D model

[0758] Output: Classified clothing data

[0759] Step 4:

[0760] The server then uses the classified clothing data to suggest outfits, taking into account the season, weather, temperature, and trend information. To do this, the server obtains relevant information from weather APIs (e.g., OpenWeatherMap) and other sources. It also uses a generative AI model to suggest outfits based on the user's input. The results are then sent to the user's device.

[0761] Input: Categorized clothing data, as well as information on seasons, weather, temperature, and trends

[0762] Output: Coordination suggestions

[0763] Step 5:

[0764] The server notifies the user of the proposed outfit. This notification is performed using a push notification system. The user receives the notification and can check the proposed outfit.

[0765] Input: Coordination suggestion

[0766] Output: Coordination suggestions notified to the user

[0767] Step 6:

[0768] Users record their clothing usage through a dedicated application (e.g., by entering the date of wear), and this data is sent to and stored on a server.

[0769] Input: Usage data

[0770] Output: Saved usage data

[0771] Step 7:

[0772] The server analyzes the frequency of clothing use from the recorded usage information. This analysis is performed using data processing libraries (e.g., Pandas, NumPy). When infrequently used clothing is identified, the server suggests recycling or reselling the clothing. This suggestion is sent to the user's device.

[0773] Input: Usage data

[0774] Output: Recycle or resell offer

[0775] Step 8:

[0776] When a user wants to buy new clothes, they input their desired category and budget through a dedicated application. The server connects with multiple purchasing sites, searches for the best products based on the input criteria, and provides a link to purchase them.

[0777] Input: desired category and budget

[0778] Output: Purchase link

[0779] Step 9:

[0780] Users can request professional coordinator advice for special events, and the server will select an appropriate coordinator and provide advice based on the request.

[0781] Input: Coordinator Request

[0782] Output: Coordination advice

[0783] (Application example 1)

[0784] 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."

[0785] In modern life, there is a great demand for systems that can efficiently manage the clothes a user owns and suggest outfits based on that clothing. However, conventional clothing management systems and outfit suggestion systems have difficulty responding flexibly to the usage and frequency of individual clothes and fluctuations in the external environment (season, weather, temperature). Furthermore, there is a lack of a means for easily connecting users with professional stylists. Therefore, the challenge is to provide a system that can optimally manage and utilize a user's clothing, comprehensively and efficiently suggest new clothing purchases and recycling of unwanted clothing.

[0786] 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.

[0787] In this invention, the server includes a means for receiving images of clothing photographed by the user, a means for generating three-dimensional data of the clothing from the received images, and a means for classifying the generated three-dimensional data by attributes such as color and shape. This allows the user to efficiently manage their clothing and provide optimal coordination and recycling suggestions that take external information into account. Furthermore, by collaborating with professional stylists, the system can provide more specialized advice to users. Furthermore, data can be stored and analyzed via a cloud server, allowing for the centralized management of clothing data photographed by users, resulting in a highly convenient system.

[0788] "Image receiving means" refers to a device or software for receiving image data of clothing photographed by a user.

[0789] "Three-dimensional data generation means" refers to technology or equipment for three-dimensionally reproducing the shape and size of clothing from received image data.

[0790] "Attribute classification means" refers to technology or equipment for classifying generated three-dimensional data by characteristics such as color, shape, and style.

[0791] "Database storage means" refers to a device or software for recording and storing classified clothing data, making it easy to search and use later.

[0792] The "coordination suggestion means" is a technology that suggests optimal clothing combinations based on stored data, taking into consideration external factors and user information.

[0793] "Notification means" refers to a device or software for notifying the user of suggested coordination and related information.

[0794] "Usage recording means" refers to technology or devices for recording data on how a user wears clothing.

[0795] "Recycling suggestion means" refers to technology or equipment that suggests recycling or reselling clothing that is rarely used or no longer needed.

[0796] "Electronic commerce site linking means" refers to technology or devices that link with multiple online shopping sites, allowing users to purchase new clothes all at once.

[0797] "Stylist matching means" refers to technology or devices that match users with professional fashion stylists and enable them to receive expert advice and outfit suggestions.

[0798] A "cloud server" is a data storage and processing function on a server that can be accessed via the Internet, and is used to centrally manage clothing data photographed by users.

[0799] "Image analysis" is a technology that analyzes received images of clothing and identifies their attributes, such as color and shape.

[0800] "Database storage" is the process of storing analyzed data so that it can be easily searched and used later.

[0801] A "professional stylist" is someone who has specialized knowledge and skills in fashion and provides users with advice on coordinating outfits.

[0802] The "chat function" is a function that allows users and professional stylists to exchange text information in real time.

[0803] The "video consulting function" allows users to consult and receive advice on coordination between themselves and professional stylists via video call.

[0804] This invention is a system for efficiently managing a user's clothing and suggesting outfits based on that clothing. The system starts when a user takes a photo of their clothing using a device such as a smartphone and uploads the image to a cloud server.

[0805] The server generates 3D data from the received images using image analysis technology and classifies the 3D data by attributes such as color and shape. This allows accurate clothing data to be stored in a database. Specifically, image analysis and classification algorithms using Python (e.g., OpenCV and TensorFlow) are used.

[0806] The server uses the stored data to suggest optimal outfits to users, taking into account external information such as the season, weather, temperature, and trend information. This involves using an API to obtain weather forecast information and current fashion trends. The suggestions are sent to the user's device, where the user can confirm the received outfit suggestions. The notification function is performed through a dedicated smartphone app (for example, an iOS or Android app).

[0807] Furthermore, based on the user's own recorded wearing information, the server accumulates information on the user's clothing usage and analyzes the frequency of use. If clothing that has been used infrequently is identified, the server will provide the user with suggestions for recycling or reselling the clothing. The system also links to multiple e-commerce sites and provides links to purchase new clothing.

[0808] Matching with professional stylists is also an important function of this system. Users can chat with stylists and conduct video consultations through a dedicated app. This function is achieved by combining a video calling system using WebRTC technology with a real-time chat app (such as Firebase Realtime Database or Socket.IO).

[0809] For example, suppose a user takes a photo of a white shirt and uploads the image from their device to a server. The server generates three-dimensional data of a white long-sleeved shirt from the received image and stores that data in a database. If the weather is sunny and the temperature is 23 degrees Celsius at a later date, the server will use that information to suggest coordinating the white shirt with casual chinos and notify the user's device. Data is also accumulated showing that the user wears the shirt once a week, and if the user wears the shirt infrequently, a notification is sent to the user's device suggesting that the shirt be put up for sale on a flea market site.

[0810] The stored data and the proposed algorithm are optimized based on user feedback, allowing for more appropriate outfit suggestions. For example, a generative AI model can be used to input prompts and update the algorithm based on user feedback.

[0811] An example of a prompt is:

[0812] "A user has uploaded an image of XXX. Please analyze this image and classify its color and shape attributes. Then, based on weather information, please suggest the best outfit for the user."

[0813] Examples include:

[0814] In this way, the present invention allows users to manage their clothing, suggest outfits, purchase, resell, and even collaborate with professional stylists in a unified manner, enabling users to enjoy fashion efficiently and smartly.

[0815] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0816] Step 1:

[0817] The user takes a photo of the clothes they own using the device. The user takes a photo of the clothes they own using the smartphone camera. This image becomes the input data for the next processing step.

[0818] Step 2:

[0819] The captured image is uploaded to the server. The device then sends the captured image over the Internet to a server on the cloud. The image received by the server becomes input data and is used for the next process.

[0820] Step 3:

[0821] The server performs image analysis. From the received images, the server generates 3D data of the clothing using a generative AI model. During this analysis process, data processing is performed to classify attributes such as color and shape. The generated 3D data becomes the input for the next step.

[0822] Step 4:

[0823] The 3D data is stored in a database. The server classifies the generated 3D data by attributes such as color and shape, and stores it in the database. This stored data is the data necessary for coordinating outfits.

[0824] Step 5:

[0825] Collecting external information. The server uses API to collect information on seasons, weather, temperature, and trends. This external information is used as input data for the outfit suggestion algorithm.

[0826] Step 6:

[0827] Generates coordination suggestions. The server generates optimal coordination suggestions for the user based on the collected external information and clothing data stored in the database. This suggestion algorithm is realized by a generative AI model on the server.

[0828] Step 7:

[0829] The server notifies the user of the coordination proposal. The server notifies the user of the coordination proposal via a dedicated application. The user confirms the proposal, which leads to the next step.

[0830] Step 8:

[0831] Records the wearing information. When a user wears clothes based on the coordination suggestions, the wearing information is recorded on the device. This data is sent to the server and added to the user's usage database.

[0832] Step 9:

[0833] Analyze frequency of use. The server analyzes the frequency of use of each piece of clothing based on the accumulated wearing information. Using this analysis data, identifying clothes that are used less frequently leads to the next step.

[0834] Step 10:

[0835] Generate recycling and resale suggestions: The server identifies clothes that are rarely used and generates recycling and resale suggestions to notify the user. These suggestions are sent to the user's device.

[0836] Step 11:

[0837] Suggesting new clothing items: The server connects with multiple e-commerce sites to suggest new clothing items based on the user's preferences and budget. Links to suggested items are also included, allowing the user to purchase them.

[0838] Step 12:

[0839] It allows users to connect with professional stylists through chat and video consultations with professional stylists via a dedicated app. This feature uses real-time chat and video calling technology.

[0840] Example prompt sentence:

[0841] "A user has uploaded an image of XXX. Please analyze this image and classify its color and shape attributes. Then, based on weather information, please suggest the best outfit for the user."

[0842] 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.

[0843] This invention is a system for efficiently managing a user's clothing and suggesting outfits based on that clothing. The system starts when the user takes a photo of the clothing with their device and uploads the image to a server. The server generates three-dimensional data from the received image and classifies it by attributes such as color and shape. The classified data is then stored in a database.

[0844] The user launches a dedicated application and takes a photo of the garment. The device has the function to upload the captured image to a server. The server analyzes the received image and generates 3D data based on the analysis results. This 3D data is categorized by attributes such as color, shape, and style, and the categorized data is stored in a database.

[0845] Based on the stored data, the server takes into account external information such as the season, weather, temperature, and trend information to suggest the most suitable outfit for the user. This suggestion is sent to the user's device, and the user can confirm the received outfit suggestion.

[0846] Furthermore, based on the user's own recorded wearing information, the server will accumulate information on clothing usage and analyze frequency of use. If clothing that has been used infrequently is identified, the server will also provide suggestions to the user on how to recycle or resell this clothing.

[0847] The system also incorporates an emotion engine for analyzing the user's emotions. When the user takes a photo of their face with their device, the server analyzes the image and recognizes the user's emotions. Based on the recognized emotions, the server adjusts the outfit suggestions. For example, if the user is feeling stressed, the server may suggest relaxing clothing.

[0848] Emotion analysis is also possible through voice input. When a user speaks to the application, the server analyzes the voice data and recognizes the emotion. Based on this, coordination suggestions can be made.

[0849] As a specific example, a user takes a photo of a white shirt and uploads the image from their device to a server. The server generates three-dimensional data of a white long-sleeved shirt from the received image and stores that data in a database. When the user then points their face toward the camera, the device sends the facial image to the server. The server recognizes from the facial image that the user is tired and suggests a white shirt and casual chinos as a relaxing outfit.

[0850] Furthermore, if a user says "I'm a little tired" through voice input, the server will analyze it and suggest a relaxing outfit to relieve fatigue. It is also possible to save the user's emotional history and reflect it in the next outfit suggestion. In this way, by making suggestions based on the user's emotional state, it is possible to provide a more personalized service.

[0851] This system is linked to multiple shopping sites, so when a user wants to buy new clothes, they can enter their desired category and budget, and the server will search for and suggest the most suitable products and provide a purchase link.

[0852] The service also has a function that matches users with professional coordinators. When a user requests stylist advice for a special event, the server selects an appropriate coordinator and the user receives advice based on the request.

[0853] In this way, the present invention allows users to manage their clothing, suggest outfits, purchase, resell, and even collaborate with professional fashion coordinators in a unified manner, allowing users to enjoy fashion efficiently and smartly. Furthermore, by taking into account the user's emotional state, more personalized suggestions can be made, improving user satisfaction.

[0854] The processing flow will be explained below.

[0855] Garment photography and upload process

[0856] Step 1:

[0857] The user launches a dedicated application on the device and selects the "photograph clothing" function.

[0858] Step 2:

[0859] The device's camera is activated, and the user points the camera at the clothing they want to photograph and takes a photo.

[0860] Step 3:

[0861] The device displays the captured image and prompts the user to confirm. The user confirms and selects "Save."

[0862] Step 4:

[0863] The device uploads the saved images to a dedicated server.

[0864] Step 5:

[0865] The server receives the uploaded images and stores them in a database.

[0866] 3D data generation and classification process

[0867] Step 1:

[0868] The server executes an algorithm to analyze the received image.

[0869] Step 2:

[0870] The server uses image analysis to identify specific attributes of the clothing (e.g., shirt, pants, etc.).

[0871] Step 3:

[0872] The server generates three-dimensional data from the images of the identified garments.

[0873] Step 4:

[0874] The server classifies the generated 3D data by attributes such as color, shape, and style.

[0875] Step 5:

[0876] The server stores the classified clothing data in a database.

[0877] Coordination proposal process

[0878] Step 1:

[0879] The server retrieves the stored clothing information from the user's clothing database.

[0880] Step 2:

[0881] The server retrieves season, weather, temperature, and trend information from an external API.

[0882] Step 3:

[0883] Based on the above information, the server generates the most suitable outfit for the user.

[0884] Step 4:

[0885] The server transmits the generated coordinate information to the user's terminal.

[0886] Step 5:

[0887] The terminal notifies the user of the received coordination proposal.

[0888] Accumulation process of clothing usage

[0889] Step 1:

[0890] The user inputs information about the clothes they are wearing today through the application.

[0891] Step 2:

[0892] The terminal transmits the input wearing information to the server.

[0893] Step 3:

[0894] The server stores the received wearing information in a database.

[0895] Step 4:

[0896] The server runs a counting algorithm to calculate how often each garment is used.

[0897] Step 5:

[0898] The server generates data to notify the user based on the frequency of use.

[0899] The process of proposing to open a store on a flea market site

[0900] Step 1:

[0901] The server analyzes the accumulated data on the frequency of use of clothing.

[0902] Step 2:

[0903] The server lists the least frequently used clothes for a specific period.

[0904] Step 3:

[0905] The server generates recycling or resale suggestion data for the listed garments.

[0906] Step 4:

[0907] The server transmits the generated proposal data to the user's terminal.

[0908] Step 5:

[0909] The terminal notifies the user of the received proposal.

[0910] Process for linking with shopping sites

[0911] Step 1:

[0912] The user inputs the category and budget of the item they wish to purchase through the application.

[0913] Step 2:

[0914] The terminal transmits the input purchase information to the server.

[0915] Step 3:

[0916] The server calls the APIs of multiple linked shopping sites and retrieves product information that matches the criteria.

[0917] Step 4:

[0918] The server generates the optimal purchase link based on the product information acquired.

[0919] Step 5:

[0920] The server sends the generated purchase link to the user's terminal.

[0921] Step 6:

[0922] The terminal presents the received purchase link to the user.

[0923] User and Coordinator Matching Process

[0924] Step 1:

[0925] A user sends a request from an application for advice from a coordinator.

[0926] Step 2:

[0927] The terminal sends the user's request to the server.

[0928] Step 3:

[0929] A matching algorithm is executed based on the coordinator list held by the server.

[0930] Step 4:

[0931] The server selects an appropriate coordinator and generates a matching result.

[0932] Step 5:

[0933] The server notifies the user of the matching results.

[0934] Step 6:

[0935] The terminal presents the received matching results to the user.

[0936] Processing process using emotion engine

[0937] Step 1:

[0938] The user inputs a face image or voice through the application.

[0939] Step 2:

[0940] The terminal transmits the captured face image or voice data to the server.

[0941] Step 3:

[0942] The server runs a sentiment analysis algorithm based on the data it receives.

[0943] Step 4:

[0944] The server adjusts the coordination proposal based on the user's emotions recognized.

[0945] Step 5:

[0946] The server transmits the adjusted coordinate information to the user's terminal.

[0947] Step 6:

[0948] The terminal notifies the user of the received coordination proposal.

[0949] Step 7:

[0950] The user inputs feedback on the proposed outfit.

[0951] Step 8:

[0952] The device sends the feedback to the server.

[0953] Step 9:

[0954] The server optimizes the proposed algorithm based on the feedback.

[0955] These are the processing steps of the present invention, which incorporates an emotion engine that recognizes the user's emotions. This allows users to efficiently and intelligently manage their clothes, get outfit suggestions, purchase new clothes, recycle and resell, and connect with professional coordinators. Personalized suggestions based on emotion recognition can further improve user satisfaction.

[0956] Example 2

[0957] 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."

[0958] Conventional methods for managing clothing and suggesting outfits are often cumbersome and time-consuming for users. Furthermore, outfit suggestions that take into account the user's emotional state, the season, weather conditions, and fashion trends are not adequately implemented. As a result, it is difficult for users to enjoy efficient and personalized fashion. Furthermore, the lack of functionality to suggest reuse or resale of infrequently used clothing results in insufficient utilization of clothing. Therefore, the present invention aims to provide a system that streamlines clothing management and suggests outfits, and can make suggestions that reflect the user's emotional state and external information.

[0959] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving images of clothes photographed by a user, means for generating three-dimensional data of the clothes from the received images, means for classifying the generated three-dimensional data by attributes such as color and shape, means for saving the classified clothing data in a database, means for proposing outfits based on the saved clothing data and taking into account seasons, weather conditions, temperature, and fashion information, means for notifying the user of the suggested outfits, means for recording the user's clothing usage, means for identifying infrequently used clothes from the recorded usage information and proposing reuse or resale, means for linking with multiple e-commerce sites to enable users to purchase new clothes in bulk, means for matching users with experts, means for receiving a user's facial image and analyzing emotions, means for adjusting the outfit suggestions based on the emotion analysis results, means for receiving voice input and analyzing the voice data to recognize emotions, and means for adjusting the outfit suggestions based on the emotion recognition results. This improves the efficiency of clothing management and enables personalized outfit suggestions that reflect the user's emotions and external information. It also encourages the reuse and resale of clothing that is used less frequently, optimizing the use of clothing.

[0960] A "user" is a customer who uses the system to manage their clothing and receive coordination suggestions.

[0961] "Clothing image" is photographic data of clothing taken by a user using a terminal.

[0962] "Three-dimensional data" is data that aggregates three-dimensional shapes and attribute information generated from images of clothing.

[0963] "Classification" is the process of organizing the generated 3D data by attributes such as color, shape, and style.

[0964] A "database" is an information management system for storing classified clothing data.

[0965] "Season, weather conditions, temperature, and fashion information" is external environmental information that is taken into consideration when suggesting outfits.

[0966] "Coordination suggestions" refers to presenting optimal clothing combinations to users based on stored clothing data and external information.

[0967] "Notification" is a means by which the server conveys information such as coordination suggestions to the user's terminal.

[0968] "Usage status" is information indicating how frequently the user uses each piece of clothing.

[0969] "Usage information" is data that records the date and number of times the user has used the clothing.

[0970] "Reuse or resale" refers to the offer to repurpose or sell gently used clothing.

[0971] An "e-commerce site" is an online marketplace where users can purchase new clothing.

[0972] An "expert" is a person with specialized knowledge of fashion who gives coordination advice to the user.

[0973] A "face image" is photographic data of a user's own face taken with a terminal.

[0974] "Emotion analysis" is the process of recognizing a user's emotional state from facial images and voice data.

[0975] "Voice input" refers to voice data that is input by the user speaking into the terminal.

[0976] "Emotion recognition" is the process of identifying a user's emotions from speech data.

[0977] The present invention relates to a system for efficiently managing clothing owned by a user and proposing outfit coordination based on the managed clothing. Hereinafter, an embodiment of the system will be described in detail.

[0978] Overall system configuration

[0979] The system's main components are a terminal, a server, and a database. It also utilizes various software and APIs to realize functions such as image analysis, data management, outfit suggestions, emotion analysis, voice recognition, and online shopping.

[0980] Hardware and software used

[0981] The device used is a smartphone or tablet equipped with a camera, which allows users to take pictures of their clothes and their own faces.

[0982] The server is a high-performance computer that runs an image analysis engine, a database management system, and an AI model (e.g., TensorFlow or OpenCV).

[0983] The database uses a relational database management system (RDBMS, such as MySQL or PostgreSQL).

[0984] Program processing flow

[0985] 1. Photographing and uploading the garment:

[0986] The user launches the dedicated application and takes a picture of the garment using the camera, after which the device uploads the image to the server.

[0987] 2. Image analysis and 3D data generation:

[0988] The server uses an image analysis engine to analyze the received images and generate 3D data of the clothing. Image processing libraries such as TensorFlow and OpenCV are used for image analysis.

[0989] 3. Data Storage and Classification:

[0990] The server classifies the 3D data generated based on the analysis results by attributes such as color, shape, and style, and stores the classified data in a database.

[0991] 4. Coordination suggestions:

[0992] The server obtains external information such as the season, weather conditions, temperature, and fashion trends, and suggests optimal outfits to users based on the saved 3D data. The server uses the OpenWeatherMap API to obtain external information. The suggested outfits are then sent to the user via their device.

[0993] 5. Clothing usage analysis:

[0994] When a user enters their clothing information into their application, the device sends that information to a server, which analyzes the frequency of use based on the accumulated data and suggests reuse or resale of infrequently worn clothing.

[0995] 6. Sentiment analysis and suggestion adjustment:

[0996] The user inputs their emotional state using images or voice. The captured facial image is uploaded from the device to a server, which then uses an emotion analysis engine to recognize the emotion. The voice input data is also sent to the server and converted to text using, for example, the Google Cloud Speech-to-Text API. The outfit suggestions are then adjusted based on the emotion recognition results.

[0997] 7. Collaboration with shopping sites:

[0998] When a user wants to buy new clothes, they input their request through the terminal, and the server retrieves data from multiple e-commerce sites and suggests the best products to the user, for example, using the Amazon Product Advertising API.

[0999] 8. Matching with a professional coordinator:

[1000] When a user requests advice from a stylist for a specific event, they send a special request, and the server selects the most suitable person from the registered coordinators and matches them with the user.

[1001] Specific examples

[1002] As a concrete use case, consider the following scenario:

[1003] The user takes a photo of a white shirt and uploads the image from their device to the server. The server analyzes the image, identifies it as a white shirt, generates three-dimensional data, and stores it in a database. If the user then feels tired, they can notify the server via their device using a facial image or voice. The server then performs emotion analysis and suggests relaxing outfits to soothe fatigue.

[1004] Prompt Sentence Examples

[1005] "You take a photo of a white shirt and upload it to the server. Then you use the camera to take a photo of your face and receive outfit suggestions based on your emotional state. If you're tired, we'll suggest outfits that will help you relax."

[1006] In this way, the present invention provides a system that improves the efficiency of managing the clothes owned by the user and suggesting outfits, allowing the user to enjoy fashion comfortably.

[1007] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1008] Step 1:

[1009] The user launches the dedicated application and takes a picture of the garment using the camera, at which point the camera application installed on the device captures a high-resolution image.

[1010] Input: A user-taken image of the clothing

[1011] Output: Image file of the clothing saved on the device

[1012] Step 2:

[1013] The device uploads the captured image of the clothing to a server, where it is securely transmitted using HTTPS.

[1014] Input: Image file of clothing saved on the device

[1015] Output: Images of the garment uploaded to the server

[1016] Step 3:

[1017] The server analyzes the received images and generates 3D data of the clothing. Specifically, it processes the images with a deep learning model using TensorFlow and OpenCV to extract the 3D shape.

[1018] Input: Images of clothing uploaded to the server

[1019] Output: 3D data of the generated garment

[1020] Step 4:

[1021] The server classifies the generated 3D data by attributes such as color, shape, and style, using machine learning algorithms.

[1022] Input: 3D data of the generated clothing

[1023] Output: Classified clothing data

[1024] Step 5:

[1025] The server stores the classified data in a database, which is then inserted into the database (e.g., MySQL or PostgreSQL) using SQL queries.

[1026] Input: Categorized clothing data

[1027] Output: Clothing data stored in a database

[1028] Step 6:

[1029] The server uses external APIs to obtain external information such as seasons, weather conditions, temperature, and trend information. Examples of APIs used include the OpenWeatherMap API.

[1030] Input: Request for external information obtained from API

[1031] Output: The external information obtained

[1032] Step 7:

[1033] The server runs an algorithm based on the stored data and external information to suggest the best outfits for the user. In this case, a generative AI model is used.

[1034] Input: Garment data and external information stored in the database

[1035] Output: Proposed coordinate data

[1036] Step 8:

[1037] The device receives coordination suggestions from the server and displays an interface to notify the user. Push notifications may also be used.

[1038] Input: Coordination proposal data sent from the server

[1039] Output: Coordination suggestions displayed to the user

[1040] Step 9:

[1041] The wearing information entered by the user is recorded on the terminal. Once the input is complete, the terminal sends the wearing information to the server.

[1042] Input: Wearing information entered by the user

[1043] Output: Wearing information sent to the server

[1044] Step 10:

[1045] The server analyzes the frequency of use based on the accumulated wearing information, and uses SQL to retrieve data from the database, aggregate and analyze it.

[1046] Input: Wearing information stored on the server

[1047] Output: Analysis results on frequency of use

[1048] Step 11:

[1049] The server identifies gently used clothing and makes suggestions for reuse or resale, which are then notified to the user.

[1050] Input: Analysis results on frequency of use

[1051] Output: Proposal data for reuse or resale

[1052] Step 12:

[1053] The user takes a picture of their face with the device, which then uploads the captured image to the server.

[1054] Input: A face image taken by the user

[1055] Output: Face image uploaded to the server

[1056] Step 13:

[1057] The server analyzes the facial image and recognizes the user's emotions. Image recognition is performed using OpenCV or deep learning models, for example.

[1058] Input: Face image uploaded to the server

[1059] Output: Recognized user emotion data

[1060] Step 14:

[1061] The server adjusts the outfit suggestions based on the emotion recognition results, selecting outfits that will alleviate emotions such as stress and fatigue.

[1062] Input: Recognized user emotion data

[1063] Output: Adjusted coordinate suggestion data

[1064] Step 15:

[1065] The user speaks to the application to provide voice input, and the device sends the voice data to the server.

[1066] Input: Voice data spoken by the user

[1067] Output: Audio data sent to the server

[1068] Step 16:

[1069] The server analyzes the voice data and recognizes the user's emotions. It converts the voice data into text using the Google Cloud Speech-to-Text API and then analyzes the emotions.

[1070] Input: Audio data sent to the server

[1071] Output: Translated speech data and recognized emotion data

[1072] Step 17:

[1073] The server adjusts the coordination suggestions based on the emotion recognition results, allowing suggestions to be tailored to the user's emotions.

[1074] Input: Recognized emotion data

[1075] Output: Adjusted coordinate suggestion data

[1076] Step 18:

[1077] The user inputs their desired clothing purchase, and the terminal sends the desired category and budget to the server.

[1078] Input: New purchase request (category and budget) entered by the user

[1079] Output: Purchase request data sent to the server

[1080] Step 19:

[1081] The server searches for product information from multiple e-commerce sites, using the Amazon Product Advertising API, etc.

[1082] Input: Purchase request data sent to the server

[1083] Output: Retrieved product information data

[1084] Step 20:

[1085] The server selects the most suitable product based on the search results and provides the user with a purchase link.

[1086] Input: Retrieved product information data

[1087] Output: Purchase link and product information provided to the user

[1088] Step 21:

[1089] The user requests advice from a stylist. The device sends the request to the server.

[1090] Input: A user-entered request for stylist advice

[1091] Output: Request data sent to the server

[1092] Step 22:

[1093] The server selects the most suitable coordinator based on the information of registered coordinators and matches it with the user.

[1094] Input: Coordinator information stored on the server and user request data

[1095] Output: Selected coordinator information and matching results

[1096] The above is a description of the specific operations and inputs and outputs for each processing step of the program of this system.

[1097] (Application example 2)

[1098] 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."

[1099] Traditionally, managing a user's clothing and suggesting outfits was often done manually, which was time-consuming and labor-intensive. Furthermore, outfit suggestions that took into account the user's emotions and external environment were rarely provided, making it difficult to increase user satisfaction. Furthermore, there were cases where infrequently worn clothing was not managed and collaboration with professional outfit coordinators was not fully implemented, preventing efficient clothing utilization.

[1100] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1101] In this invention, the server includes means for receiving images of clothing photographed by a user, means for generating three-dimensional data of the clothing from the received images, means for classifying the generated three-dimensional data by attributes such as color and shape, means for saving the classified clothing data in a database, means for suggesting outfits based on the saved clothing data and taking into account season, weather, temperature, and trend information, means for notifying the user of the suggested outfits, means for recording the user's clothing usage, means for identifying infrequently used clothing from the recorded usage information and suggesting recycling or resale, means for linking with multiple purchasing sites to enable the user to purchase new clothing in bulk, means for matching users with experts, means for receiving a user's facial image or voice input and analyzing emotions, and means for adjusting the outfit suggestions based on the analyzed emotions. This enables more accurate and personalized clothing management and outfit suggestions that take into account the user's emotions and external environment.

[1102] "User" refers to an individual who uses the system to manage clothing and receive coordination suggestions.

[1103] "Clothing image" refers to photographic data of specific clothing that a user takes and uploads to the system.

[1104] "Three-dimensional data" is three-dimensional data generated from an image and has attributes such as the color and shape of clothing.

[1105] "Database" means an information management system for storing classified garment data and other related information.

[1106] "Coordination suggestions" refers to suggestions to the user for appropriate clothing combinations based on stored clothing data and external information.

[1107] "Notification" refers to the act of sending and informing a user of suggested outfits and other information.

[1108] "Usage status" is information that records how much a user uses the clothing.

[1109] "Recycle or resell" is the act of offering to reuse gently used clothing.

[1110] "Shopping sites" are multiple online sales sites where users can purchase new clothing.

[1111] An "expert" is a professional with specialized knowledge about clothing coordination who provides advice to users.

[1112] "Emotion analysis" is a process that analyzes the user's facial image and voice input to recognize their current state of mind and emotions.

[1113] "Adjustment" refers to the act of optimizing the coordination suggestions to suit the user's emotional state based on the analyzed emotions.

[1114] The present invention provides a system for managing a user's clothing and for efficiently suggesting outfits based on that data. Hereinafter, an embodiment of the present invention will be described based on a specific operational example.

[1115] First, the user takes a picture of the clothing using their smartphone. The image is then uploaded to a server via the smartphone's application. The server then analyzes the received image using the Google Cloud Vision API and generates 3D data with attributes such as the color and shape of the clothing. This 3D data is then stored in a database such as MySQL.

[1116] Based on the stored data, the server takes into account the season, weather, temperature, and trend information to suggest appropriate outfits. These suggestions are provided to the user via the smartphone's notification function. In particular, when the user takes a facial image or enters voice input, the respective data is sent to the server, and emotions are analyzed using the Microsoft Azure Emotion API. Based on the analyzed emotions, the outfit suggestions are further adjusted.

[1117] For example, if a user takes a photo of a black jacket and uploads it to the application, the server generates three-dimensional data of the black jacket from the received image and stores it in a database. If the user then voice-inputs "It's cold today" into their smartphone, the server analyzes the voice data, recognizes that the user is feeling cold, and suggests corresponding outfits.

[1118] Furthermore, the server records the user's clothing usage and identifies infrequently worn clothing. The server then offers suggestions for recycling or reselling the identified clothing. The server also connects with multiple purchasing sites to offer shopping suggestions, allowing users to purchase desired new clothing all at once. For special events, the server matches users with experts to provide professional coordination advice.

[1119] Below are some example prompts for the generative AI model:

[1120] Example prompt sentence:

[1121] Please convert a photo of a black jacket taken by the user into 3D data using the image analysis API and save it in the user database. Also, please analyze the user's voice input "It's cold today" and suggest the warmest possible outfit.

[1122] Such a system allows users to manage their clothing and receive coordination suggestions in an efficient and personalized manner.

[1123] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1124] Step 1:

[1125] A user takes an image of the garment using a smartphone.

[1126] Input: Images of clothing

[1127] Output: Image data

[1128] The user uses the camera application on their smartphone to take a picture of the garment, and the captured image data is saved in the application.

[1129] Step 2:

[1130] The device uploads the captured image to the server.

[1131] Input: Saved image data

[1132] Output: Image data transferred to the server

[1133] The device (smartphone) uses an Internet connection to transfer the image data of the garment to the server. The data is transmitted via the HTTP protocol.

[1134] Step 3:

[1135] The server receives the image data and generates three-dimensional data using the Google Cloud Vision API.

[1136] Input: Image data

[1137] Output: 3D data

[1138] The server then sends the received image data to the Google Cloud Vision API, which analyzes attributes such as the color and shape of the clothing. Based on the results of this analysis, 3D data is generated.

[1139] Step 4:

[1140] The server classifies the generated 3D data by attributes such as color and shape and stores it in a MySQL database.

[1141] Input: 3D data

[1142] Output: Categorized database entries

[1143] The server classifies the 3D data by attributes such as color, shape, style, etc. The classified data is stored in a MySQL database.

[1144] Step 5:

[1145] The server generates coordination suggestions based on the stored data, taking into account the season, weather, temperature, and trend information.

[1146] Input: Stored clothing data, season, weather, temperature, trend information

[1147] Output: Coordination suggestions

[1148] The server uses the stored clothing data and external information (season, weather, temperature, trend information) to generate optimal coordination suggestions for the user.

[1149] Step 6:

[1150] The terminal notifies the user of the coordination proposal.

[1151] Input: Coordination suggestion

[1152] Output: User notification

[1153] The device will then send a push notification to the user informing them of the outfit suggestions received from the server, and the user can view the suggestions through their smartphone's notification function.

[1154] Step 7:

[1155] The user inputs a facial image or voice, and the device sends it to the server.

[1156] Input: Face image, voice input

[1157] Output: Facial image and audio data transferred to the server

[1158] Users use the smartphone's camera and microphone to input facial images and voice data, which are then sent to a server via an application.

[1159] Step 8:

[1160] The server analyzes facial images and voice data and recognizes the user's emotions using the Microsoft Azure Emotion API.

[1161] Input: face image, voice data

[1162] Output: Recognized emotion data

[1163] The server uses the Microsoft Azure Emotion API to analyze and recognize the user's emotional state from the facial images and voice data sent.

[1164] Step 9:

[1165] The server adjusts the coordination suggestions based on the analyzed emotional data.

[1166] Input: Emotion data, initial coordination proposal

[1167] Output: Tailored outfit suggestions

[1168] The server uses the analyzed emotion data to adjust the initial outfit suggestions depending on the user's emotions, for example, suggesting warm outfits if the user is feeling cold.

[1169] Step 10:

[1170] The server records the user's clothing usage, identifies less frequently used clothing, and suggests recycling or reselling it.

[1171] Input: Usage data

[1172] Output: Offer to recycle or resell

[1173] The server analyzes the user's usage frequency data and identifies clothes that are used less frequently, and based on that, makes suggestions to the user about recycling or reselling them.

[1174] 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.

[1175] 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.

[1176] 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.

[1177] [Third embodiment]

[1178] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1179] 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.

[1180] 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).

[1181] 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.

[1182] 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.

[1183] 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).

[1184] 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.

[1185] 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.

[1186] 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.

[1187] 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.

[1188] 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.

[1189] 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."

[1190] This invention is a system for efficiently managing a user's clothing and suggesting outfits based on that clothing. The system starts when the user takes a photo of the clothing with their device and uploads the image to a server. The server generates three-dimensional data from the received image and classifies it by attributes such as color and shape. The classified data is then stored in a database.

[1191] The user launches a dedicated application and takes a photo of the garment. The device has the function to upload the captured image to a server. The server analyzes the received image and generates 3D data based on the analysis results. This 3D data is categorized by attributes such as color, shape, and style, and the categorized data is stored in a database.

[1192] Based on the stored data, the server takes into account external information such as the season, weather, temperature, and trend information to suggest the most suitable outfit for the user. This suggestion is sent to the user's device, and the user can confirm the received outfit suggestion.

[1193] Furthermore, based on the user's own recorded wearing information, the server will accumulate information on clothing usage and analyze frequency of use. If clothing that has been used infrequently is identified, the server will also provide suggestions to the user on how to recycle or resell this clothing.

[1194] As a specific example, a user takes a photo of a white shirt and uploads the image from their device to a server. The server generates three-dimensional data of a white long-sleeved shirt from the received image and stores that data in a database. Later, if the weather is sunny and the temperature is 23 degrees, the server will use that information to suggest coordinating the white shirt with casual chinos and notify the user's device. Data is also accumulated showing that the user wears the shirt once a week, and if the user wears the shirt infrequently, a notification is sent to the user's device suggesting that the shirt be put up for sale on a flea market site.

[1195] In addition, the system is linked to multiple shopping sites, so when a user wants to buy new clothes, they can enter their desired category and budget, and the server will search for and suggest the most suitable products and provide a purchase link.

[1196] The service also has a function that matches users with professional coordinators. When a user requests stylist advice for a special event, the server selects an appropriate coordinator and the user receives advice based on the request.

[1197] In this way, the present invention allows users to manage their clothing, suggest outfits, purchase, resell, and even collaborate with professional coordinators in a unified manner, enabling users to enjoy fashion efficiently and smartly.

[1198] The processing flow will be explained below.

[1199] Garment photography and upload process

[1200] Step 1:

[1201] The user launches a dedicated application on the device and selects the "photograph clothing" function.

[1202] Step 2:

[1203] The device's camera is activated, and the user points the camera at the clothing they want to photograph and takes a photo.

[1204] Step 3:

[1205] The device displays the captured image and prompts the user to confirm. The user confirms and selects "Save."

[1206] Step 4:

[1207] The device uploads the saved images to a dedicated server.

[1208] Step 5:

[1209] The server receives the uploaded images and stores them in a database.

[1210] 3D data generation and classification process

[1211] Step 1:

[1212] The server executes an algorithm to analyze the received image.

[1213] Step 2:

[1214] The server uses image analysis to identify specific attributes of the clothing (e.g., shirt, pants, etc.).

[1215] Step 3:

[1216] The server generates three-dimensional data from the images of the identified garments.

[1217] Step 4:

[1218] The server classifies the generated 3D data by attributes such as color, shape, and style.

[1219] Step 5:

[1220] The server stores the classified clothing data in a database.

[1221] Coordination proposal process

[1222] Step 1:

[1223] The server retrieves the stored clothing information from the user's clothing database.

[1224] Step 2:

[1225] The server retrieves season, weather, temperature, and trend information from an external API.

[1226] Step 3:

[1227] Based on the above information, the server generates the most suitable outfit for the user.

[1228] Step 4:

[1229] The server transmits the generated coordinate information to the user's terminal.

[1230] Step 5:

[1231] The terminal notifies the user of the received coordination proposal.

[1232] Accumulation process of clothing usage

[1233] Step 1:

[1234] The user inputs information about the clothes they are wearing today through the application.

[1235] Step 2:

[1236] The terminal transmits the input wearing information to the server.

[1237] Step 3:

[1238] The server stores the received wearing information in a database.

[1239] Step 4:

[1240] The server runs a counting algorithm to calculate how often each garment is used.

[1241] Step 5:

[1242] The server generates data to notify the user based on the frequency of use.

[1243] The process of proposing to open a store on a flea market site

[1244] Step 1:

[1245] The server analyzes the accumulated data on the frequency of use of clothing.

[1246] Step 2:

[1247] The server lists the least frequently used clothes for a specific period.

[1248] Step 3:

[1249] The server generates recycling or resale suggestion data for the listed garments.

[1250] Step 4:

[1251] The server transmits the generated proposal data to the user's terminal.

[1252] Step 5:

[1253] The terminal notifies the user of the received proposal.

[1254] Process for linking with shopping sites

[1255] Step 1:

[1256] The user inputs the category and budget of the item they wish to purchase through the application.

[1257] Step 2:

[1258] The terminal transmits the input purchase information to the server.

[1259] Step 3:

[1260] The server calls the APIs of multiple linked shopping sites and retrieves product information that matches the criteria.

[1261] Step 4:

[1262] The server generates the optimal purchase link based on the product information acquired.

[1263] Step 5:

[1264] The server sends the generated purchase link to the user's terminal.

[1265] Step 6:

[1266] The terminal presents the received purchase link to the user.

[1267] User and Coordinator Matching Process

[1268] Step 1:

[1269] A user sends a request from an application for advice from a coordinator.

[1270] Step 2:

[1271] The terminal sends the user's request to the server.

[1272] Step 3:

[1273] A matching algorithm is executed based on the coordinator list held by the server.

[1274] Step 4:

[1275] The server selects an appropriate coordinator and generates a matching result.

[1276] Step 5:

[1277] The server notifies the user of the matching results.

[1278] Step 6:

[1279] The terminal presents the received matching results to the user.

[1280] These are the specific processing steps of the system, which allows users to efficiently and smartly manage their clothes, get outfit suggestions, purchase new clothes, recycle and resell, and connect with professional outfit coordinators.

[1281] Example 1

[1282] 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."

[1283] Today's consumers tend to own a wide variety of clothing, and managing and coordinating them on a daily basis requires a great deal of time and effort. Infrequently worn clothes can easily end up forgotten in the closet, and finding the right items can be difficult when buying new ones. Furthermore, there are still challenges in getting professional advice for special events. A system that solves these problems and allows people to enjoy fashion efficiently and smartly is needed.

[1284] 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.

[1285] In this invention, the server includes means for receiving images of clothing photographed by a user, means for generating three-dimensional data of the clothing from the received images, means for classifying the generated three-dimensional data by attributes such as color and shape, means for saving the classified clothing data in a database, means for suggesting outfits based on the saved clothing data and taking into account season, weather, temperature, and trend information, means for notifying the user of the suggested outfits, means for recording the user's clothing usage, means for identifying infrequently used clothing from the recorded usage information and suggesting recycling or resale, means for linking with multiple purchasing sites to enable the user to purchase new clothing in bulk, means for matching the user with a professional outfitter, means for the user to input a desired category and budget for purchasing new clothing, means for acquiring weather information and temperature, and means for generating outfit suggestions using a generative AI model based on the conditions entered by the user. This allows the user to manage their clothing, get outfit suggestions, purchase, resell, and collaborate with professional outfitters in a unified manner.

[1286] "User" refers to an individual or group that uses the system to manage clothing and receive coordination suggestions.

[1287] A "terminal" refers to a device that a user owns and connects to the system for use, and specifically includes smartphones and tablets.

[1288] "Server" means a central computing device that processes, stores and presents data submitted by users.

[1289] The "means for receiving images" refers to a process or device that transfers the clothing image data sent from the terminal to the server.

[1290] "Means for generating three-dimensional data" refers to software or algorithms for generating a three-dimensional model of the garment from received image data.

[1291] "Means for classifying by attributes such as color, shape, etc." refers to the algorithm or software used to classify the generated 3D data into categories such as color, shape, style, etc.

[1292] "Means for storing in a database" refers to a data management system and storage for long-term storage of classified clothing data.

[1293] "Means for suggesting outfits" refers to processes or software that provide optimal outfits to users based on stored clothing data and external information.

[1294] "Means for notifying a user of a coordinated outfit" refers to a communication system and software for transmitting suggested coordinated outfit information to a user's terminal.

[1295] "Means for recording the usage of clothing" refers to an interface and data storage system for inputting and recording information about clothing worn by a user.

[1296] "Recycle or resale suggestion mechanism" refers to a process or notification system for suggesting to users to recycle or resell gently used clothing.

[1297] "Buying Site" refers to an online platform that sells clothing over the Internet and allows users to purchase them.

[1298] "Professional coordinator" refers to a person or organization who is a fashion professional and provides styling advice to users.

[1299] A "generative AI model" refers to a computer model that uses artificial intelligence technology to generate optimal outfits from text and images.

[1300] A "prompt" is text that is input into a generative AI model and is an instruction that the model uses to make coordination suggestions.

[1301] The present invention is a system for efficiently managing a user's clothing and suggesting outfits based on that clothing. This system starts when a user takes a photo of the clothing with their device and uploads the image to a server. The specific operation method of the system is described below.

[1302] Photographing and uploading clothing

[1303] First, the user takes a photo of the clothing using a device (such as a smartphone or tablet) with the dedicated application installed. It is recommended that the photo be taken in sufficient light so that the entire clothing is clearly visible. The user then presses the upload button in the application to send the image to the server. The protocol used for this transmission is an HTTP request.

[1304] Image analysis and 3D data generation

[1305] The server uses image analysis software (e.g., OpenCV or TensorFlow) to analyze the received images. The server extracts feature points from the images and generates three-dimensional data (3D models). Specifically, it creates a 3D model of the clothing using a deep learning model (e.g., YOLO, Mask R-CNN).

[1306] Data classification and storage

[1307] The server classifies the generated 3D data by attributes such as color, shape, and style. A machine learning algorithm (e.g., K-means clustering) is used for classification. The classified data is then stored in a database (e.g., MySQL or PostgreSQL), allowing for quick search and reference later.

[1308] Coordination suggestions

[1309] The server compares the stored clothing data with external information obtained from a weather API (e.g., OpenWeatherMap) to suggest optimal outfits. Using a generative AI model, it makes outfit suggestions based on the user's input criteria. The suggested outfits are sent to the user's device as push notifications.

[1310] As a concrete example, a user takes a photo of a white shirt and uploads the image from their device to a server. The server generates three-dimensional data of a white long-sleeved shirt from the received image and stores that data in a database. Later, if the weather is sunny and the temperature is 23 degrees, the server will use that information to suggest a combination of the white shirt and casual chinos and notify the user's device.

[1311] Usage management and recycling / resale suggestions

[1312] Users can record their clothing usage through the application (e.g., by entering the date of wear). The server analyzes the recorded data and uses Pandas and NumPy to calculate how often the clothing has been used. If the clothing is deemed to have been used infrequently, the server sends a notification to the user's device suggesting that the clothing be recycled or resold.

[1313] Linking with purchasing sites

[1314] When a user wants to buy new clothes, the system provides a way for them to input their desired category and budget by linking with multiple purchasing sites. The server then searches for the best products based on the input criteria and provides a link to purchase them.

[1315] Collaboration with professional coordinators

[1316] Users can request the advice of professional coordinators for special events, and the server will select an appropriate coordinator and provide advice according to the user's request.

[1317] Prompt Sentence Examples

[1318] "Please suggest a casual outfit using a white shirt. The weather is sunny and the temperature is 23 degrees."

[1319] In this way, the present invention provides a comprehensive system that makes users' lives more efficient and smarter by enabling them to manage their clothing, suggest outfits, purchase, resell, and even collaborate with professional coordinators in a unified manner.

[1320] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1321] Step 1:

[1322] The user takes a photo of the clothing using a device with a dedicated application installed. It is recommended that the photo be taken in sufficient light so that the entire clothing is clearly visible. This captured image is the data input to the next step. The device then sends the image data to the server. An HTTP request is used for transmission.

[1323] Input: Image data of clothing

[1324] Output: Image data sent to the server

[1325] Step 2:

[1326] The server processes the image data of the clothing received from the device. First, it analyzes the image using image analysis software (e.g., OpenCV, TensorFlow). At this time, the server extracts feature points from the image and generates three-dimensional data (3D model). The generated 3D model is input into the next step.

[1327] Input: Image data of clothing

[1328] Output: Analyzed 3D model

[1329] Step 3:

[1330] The server classifies the generated 3D data by attributes such as color, shape, and style using machine learning algorithms (e.g., K-means clustering), and stores the classified data in a database.

[1331] Input: 3D model

[1332] Output: Classified clothing data

[1333] Step 4:

[1334] The server then uses the classified clothing data to suggest outfits, taking into account the season, weather, temperature, and trend information. To do this, the server obtains relevant information from weather APIs (e.g., OpenWeatherMap) and other sources. It also uses a generative AI model to suggest outfits based on the user's input. The results are then sent to the user's device.

[1335] Input: Categorized clothing data, as well as information on seasons, weather, temperature, and trends

[1336] Output: Coordination suggestions

[1337] Step 5:

[1338] The server notifies the user of the proposed outfit. This notification is performed using a push notification system. The user receives the notification and can check the proposed outfit.

[1339] Input: Coordination suggestion

[1340] Output: Coordination suggestions notified to the user

[1341] Step 6:

[1342] Users record their clothing usage through a dedicated application (e.g., by entering the date of wear), and this data is sent to and stored on a server.

[1343] Input: Usage data

[1344] Output: Saved usage data

[1345] Step 7:

[1346] The server analyzes the frequency of clothing use from the recorded usage information. This analysis is performed using data processing libraries (e.g., Pandas, NumPy). When infrequently used clothing is identified, the server suggests recycling or reselling the clothing. This suggestion is sent to the user's device.

[1347] Input: Usage data

[1348] Output: Recycle or resell offer

[1349] Step 8:

[1350] When a user wants to buy new clothes, they input their desired category and budget through a dedicated application. The server connects with multiple purchasing sites, searches for the best products based on the input criteria, and provides a link to purchase them.

[1351] Input: desired category and budget

[1352] Output: Purchase link

[1353] Step 9:

[1354] Users can request professional coordinator advice for special events, and the server will select an appropriate coordinator and provide advice based on the request.

[1355] Input: Coordinator Request

[1356] Output: Coordination advice

[1357] (Application example 1)

[1358] 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."

[1359] In modern life, there is a great demand for systems that can efficiently manage the clothes a user owns and suggest outfits based on that clothing. However, conventional clothing management systems and outfit suggestion systems have difficulty responding flexibly to the usage and frequency of individual clothes and fluctuations in the external environment (season, weather, temperature). Furthermore, there is a lack of a means for easily connecting users with professional stylists. Therefore, the challenge is to provide a system that can optimally manage and utilize a user's clothing, comprehensively and efficiently suggest new clothing purchases and recycling of unwanted clothing.

[1360] 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.

[1361] In this invention, the server includes a means for receiving images of clothing photographed by the user, a means for generating three-dimensional data of the clothing from the received images, and a means for classifying the generated three-dimensional data by attributes such as color and shape. This allows the user to efficiently manage their clothing and provide optimal coordination and recycling suggestions that take external information into account. Furthermore, by collaborating with professional stylists, the system can provide more specialized advice to users. Furthermore, data can be stored and analyzed via a cloud server, allowing for the centralized management of clothing data photographed by users, resulting in a highly convenient system.

[1362] "Image receiving means" refers to a device or software for receiving image data of clothing photographed by a user.

[1363] "Three-dimensional data generation means" refers to technology or equipment for three-dimensionally reproducing the shape and size of clothing from received image data.

[1364] "Attribute classification means" refers to technology or equipment for classifying generated three-dimensional data by characteristics such as color, shape, and style.

[1365] "Database storage means" refers to a device or software for recording and storing classified clothing data, making it easy to search and use later.

[1366] The "coordination suggestion means" is a technology that suggests optimal clothing combinations based on stored data, taking into consideration external factors and user information.

[1367] "Notification means" refers to a device or software for notifying the user of suggested coordination and related information.

[1368] "Usage recording means" refers to technology or devices for recording data on how a user wears clothing.

[1369] "Recycling suggestion means" refers to technology or equipment that suggests recycling or reselling clothing that is rarely used or no longer needed.

[1370] "Electronic commerce site linking means" refers to technology or devices that link with multiple online shopping sites, allowing users to purchase new clothes all at once.

[1371] "Stylist matching means" refers to technology or devices that match users with professional fashion stylists and enable them to receive expert advice and outfit suggestions.

[1372] A "cloud server" is a data storage and processing function on a server that can be accessed via the Internet, and is used to collectively manage clothing data photographed by users.

[1373] "Image analysis" is a technology that analyzes received images of clothing and identifies their attributes, such as color and shape.

[1374] "Database storage" is the process of storing analyzed data so that it can be easily searched and used later.

[1375] A "professional stylist" is someone who has specialized knowledge and skills in fashion and provides users with advice on coordinating outfits.

[1376] The "chat function" is a function that allows users and professional stylists to exchange text information in real time.

[1377] The "video consulting function" allows users to consult and receive advice on coordination between themselves and professional stylists via video call.

[1378] This invention is a system for efficiently managing a user's clothing and suggesting outfits based on that clothing. The system starts when a user takes a photo of their clothing using a device such as a smartphone and uploads the image to a cloud server.

[1379] The server generates 3D data from the received images using image analysis technology and classifies the 3D data by attributes such as color and shape. This allows accurate clothing data to be stored in a database. Specifically, it uses image analysis and classification algorithms using Python (e.g., OpenCV and TensorFlow).

[1380] The server uses the stored data to suggest optimal outfits to users, taking into account external information such as the season, weather, temperature, and trend information. This involves using an API to obtain weather forecast information and current fashion trends. The suggestions are sent to the user's device, where the user can confirm the received outfit suggestions. The notification function is performed through a dedicated smartphone app (for example, an iOS or Android app).

[1381] Furthermore, based on the user's own recorded wearing information, the server accumulates information on the user's clothing usage and analyzes the frequency of use. If clothing that has been used infrequently is identified, the server will provide the user with suggestions for recycling or reselling the clothing. The system also links to multiple e-commerce sites and provides links to purchase new clothing.

[1382] Matching with professional stylists is also an important function of this system. Users can chat with stylists and conduct video consultations through a dedicated app. This function is achieved by combining a video calling system using WebRTC technology with a real-time chat app (such as Firebase Realtime Database or Socket.IO).

[1383] For example, suppose a user takes a photo of a white shirt and uploads the image from their device to a server. The server generates three-dimensional data of a white long-sleeved shirt from the received image and stores that data in a database. If the weather is sunny and the temperature is 23 degrees Celsius at a later date, the server will use that information to suggest coordinating the white shirt with casual chinos and notify the user's device. Data is also accumulated showing that the user wears the shirt once a week, and if the user wears the shirt infrequently, a notification is sent to the user's device suggesting that the shirt be put up for sale on a flea market site.

[1384] The stored data and the proposed algorithm are optimized based on user feedback, allowing for more appropriate outfit suggestions. For example, a generative AI model can be used to input prompts and update the algorithm based on user feedback.

[1385] An example of a prompt is:

[1386] "A user has uploaded an image of XXX. Please analyze this image and classify its color and shape attributes. Then, based on weather information, please suggest the best outfit for the user."

[1387] Examples include:

[1388] In this way, the present invention allows users to manage their clothing, suggest outfits, purchase, resell, and even collaborate with professional stylists in a unified manner, enabling users to enjoy fashion efficiently and smartly.

[1389] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1390] Step 1:

[1391] The user takes a photo of the clothes they own using the device. The user takes a photo of the clothes they own using the smartphone camera. This image becomes the input data for the next processing step.

[1392] Step 2:

[1393] The captured image is uploaded to the server. The device then sends the captured image over the Internet to a server on the cloud. The image received by the server becomes input data and is used for the next process.

[1394] Step 3:

[1395] The server performs image analysis. From the received images, the server generates 3D data of the clothing using a generative AI model. During this analysis process, data processing is performed to classify attributes such as color and shape. The generated 3D data becomes the input for the next step.

[1396] Step 4:

[1397] The 3D data is stored in a database. The server classifies the generated 3D data by attributes such as color and shape, and stores it in the database. This stored data is the data necessary for coordinating outfits.

[1398] Step 5:

[1399] Collecting external information. The server uses API to collect information on seasons, weather, temperature, and trends. This external information is used as input data for the outfit suggestion algorithm.

[1400] Step 6:

[1401] Generates coordination suggestions. The server generates optimal coordination suggestions for the user based on the collected external information and clothing data stored in the database. This suggestion algorithm is realized by a generative AI model on the server.

[1402] Step 7:

[1403] The server notifies the user of the coordination proposal. The server notifies the user of the coordination proposal via a dedicated application. The user confirms the proposal, which leads to the next step.

[1404] Step 8:

[1405] Records the wearing information. When a user wears clothes based on the coordination suggestions, the wearing information is recorded on the device. This data is sent to the server and added to the user's usage database.

[1406] Step 9:

[1407] Analyze frequency of use. The server analyzes the frequency of use of each piece of clothing based on the accumulated wearing information. Using this analysis data, identifying clothes that are used less frequently leads to the next step.

[1408] Step 10:

[1409] Generate recycling and resale suggestions: The server identifies clothes that are rarely used and generates recycling and resale suggestions to notify the user. These suggestions are sent to the user's device.

[1410] Step 11:

[1411] Suggesting new clothing items: The server connects with multiple e-commerce sites to suggest new clothing items based on the user's preferences and budget. Links to suggested items are also included, allowing the user to purchase them.

[1412] Step 12:

[1413] It allows users to connect with professional stylists through chat and video consultations with professional stylists via a dedicated app. This feature uses real-time chat and video calling technology.

[1414] Example prompt sentence:

[1415] "A user has uploaded an image of XXX. Please analyze this image and classify its color and shape attributes. Then, based on weather information, please suggest the best outfit for the user."

[1416] 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.

[1417] This invention is a system for efficiently managing a user's clothing and suggesting outfits based on that clothing. The system starts when the user takes a photo of the clothing with their device and uploads the image to a server. The server generates three-dimensional data from the received image and classifies it by attributes such as color and shape. The classified data is then stored in a database.

[1418] The user launches a dedicated application and takes a photo of the garment. The device has the function to upload the captured image to a server. The server analyzes the received image and generates 3D data based on the analysis results. This 3D data is categorized by attributes such as color, shape, and style, and the categorized data is stored in a database.

[1419] Based on the stored data, the server takes into account external information such as the season, weather, temperature, and trend information to suggest the most suitable outfit for the user. This suggestion is sent to the user's device, and the user can confirm the received outfit suggestion.

[1420] Furthermore, based on the user's own recorded wearing information, the server will accumulate information on clothing usage and analyze frequency of use. If clothing that has been used infrequently is identified, the server will also provide suggestions to the user on how to recycle or resell this clothing.

[1421] The system also incorporates an emotion engine for analyzing the user's emotions. When the user takes a photo of their face with their device, the server analyzes the image and recognizes the user's emotions. Based on the recognized emotions, the server adjusts the outfit suggestions. For example, if the user is feeling stressed, the server may suggest relaxing clothing.

[1422] Emotion analysis is also possible through voice input. When a user speaks to the application, the server analyzes the voice data and recognizes the emotion. Based on this, coordination suggestions can be made.

[1423] As a specific example, a user takes a photo of a white shirt and uploads the image from their device to a server. The server generates three-dimensional data of a white long-sleeved shirt from the received image and stores that data in a database. When the user then points their face toward the camera, the device sends the facial image to the server. The server recognizes from the facial image that the user is tired and suggests a white shirt and casual chinos as a relaxing outfit.

[1424] Furthermore, if a user says "I'm a little tired" through voice input, the server will analyze it and suggest a relaxing outfit to relieve fatigue. It is also possible to save the user's emotional history and reflect it in the next outfit suggestion. In this way, by making suggestions based on the user's emotional state, it is possible to provide a more personalized service.

[1425] This system is linked to multiple shopping sites, so when a user wants to buy new clothes, they can enter their desired category and budget, and the server will search for and suggest the most suitable products and provide a purchase link.

[1426] The service also has a function that matches users with professional coordinators. When a user requests stylist advice for a special event, the server selects an appropriate coordinator and the user receives advice based on the request.

[1427] In this way, the present invention allows users to manage their clothing, suggest outfits, purchase, resell, and even collaborate with professional fashion coordinators in a unified manner, allowing users to enjoy fashion efficiently and smartly. Furthermore, by taking into account the user's emotional state, more personalized suggestions can be made, improving user satisfaction.

[1428] The processing flow will be explained below.

[1429] Garment photography and upload process

[1430] Step 1:

[1431] The user launches a dedicated application on the device and selects the "photograph clothing" function.

[1432] Step 2:

[1433] The device's camera is activated, and the user points the camera at the clothing they want to photograph and takes a photo.

[1434] Step 3:

[1435] The device displays the captured image and prompts the user to confirm. The user confirms and selects "Save."

[1436] Step 4:

[1437] The device uploads the saved images to a dedicated server.

[1438] Step 5:

[1439] The server receives the uploaded images and stores them in a database.

[1440] 3D data generation and classification process

[1441] Step 1:

[1442] The server executes an algorithm to analyze the received image.

[1443] Step 2:

[1444] The server uses image analysis to identify specific attributes of the clothing (e.g., shirt, pants, etc.).

[1445] Step 3:

[1446] The server generates three-dimensional data from the images of the identified garments.

[1447] Step 4:

[1448] The server classifies the generated 3D data by attributes such as color, shape, and style.

[1449] Step 5:

[1450] The server stores the classified clothing data in a database.

[1451] Coordination proposal process

[1452] Step 1:

[1453] The server retrieves the stored clothing information from the user's clothing database.

[1454] Step 2:

[1455] The server retrieves season, weather, temperature, and trend information from an external API.

[1456] Step 3:

[1457] Based on the above information, the server generates the most suitable outfit for the user.

[1458] Step 4:

[1459] The server transmits the generated coordinate information to the user's terminal.

[1460] Step 5:

[1461] The terminal notifies the user of the received coordination proposal.

[1462] Accumulation process of clothing usage

[1463] Step 1:

[1464] The user inputs information about the clothes they are wearing today through the application.

[1465] Step 2:

[1466] The terminal transmits the input wearing information to the server.

[1467] Step 3:

[1468] The server stores the received wearing information in a database.

[1469] Step 4:

[1470] The server runs a counting algorithm to calculate how often each garment is used.

[1471] Step 5:

[1472] The server generates data to notify the user based on the frequency of use.

[1473] The process of proposing to open a store on a flea market site

[1474] Step 1:

[1475] The server analyzes the accumulated data on the frequency of use of clothing.

[1476] Step 2:

[1477] The server lists the least frequently used clothes for a specific period.

[1478] Step 3:

[1479] The server generates recycling or resale suggestion data for the listed garments.

[1480] Step 4:

[1481] The server transmits the generated proposal data to the user's terminal.

[1482] Step 5:

[1483] The terminal notifies the user of the received proposal.

[1484] Process for linking with shopping sites

[1485] Step 1:

[1486] The user inputs the category and budget of the item they wish to purchase through the application.

[1487] Step 2:

[1488] The terminal transmits the input purchase information to the server.

[1489] Step 3:

[1490] The server calls the APIs of multiple linked shopping sites and retrieves product information that matches the criteria.

[1491] Step 4:

[1492] The server generates the optimal purchase link based on the product information acquired.

[1493] Step 5:

[1494] The server sends the generated purchase link to the user's terminal.

[1495] Step 6:

[1496] The terminal presents the received purchase link to the user.

[1497] User and Coordinator Matching Process

[1498] Step 1:

[1499] A user sends a request from an application for advice from a coordinator.

[1500] Step 2:

[1501] The terminal sends the user's request to the server.

[1502] Step 3:

[1503] A matching algorithm is executed based on the coordinator list held by the server.

[1504] Step 4:

[1505] The server selects an appropriate coordinator and generates a matching result.

[1506] Step 5:

[1507] The server notifies the user of the matching results.

[1508] Step 6:

[1509] The terminal presents the received matching results to the user.

[1510] Processing process using emotion engine

[1511] Step 1:

[1512] The user inputs a face image or voice through the application.

[1513] Step 2:

[1514] The terminal transmits the captured face image or voice data to the server.

[1515] Step 3:

[1516] The server runs a sentiment analysis algorithm based on the data it receives.

[1517] Step 4:

[1518] The server adjusts the coordination proposal based on the user's emotions recognized.

[1519] Step 5:

[1520] The server transmits the adjusted coordinate information to the user's terminal.

[1521] Step 6:

[1522] The terminal notifies the user of the received coordination proposal.

[1523] Step 7:

[1524] The user inputs feedback on the proposed outfit.

[1525] Step 8:

[1526] The device sends the feedback to the server.

[1527] Step 9:

[1528] The server optimizes the proposed algorithm based on the feedback.

[1529] These are the processing steps of the present invention, which incorporates an emotion engine that recognizes the user's emotions. This allows users to efficiently and intelligently manage their clothes, get outfit suggestions, purchase new clothes, recycle and resell, and connect with professional coordinators. Personalized suggestions based on emotion recognition can further improve user satisfaction.

[1530] Example 2

[1531] 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."

[1532] Conventional methods for managing clothing and suggesting outfits are often cumbersome and time-consuming for users. Furthermore, outfit suggestions that take into account the user's emotional state, the season, weather conditions, and fashion trends are not adequately implemented. As a result, it is difficult for users to enjoy efficient and personalized fashion. Furthermore, the lack of functionality to suggest reuse or resale of infrequently used clothing results in insufficient utilization of clothing. Therefore, the present invention aims to provide a system that streamlines clothing management and suggests outfits, and can make suggestions that reflect the user's emotional state and external information.

[1533] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving images of clothing photographed by a user, means for generating three-dimensional data of the clothing from the received images, means for classifying the generated three-dimensional data by attributes such as color and shape, means for saving the classified clothing data in a database, means for proposing outfits based on the saved clothing data and taking into account seasons, weather conditions, temperature, and fashion information, means for notifying the user of the suggested outfits, means for recording the user's clothing usage, means for identifying infrequently used clothing from the recorded usage information and proposing reuse or resale of the clothing, means for linking with multiple e-commerce sites to enable the user to purchase new clothing in bulk, means for matching the user with an expert, means for receiving a user's facial image and analyzing emotions, means for adjusting the outfit suggestions based on the emotion analysis results, means for receiving voice input and analyzing the voice data to recognize emotions, and means for adjusting the outfit suggestions based on the emotion recognition results. This improves the efficiency of clothing management and enables personalized outfit suggestions that reflect the user's emotions and external information. It also encourages the reuse and resale of clothing that is used less frequently, optimizing the use of clothing.

[1534] A "user" is a customer who uses the system to manage their clothing and receive coordination suggestions.

[1535] "Clothing image" is photographic data of clothing taken by a user using a terminal.

[1536] "Three-dimensional data" is data that aggregates three-dimensional shapes and attribute information generated from images of clothing.

[1537] "Classification" is the process of organizing the generated 3D data by attributes such as color, shape, and style.

[1538] A "database" is an information management system for storing classified clothing data.

[1539] "Season, weather conditions, temperature, and fashion information" is external environmental information that is taken into consideration when suggesting outfits.

[1540] "Coordination suggestions" refers to presenting optimal clothing combinations to users based on stored clothing data and external information.

[1541] "Notification" is a means by which the server conveys information such as coordination suggestions to the user's terminal.

[1542] "Usage status" is information indicating how frequently the user uses each piece of clothing.

[1543] "Usage information" is data that records the date and number of times the user has used the clothing.

[1544] "Reuse or resale" refers to the offer to repurpose or sell gently used clothing.

[1545] An "e-commerce site" is an online marketplace where users can purchase new clothing.

[1546] An "expert" is a person with specialized knowledge of fashion who gives coordination advice to the user.

[1547] A "face image" is photographic data of a user's own face taken with a terminal.

[1548] "Emotion analysis" is the process of recognizing a user's emotional state from facial images and voice data.

[1549] "Voice input" refers to voice data that is input by the user speaking into the terminal.

[1550] "Emotion recognition" is the process of identifying a user's emotions from speech data.

[1551] The present invention relates to a system for efficiently managing a user's clothing and suggesting outfits based on the managed clothing. Hereinafter, an embodiment of the system will be described in detail.

[1552] Overall system configuration

[1553] The system's main components are a terminal, a server, and a database. It also utilizes various software and APIs to realize functions such as image analysis, data management, outfit suggestions, emotion analysis, voice recognition, and online shopping.

[1554] Hardware and software used

[1555] The device used is a smartphone or tablet equipped with a camera, which allows users to take pictures of their clothes and their own faces.

[1556] The server is a high-performance computer that runs an image analysis engine, a database management system, and an AI model (e.g., TensorFlow or OpenCV).

[1557] The database uses a relational database management system (RDBMS, such as MySQL or PostgreSQL).

[1558] Program processing flow

[1559] 1. Photographing and uploading the garment:

[1560] The user launches the dedicated application and takes a picture of the garment using the camera, after which the device uploads the image to the server.

[1561] 2. Image analysis and 3D data generation:

[1562] The server uses an image analysis engine to analyze the received images and generate 3D data of the clothing. Image processing libraries such as TensorFlow and OpenCV are used for image analysis.

[1563] 3. Data Storage and Classification:

[1564] The server classifies the 3D data generated based on the analysis results by attributes such as color, shape, and style, and stores the classified data in a database.

[1565] 4. Coordination suggestions:

[1566] The server obtains external information such as the season, weather conditions, temperature, and fashion trends, and suggests optimal outfits to users based on the saved 3D data. The server uses the OpenWeatherMap API to obtain external information. The suggested outfits are then sent to the user via their device.

[1567] 5. Clothing usage analysis:

[1568] When a user enters their clothing information into their application, the device sends that information to a server, which analyzes the frequency of use based on the accumulated data and suggests reuse or resale of infrequently worn clothing.

[1569] 6. Sentiment analysis and suggestion adjustment:

[1570] The user inputs their emotional state using images or voice. The captured facial image is uploaded from the device to a server, which then uses an emotion analysis engine to recognize the emotion. The voice input data is also sent to the server and converted to text using, for example, the Google Cloud Speech-to-Text API. The outfit suggestions are then adjusted based on the emotion recognition results.

[1571] 7. Collaboration with shopping sites:

[1572] When a user wants to buy new clothes, they input their request through the terminal, and the server retrieves data from multiple e-commerce sites and suggests the best products to the user, for example, using the Amazon Product Advertising API.

[1573] 8. Matching with a professional coordinator:

[1574] When a user requests advice from a stylist for a specific event, they send a special request, and the server selects the most suitable person from the registered coordinators and matches them with the user.

[1575] Specific examples

[1576] As a concrete use case, consider the following scenario:

[1577] The user takes a photo of a white shirt and uploads the image from their device to the server. The server analyzes the image, identifies it as a white shirt, generates three-dimensional data, and stores it in a database. If the user then feels tired, they can notify the server via their device using a facial image or voice. The server then performs emotion analysis and suggests relaxing outfits to soothe fatigue.

[1578] Prompt Sentence Examples

[1579] "You take a picture of a white shirt and upload it to the server. Then you use the camera to take a picture of your face and receive outfit suggestions based on your emotional state. If you're tired, we'll suggest outfits that will help you relax."

[1580] In this way, the present invention provides a system that improves the efficiency of managing the clothes owned by the user and suggesting outfits, allowing the user to enjoy fashion comfortably.

[1581] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1582] Step 1:

[1583] The user launches the dedicated application and takes a picture of the garment using the camera, at which point the camera application installed on the device captures a high-resolution image.

[1584] Input: A user-taken image of the clothing

[1585] Output: Image file of the clothing saved on the device

[1586] Step 2:

[1587] The device uploads the captured image of the clothing to a server, where it is securely transmitted using HTTPS.

[1588] Input: Image file of clothing saved on the device

[1589] Output: Images of the garment uploaded to the server

[1590] Step 3:

[1591] The server analyzes the received images and generates 3D data of the clothing. Specifically, it processes the images with a deep learning model using TensorFlow and OpenCV to extract the 3D shape.

[1592] Input: Images of clothing uploaded to the server

[1593] Output: 3D data of the generated garment

[1594] Step 4:

[1595] The server classifies the generated 3D data by attributes such as color, shape, and style, using machine learning algorithms.

[1596] Input: 3D data of the generated clothing

[1597] Output: Classified clothing data

[1598] Step 5:

[1599] The server stores the classified data in a database, which is then inserted into the database (e.g., MySQL or PostgreSQL) using SQL queries.

[1600] Input: Categorized clothing data

[1601] Output: Clothing data stored in a database

[1602] Step 6:

[1603] The server uses external APIs to obtain external information such as seasons, weather conditions, temperature, and trend information. Examples of APIs used include the OpenWeatherMap API.

[1604] Input: Request for external information obtained from API

[1605] Output: The external information obtained

[1606] Step 7:

[1607] The server runs an algorithm based on the stored data and external information to suggest the best outfits for the user. In this case, a generative AI model is used.

[1608] Input: Garment data and external information stored in the database

[1609] Output: Proposed coordinate data

[1610] Step 8:

[1611] The device receives coordination suggestions from the server and displays an interface to notify the user. Push notifications may also be used.

[1612] Input: Coordination proposal data sent from the server

[1613] Output: Coordination suggestions displayed to the user

[1614] Step 9:

[1615] The wearing information entered by the user is recorded on the terminal. Once the input is complete, the terminal sends the wearing information to the server.

[1616] Input: Wearing information entered by the user

[1617] Output: Wearing information sent to the server

[1618] Step 10:

[1619] The server analyzes the frequency of use based on the accumulated wearing information, and uses SQL to retrieve data from the database, aggregate and analyze it.

[1620] Input: Wearing information stored on the server

[1621] Output: Analysis results on frequency of use

[1622] Step 11:

[1623] The server identifies gently used clothing and makes suggestions for reuse or resale, which are then notified to the user.

[1624] Input: Analysis results on frequency of use

[1625] Output: Proposal data for reuse or resale

[1626] Step 12:

[1627] The user takes a picture of their face with the device, which then uploads the captured image to the server.

[1628] Input: A face image taken by the user

[1629] Output: Face image uploaded to the server

[1630] Step 13:

[1631] The server analyzes the facial image and recognizes the user's emotions. Image recognition is performed using OpenCV or deep learning models, for example.

[1632] Input: Face image uploaded to the server

[1633] Output: Recognized user emotion data

[1634] Step 14:

[1635] The server adjusts the outfit suggestions based on the emotion recognition results, selecting outfits that will alleviate emotions such as stress and fatigue.

[1636] Input: Recognized user emotion data

[1637] Output: Adjusted coordinate suggestion data

[1638] Step 15:

[1639] The user speaks to the application to provide voice input, and the device sends the voice data to the server.

[1640] Input: Voice data spoken by the user

[1641] Output: Audio data sent to the server

[1642] Step 16:

[1643] The server analyzes the voice data and recognizes the user's emotions. It converts the voice data into text using the Google Cloud Speech-to-Text API and then analyzes the emotions.

[1644] Input: Audio data sent to the server

[1645] Output: Translated speech data and recognized emotion data

[1646] Step 17:

[1647] The server adjusts the coordination suggestions based on the emotion recognition results, allowing suggestions to be tailored to the user's emotions.

[1648] Input: Recognized emotion data

[1649] Output: Adjusted coordinate suggestion data

[1650] Step 18:

[1651] The user inputs their desired clothing purchase, and the terminal sends the desired category and budget to the server.

[1652] Input: New purchase request (category and budget) entered by the user

[1653] Output: Purchase request data sent to the server

[1654] Step 19:

[1655] The server searches for product information from multiple e-commerce sites, using the Amazon Product Advertising API, etc.

[1656] Input: Purchase request data sent to the server

[1657] Output: Retrieved product information data

[1658] Step 20:

[1659] The server selects the most suitable product based on the search results and provides the user with a purchase link.

[1660] Input: Retrieved product information data

[1661] Output: Purchase link and product information provided to the user

[1662] Step 21:

[1663] The user requests advice from a stylist. The device sends the request to the server.

[1664] Input: A user-entered request for stylist advice

[1665] Output: Request data sent to the server

[1666] Step 22:

[1667] The server selects the most suitable coordinator based on the information of registered coordinators and matches it with the user.

[1668] Input: Coordinator information stored on the server and user request data

[1669] Output: Selected coordinator information and matching results

[1670] The above is a description of the specific operations and inputs and outputs for each processing step of the program of this system.

[1671] (Application example 2)

[1672] 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."

[1673] Traditionally, managing a user's clothing and suggesting outfits was often done manually, which was time-consuming and labor-intensive. Furthermore, outfit suggestions that took into account the user's emotions and external environment were rarely provided, making it difficult to increase user satisfaction. Furthermore, there were cases where infrequently worn clothing was not managed and collaboration with professional outfit coordinators was not fully implemented, preventing efficient clothing utilization.

[1674] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1675] In this invention, the server includes means for receiving images of clothing photographed by a user, means for generating three-dimensional data of the clothing from the received images, means for classifying the generated three-dimensional data by attributes such as color and shape, means for saving the classified clothing data in a database, means for suggesting outfits based on the saved clothing data and taking into account season, weather, temperature, and trend information, means for notifying the user of the suggested outfits, means for recording the user's clothing usage, means for identifying infrequently used clothing from the recorded usage information and suggesting recycling or resale, means for linking with multiple purchasing sites to enable the user to purchase new clothing in bulk, means for matching users with experts, means for receiving a user's facial image or voice input and analyzing emotions, and means for adjusting the outfit suggestions based on the analyzed emotions. This enables more accurate and personalized clothing management and outfit suggestions that take into account the user's emotions and external environment.

[1676] "User" refers to an individual who uses the system to manage clothing and receive coordination suggestions.

[1677] "Clothing image" refers to photographic data of specific clothing that a user takes and uploads to the system.

[1678] "Three-dimensional data" is three-dimensional data generated from an image and has attributes such as the color and shape of clothing.

[1679] "Database" means an information management system for storing classified garment data and other related information.

[1680] "Coordination suggestions" refers to suggestions to the user for appropriate clothing combinations based on stored clothing data and external information.

[1681] "Notification" refers to the act of sending and informing a user of suggested outfits and other information.

[1682] "Usage status" is information that records how much a user uses the clothing.

[1683] "Recycle or resell" is the act of offering to reuse gently used clothing.

[1684] "Shopping sites" are multiple online sales sites where users can purchase new clothing.

[1685] An "expert" is a professional with specialized knowledge about clothing coordination who provides advice to users.

[1686] "Emotion analysis" is a process that analyzes the user's facial image and voice input to recognize their current state of mind and emotions.

[1687] "Adjustment" refers to the act of optimizing the coordination suggestions to suit the user's emotional state based on the analyzed emotions.

[1688] The present invention provides a system for managing a user's clothing and for efficiently suggesting outfits based on that data. Hereinafter, an embodiment of the present invention will be described based on a specific operational example.

[1689] First, the user takes a picture of the clothing using their smartphone. The image is then uploaded to a server via the smartphone's application. The server then analyzes the received image using the Google Cloud Vision API and generates 3D data with attributes such as the color and shape of the clothing. This 3D data is then stored in a database such as MySQL.

[1690] Based on the stored data, the server takes into account the season, weather, temperature, and trend information to suggest appropriate outfits. These suggestions are provided to the user via the smartphone's notification function. In particular, when the user takes a facial image or enters voice input, the respective data is sent to the server, and emotions are analyzed using the Microsoft Azure Emotion API. Based on the analyzed emotions, the outfit suggestions are further adjusted.

[1691] For example, if a user takes a photo of a black jacket and uploads it to the application, the server generates three-dimensional data of the black jacket from the received image and stores it in a database. If the user then voice-inputs "It's cold today" into their smartphone, the server analyzes the voice data, recognizes that the user is feeling cold, and suggests corresponding outfits.

[1692] Furthermore, the server records the user's clothing usage and identifies infrequently worn clothing. The server then offers suggestions for recycling or reselling the identified clothing. The server also connects with multiple purchasing sites to offer shopping suggestions, allowing users to purchase desired new clothing all at once. For special events, the server matches users with experts to provide professional coordination advice.

[1693] Below are some example prompts for the generative AI model:

[1694] Example prompt sentence:

[1695] Please convert a photo of a black jacket taken by the user into 3D data using the image analysis API and save it in the user database. Also, please analyze the user's voice input "It's cold today" and suggest the warmest possible outfit.

[1696] Such a system allows users to manage their clothing and receive coordination suggestions in an efficient and personalized manner.

[1697] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1698] Step 1:

[1699] A user takes an image of the garment using a smartphone.

[1700] Input: Images of clothing

[1701] Output: Image data

[1702] The user uses the camera application on their smartphone to take a picture of the garment, and the captured image data is saved in the application.

[1703] Step 2:

[1704] The device uploads the captured image to the server.

[1705] Input: Saved image data

[1706] Output: Image data transferred to the server

[1707] The device (smartphone) uses an Internet connection to transfer the image data of the garment to the server. The data is transmitted via the HTTP protocol.

[1708] Step 3:

[1709] The server receives the image data and generates three-dimensional data using the Google Cloud Vision API.

[1710] Input: Image data

[1711] Output: 3D data

[1712] The server then sends the received image data to the Google Cloud Vision API, which analyzes attributes such as the color and shape of the clothing. Based on the results of this analysis, 3D data is generated.

[1713] Step 4:

[1714] The server classifies the generated 3D data by attributes such as color and shape and stores it in a MySQL database.

[1715] Input: 3D data

[1716] Output: Categorized database entries

[1717] The server classifies the 3D data by attributes such as color, shape, style, etc. The classified data is stored in a MySQL database.

[1718] Step 5:

[1719] The server generates coordination suggestions based on the stored data, taking into account the season, weather, temperature, and trend information.

[1720] Input: Stored clothing data, season, weather, temperature, trend information

[1721] Output: Coordination suggestions

[1722] The server uses the stored clothing data and external information (season, weather, temperature, trend information) to generate optimal coordination suggestions for the user.

[1723] Step 6:

[1724] The terminal notifies the user of the coordination proposal.

[1725] Input: Coordination suggestion

[1726] Output: User notification

[1727] The device will then send a push notification to the user informing them of the outfit suggestions received from the server, and the user can view the suggestions through their smartphone's notification function.

[1728] Step 7:

[1729] The user inputs a facial image or voice, and the device sends it to the server.

[1730] Input: Face image, voice input

[1731] Output: Facial image and audio data transferred to the server

[1732] Users use the smartphone's camera and microphone to input facial images and voice data, which are then sent to a server via an application.

[1733] Step 8:

[1734] The server analyzes facial images and voice data and recognizes the user's emotions using the Microsoft Azure Emotion API.

[1735] Input: face image, voice data

[1736] Output: Recognized emotion data

[1737] The server uses the Microsoft Azure Emotion API to analyze and recognize the user's emotional state from the facial images and voice data sent.

[1738] Step 9:

[1739] The server adjusts the coordination suggestions based on the analyzed emotional data.

[1740] Input: Emotion data, initial coordination proposal

[1741] Output: Tailored outfit suggestions

[1742] The server uses the analyzed emotion data to adjust the initial outfit suggestions depending on the user's emotions, for example, suggesting warm outfits if the user is feeling cold.

[1743] Step 10:

[1744] The server records the user's clothing usage, identifies less frequently used clothing, and suggests recycling or reselling it.

[1745] Input: Usage data

[1746] Output: Offer to recycle or resell

[1747] The server analyzes the user's usage frequency data and identifies clothes that are used less frequently, and based on that, makes suggestions to the user about recycling or reselling them.

[1748] 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.

[1749] 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.

[1750] 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.

[1751] [Fourth embodiment]

[1752] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1753] 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.

[1754] 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).

[1755] 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.

[1756] 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.

[1757] 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).

[1758] 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.

[1759] 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.

[1760] 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.

[1761] 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.

[1762] 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.

[1763] 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.

[1764] 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."

[1765] This invention is a system for efficiently managing a user's clothing and suggesting outfits based on that clothing. The system starts when the user takes a photo of the clothing with their device and uploads the image to a server. The server generates three-dimensional data from the received image and classifies it by attributes such as color and shape. The classified data is then stored in a database.

[1766] The user launches a dedicated application and takes a photo of the garment. The device has the function to upload the captured image to a server. The server analyzes the received image and generates 3D data based on the analysis results. This 3D data is categorized by attributes such as color, shape, and style, and the categorized data is stored in a database.

[1767] Based on the stored data, the server takes into account external information such as the season, weather, temperature, and trend information to suggest the most suitable outfit for the user. This suggestion is sent to the user's device, and the user can confirm the received outfit suggestion.

[1768] Furthermore, based on the user's own recorded wearing information, the server will accumulate information on clothing usage and analyze frequency of use. If clothing that has been used infrequently is identified, the server will also provide suggestions to the user on how to recycle or resell this clothing.

[1769] As a specific example, a user takes a photo of a white shirt and uploads the image from their device to a server. The server generates three-dimensional data of a white long-sleeved shirt from the received image and stores that data in a database. Later, if the weather is sunny and the temperature is 23 degrees, the server will use that information to suggest coordinating the white shirt with casual chinos and notify the user's device. Data is also accumulated showing that the user wears the shirt once a week, and if the user wears the shirt infrequently, a notification is sent to the user's device suggesting that the shirt be put up for sale on a flea market site.

[1770] In addition, the system is linked to multiple shopping sites, so when a user wants to buy new clothes, they can enter their desired category and budget, and the server will search for and suggest the most suitable products and provide a purchase link.

[1771] The service also has a function that matches users with professional coordinators. When a user requests stylist advice for a special event, the server selects an appropriate coordinator and the user receives advice based on the request.

[1772] In this way, the present invention allows users to manage their clothing, suggest outfits, purchase, resell, and even collaborate with professional coordinators in a unified manner, enabling users to enjoy fashion efficiently and smartly.

[1773] The processing flow will be explained below.

[1774] Garment photography and upload process

[1775] Step 1:

[1776] The user launches a dedicated application on the device and selects the "photograph clothing" function.

[1777] Step 2:

[1778] The device's camera is activated, and the user points the camera at the clothing they want to photograph and takes a photo.

[1779] Step 3:

[1780] The device displays the captured image and prompts the user to confirm. The user confirms and selects "Save."

[1781] Step 4:

[1782] The device uploads the saved images to a dedicated server.

[1783] Step 5:

[1784] The server receives the uploaded images and stores them in a database.

[1785] 3D data generation and classification process

[1786] Step 1:

[1787] The server executes an algorithm to analyze the received image.

[1788] Step 2:

[1789] The server uses image analysis to identify specific attributes of the clothing (e.g., shirt, pants, etc.).

[1790] Step 3:

[1791] The server generates three-dimensional data from the images of the identified garments.

[1792] Step 4:

[1793] The server classifies the generated 3D data by attributes such as color, shape, and style.

[1794] Step 5:

[1795] The server stores the classified clothing data in a database.

[1796] Coordination proposal process

[1797] Step 1:

[1798] The server retrieves the stored clothing information from the user's clothing database.

[1799] Step 2:

[1800] The server retrieves season, weather, temperature, and trend information from an external API.

[1801] Step 3:

[1802] Based on the above information, the server generates the most suitable outfit for the user.

[1803] Step 4:

[1804] The server transmits the generated coordinate information to the user's terminal.

[1805] Step 5:

[1806] The terminal notifies the user of the received coordination proposal.

[1807] Accumulation process of clothing usage

[1808] Step 1:

[1809] The user inputs information about the clothes they are wearing today through the application.

[1810] Step 2:

[1811] The terminal transmits the input wearing information to the server.

[1812] Step 3:

[1813] The server stores the received wearing information in a database.

[1814] Step 4:

[1815] The server runs a counting algorithm to calculate how often each garment is used.

[1816] Step 5:

[1817] The server generates data to notify the user based on the frequency of use.

[1818] The process of proposing to open a store on a flea market site

[1819] Step 1:

[1820] The server analyzes the accumulated data on the frequency of use of clothing.

[1821] Step 2:

[1822] The server lists the least frequently used clothes for a specific period.

[1823] Step 3:

[1824] The server generates recycling or resale suggestion data for the listed garments.

[1825] Step 4:

[1826] The server transmits the generated proposal data to the user's terminal.

[1827] Step 5:

[1828] The terminal notifies the user of the received proposal.

[1829] Process for linking with shopping sites

[1830] Step 1:

[1831] The user inputs the category and budget of the item they wish to purchase through the application.

[1832] Step 2:

[1833] The terminal transmits the input purchase information to the server.

[1834] Step 3:

[1835] The server calls the APIs of multiple linked shopping sites and retrieves product information that matches the criteria.

[1836] Step 4:

[1837] The server generates the optimal purchase link based on the product information acquired.

[1838] Step 5:

[1839] The server sends the generated purchase link to the user's terminal.

[1840] Step 6:

[1841] The terminal presents the received purchase link to the user.

[1842] User and Coordinator Matching Process

[1843] Step 1:

[1844] A user sends a request from an application for advice from a coordinator.

[1845] Step 2:

[1846] The terminal sends the user's request to the server.

[1847] Step 3:

[1848] A matching algorithm is executed based on the coordinator list held by the server.

[1849] Step 4:

[1850] The server selects an appropriate coordinator and generates a matching result.

[1851] Step 5:

[1852] The server notifies the user of the matching results.

[1853] Step 6:

[1854] The terminal presents the received matching results to the user.

[1855] These are the specific processing steps of the system, which allows users to efficiently and smartly manage their clothes, get outfit suggestions, purchase new clothes, recycle and resell, and connect with professional outfit coordinators.

[1856] Example 1

[1857] 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."

[1858] Today's consumers tend to own a wide variety of clothing, and managing and coordinating them on a daily basis requires a great deal of time and effort. Infrequently worn clothes can easily end up forgotten in the closet, and finding the right items can be difficult when buying new ones. Furthermore, there are still challenges in getting professional advice for special events. A system that solves these problems and allows people to enjoy fashion efficiently and smartly is needed.

[1859] 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.

[1860] In this invention, the server includes means for receiving images of clothing photographed by a user, means for generating three-dimensional data of the clothing from the received images, means for classifying the generated three-dimensional data by attributes such as color and shape, means for saving the classified clothing data in a database, means for suggesting outfits based on the saved clothing data and taking into account season, weather, temperature, and trend information, means for notifying the user of the suggested outfits, means for recording the user's clothing usage, means for identifying infrequently used clothing from the recorded usage information and suggesting recycling or resale, means for linking with multiple purchasing sites to enable the user to purchase new clothing in bulk, means for matching the user with a professional outfitter, means for the user to input a desired category and budget for purchasing new clothing, means for acquiring weather information and temperature, and means for generating outfit suggestions using a generative AI model based on the conditions entered by the user. This allows the user to manage their clothing, get outfit suggestions, purchase, resell, and collaborate with professional outfitters in a unified manner.

[1861] "User" refers to an individual or group that uses the system to manage clothing and receive coordination suggestions.

[1862] A "terminal" refers to a device that a user owns and connects to the system for use, and specifically includes smartphones and tablets.

[1863] "Server" means a central computing device that processes, stores and presents data submitted by users.

[1864] The "means for receiving images" refers to a process or device that transfers the clothing image data sent from the terminal to the server.

[1865] "Means for generating three-dimensional data" refers to software or algorithms for generating a three-dimensional model of the garment from received image data.

[1866] "Means for classifying by attributes such as color, shape, etc." refers to the algorithm or software used to classify the generated 3D data into categories such as color, shape, style, etc.

[1867] "Means for storing in a database" refers to a data management system and storage for long-term storage of classified clothing data.

[1868] "Means for suggesting outfits" refers to processes or software that provide optimal outfits to users based on stored clothing data and external information.

[1869] "Means for notifying a user of a coordinated outfit" refers to a communication system and software for transmitting suggested coordinated outfit information to a user's terminal.

[1870] "Means for recording the usage of clothing" refers to an interface and data storage system for inputting and recording information about clothing worn by a user.

[1871] "Recycle or resale suggestion mechanism" refers to a process or notification system for suggesting to users to recycle or resell gently used clothing.

[1872] "Buying Site" refers to an online platform that sells clothing over the Internet and allows users to purchase them.

[1873] "Professional coordinator" refers to a person or organization who is a fashion professional and provides styling advice to users.

[1874] A "generative AI model" refers to a computer model that uses artificial intelligence technology to generate optimal outfits from text and images.

[1875] A "prompt" is text that is input into a generative AI model and is an instruction that the model uses to make coordination suggestions.

[1876] The present invention is a system for efficiently managing a user's clothing and suggesting outfits based on that clothing. This system starts when a user takes a photo of the clothing with their device and uploads the image to a server. The specific operation method of the system is described below.

[1877] Photographing and uploading clothing

[1878] First, the user takes a photo of the clothing using a device (such as a smartphone or tablet) with the dedicated application installed. It is recommended that the photo be taken in sufficient light so that the entire clothing is clearly visible. The user then presses the upload button in the application to send the image to the server. The protocol used for this transmission is an HTTP request.

[1879] Image analysis and 3D data generation

[1880] The server uses image analysis software (e.g., OpenCV or TensorFlow) to analyze the received images. The server extracts feature points from the images and generates three-dimensional data (3D models). Specifically, it creates a 3D model of the clothing using a deep learning model (e.g., YOLO, Mask R-CNN).

[1881] Data classification and storage

[1882] The server classifies the generated 3D data by attributes such as color, shape, and style. A machine learning algorithm (e.g., K-means clustering) is used for classification. The classified data is then stored in a database (e.g., MySQL or PostgreSQL), allowing for quick search and reference later.

[1883] Coordination suggestions

[1884] The server compares the stored clothing data with external information obtained from a weather API (e.g., OpenWeatherMap) to suggest optimal outfits. Using a generative AI model, it makes outfit suggestions based on the user's input criteria. The suggested outfits are sent to the user's device as push notifications.

[1885] As a concrete example, a user takes a photo of a white shirt and uploads the image from their device to a server. The server generates three-dimensional data of a white long-sleeved shirt from the received image and stores that data in a database. Later, if the weather is sunny and the temperature is 23 degrees, the server will use that information to suggest a combination of the white shirt and casual chinos and notify the user's device.

[1886] Usage management and recycling / resale suggestions

[1887] Users can record their clothing usage through the application (e.g., by entering the date of wear). The server analyzes the recorded data and uses Pandas and NumPy to calculate how often the clothing has been used. If the clothing is deemed to have been used infrequently, the server sends a notification to the user's device suggesting that the clothing be recycled or resold.

[1888] Linking with purchasing sites

[1889] When a user wants to buy new clothes, the system provides a way for them to input their desired category and budget by linking with multiple purchasing sites. The server then searches for the best products based on the input criteria and provides a link to purchase them.

[1890] Collaboration with professional coordinators

[1891] Users can request the advice of professional coordinators for special events, and the server will select an appropriate coordinator and provide advice according to the user's request.

[1892] Prompt Sentence Examples

[1893] "Please suggest a casual outfit using a white shirt. The weather is sunny and the temperature is 23 degrees."

[1894] In this way, the present invention provides a comprehensive system that makes users' lives more efficient and smarter by enabling them to manage their clothing, suggest outfits, purchase, resell, and even collaborate with professional coordinators in a unified manner.

[1895] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1896] Step 1:

[1897] The user takes a photo of the clothing using a device with a dedicated application installed. It is recommended that the photo be taken in sufficient light so that the entire clothing is clearly visible. This captured image is the data input to the next step. The device then sends the image data to the server. An HTTP request is used for transmission.

[1898] Input: Image data of clothing

[1899] Output: Image data sent to the server

[1900] Step 2:

[1901] The server processes the image data of the clothing received from the device. First, it analyzes the image using image analysis software (e.g., OpenCV, TensorFlow). At this time, the server extracts feature points from the image and generates three-dimensional data (3D model). The generated 3D model is input into the next step.

[1902] Input: Image data of clothing

[1903] Output: Analyzed 3D model

[1904] Step 3:

[1905] The server classifies the generated 3D data by attributes such as color, shape, and style using machine learning algorithms (e.g., K-means clustering), and stores the classified data in a database.

[1906] Input: 3D model

[1907] Output: Classified clothing data

[1908] Step 4:

[1909] The server then uses the classified clothing data to suggest outfits, taking into account the season, weather, temperature, and trend information. To do this, the server obtains relevant information from weather APIs (e.g., OpenWeatherMap) and other sources. It also uses a generative AI model to suggest outfits based on the user's input. The results are then sent to the user's device.

[1910] Input: Categorized clothing data, as well as information on seasons, weather, temperature, and trends

[1911] Output: Coordination suggestions

[1912] Step 5:

[1913] The server notifies the user of the proposed outfit. This notification is performed using a push notification system. The user receives the notification and can check the proposed outfit.

[1914] Input: Coordination suggestion

[1915] Output: Coordination suggestions notified to the user

[1916] Step 6:

[1917] Users record their clothing usage through a dedicated application (e.g., by entering the date of wear), and this data is sent to and stored on a server.

[1918] Input: Usage data

[1919] Output: Saved usage data

[1920] Step 7:

[1921] The server analyzes the frequency of clothing use from the recorded usage information. This analysis is performed using data processing libraries (e.g., Pandas, NumPy). When infrequently used clothing is identified, the server suggests recycling or reselling the clothing. This suggestion is sent to the user's device.

[1922] Input: Usage data

[1923] Output: Recycle or resell offer

[1924] Step 8:

[1925] When a user wants to buy new clothes, they input their desired category and budget through a dedicated application. The server connects with multiple purchasing sites, searches for the best products based on the input criteria, and provides a link to purchase them.

[1926] Input: desired category and budget

[1927] Output: Purchase link

[1928] Step 9:

[1929] Users can request professional coordinator advice for special events, and the server will select an appropriate coordinator and provide advice based on the request.

[1930] Input: Coordinator Request

[1931] Output: Coordination advice

[1932] (Application example 1)

[1933] 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."

[1934] In modern life, there is a great demand for systems that can efficiently manage the clothes a user owns and suggest outfits based on that clothing. However, conventional clothing management systems and outfit suggestion systems have difficulty responding flexibly to the usage and frequency of individual clothes and fluctuations in the external environment (season, weather, temperature). Furthermore, there is a lack of a means for easily connecting users with professional stylists. Therefore, the challenge is to provide a system that can optimally manage and utilize a user's clothing, comprehensively and efficiently suggest new clothing purchases and recycling of unwanted clothing.

[1935] 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.

[1936] In this invention, the server includes a means for receiving images of clothing photographed by the user, a means for generating three-dimensional data of the clothing from the received images, and a means for classifying the generated three-dimensional data by attributes such as color and shape. This allows the user to efficiently manage their clothing and provide optimal coordination and recycling suggestions that take external information into account. Furthermore, by collaborating with professional stylists, the system can provide more specialized advice to users. Furthermore, data can be stored and analyzed via a cloud server, allowing for the centralized management of clothing data photographed by users, resulting in a highly convenient system.

[1937] "Image receiving means" refers to a device or software for receiving image data of clothing photographed by a user.

[1938] "Three-dimensional data generation means" refers to technology or equipment for three-dimensionally reproducing the shape and size of clothing from received image data.

[1939] "Attribute classification means" refers to technology or equipment for classifying generated three-dimensional data by characteristics such as color, shape, and style.

[1940] "Database storage means" refers to a device or software for recording and storing classified clothing data, making it easy to search and use later.

[1941] The "coordination suggestion means" is a technology that suggests optimal clothing combinations based on stored data, taking into consideration external factors and user information.

[1942] "Notification means" refers to a device or software for notifying the user of suggested coordination and related information.

[1943] "Usage recording means" refers to technology or devices for recording data on how a user wears clothing.

[1944] "Recycling suggestion means" refers to technology or equipment that suggests recycling or reselling clothing that is rarely used or no longer needed.

[1945] "Electronic commerce site linking means" refers to technology or devices that link with multiple online shopping sites, allowing users to purchase new clothes all at once.

[1946] "Stylist matching means" refers to technology or devices that match users with professional fashion stylists and enable them to receive expert advice and outfit suggestions.

[1947] A "cloud server" is a data storage and processing function on a server that can be accessed via the Internet, and is used to collectively manage clothing data photographed by users.

[1948] "Image analysis" is a technology that analyzes received images of clothing and identifies their attributes, such as color and shape.

[1949] "Database storage" is the process of storing analyzed data so that it can be easily searched and used later.

[1950] A "professional stylist" is someone who has specialized knowledge and skills in fashion and provides users with advice on coordinating outfits.

[1951] The "chat function" is a function that allows users and professional stylists to exchange text information in real time.

[1952] The "video consulting function" allows users to consult and receive advice on coordination between themselves and professional stylists via video call.

[1953] This invention is a system for efficiently managing a user's clothing and suggesting outfits based on that clothing. The system starts when a user takes a photo of their clothing using a device such as a smartphone and uploads the image to a cloud server.

[1954] The server generates 3D data from the received images using image analysis technology and classifies the 3D data by attributes such as color and shape. This allows accurate clothing data to be stored in a database. Specifically, it uses image analysis and classification algorithms using Python (e.g., OpenCV and TensorFlow).

[1955] The server uses the stored data to suggest optimal outfits to users, taking into account external information such as the season, weather, temperature, and trend information. This involves using an API to obtain weather forecast information and current fashion trends. The suggestions are sent to the user's device, where the user can confirm the received outfit suggestions. The notification function is performed through a dedicated smartphone app (for example, an iOS or Android app).

[1956] Furthermore, based on the user's own recorded wearing information, the server accumulates information on the user's clothing usage and analyzes the frequency of use. If clothing that has been used infrequently is identified, the server will provide the user with suggestions for recycling or reselling the clothing. The system also links to multiple e-commerce sites and provides links to purchase new clothing.

[1957] Matching with professional stylists is also an important function of this system. Users can chat with stylists and conduct video consultations through a dedicated app. This function is achieved by combining a video calling system using WebRTC technology with a real-time chat app (such as Firebase Realtime Database or Socket.IO).

[1958] For example, suppose a user takes a photo of a white shirt and uploads the image from their device to a server. The server generates three-dimensional data of a white long-sleeved shirt from the received image and stores that data in a database. If the weather is sunny and the temperature is 23 degrees Celsius at a later date, the server will use that information to suggest coordinating the white shirt with casual chinos and notify the user's device. Data is also accumulated showing that the user wears the shirt once a week, and if the user wears the shirt infrequently, a notification is sent to the user's device suggesting that the shirt be put up for sale on a flea market site.

[1959] The stored data and the proposed algorithm are optimized based on user feedback, allowing for more appropriate outfit suggestions. For example, a generative AI model can be used to input prompts and update the algorithm based on user feedback.

[1960] An example of a prompt is:

[1961] "A user has uploaded an image of XXX. Please analyze this image and classify its color and shape attributes. Then, based on weather information, please suggest the best outfit for the user."

[1962] Examples include:

[1963] In this way, the present invention allows users to manage their clothing, suggest outfits, purchase, resell, and even collaborate with professional stylists in a unified manner, enabling users to enjoy fashion efficiently and smartly.

[1964] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1965] Step 1:

[1966] The user takes a photo of the clothes they own using the device. The user takes a photo of the clothes they own using the smartphone camera. This image becomes the input data for the next processing step.

[1967] Step 2:

[1968] The captured image is uploaded to the server. The device then sends the captured image over the Internet to a server on the cloud. The image received by the server becomes input data and is used for the next process.

[1969] Step 3:

[1970] The server performs image analysis. From the received images, the server generates 3D data of the clothing using a generative AI model. During this analysis process, data processing is performed to classify attributes such as color and shape. The generated 3D data becomes the input for the next step.

[1971] Step 4:

[1972] The 3D data is stored in a database. The server classifies the generated 3D data by attributes such as color and shape, and stores it in the database. This stored data is the data necessary for coordinating outfits.

[1973] Step 5:

[1974] Collecting external information. The server uses API to collect information on seasons, weather, temperature, and trends. This external information is used as input data for the outfit suggestion algorithm.

[1975] Step 6:

[1976] Generates coordination suggestions. The server generates optimal coordination suggestions for the user based on the collected external information and clothing data stored in the database. This suggestion algorithm is realized by a generative AI model on the server.

[1977] Step 7:

[1978] The server notifies the user of the coordination proposal. The server notifies the user of the coordination proposal via a dedicated application. The user confirms the proposal, which leads to the next step.

[1979] Step 8:

[1980] Records the wearing information. When a user wears clothes based on the coordination suggestions, the wearing information is recorded on the device. This data is sent to the server and added to the user's usage database.

[1981] Step 9:

[1982] Analyze frequency of use. The server analyzes the frequency of use of each piece of clothing based on the accumulated wearing information. Using this analysis data, identifying clothes that are used less frequently leads to the next step.

[1983] Step 10:

[1984] Generate recycling and resale suggestions: The server identifies clothes that are rarely used and generates recycling and resale suggestions to notify the user. These suggestions are sent to the user's device.

[1985] Step 11:

[1986] Suggesting new clothing items: The server connects with multiple e-commerce sites to suggest new clothing items based on the user's preferences and budget. Links to suggested items are also included, allowing the user to purchase them.

[1987] Step 12:

[1988] It allows users to connect with professional stylists through chat and video consultations with professional stylists via a dedicated app. This feature uses real-time chat and video calling technology.

[1989] Example prompt sentence:

[1990] "A user has uploaded an image of XXX. Please analyze this image and classify its color and shape attributes. Then, based on weather information, please suggest the best outfit for the user."

[1991] 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.

[1992] This invention is a system for efficiently managing a user's clothing and suggesting outfits based on that clothing. The system starts when the user takes a photo of the clothing with their device and uploads the image to a server. The server generates three-dimensional data from the received image and classifies it by attributes such as color and shape. The classified data is then stored in a database.

[1993] The user launches a dedicated application and takes a photo of the garment. The device has the function to upload the captured image to a server. The server analyzes the received image and generates 3D data based on the analysis results. This 3D data is categorized by attributes such as color, shape, and style, and the categorized data is stored in a database.

[1994] Based on the stored data, the server takes into account external information such as the season, weather, temperature, and trend information to suggest the most suitable outfit for the user. This suggestion is sent to the user's device, and the user can confirm the received outfit suggestion.

[1995] Furthermore, based on the user's own recorded wearing information, the server will accumulate information on clothing usage and analyze frequency of use. If clothing that has been used infrequently is identified, the server will also provide suggestions to the user on how to recycle or resell this clothing.

[1996] The system also incorporates an emotion engine for analyzing the user's emotions. When the user takes a photo of their face with their device, the server analyzes the image and recognizes the user's emotions. Based on the recognized emotions, the server adjusts the outfit suggestions. For example, if the user is feeling stressed, the server may suggest relaxing clothing.

[1997] Emotion analysis is also possible through voice input. When a user speaks to the application, the server analyzes the voice data and recognizes the emotion. Based on this, coordination suggestions can be made.

[1998] As a specific example, a user takes a photo of a white shirt and uploads the image from their device to a server. The server generates three-dimensional data of a white long-sleeved shirt from the received image and stores that data in a database. When the user then points their face toward the camera, the device sends the facial image to the server. The server recognizes from the facial image that the user is tired and suggests a white shirt and casual chinos as a relaxing outfit.

[1999] Furthermore, if a user says "I'm a little tired" through voice input, the server will analyze it and suggest a relaxing outfit to relieve fatigue. It is also possible to save the user's emotional history and reflect it in the next outfit suggestion. In this way, by making suggestions based on the user's emotional state, it is possible to provide a more personalized service.

[2000] This system is linked to multiple shopping sites, so when a user wants to buy new clothes, they can enter their desired category and budget, and the server will search for and suggest the most suitable products and provide a purchase link.

[2001] The service also has a function that matches users with professional coordinators. When a user requests stylist advice for a special event, the server selects an appropriate coordinator and the user receives advice based on the request.

[2002] In this way, the present invention allows users to manage their clothing, suggest outfits, purchase, resell, and even collaborate with professional fashion coordinators in a unified manner, allowing users to enjoy fashion efficiently and smartly. Furthermore, by taking into account the user's emotional state, more personalized suggestions can be made, improving user satisfaction.

[2003] The processing flow will be explained below.

[2004] Garment photography and upload process

[2005] Step 1:

[2006] The user launches a dedicated application on the device and selects the "photograph clothing" function.

[2007] Step 2:

[2008] The device's camera is activated, and the user points the camera at the clothing they want to photograph and takes a photo.

[2009] Step 3:

[2010] The device displays the captured image and prompts the user to confirm. The user confirms and selects "Save."

[2011] Step 4:

[2012] The device uploads the saved images to a dedicated server.

[2013] Step 5:

[2014] The server receives the uploaded images and stores them in a database.

[2015] 3D data generation and classification process

[2016] Step 1:

[2017] The server executes an algorithm to analyze the received image.

[2018] Step 2:

[2019] The server uses image analysis to identify specific attributes of the clothing (e.g., shirt, pants, etc.).

[2020] Step 3:

[2021] The server generates three-dimensional data from the images of the identified garments.

[2022] Step 4:

[2023] The server classifies the generated 3D data by attributes such as color, shape, and style.

[2024] Step 5:

[2025] The server stores the classified clothing data in a database.

[2026] Coordination proposal process

[2027] Step 1:

[2028] The server retrieves the stored clothing information from the user's clothing database.

[2029] Step 2:

[2030] The server retrieves season, weather, temperature, and trend information from an external API.

[2031] Step 3:

[2032] Based on the above information, the server generates the most suitable outfit for the user.

[2033] Step 4:

[2034] The server transmits the generated coordinate information to the user's terminal.

[2035] Step 5:

[2036] The terminal notifies the user of the received coordination proposal.

[2037] Accumulation process of clothing usage

[2038] Step 1:

[2039] The user inputs information about the clothes they are wearing today through the application.

[2040] Step 2:

[2041] The terminal transmits the input wearing information to the server.

[2042] Step 3:

[2043] The server stores the received wearing information in a database.

[2044] Step 4:

[2045] The server runs a counting algorithm to calculate how often each garment is used.

[2046] Step 5:

[2047] The server generates data to notify the user based on the frequency of use.

[2048] The process of proposing to open a store on a flea market site

[2049] Step 1:

[2050] The server analyzes the accumulated data on the frequency of use of clothing.

[2051] Step 2:

[2052] The server lists the least frequently used clothes for a specific period.

[2053] Step 3:

[2054] The server generates recycling or resale suggestion data for the listed garments.

[2055] Step 4:

[2056] The server transmits the generated proposal data to the user's terminal.

[2057] Step 5:

[2058] The terminal notifies the user of the received proposal.

[2059] Process for linking with shopping sites

[2060] Step 1:

[2061] The user inputs the category and budget of the item they wish to purchase through the application.

[2062] Step 2:

[2063] The terminal transmits the input purchase information to the server.

[2064] Step 3:

[2065] The server calls the APIs of multiple linked shopping sites and retrieves product information that matches the criteria.

[2066] Step 4:

[2067] The server generates the optimal purchase link based on the product information acquired.

[2068] Step 5:

[2069] The server sends the generated purchase link to the user's terminal.

[2070] Step 6:

[2071] The terminal presents the received purchase link to the user.

[2072] User and Coordinator Matching Process

[2073] Step 1:

[2074] A user sends a request from an application for advice from a coordinator.

[2075] Step 2:

[2076] The terminal sends the user's request to the server.

[2077] Step 3:

[2078] A matching algorithm is executed based on the coordinator list held by the server.

[2079] Step 4:

[2080] The server selects an appropriate coordinator and generates a matching result.

[2081] Step 5:

[2082] The server notifies the user of the matching results.

[2083] Step 6:

[2084] The terminal presents the received matching results to the user.

[2085] Processing process using emotion engine

[2086] Step 1:

[2087] The user inputs a face image or voice through the application.

[2088] Step 2:

[2089] The terminal transmits the captured face image or voice data to the server.

[2090] Step 3:

[2091] The server runs a sentiment analysis algorithm based on the data it receives.

[2092] Step 4:

[2093] The server adjusts the coordination proposal based on the user's emotions recognized.

[2094] Step 5:

[2095] The server transmits the adjusted coordinate information to the user's terminal.

[2096] Step 6:

[2097] The terminal notifies the user of the received coordination proposal.

[2098] Step 7:

[2099] The user inputs feedback on the proposed outfit.

[2100] Step 8:

[2101] The device sends the feedback to the server.

[2102] Step 9:

[2103] The server optimizes the proposed algorithm based on the feedback.

[2104] These are the processing steps of the present invention, which incorporates an emotion engine that recognizes the user's emotions. This allows users to efficiently and intelligently manage their clothes, get outfit suggestions, purchase new clothes, recycle and resell, and connect with professional coordinators. Personalized suggestions based on emotion recognition can further improve user satisfaction.

[2105] Example 2

[2106] 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."

[2107] Conventional methods for managing clothing and suggesting outfits are often cumbersome and time-consuming for users. Furthermore, outfit suggestions that take into account the user's emotional state, the season, weather conditions, and fashion trends are not adequately implemented. As a result, it is difficult for users to enjoy efficient and personalized fashion. Furthermore, the lack of functionality to suggest reuse or resale of infrequently used clothing results in insufficient utilization of clothing. Therefore, the present invention aims to provide a system that streamlines clothing management and suggests outfits, and can make suggestions that reflect the user's emotional state and external information.

[2108] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving images of clothing photographed by a user, means for generating three-dimensional data of the clothing from the received images, means for classifying the generated three-dimensional data by attributes such as color and shape, means for saving the classified clothing data in a database, means for proposing outfits based on the saved clothing data and taking into account seasons, weather conditions, temperature, and fashion information, means for notifying the user of the suggested outfits, means for recording the user's clothing usage, means for identifying infrequently used clothing from the recorded usage information and proposing reuse or resale of the clothing, means for linking with multiple e-commerce sites to enable the user to purchase new clothing in bulk, means for matching the user with an expert, means for receiving a user's facial image and analyzing emotions, means for adjusting the outfit suggestions based on the emotion analysis results, means for receiving voice input and analyzing the voice data to recognize emotions, and means for adjusting the outfit suggestions based on the emotion recognition results. This improves the efficiency of clothing management and enables personalized outfit suggestions that reflect the user's emotions and external information. It also encourages the reuse and resale of clothing that is used less frequently, optimizing the use of clothing.

[2109] A "user" is a customer who uses the system to manage their clothing and receive coordination suggestions.

[2110] "Clothing image" is photographic data of clothing taken by a user using a terminal.

[2111] "Three-dimensional data" is data that aggregates three-dimensional shapes and attribute information generated from images of clothing.

[2112] "Classification" is the process of organizing the generated 3D data by attributes such as color, shape, and style.

[2113] A "database" is an information management system for storing classified clothing data.

[2114] "Season, weather conditions, temperature, and fashion information" is external environmental information that is taken into consideration when suggesting outfits.

[2115] "Coordination suggestions" refers to presenting optimal clothing combinations to users based on stored clothing data and external information.

[2116] "Notification" is a means by which the server conveys information such as coordination suggestions to the user's terminal.

[2117] "Usage status" is information indicating how frequently the user uses each piece of clothing.

[2118] "Usage information" is data that records the date and number of times the user has used the clothing.

[2119] "Reuse or resale" refers to the offer to repurpose or sell gently used clothing.

[2120] An "e-commerce site" is an online marketplace where users can purchase new clothing.

[2121] An "expert" is a person with specialized knowledge of fashion who gives coordination advice to the user.

[2122] A "face image" is photographic data of a user's own face taken with a terminal.

[2123] "Emotion analysis" is the process of recognizing a user's emotional state from facial images and voice data.

[2124] "Voice input" refers to voice data that is input by the user speaking into the terminal.

[2125] "Emotion recognition" is the process of identifying a user's emotions from speech data.

[2126] The present invention relates to a system for efficiently managing a user's clothing and suggesting outfits based on the managed clothing. Hereinafter, an embodiment of the system will be described in detail.

[2127] Overall system configuration

[2128] The system's main components are a terminal, a server, and a database. It also utilizes various software and APIs to realize functions such as image analysis, data management, outfit suggestions, emotion analysis, voice recognition, and online shopping.

[2129] Hardware and software used

[2130] The device used is a smartphone or tablet equipped with a camera, which allows users to take pictures of their clothes and their own faces.

[2131] The server is a high-performance computer that runs an image analysis engine, a database management system, and an AI model (e.g., TensorFlow or OpenCV).

[2132] The database uses a relational database management system (RDBMS, such as MySQL or PostgreSQL).

[2133] Program processing flow

[2134] 1. Photographing and uploading the garment:

[2135] The user launches the dedicated application and takes a picture of the garment using the camera, after which the device uploads the image to the server.

[2136] 2. Image analysis and 3D data generation:

[2137] The server uses an image analysis engine to analyze the received images and generate 3D data of the clothing. Image processing libraries such as TensorFlow and OpenCV are used for image analysis.

[2138] 3. Data Storage and Classification:

[2139] The server classifies the 3D data generated based on the analysis results by attributes such as color, shape, and style, and stores the classified data in a database.

[2140] 4. Coordination suggestions:

[2141] The server obtains external information such as the season, weather conditions, temperature, and fashion trends, and suggests optimal outfits to users based on the saved 3D data. The server uses the OpenWeatherMap API to obtain external information. The suggested outfits are then sent to the user via their device.

[2142] 5. Clothing usage analysis:

[2143] When a user enters their clothing information into their application, the device sends that information to a server, which analyzes the frequency of use based on the accumulated data and suggests reuse or resale of infrequently worn clothing.

[2144] 6. Sentiment analysis and suggestion adjustment:

[2145] The user inputs their emotional state using images or voice. The captured facial image is uploaded from the device to a server, which then uses an emotion analysis engine to recognize the emotion. The voice input data is also sent to the server and converted to text using, for example, the Google Cloud Speech-to-Text API. The outfit suggestions are then adjusted based on the emotion recognition results.

[2146] 7. Collaboration with shopping sites:

[2147] When a user wants to buy new clothes, they input their request through the terminal, and the server retrieves data from multiple e-commerce sites and suggests the best products to the user, for example, using the Amazon Product Advertising API.

[2148] 8. Matching with a professional coordinator:

[2149] When a user requests advice from a stylist for a specific event, they send a special request, and the server selects the most suitable person from the registered coordinators and matches them with the user.

[2150] Specific examples

[2151] As a concrete use case, consider the following scenario:

[2152] The user takes a photo of a white shirt and uploads the image from their device to the server. The server analyzes the image, identifies it as a white shirt, generates three-dimensional data, and stores it in a database. If the user then feels tired, they can notify the server via their device using a facial image or voice. The server then performs emotion analysis and suggests relaxing outfits to soothe fatigue.

[2153] Prompt Sentence Examples

[2154] "You take a picture of a white shirt and upload it to the server. Then you use the camera to take a picture of your face and receive outfit suggestions based on your emotional state. If you're tired, we'll suggest outfits that will help you relax."

[2155] In this way, the present invention provides a system that improves the efficiency of managing the clothes owned by the user and suggesting outfits, allowing the user to enjoy fashion comfortably.

[2156] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2157] Step 1:

[2158] The user launches the dedicated application and takes a picture of the garment using the camera, at which point the camera application installed on the device captures a high-resolution image.

[2159] Input: A user-taken image of the clothing

[2160] Output: Image file of the clothing saved on the device

[2161] Step 2:

[2162] The device uploads the captured image of the clothing to a server, where it is securely transmitted using HTTPS.

[2163] Input: Image file of clothing saved on the device

[2164] Output: Images of the garment uploaded to the server

[2165] Step 3:

[2166] The server analyzes the received images and generates 3D data of the clothing. Specifically, it processes the images with a deep learning model using TensorFlow and OpenCV to extract the 3D shape.

[2167] Input: Images of clothing uploaded to the server

[2168] Output: 3D data of the generated garment

[2169] Step 4:

[2170] The server classifies the generated 3D data by attributes such as color, shape, and style, using machine learning algorithms.

[2171] Input: 3D data of the generated clothing

[2172] Output: Classified clothing data

[2173] Step 5:

[2174] The server stores the classified data in a database, which is then inserted into the database (e.g., MySQL or PostgreSQL) using SQL queries.

[2175] Input: Categorized clothing data

[2176] Output: Clothing data stored in a database

[2177] Step 6:

[2178] The server uses external APIs to obtain external information such as seasons, weather conditions, temperature, and trend information. Examples of APIs used include the OpenWeatherMap API.

[2179] Input: Request for external information obtained from API

[2180] Output: The external information obtained

[2181] Step 7:

[2182] The server runs an algorithm based on the stored data and external information to suggest the best outfits for the user. In this case, a generative AI model is used.

[2183] Input: Garment data and external information stored in the database

[2184] Output: Proposed coordinate data

[2185] Step 8:

[2186] The device receives coordination suggestions from the server and displays an interface to notify the user. Push notifications may also be used.

[2187] Input: Coordination proposal data sent from the server

[2188] Output: Coordination suggestions displayed to the user

[2189] Step 9:

[2190] The wearing information entered by the user is recorded on the terminal. Once the input is complete, the terminal sends the wearing information to the server.

[2191] Input: Wearing information entered by the user

[2192] Output: Wearing information sent to the server

[2193] Step 10:

[2194] The server analyzes the frequency of use based on the accumulated wearing information, and uses SQL to retrieve data from the database, aggregate and analyze it.

[2195] Input: Wearing information stored on the server

[2196] Output: Analysis results on frequency of use

[2197] Step 11:

[2198] The server identifies gently used clothing and makes suggestions for reuse or resale, which are then notified to the user.

[2199] Input: Analysis results on frequency of use

[2200] Output: Proposal data for reuse or resale

[2201] Step 12:

[2202] The user takes a picture of their face with the device, which then uploads the captured image to the server.

[2203] Input: A face image taken by the user

[2204] Output: Face image uploaded to the server

[2205] Step 13:

[2206] The server analyzes the facial image and recognizes the user's emotions. Image recognition is performed using OpenCV or deep learning models, for example.

[2207] Input: Face image uploaded to the server

[2208] Output: Recognized user emotion data

[2209] Step 14:

[2210] The server adjusts the outfit suggestions based on the emotion recognition results, selecting outfits that will alleviate emotions such as stress and fatigue.

[2211] Input: Recognized user emotion data

[2212] Output: Adjusted coordinate suggestion data

[2213] Step 15:

[2214] The user speaks to the application to provide voice input, and the device sends the voice data to the server.

[2215] Input: Voice data spoken by the user

[2216] Output: Audio data sent to the server

[2217] Step 16:

[2218] The server analyzes the voice data and recognizes the user's emotions. It converts the voice data into text using the Google Cloud Speech-to-Text API and then analyzes the emotions.

[2219] Input: Audio data sent to the server

[2220] Output: Translated speech data and recognized emotion data

[2221] Step 17:

[2222] The server adjusts the coordination suggestions based on the emotion recognition results, allowing suggestions to be tailored to the user's emotions.

[2223] Input: Recognized emotion data

[2224] Output: Adjusted coordinate suggestion data

[2225] Step 18:

[2226] The user inputs their desired clothing purchase, and the terminal sends the desired category and budget to the server.

[2227] Input: New purchase request (category and budget) entered by the user

[2228] Output: Purchase request data sent to the server

[2229] Step 19:

[2230] The server searches for product information from multiple e-commerce sites, using the Amazon Product Advertising API, etc.

[2231] Input: Purchase request data sent to the server

[2232] Output: Retrieved product information data

[2233] Step 20:

[2234] The server selects the most suitable product based on the search results and provides the user with a purchase link.

[2235] Input: Retrieved product information data

[2236] Output: Purchase link and product information provided to the user

[2237] Step 21:

[2238] The user requests advice from a stylist. The device sends the request to the server.

[2239] Input: A user-entered request for stylist advice

[2240] Output: Request data sent to the server

[2241] Step 22:

[2242] The server selects the most suitable coordinator based on the information of registered coordinators and matches it with the user.

[2243] Input: Coordinator information stored on the server and user request data

[2244] Output: Selected coordinator information and matching results

[2245] The above is a description of the specific operations and inputs and outputs for each processing step of the program of this system.

[2246] (Application example 2)

[2247] 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."

[2248] Traditionally, managing a user's clothing and suggesting outfits was often done manually, which was time-consuming and labor-intensive. Furthermore, outfit suggestions that took into account the user's emotions and external environment were rarely provided, making it difficult to increase user satisfaction. Furthermore, there were cases where infrequently worn clothing was not managed and collaboration with professional outfit coordinators was not fully implemented, preventing efficient clothing utilization.

[2249] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2250] In this invention, the server includes means for receiving images of clothing photographed by a user, means for generating three-dimensional data of the clothing from the received images, means for classifying the generated three-dimensional data by attributes such as color and shape, means for saving the classified clothing data in a database, means for suggesting outfits based on the saved clothing data and taking into account season, weather, temperature, and trend information, means for notifying the user of the suggested outfits, means for recording the user's clothing usage, means for identifying infrequently used clothing from the recorded usage information and suggesting recycling or resale, means for linking with multiple purchasing sites to enable the user to purchase new clothing in bulk, means for matching users with experts, means for receiving a user's facial image or voice input and analyzing emotions, and means for adjusting the outfit suggestions based on the analyzed emotions. This enables more accurate and personalized clothing management and outfit suggestions that take into account the user's emotions and external environment.

[2251] "User" refers to an individual who uses the system to manage clothing and receive coordination suggestions.

[2252] "Clothing image" refers to photographic data of specific clothing that a user takes and uploads to the system.

[2253] "Three-dimensional data" is three-dimensional data generated from an image and has attributes such as the color and shape of clothing.

[2254] "Database" means an information management system for storing classified garment data and other related information.

[2255] "Coordination suggestions" refers to suggestions to the user for appropriate clothing combinations based on stored clothing data and external information.

[2256] "Notification" refers to the act of sending and informing a user of suggested outfits and other information.

[2257] "Usage status" is information that records how much a user uses the clothing.

[2258] "Recycle or resell" is the act of offering to reuse gently used clothing.

[2259] "Shopping sites" are multiple online sales sites where users can purchase new clothing.

[2260] An "expert" is a professional with specialized knowledge about clothing coordination who provides advice to users.

[2261] "Emotion analysis" is a process that analyzes the user's facial image and voice input to recognize their current state of mind and emotions.

[2262] "Adjustment" refers to the act of optimizing the coordination suggestions to suit the user's emotional state based on the analyzed emotions.

[2263] The present invention provides a system for managing a user's clothing and for efficiently suggesting outfits based on that data. Hereinafter, an embodiment of the present invention will be described based on a specific operational example.

[2264] First, the user takes a picture of the clothing using their smartphone. The image is then uploaded to a server via the smartphone's application. The server then analyzes the received image using the Google Cloud Vision API and generates 3D data with attributes such as the color and shape of the clothing. This 3D data is then stored in a database such as MySQL.

[2265] Based on the stored data, the server takes into account the season, weather, temperature, and trend information to suggest appropriate outfits. These suggestions are provided to the user via the smartphone's notification function. In particular, when the user takes a facial image or enters voice input, the respective data is sent to the server, and emotions are analyzed using the Microsoft Azure Emotion API. Based on the analyzed emotions, the outfit suggestions are further adjusted.

[2266] For example, if a user takes a photo of a black jacket and uploads it to the application, the server generates three-dimensional data of the black jacket from the received image and stores it in a database. If the user then voice-inputs "It's cold today" into their smartphone, the server analyzes the voice data, recognizes that the user is feeling cold, and suggests corresponding outfits.

[2267] Furthermore, the server records the user's clothing usage and identifies infrequently worn clothing. The server then offers suggestions for recycling or reselling the identified clothing. The server also connects with multiple purchasing sites to offer shopping suggestions, allowing users to purchase desired new clothing all at once. For special events, the server matches users with experts to provide professional coordination advice.

[2268] Below are some example prompts for the generative AI model:

[2269] Example prompt sentence:

[2270] Please convert a photo of a black jacket taken by the user into 3D data using the image analysis API and save it in the user database. Also, please analyze the user's voice input "It's cold today" and suggest the warmest possibl...

Claims

1. means for receiving an image of clothing taken by a user; means for generating three-dimensional data of the garment from the received image; A means for classifying the generated 3D data by attributes such as color and shape; a means for storing the classified clothing data in a database; A method for suggesting outfits based on stored clothing data, taking into account season, weather, temperature, and trend information; means for notifying a user of the suggested coordination; means for recording the user's clothing usage; A means of identifying gently used clothing from the recorded usage information and suggesting recycling or resale; A way to connect with multiple shopping sites and allow users to buy new clothes in bulk; A means of matching users with professional coordinators, A system including:

2. 2. The system according to claim 1, further comprising means for recording the usage of the clothing based on an input from the user and analyzing the frequency of usage based on the recorded data.

3. The system of claim 1 , further comprising means for obtaining feedback from a user regarding suggested outfits and using the feedback to optimize the suggestion algorithm.

4. 10. The system of claim 1, further comprising means for receiving online lessons from a professional coordinator.

5. 2. The system according to claim 1, further comprising means for acquiring weather information for each specific time in real time and reflecting the information in the coordination proposal.

Images