System

Abstract

A system is provided.SOLUTION: The system includes a means for collecting personal information of a user, a means for determining a style most suitable for the user by using a machine learning algorithm based on the collected personal information, a means for capturing a video of the user and generating the determined style as a simulation video, a means for acquiring product information proposed from an online store, and a means for presenting the product information proposed to the user and allowing the user to select and purchase.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] In today's consumer society, the fashion industry produces a large amount of clothing, and consumers often have difficulty finding the right size and style, resulting in an increasing amount of clothing that is discarded after purchase. As a result, a large amount of clothing is discarded, increasing the burden on the environment. Furthermore, consumers often find it difficult to choose products that suit their preferences and body type, which often leaves them dissatisfied with their purchases. To solve these problems, a system is needed that can suggest optimal clothing to consumers and reduce unnecessary purchases. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for collecting a user's personal information, a means for determining the user's optimal style based on the collected personal information using a machine learning algorithm, a means for capturing a user's video and generating a simulation video of the determined style, a means for acquiring suggested product information from an online store, and a means for presenting the suggested product information to the user, allowing the user to select and purchase. Specifically, the user inputs personal information, body type diagnosis, and personal color diagnosis information through an application, and the optimal style analyzed by the machine learning algorithm is simulated on the user's video. The online store then presents suggested product information to the user, allowing the user to select and purchase the best items that suit their preferences and body type. This prevents unnecessary clothing purchases and reduces clothing waste.

[0006] "User Information" refers to personal information provided by the user, specifically information including name, age, gender, height, weight, fashion preferences, usage situation, and results of bone structure diagnosis and personal color diagnosis.

[0007] "Machine learning algorithms" refer to statistical models and computational methods for analyzing large amounts of data, learning patterns from it, and making predictions and classifications.

[0008] "Best Style" identifies the fashion style, clothing design, color, and silhouette that best suits a user based on the user's personal information and individual characteristics.

[0009] "Capturing video" refers to the process of using a camera to digitally capture an image of the user's current posture and face.

[0010] "Simulated video" refers to a virtual video generated by overlaying the optimal style determined by a machine learning algorithm onto a user's video.

[0011] "Online Store" means a website or application that sells goods or services over the Internet.

[0012] "Product information" refers to detailed product information obtained from an online store, including information such as price, design, material, and size.

[0013] "Suggest" refers to the process of providing the best options to the user based on the results of machine learning algorithms and user information.

[0014] "Selection" refers to the act of a user choosing from multiple options presented the option that best suits their preferences and needs.

[0015] "Purchase" refers to the process of obtaining a product through an online store or other sales channel by completing payment based on the selected product information. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7]FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

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

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] The system of the present invention collects personal information of a user and proposes an optimal fashion style, thereby providing a consumer-friendly and environmentally friendly approach. Hereinafter, an embodiment of the present invention will be described.

[0038] This system mainly consists of a user terminal, a server, and an online store. Users access the system using their own smartphones or computers (user terminals).

[0039] Program processing

[0040] 1. Collection of User Information

[0041] The user launches the application and enters personal information

[0042] The user device displays a screen for entering basic information such as name, age, gender, height, weight, fashion preferences, and usage situation (e.g., business, casual).

[0043] The user performs a bone structure diagnosis and a personal color diagnosis.

[0044] The user terminal presents the user with a question using a plurality of images and prompts the user to input an answer.

[0045] The server stores the collected data in a database and analyzes it.

[0046] 2. Automatic judgment by AI

[0047] The server proposes the best style based on the information collected

[0048] The server inputs the stored user information into a machine learning model to automatically determine the style and color that best suits the user.

[0049] The server stores the results of the assessment in a database and generates recommended styles tailored to each user.

[0050] 3. Simulation using the person's own video

[0051] The user uses the camera in the application to capture their own video.

[0052] The user device uses its camera function to capture images of the user's current posture and face.

[0053] The server runs the simulation

[0054] The user terminal transmits the captured video to the server.

[0055] The server combines the captured video with a pre-determined style to generate a simulation video in which the costume is superimposed on the user's image.

[0056] The server transmits the generated simulation video to the user terminal.

[0057] 4. AI recommends suitable clothing from apparel sites

[0058] The server acquires product information from the apparel site based on the proposal results.

[0059] The server searches the online store for products that match the proposed style and retrieves multiple options.

[0060] The server organizes the acquired product information and generates a list to suggest to the user.

[0061] Present the proposed results to the user

[0062] The user terminal displays a list of the proposal results received from the server, allowing the user to make a selection.

[0063] 5. Users can purchase original items that suit their tastes

[0064] The user selects and purchases from the suggested products

[0065] The user terminal provides an interface for the user to select items they wish to purchase from the suggested merchandise.

[0066] The server handles the purchase process

[0067] The user terminal transmits the selected product information and data required for the purchase procedure to the server.

[0068] The server sends the necessary information to the online store to proceed with the purchase, allowing the user to complete the purchase.

[0069] The server notifies the user terminal that the purchase has been completed and asks the user to confirm.

[0070] Specific examples

[0071] For example, suppose User A starts an application, enters personal information such as name, age, and height, and answers questions about bone structure and personal color diagnosis. The collected information is sent to the server, where a machine learning algorithm determines the optimal style. User A then takes a video of themselves with a camera and checks which style suits them best in the simulation video sent from the server. The server then retrieves product information from the online store that matches the suggested style and suggests it to User A. User A then selects and purchases the items they like from the presented list. Through this process, User A can select the optimal products based on their personal information and avoid unnecessary purchases.

[0072] This will enable consumers to enjoy a more satisfying purchasing experience and reduce the burden on the environment.

[0073] The processing flow will be explained below.

[0074] Step 1:

[0075] The user launches the application and enters personal information

[0076] Users enter basic information such as their name, age, gender, height, weight, fashion preferences, and usage situation (e.g., business, casual) on their device.

[0077] Step 2:

[0078] The user performs a bone structure diagnosis and a personal color diagnosis.

[0079] The user device shows the user multiple images for skeletal diagnosis and asks them to choose the one that most closely resembles their own.

[0080] Similarly, personal color diagnosis questions are presented and the user answers them.

[0081] The terminal transmits the input information to the server.

[0082] Step 3:

[0083] The server analyzes the user information

[0084] The server stores the received user information in a database.

[0085] The server then feeds the stored information into a machine learning algorithm to analyze the style and color that best suits the user.

[0086] The analysis results are saved in a database.

[0087] Step 4:

[0088] The user captures the video using the camera

[0089] The user activates the camera function of the user device to take a video of themselves.

[0090] The terminal transmits the captured video data to the server.

[0091] Step 5:

[0092] The server generates the simulation video

[0093] The server generates a simulation video by overlaying the captured user video with the optimal style information determined by machine learning.

[0094] The simulation video is sent to the user's device so that the user can view it.

[0095] Step 6:

[0096] The server will suggest suitable clothing items

[0097] Based on the generated style information, the server retrieves product information from the online store via API.

[0098] The server analyzes the acquired product information and selects clothing candidates that are best suited to the user.

[0099] A list of suggested product information is sent to the user's device.

[0100] Step 7:

[0101] The user selects and purchases the suggested product

[0102] The user selects the desired product from the product list displayed on the user terminal.

[0103] The terminal presents the user with a form to complete the purchase process and prompts them to enter the necessary information (e.g., payment information, etc.).

[0104] The terminal transmits the input information to the server.

[0105] Step 8:

[0106] The server handles the purchase process

[0107] The server sends the user's selected product information and payment information to the online store to complete the purchase.

[0108] The server sends a purchase confirmation message to the user's terminal, allowing the user to confirm the purchase.

[0109] The process at each step utilizes machine learning and simulation technology to provide optimal products tailored to user needs, preventing unnecessary purchases and reducing environmental impact.

[0110] Example 1

[0111] 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."

[0112] In modern society, consumers spend a lot of time and effort selecting the fashion style that best suits them. Furthermore, the increased purchase of inappropriate fashion items can have a negative impact on the environment. Furthermore, even with online shopping, consumers often feel dissatisfied after purchasing because they cannot actually try on the products. To solve these problems, a system is needed that can suggest optimal fashion styles tailored to individual consumers and perform a try-on simulation.

[0113] 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.

[0114] In this invention, the server includes means for collecting personal information of a user, means for determining the optimal style for the user based on the collected personal information using a machine learning algorithm, means for capturing an image of the user and generating a simulation image of the determined style, means for acquiring suggested product information from an online store, means for presenting the suggested product information to the user so that the user can select and purchase, means for saving the user's personal information and diagnostic information in a database and analyzing that information, means for capturing an image of the user's current posture and face when generating the simulation image, means for organizing the acquired product information and generating a list to suggest to the user, and means for supporting the purchase procedure based on the user's selection. This allows the user to efficiently select appropriate fashion items based on their personal information and enjoy a satisfying purchasing experience through a try-on simulation.

[0115] "User's personal information" refers to basic information such as the user's name, age, gender, height, weight, fashion preferences, and usage situation.

[0116] "Machine learning algorithm" refers to an algorithm that learns patterns from collected data and uses the results to suggest the best styles and colors for users.

[0117] "User's Images" refers to image and video data of the user's appearance, voice, and face captured by the user's camera using the application.

[0118] "Simulation video" refers to video data that provides a visual like trying on clothes, with the determined style superimposed on the user's video.

[0119] "Online store" refers to a store that sells products via the Internet.

[0120] A "database" refers to a system for organizing and storing data so that it can be searched and analyzed later.

[0121] A "web scraping tool" refers to software for automatically extracting specific data from web pages on the Internet.

[0122] "User terminal" refers to a device such as a smartphone or computer operated by a user.

[0123] "Checkout" refers to the series of steps (e.g., selection, payment, delivery arrangements) required by a User to purchase an item from an online store.

[0124] "Image processing technology" refers to the technology of processing and analyzing image data using a computer, and is used to generate simulation images.

[0125] "Judgment results" refer to the optimal fashion style and color combinations suggested to users based on analysis by machine learning algorithms.

[0126] "Product Information" refers to detailed product information (price, size, color, material, etc.) obtained from the online store.

[0127] MODE FOR CARRYING OUT THE INVENTION

[0128] The present invention is a system that collects personal information of a user and suggests an optimal fashion style. This system is mainly composed of a user terminal, a server, and an online store. Specific embodiments for carrying out the present invention will be described below.

[0129] Hardware and software used

[0130] User devices: Smartphones, computers, etc. These devices provide an interface for users to input information.

[0131] Server: Operates database software (e.g., MySQL®) and machine learning models (e.g., TENSORFLOW®).

[0132] Image processing software: such as OpenCV. Used to generate simulation images.

[0133] Web scraping tools, such as BeautifulSoup, are used to retrieve product information from online stores.

[0134] Program processing

[0135] Users access the system using a smartphone or computer and follow the process below.

[0136] 1. Collection of User Information

[0137] The user starts the application and enters basic information such as name, age, gender, height, weight, fashion preferences, and usage situation. The user's device sends this data to the server. The user also performs a bone structure diagnosis and personal color diagnosis, and sends the data to the server.

[0138] 2. Automatic judgment by AI

[0139] The server stores the collected personal information and diagnostic data in a database and uses machine learning algorithms to determine the best style and color for each user. The results are then stored in the database.

[0140] 3. Simulation using the person's own video

[0141] The user captures video of their posture and face through the application. The user device sends this video data to the server. The server combines the captured video with the determined style to generate a simulation video and sends it to the user device.

[0142] 4. AI recommends suitable clothing from apparel sites

[0143] The server searches the online store for products that match the proposed style, organizes the obtained product information, and generates a list to suggest to the user. This list is sent to the user's terminal and presented to the user.

[0144] 5. Users can purchase original items that suit their tastes

[0145] The user selects the item they wish to purchase from the list of suggested products and clicks the purchase button. The user's device sends the selected product information and data required for the purchase process to the server. The server then sends the information required to proceed with the purchase to the online store and notifies the user's device that the purchase is complete.

[0146] Specific examples

[0147] For example, User A starts the application, enters personal information such as name, age, and height, and answers questions about bone structure and personal color diagnosis. This information is sent to the server, and a machine learning algorithm determines the optimal style. User A then takes a video of themselves with a camera and checks which style suits them best in the simulation video sent from the server. The server then retrieves product information from the online store that matches the suggested style and suggests it to User A. User A then selects their preferred item from the list provided and purchases it.

[0148] This allows User A to select the most suitable product based on their personal information and avoid unnecessary purchases. Through this process, consumers can enjoy a more satisfying shopping experience and reduce their environmental impact.

[0149] Prompt Sentence Examples

[0150] Below are some example prompts to input to machine learning algorithms:

[0151] "User A is 25 years old, 160cm tall, weighs 50kg, and wants fashion suitable for business situations. His bone structure diagnosis is ectomorph, and his personal color is spring."

[0152] This allows the server to determine and suggest the best style and color for user A.

[0153] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0154] Program processing flow

[0155] Step 1: Collect user information

[0156] Input: User's personal information (name, age, gender, height, weight, fashion preferences, usage situation) and answers to the bone structure diagnosis and personal color diagnosis.

[0157] process:

[0158] The user launches the application and enters their basic information into the form that appears.

[0159] The user answers diagnostic questions.

[0160] The user terminal collects this information and sends it to the server.

[0161] Output: User personal and diagnostic information sent to the server.

[0162] Step 2: Data storage and analysis

[0163] Input: The user's personal and diagnostic information.

[0164] process:

[0165] The server stores the received data in a database.

[0166] The server inputs the data into the machine learning model and performs the analysis.

[0167] Machine learning algorithms use the collected data to determine the best fashion style and color.

[0168] Output: The result of the judgement (the best style and color combination for the user).

[0169] Step 3: Import your own video

[0170] Input: Video of the user's current pose and face.

[0171] process:

[0172] Users use the application to activate the camera and capture footage of themselves.

[0173] The user device sends the captured video to the server.

[0174] Output: User video data sent to the server.

[0175] Step 4: Generate simulation footage

[0176] Input: User video data and determined style information.

[0177] process:

[0178] The server generates a simulation video using the received video data and the determined style information.

[0179] The server uses image processing techniques (e.g. OpenCV) to overlay a style onto the user's video.

[0180] Output: Simulation video.

[0181] Step 5: Obtaining proposed product information

[0182] Input: Determined style information.

[0183] process:

[0184] The server searches the online store for product information that matches the suggested style.

[0185] The server uses a web scraping tool (e.g. BeautifulSoup) to retrieve and organize product information.

[0186] Output: A list of suggested product information.

[0187] Step 6: Presenting the proposed results

[0188] Input: Proposed product information.

[0189] process:

[0190] The server transmits the proposal results to the user terminal.

[0191] The user terminal displays a list of suggested product information to the user.

[0192] Output: A list of suggestion results shown to the user.

[0193] Step 7: Select and purchase products

[0194] Input: List of proposed product information.

[0195] process:

[0196] The user selects the items to purchase from the suggested products.

[0197] The user terminal transmits the selected product information and necessary purchase data to the server.

[0198] Output: Purchase data sent to the server.

[0199] Step 8: Support with checkout

[0200] Input: User-selected product information and purchase data.

[0201] process:

[0202] The server passes the purchase procedure to the online store's system.

[0203] The server sends a purchase completion notification to the user terminal, and the user confirms it.

[0204] Output: Notification and confirmation that the purchase has been completed.

[0205] (Application example 1)

[0206] 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."

[0207] Conventional fashion suggestion systems are limited to suggesting optimal styles based on a user's personal information, which is insufficient for improving the shopping experience in physical stores. Furthermore, most virtual try-on systems are limited to online stores, making it difficult to use in stores in real time. The present invention aims to solve these problems and make shopping in physical stores more intuitive and satisfying for users.

[0208] 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.

[0209] In this invention, the server includes means for collecting personal information of the user, means for determining the optimal style for the user based on the collected personal information using a machine learning algorithm, means for capturing an image of the user and generating a simulation image of the determined style, means for acquiring suggested product information from an online store, means for presenting the suggested product information to the user so that the user can select and purchase, means for capturing an image of the user in real time using a camera function of the smart glasses, and means for acquiring in-store inventory information and generating a product list to be suggested to the user. This allows the user to check the fashion items that are optimal for them in real time, improving the shopping experience in physical stores.

[0210] "User's personal information" refers to individual information about the user, such as the user's name, age, gender, height, weight, fashion preferences, and usage situation.

[0211] A "machine learning algorithm" is an artificial intelligence technique that uses data to train models to identify patterns and relationships and make predictions.

[0212] "Simulation video" is a video in which the judged style and outfit are superimposed on the user's video, giving the impression of virtually trying on the outfits.

[0213] An "online store" is a website or platform that sells products over the Internet.

[0214] "Smart glasses" are glasses-type wearable devices that have the function of displaying information in the user's field of vision.

[0215] "Camera function" refers to hardware and software that has the function of taking images and videos.

[0216] "Stock information" is information about the quantity and types of products available in the store.

[0217] A "product list" is a list of suggested products that is presented in a format that allows the user to select from them.

[0218] The system embodying this invention mainly collects personal information of users and suggests optimal fashion styles based on that information. Furthermore, this system is designed to enhance users' shopping experience in physical stores, and uses smart glasses to suggest optimal styles in real time.

[0219] Configuration and Operation Procedures

[0220] 1. Collection of User Information

[0221] Users input their personal information (such as name, age, gender, height, weight, preferred style, and usage situation) through smart glasses or other devices. This operation is carried out through a dedicated application.

[0222] 2. Body type diagnosis and personal color diagnosis

[0223] Users upload their own images and the system asks them to answer a number of questions to diagnose their body type and personal color. This information is also sent to the server and stored in a database.

[0224] 3. Determining the best style

[0225] The server uses machine learning algorithms based on the collected personal information to determine the best style for the user, using a generative AI model for this process.

[0226] 4. Real-time video capture and simulation

[0227] The camera function of the smart glasses is used to capture real-time footage of the user, and a simulated video is generated with the determined style overlaid on it, which the user can view through the smart glasses.

[0228] 5. Obtaining in-store inventory information

[0229] The server retrieves inventory information from physical stores and generates a list of products to suggest to users, allowing them to check the items available in the store in real time.

[0230] 6. Recommended styles and product suggestions

[0231] The server retrieves the best product information from online and physical stores and suggests it to the user, who can then review the suggestions through the smart glasses and make a purchase decision.

[0232] Specific examples

[0233] For example, when User A enters a physical store, the smart glasses capture User A's image in real time and suggest the best style based on the personal information input in advance. The server uses the results of User A's bone structure and personal color diagnosis to display a simulation image of an outfit that would suit User A.

[0234] The server then retrieves in-store inventory information and generates a list of products that are optimal for User A. User A can then view, select, and purchase items through the smart glasses.

[0235] Hardware and software used

[0236] Hardware: Smart glasses (with camera function), user devices (smartphones, tablets, PCs)

[0237] Software: Machine learning algorithms (generative AI models), image processing technology, online store API, store inventory management system

[0238] Prompt Sentence Examples

[0239] "Please suggest the best fashion style for user A based on their age, gender, build, and preferences. Also, please generate a virtual try-on image and display it in real time. User camera: user_image.jpg"

[0240] By using this prompt, the generative AI model can provide optimal fashion suggestions to users.

[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 enters personal information using smart glasses or other devices. The user information input form includes name, age, gender, height, weight, fashion preferences, and usage situation. After input, this information is sent to the server. The entered data is stored in the server's database and used for further processing.

[0244] Step 2:

[0245] The user performs a bone structure diagnosis and a personal color diagnosis. The user uploads an image, and the system asks the user several questions along with the image, prompting the user to answer. This diagnostic information is also sent to the server and stored in a database. The server uses this data to analyze the user's body shape and skin color.

[0246] Step 3:

[0247] The server uses a machine learning algorithm to determine the best style for the user based on the collected personal information and diagnostic results. This data is input into a generative AI model, which then suggests the best style and color. The server then stores the generated style data in a database.

[0248] Step 4:

[0249] The user captures a real-time video of themselves using the camera function of their smart glasses. The device then sends the image captured by the camera to the server. The server then overlays the received image with a pre-determined style to generate a simulated video. The generated simulated video is then sent from the server to the user's smart glasses.

[0250] Step 5:

[0251] The server retrieves product information to be suggested from both online and physical stores. It searches for products that match the style suggested by the AI ​​through the online store's API and the physical store's inventory management system. The server organizes the retrieved product information and generates a list to suggest to the user. The list is then sent from the server to the user's smart glasses.

[0252] Step 6:

[0253] The user checks the suggested product information and selects it using the smart glasses. The user then selects the item they want from the list and proceeds with the purchase using the smart glasses. The device then sends the selected product information and the data required for the purchase to the server, which then forwards it to the online store to complete the purchase. The user can receive a confirmation message through the smart glasses.

[0254] Step 7:

[0255] The server stores the completed purchase information in a database and manages it as the user's purchase history. The user can use this history as reference for their next purchase. The server can also use this data to learn how to make more advanced personalized fashion suggestions.

[0256] 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.

[0257] The system of the present invention not only collects personal information of a user and suggests the most suitable fashion style, but also recognizes the user's emotions and adjusts the information and suggestions provided, and combines an emotion engine to improve the consumer experience. Hereinafter, embodiments for carrying out the present invention will be described in detail.

[0258] This system mainly consists of a user terminal, a server, an emotion engine, and an online store. Users access the system using their own smartphones or computers (user terminals).

[0259] Program processing

[0260] 1. Collection of User Information

[0261] The user launches the application and enters personal information

[0262] The user device displays a screen for entering basic information such as name, age, gender, height, weight, fashion preferences, and usage situation (e.g., business, casual).

[0263] The user performs a bone structure diagnosis and a personal color diagnosis.

[0264] The user terminal presents the user with a question using a plurality of images and prompts the user to input an answer.

[0265] The terminal transmits the input information to the server.

[0266] 2. Automatic judgment by AI

[0267] The server analyzes the user information

[0268] The server stores the received user information in a database.

[0269] The server then feeds the stored information into a machine learning algorithm to analyze the style and color that best suits the user.

[0270] The analysis results are saved in a database.

[0271] 3. Simulation using the person's own video

[0272] The user captures the video using the camera

[0273] The user activates the camera function of the user device to take a video of themselves.

[0274] The terminal transmits the captured video data to the server.

[0275] The server generates the simulation video

[0276] The server generates a simulation video by overlaying the captured user video with the optimal style information determined by machine learning.

[0277] The simulation video is sent to the user's device so that the user can view it.

[0278] 4. Use of Emotion Engine

[0279] User uses camera to recognize emotions

[0280] The user device uses a camera function to capture the user's facial expression and transmits the image to the server.

[0281] The server uses an emotion engine to recognize emotions from the user's facial expressions.

[0282] Emotion engine adjusts suggestions

[0283] Based on the recognized emotion data, the server adjusts the product information and simulation images it proposes to make suggestions that are appropriate for the user.

[0284] For example, if a user is feeling stressed, it will suggest fashion that will help them relax.

[0285] 5. AI suggests suitable clothing from apparel sites

[0286] The server acquires product information from the apparel site based on the proposal results.

[0287] The server searches the online store for products that match the proposed style and retrieves multiple options.

[0288] The server organizes the acquired product information and generates a list to suggest to the user.

[0289] A list of suggested product information is sent to the user's device.

[0290] 6. Users can purchase original items that suit their tastes

[0291] The user selects and purchases from the suggested products

[0292] The user selects the desired product from the product list displayed on the user terminal.

[0293] The terminal presents the user with a form for completing the purchase procedure and prompts the user to enter the necessary information.

[0294] The terminal transmits the input information to the server.

[0295] The server handles the purchase process

[0296] The server sends the user's selected product information and payment information to the online store to complete the purchase.

[0297] The server sends a purchase confirmation message to the user's terminal, allowing the user to confirm the purchase.

[0298] Specific examples

[0299] For example, suppose User B launches the application, enters personal information, and answers questions about bone structure and personal color. This information is sent to the server, where a machine learning algorithm determines the optimal style. Next, User B takes a video of themselves with a camera and checks which style suits them best in the simulation video sent from the server. At the same time, the emotion engine analyzes User B's facial expressions and suggests a casual style if they are relaxed, or a style that gives them a sense of security if they are nervous. This suggestion is based on information obtained from the online store, and User B selects and purchases the most suitable items. This process allows User B to achieve high satisfaction while reducing their environmental impact through purchases.

[0300] The processing flow will be explained below.

[0301] Step 1:

[0302] The user launches the application and enters personal information

[0303] The user launches the application on their device and operates a screen to enter basic information such as name, age, gender, height, weight, fashion preferences, and usage situation (e.g., business, casual).

[0304] The terminal stores the information entered by the user and transmits it to the server.

[0305] Step 2:

[0306] The user performs a bone structure diagnosis and a personal color diagnosis.

[0307] The user device displays multiple images and options for skeletal diagnosis and prompts the user to choose the one that best suits them.

[0308] Similarly, a number of questions and images are presented for personal color diagnosis, and the user answers them.

[0309] The terminal obtains the user's answer and sends it to the server.

[0310] Step 3:

[0311] The server analyzes the user information

[0312] The server stores the received personal information and diagnostic results in a database.

[0313] The server runs machine learning algorithms based on the stored information to analyze the style and color that best suits the user.

[0314] The analysis results are stored in a database for further processing.

[0315] Step 4:

[0316] The user captures the video using the camera

[0317] The user activates the camera function of the user device and takes an image of their current posture and face.

[0318] The terminal transmits the captured video data to the server.

[0319] Step 5:

[0320] The server generates the simulation video

[0321] The server generates a simulation video using the captured user video and optimal style information determined by machine learning.

[0322] The server transmits the generated simulation video to the user terminal so that the user can visually check it.

[0323] Step 6:

[0324] User uses camera to recognize emotions

[0325] The user captures their facial expression using the camera function of their device.

[0326] The terminal transmits the acquired video data to the server.

[0327] Step 7:

[0328] The server recognizes emotions using an emotion engine

[0329] The server analyzes the transmitted video data and uses an emotion engine to recognize emotions from the user's facial expressions.

[0330] The user's psychological state is determined based on the recognized emotional data.

[0331] Step 8:

[0332] Emotion engine adjusts suggestions

[0333] The server then adjusts the product information and simulation images it recommends based on the user's emotional data. For example, if it determines that the user is relaxed, it will suggest a casual, relaxed style.

[0334] The adjusted proposal content is sent to the user device.

[0335] Step 9:

[0336] The server acquires product information from the apparel site based on the proposal results.

[0337] The server retrieves multiple options from the online store via API, searching for products that match the user's best style.

[0338] The server analyzes the acquired product information and selects clothing candidates that are best suited to the user.

[0339] A list of suggested product information is sent to the user's device.

[0340] Step 10:

[0341] The user selects and purchases the suggested product

[0342] The user selects the desired product from the product list displayed on the user terminal.

[0343] The terminal displays a form for the user to complete the purchase procedure and prompts the user to enter the necessary information.

[0344] The terminal transmits the input information to the server.

[0345] Step 11:

[0346] The server handles the purchase process

[0347] The server sends the user's selected product information and payment information to the online store to complete the purchase.

[0348] The server sends a purchase confirmation message to the user's terminal, allowing the user to confirm the purchase.

[0349] This system allows users to receive suggestions for optimal fashion styles based on their personal information and emotional data, reducing unnecessary purchases and waste, and easing the burden on the environment.

[0350] Example 2

[0351] 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."

[0352] Conventional fashion suggestion systems only considered the user's personal information and preferences, and therefore did not provide flexible suggestions that took into account the user's real-time emotions and circumstances. Furthermore, they only provided fashion suggestions in the form of still images or text, and lacked a way for users to visually confirm how the fashion would look when actually worn. This led to problems such as lower user satisfaction and a decline in purchasing motivation.

[0353] 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 collecting personal information of the user, means for determining the optimal style for the user based on the collected personal information using a machine learning algorithm, means for capturing an image of the user and generating a simulation image of the determined style, means for analyzing the user's facial expression and recognizing emotions, means for adjusting the suggestions based on the recognized emotions, means for acquiring information on products to be suggested from an online store, and means for presenting the suggested product information to the user so that the user can select and purchase. This makes it possible to reflect the user's real-time emotions and provide an image of how the product will actually look when worn, thereby making it possible to make more personalized fashion suggestions and improve user satisfaction and purchasing motivation.

[0354] "User's personal information" refers to basic information about an individual, such as the user's name, age, gender, height, weight, fashion preferences, and usage situation.

[0355] "Machine learning algorithms" are algorithms that analyze optimal fashion styles and colors based on collected data, and primarily use technologies such as TensorFlow and PyTorch.

[0356] A "simulation video" is a moving or still image generated by superimposing a determined fashion style onto a user's video.

[0357] The "means for recognizing emotions" refers to a technology that analyzes the user's facial expression data and identifies the user's current emotional state, such as using Microsoft® Azure®'s Emotion API.

[0358] The "means for adjusting the content of suggestions" is a technology that appropriately changes or adjusts the fashion and product information suggestions based on the recognized user emotions.

[0359] An "online store" is a website that provides product information and sells products via the Internet, and examples include Amazon and Rakuten.

[0360] "Product information" refers to data about a product, such as its name, price, size, color, material, and photo, obtained from an online store.

[0361] MODE FOR CARRYING OUT THE INVENTION

[0362] The system of the present invention not only collects personal information of the user and suggests the most suitable fashion style, but also recognizes the user's emotions and adjusts the suggestions accordingly, and combines an emotion engine to improve the consumer experience. The following describes in detail the embodiments of the present invention.

[0363] System configuration

[0364] This system mainly consists of a user terminal, a server, an emotion engine, and an online store. Users access the system using their own smartphones or computers (user terminals).

[0365] Hardware and software used

[0366] User device: Uses a smartphone or computer. Provides an interface for users to input information and use a camera.

[0367] Server: Receives and stores information from users, processes and analyzes the data using machine learning algorithms and emotion engines.

[0368] Machine learning algorithms: using frameworks such as TensorFlow and PyTorch.

[0369] Emotion engine: Uses services such as Microsoft Azure's Emotion API.

[0370] Online store: Obtain product information from online e-commerce sites (e.g., Amazon, Rakuten).

[0371] Program processing

[0372] 1. Collection of User Information

[0373] The user starts the application and enters personal information (such as name, age, gender, height, weight, fashion preferences, and usage situation). Furthermore, the application performs a bone structure diagnosis and a personal color diagnosis, and answers questions using multiple images. This information is then sent from the user's device to the server.

[0374] 2. Automatic judgment by AI

[0375] The server stores the received user information in a database and uses machine learning algorithms to analyze the optimal style and color. The analysis results are then stored in the database.

[0376] 3. Simulation using the person's own video

[0377] The user captures a video of themselves using a camera, and the device sends the video data to the server. The server then overlays the captured user video with the optimal style information determined by machine learning to generate a simulation video, which is then sent to the user's device. This allows the user to visually check the style that suits them best.

[0378] 4. Use of Emotion Engine

[0379] The user captures their facial expressions using a camera, and the device sends the video to a server. The server then uses an emotion engine to recognize the emotion from the user's facial expressions and adjusts the recommendations based on the recognized emotion data. For example, if the user is feeling stressed, the server will suggest relaxing fashion.

[0380] 5. AI suggests suitable clothing from apparel sites

[0381] The server then searches online stores for matching product information based on the results of the suggestions, retrieves multiple options, and organizes the information before sending it to the user's device.

[0382] 6. Users can purchase original items that suit their tastes

[0383] The user selects from the suggested products and completes the purchase. The user's device displays a form for the purchase and asks them to enter the necessary information. The server then sends this information to the online store to complete the purchase.

[0384] Specific examples

[0385] For example, suppose User B launches the application, enters personal information, and answers questions about bone structure and personal color. This information is sent to the server, where a machine learning algorithm determines the optimal style. Next, User B takes a video of themselves with a camera and checks which style suits them best in the simulated video sent from the server. At the same time, the emotion engine analyzes User B's facial expressions and suggests a casual style if he is relaxed, or a style that gives him a sense of security if he is nervous. These suggestions are based on information obtained from the online store, and User B selects and purchases the most suitable items.

[0386] Prompt Sentence Examples

[0387] Here is an example of a prompt that allows the user to ask the system a specific question:

[0388] "I'm a 34-year-old man, 180cm tall and 75kg. I like casual style and am looking for fashion that I can wear in business casual situations. I took a recent photo of myself. Please suggest the best fashion style based on this photo. I'd also like you to use the emotion engine to suggest a style that takes my current mood into account."

[0389] Based on this prompt, the system collects and analyzes the user's information and suggests the most suitable fashion style and corresponding products.

[0390] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0391] Step 1: User launches application and enters personal information

[0392] Input: Basic information of the user (name, age, gender, height, weight, fashion preferences, usage situation, etc.).

[0393] Operation: The user launches the application on their smartphone or computer and displays the personal information entry screen. The user enters information for each item.

[0394] Data processing and calculation: The user terminal organizes the input information and converts it into an appropriate format.

[0395] Output: The organized personal information is sent to the server.

[0396] Step 2: User's procedure for performing bone structure diagnosis and personal color diagnosis

[0397] Input: User answers (answers to questions about bone structure and personal color).

[0398] Operation: The user terminal displays a number of questions to the user, who then enters answers to the displayed questions.

[0399] Data processing and calculation: The user terminal converts the input answers into a data format and extracts the necessary diagnostic data.

[0400] Output: The converted diagnostic data is sent to the server.

[0401] Step 3: The server analyzes the user information and determines the most suitable style

[0402] Input: Your personal and diagnostic data.

[0403] How it works: The server stores the received personal information and diagnostic data in a database, then inputs the stored information into a machine learning algorithm for analysis.

[0404] Data processing and calculation: Using machine learning algorithms (such as TensorFlow and PyTorch), we analyze the fashion style and color that best suits the user.

[0405] Output: The analysis results are saved in a database.

[0406] Step 4: User instructions for capturing video using the camera

[0407] Input: User's video (video data captured by a camera).

[0408] How it works: The user activates the device's camera and takes a video of themselves.

[0409] Data processing and calculation: The user device converts the captured video data into an appropriate format and adjusts the size and image quality.

[0410] Output: The converted video data is sent to the server.

[0411] Step 5: Procedure for the server to generate the simulation video

[0412] Input: User's video data and analysis results (optimal style information).

[0413] How it works: The server overlays style information determined by machine learning onto the captured user video.

[0414] Data processing and calculation: Using image processing technology, the user's video and style information are combined to generate a simulation video.

[0415] Output: The generated simulation video is sent to the user's device.

[0416] Step 6: User uses camera to capture facial expressions and recognize emotions

[0417] Input: User's facial expression video (video data captured by a camera).

[0418] Action: The user activates the device's camera and captures their facial expressions.

[0419] Data processing and calculation: The device converts the captured facial expression video into an appropriate format and sends it to the server.

[0420] Output: The converted facial expression video data is sent to the server.

[0421] Step 7: The server uses the emotion engine to recognize the user's emotions and adjust the suggestions.

[0422] Input: User's facial expression data.

[0423] How it works: The server inputs the received facial expression data into an emotion engine (such as Microsoft Azure's Emotion API) to recognize emotions.

[0424] Data processing and calculation: Analyzes emotional data to understand the user's current emotional state, and adjusts suggestions based on the analysis results.

[0425] Output: The adjusted proposal is sent to the user's device.

[0426] Step 8: Procedure for the server to obtain product information from the apparel site based on the proposal results

[0427] Input: Adjusted proposal.

[0428] How it works: The server searches online stores for matching products based on the suggested style.

[0429] Data processing and calculation: Utilizing the online store's API, we organize the obtained product information.

[0430] Output: The organized product information is sent to the user's terminal.

[0431] Step 9: User selects and purchases from the suggested products

[0432] Input: Suggested product information.

[0433] How it works: The user selects the product they want from a list of products displayed on the device, and the device displays a checkout form and asks them to enter the necessary information.

[0434] Data processing and calculation: The terminal sends the input information to the server, which then transmits it to the online store.

[0435] Output: A purchase confirmation message is sent to the user's device.

[0436] (Application example 2)

[0437] 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."

[0438] When shopping at traditional online or physical stores, it was difficult for users to fully reflect their personal information or their mood at the time when selecting the perfect fashion item. Furthermore, it often took time and effort for users to try on items, which often led to an unsatisfactory consumer experience. Furthermore, since appropriate suggestions were not made taking emotions into consideration, user satisfaction could decrease.

[0439] 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.

[0440] In this invention, the server includes means for collecting personal information of the user, means for determining the optimal style for the user based on the collected personal information using a machine learning algorithm, means for capturing an image of the user and generating a simulation image of the determined style, means for obtaining suggested product information from an online store, means for presenting the suggested product information to the user so that the user can select and purchase, means for analyzing the user's emotions and adjusting the suggested content based on the analysis results, and means for allowing the user to visually check a simulation of trying on the suggested items in real time. This enables the server to recommend optimal fashion items taking into account the user's personal information and emotions, and to provide an effective try-on experience.

[0441] "Personal information" is a general term for data necessary for fashion suggestions, such as personal information about the user, fashion preferences, body type diagnosis, and personal color diagnosis information.

[0442] "Machine learning algorithm" is an artificial intelligence technology that determines the best fashion style for a user based on collected personal information.

[0443] A "simulation video" is a video of a virtual try-on that is generated by overlaying the determined style onto a video of the user.

[0444] "Emotion analysis" is a technology that recognizes and analyzes a user's emotional state at any given time based on their facial expressions and behavior.

[0445] "Adjusting suggestion content" is the process of appropriately changing the fashion suggestions presented to the user based on the results of sentiment analysis.

[0446] "Real-time try-on simulation" is a technology that simulates the user trying on suggested items instantly, allowing them to visually confirm the experience.

[0447] "Acquisition of product information from online stores" is a data collection process in which suggested product information is acquired from online stores and provided to users.

[0448] "User Selection and Purchasing Instrument" means the interface and support system through which a user can review suggested product information and make a selection or purchase.

[0449] The system of the present invention is designed to suggest the most suitable fashion items to a user while they are shopping in a physical store using smart glasses. The details of the embodiment of the system are described below.

[0450] Program processing

[0451] Collection of User Information

[0452] The user puts on the smart glasses and launches the application. First, the user enters their personal information into the application. This information includes name, age, gender, height, weight, fashion preference, and usage situation (e.g., business, casual). This information is sent via Wi-Fi to the server and stored in a database.

[0453] User sentiment analysis

[0454] The smart glasses use a built-in camera to capture the user's facial expressions. The captured images are sent to a server, where an emotion recognition engine (e.g., IBM Watson®, Microsoft Azure Emotion API) is used to analyze the user's emotional state. The analysis results are applied in real time and reflected in the recommendations.

[0455] Style detection using machine learning algorithms

[0456] The server uses machine learning algorithms (e.g., TensorFlow, PyTorch) to determine the best style for each user based on the collected personal information. The results of this style determination are stored in a database.

[0457] Adjusting the proposal

[0458] The server then adjusts the fashion suggestions it presents to the user based on the results of the emotion analysis. For example, if the user is relaxed, it will suggest a casual style, and if they are nervous, it will suggest a formal style.

[0459] Simulation video generation

[0460] When a user is interested in a particular item in a physical store, they look at the glasses and say, "Tell me more about this shirt." The server processes this request and retrieves the item's details. The server then combines the user's image with the defined style to generate a simulated image, which is then displayed on the smart glasses' display.

[0461] Product Information and Checkout

[0462] The server retrieves the suggested product information from the online store and displays it to the user. The user checks the product list through the smart glasses, selects, and completes the purchase. The result of the purchase is sent to the server, and the purchase is completed at the online store.

[0463] Specific examples

[0464] For example, User A wears smart glasses and uses the application in a physical store. User A finds a shirt he likes in the store and, while looking at the shirt, issues a voice command saying, "Tell me more about this shirt." The camera in the smart glasses captures User A's facial expression, and the server analyzes from the expression that User A is relaxed. Detailed information about the suggested shirt and a try-on simulation are displayed on the smart glasses, allowing User A to check whether the shirt suits him or her. As a result, User A selects the shirt and completes the purchase process through the smart glasses.

[0465] Example prompt sentence:

[0466] You are a user of an emotion-aware fashion advisor application using smart glasses. The app analyzes your emotions and suggests the best fashion items for you. Imagine staring at a particular item in a physical store and speaking to the smart glasses, saying, "Tell me more about this shirt." The smart glasses then display detailed information about the item and a simulated try-on.

[0467] In this way, the user can receive suggestions for the most suitable fashion items that take into consideration personal information and emotions, providing an effective try-on experience.

[0468] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0469] Step 1:

[0470] Entering user information

[0471] The user puts on the smart glasses and launches the application. The user enters personal information such as name, age, gender, height, weight, fashion preferences, and usage situation. This information is sent via Wi-Fi to the server, which stores the received information in a database for later processing.

[0472] Step 2:

[0473] Video capture for emotion analysis

[0474] The camera in the smart glasses captures the user's facial expressions in real time. The captured video is then sent to a server via Wi-Fi. The server then inputs the received video data into an emotion recognition engine (e.g., IBM Watson, Microsoft Azure Emotion API) to analyze the user's emotions. The analysis results are then returned to the server for use in the next step.

[0475] Step 3:

[0476] Style Determination

[0477] Based on the personal information collected in step 1, the server uses machine learning algorithms (e.g., TensorFlow, PyTorch) to determine the style that best suits the user. The results of this determination are stored in a database and used to adjust future recommendations. Specifically, the style is determined by analyzing multiple features using data such as height, weight, bone structure diagnosis, and personal color diagnosis results.

[0478] Step 4:

[0479] Adjusting the proposal

[0480] The server combines the results of the emotion analysis obtained in step 2 with the style information determined in step 3 to adjust the fashion item suggestions presented to the user. For example, if the user is relaxed, it will suggest a casual style, and if the user is nervous, it will suggest a formal style. This suggestion is important for providing the user with the optimal experience.

[0481] Step 5:

[0482] Simulation video generation

[0483] When a user is interested in a particular item through the smart glasses, they issue a voice command such as "Tell me more about this shirt." This request is sent to the server via Wi-Fi. The server processes the request and retrieves detailed information about the item from online stores (e.g., Amazon, Rakuten). Based on the retrieved information, the server combines the user's image and style information to generate a simulation image. This simulation image is then displayed on the smart glasses' display.

[0484] Step 6:

[0485] Product information and purchasing assistance

[0486] The server retrieves product information from the online store and displays it in a list for the user. The user checks the product information through the smart glasses and selects the desired product. The selected information is sent back to the server to assist in the purchase process. The server then sends the purchase information to the online store to complete the purchase process. Once the purchase is complete, a confirmation message is sent to the user.

[0487] In this way, users can receive recommendations for the most suitable fashion items that take into account their personal information and emotions, enabling an effective try-on experience and a smooth purchasing process.

[0488] 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.

[0489] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0490] 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.

[0491] [Second embodiment]

[0492] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0493] 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.

[0494] 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).

[0495] 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.

[0496] 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.

[0497] 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).

[0498] 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.

[0499] 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.

[0500] 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.

[0501] 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.

[0502] 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.

[0503] 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."

[0504] The system of the present invention collects personal information of a user and proposes an optimal fashion style, thereby providing a consumer-friendly and environmentally friendly approach. Hereinafter, an embodiment of the present invention will be described.

[0505] This system mainly consists of a user terminal, a server, and an online store. Users access the system using their own smartphones or computers (user terminals).

[0506] Program processing

[0507] 1. Collection of User Information

[0508] The user launches the application and enters personal information

[0509] The user device displays a screen for entering basic information such as name, age, gender, height, weight, fashion preferences, and usage situation (e.g., business, casual).

[0510] The user performs a bone structure diagnosis and a personal color diagnosis.

[0511] The user terminal presents the user with a question using a plurality of images and prompts the user to input an answer.

[0512] The server stores the collected data in a database and analyzes it.

[0513] 2. Automatic judgment by AI

[0514] The server proposes the best style based on the information collected

[0515] The server inputs the stored user information into a machine learning model to automatically determine the style and color that best suits the user.

[0516] The server stores the results of the assessment in a database and generates recommended styles tailored to each user.

[0517] 3. Simulation using the person's own video

[0518] The user uses the camera in the application to capture their own video.

[0519] The user device uses its camera function to capture images of the user's current posture and face.

[0520] The server runs the simulation

[0521] The user terminal transmits the captured video to the server.

[0522] The server combines the captured video with a pre-determined style to generate a simulation video in which the costume is superimposed on the user's image.

[0523] The server transmits the generated simulation video to the user terminal.

[0524] 4. AI recommends suitable clothing from apparel sites

[0525] The server acquires product information from the apparel site based on the proposal results.

[0526] The server searches the online store for products that match the proposed style and retrieves multiple options.

[0527] The server organizes the acquired product information and generates a list to suggest to the user.

[0528] Present the proposed results to the user

[0529] The user terminal displays a list of the proposal results received from the server, allowing the user to make a selection.

[0530] 5. Users can purchase original items that suit their tastes

[0531] The user selects and purchases from the suggested products

[0532] The user terminal provides an interface for the user to select items they wish to purchase from the suggested merchandise.

[0533] The server handles the purchase process

[0534] The user terminal transmits the selected product information and data required for the purchase procedure to the server.

[0535] The server sends the necessary information to the online store to proceed with the purchase, allowing the user to complete the purchase.

[0536] The server notifies the user terminal that the purchase has been completed and asks the user to confirm.

[0537] Specific examples

[0538] For example, suppose User A starts an application, enters personal information such as name, age, and height, and answers questions about bone structure and personal color diagnosis. The collected information is sent to the server, where a machine learning algorithm determines the optimal style. User A then takes a video of themselves with a camera and checks which style suits them best in the simulation video sent from the server. The server then retrieves product information from the online store that matches the suggested style and suggests it to User A. User A then selects and purchases the items they like from the presented list. Through this process, User A can select the optimal products based on their personal information and avoid unnecessary purchases.

[0539] This will enable consumers to enjoy a more satisfying purchasing experience and reduce the burden on the environment.

[0540] The processing flow will be explained below.

[0541] Step 1:

[0542] The user launches the application and enters personal information

[0543] Users enter basic information such as their name, age, gender, height, weight, fashion preferences, and usage situation (e.g., business, casual) on their device.

[0544] Step 2:

[0545] The user performs a bone structure diagnosis and a personal color diagnosis.

[0546] The user device shows the user multiple images for skeletal diagnosis and asks them to choose the one that most closely resembles their own.

[0547] Similarly, personal color diagnosis questions are presented and the user answers them.

[0548] The terminal transmits the input information to the server.

[0549] Step 3:

[0550] The server analyzes the user information

[0551] The server stores the received user information in a database.

[0552] The server then feeds the stored information into a machine learning algorithm to analyze the style and color that best suits the user.

[0553] The analysis results are saved in a database.

[0554] Step 4:

[0555] The user captures the video using the camera

[0556] The user activates the camera function of the user device to take a video of themselves.

[0557] The terminal transmits the captured video data to the server.

[0558] Step 5:

[0559] The server generates the simulation video

[0560] The server generates a simulation video by overlaying the captured user video with the optimal style information determined by machine learning.

[0561] The simulation video is sent to the user's device so that the user can view it.

[0562] Step 6:

[0563] The server will suggest suitable clothing items

[0564] Based on the generated style information, the server retrieves product information from the online store via API.

[0565] The server analyzes the acquired product information and selects clothing candidates that are best suited to the user.

[0566] A list of suggested product information is sent to the user's device.

[0567] Step 7:

[0568] The user selects and purchases the suggested product

[0569] The user selects the desired product from the product list displayed on the user terminal.

[0570] The terminal presents the user with a form to complete the purchase process and prompts them to enter the necessary information (e.g., payment information, etc.).

[0571] The terminal transmits the input information to the server.

[0572] Step 8:

[0573] The server handles the purchase process

[0574] The server sends the user's selected product information and payment information to the online store to complete the purchase.

[0575] The server sends a purchase confirmation message to the user's terminal, allowing the user to confirm the purchase.

[0576] The process at each step utilizes machine learning and simulation technology to provide optimal products tailored to user needs, preventing unnecessary purchases and reducing environmental impact.

[0577] Example 1

[0578] 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."

[0579] In modern society, consumers spend a lot of time and effort selecting the fashion style that best suits them. Furthermore, the increased purchase of inappropriate fashion items can have a negative impact on the environment. Furthermore, even with online shopping, consumers often feel dissatisfied after purchasing because they cannot actually try on the products. To solve these problems, a system is needed that can suggest optimal fashion styles tailored to individual consumers and perform a try-on simulation.

[0580] 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.

[0581] In this invention, the server includes means for collecting personal information of a user, means for determining the optimal style for the user based on the collected personal information using a machine learning algorithm, means for capturing an image of the user and generating a simulation image of the determined style, means for acquiring suggested product information from an online store, means for presenting the suggested product information to the user so that the user can select and purchase, means for saving the user's personal information and diagnostic information in a database and analyzing that information, means for capturing an image of the user's current posture and face when generating the simulation image, means for organizing the acquired product information and generating a list to suggest to the user, and means for supporting the purchase procedure based on the user's selection. This allows the user to efficiently select appropriate fashion items based on their personal information and enjoy a satisfying purchasing experience through a try-on simulation.

[0582] "User's personal information" refers to basic information such as the user's name, age, gender, height, weight, fashion preferences, and usage situation.

[0583] "Machine learning algorithm" refers to an algorithm that learns patterns from collected data and uses the results to suggest the best styles and colors for users.

[0584] "User's Images" refers to image and video data of the user's appearance, voice, and face captured by the user's camera using the application.

[0585] "Simulation video" refers to video data that provides a visual like trying on clothes, with the determined style superimposed on the user's video.

[0586] "Online store" refers to a store that sells products via the Internet.

[0587] A "database" refers to a system for organizing and storing data so that it can be searched and analyzed later.

[0588] A "web scraping tool" refers to software for automatically extracting specific data from web pages on the Internet.

[0589] "User terminal" refers to a device such as a smartphone or computer operated by a user.

[0590] "Checkout" refers to the series of steps (e.g., selection, payment, delivery arrangements) required by a User to purchase an item from an online store.

[0591] "Image processing technology" refers to the technology of processing and analyzing image data using a computer, and is used to generate simulation images.

[0592] "Judgment results" refer to the optimal fashion style and color combinations suggested to users based on analysis by machine learning algorithms.

[0593] "Product Information" refers to detailed product information (price, size, color, material, etc.) obtained from the online store.

[0594] MODE FOR CARRYING OUT THE INVENTION

[0595] The present invention is a system that collects personal information of a user and suggests an optimal fashion style. This system is mainly composed of a user terminal, a server, and an online store. Specific embodiments for carrying out the present invention will be described below.

[0596] Hardware and software used

[0597] User devices: Smartphones, computers, etc. These devices provide an interface for users to input information.

[0598] Server: Runs database software (e.g., MySQL) and machine learning models (e.g., TensorFlow).

[0599] Image processing software: such as OpenCV. Used to generate simulation images.

[0600] Web scraping tools, such as BeautifulSoup, are used to retrieve product information from online stores.

[0601] Program processing

[0602] Users access the system using a smartphone or computer and follow the process below.

[0603] 1. Collection of User Information

[0604] The user starts the application and enters basic information such as name, age, gender, height, weight, fashion preferences, and usage situation. The user's device sends this data to the server. The user also performs a bone structure diagnosis and personal color diagnosis, and sends the data to the server.

[0605] 2. Automatic judgment by AI

[0606] The server stores the collected personal information and diagnostic data in a database and uses machine learning algorithms to determine the best style and color for each user. The results are then stored in the database.

[0607] 3. Simulation using the person's own video

[0608] The user captures video of their posture and face through the application. The user device sends this video data to the server. The server combines the captured video with the determined style to generate a simulation video and sends it to the user device.

[0609] 4. AI recommends suitable clothing from apparel sites

[0610] The server searches the online store for products that match the proposed style, organizes the obtained product information, and generates a list to suggest to the user. This list is sent to the user's terminal and presented to the user.

[0611] 5. Users can purchase original items that suit their tastes

[0612] The user selects the item they wish to purchase from the list of suggested products and clicks the purchase button. The user's device sends the selected product information and data required for the purchase process to the server. The server then sends the information required to proceed with the purchase to the online store and notifies the user's device that the purchase is complete.

[0613] Specific examples

[0614] For example, User A starts the application, enters personal information such as name, age, and height, and answers questions about bone structure and personal color diagnosis. This information is sent to the server, and a machine learning algorithm determines the optimal style. User A then takes a video of themselves with a camera and checks which style suits them best in the simulation video sent from the server. The server then retrieves product information from the online store that matches the suggested style and suggests it to User A. User A then selects their preferred item from the list provided and purchases it.

[0615] This allows User A to select the most suitable product based on their personal information and avoid unnecessary purchases. Through this process, consumers can enjoy a more satisfying shopping experience and reduce their environmental impact.

[0616] Prompt Sentence Examples

[0617] Below are some example prompts to input to machine learning algorithms:

[0618] "User A is 25 years old, 160cm tall, weighs 50kg, and wants fashion suitable for business situations. His bone structure diagnosis is ectomorph, and his personal color is spring."

[0619] This allows the server to determine and suggest the best style and color for user A.

[0620] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0621] Program processing flow

[0622] Step 1: Collect user information

[0623] Input: User's personal information (name, age, gender, height, weight, fashion preferences, usage situation) and answers to the bone structure diagnosis and personal color diagnosis.

[0624] process:

[0625] The user launches the application and enters their basic information into the form that appears.

[0626] The user answers diagnostic questions.

[0627] The user terminal collects this information and sends it to the server.

[0628] Output: User personal and diagnostic information sent to the server.

[0629] Step 2: Data storage and analysis

[0630] Input: The user's personal and diagnostic information.

[0631] process:

[0632] The server stores the received data in a database.

[0633] The server inputs the data into the machine learning model and performs the analysis.

[0634] Machine learning algorithms use the collected data to determine the best fashion style and color.

[0635] Output: The result of the judgement (the best style and color combination for the user).

[0636] Step 3: Import your own video

[0637] Input: Video of the user's current pose and face.

[0638] process:

[0639] Users use the application to activate the camera and capture footage of themselves.

[0640] The user device sends the captured video to the server.

[0641] Output: User video data sent to the server.

[0642] Step 4: Generate simulation footage

[0643] Input: User video data and determined style information.

[0644] process:

[0645] The server generates a simulation video using the received video data and the determined style information.

[0646] The server uses image processing techniques (e.g. OpenCV) to overlay a style onto the user's video.

[0647] Output: Simulation video.

[0648] Step 5: Obtaining proposed product information

[0649] Input: Determined style information.

[0650] process:

[0651] The server searches the online store for product information that matches the suggested style.

[0652] The server uses a web scraping tool (e.g. BeautifulSoup) to retrieve and organize product information.

[0653] Output: A list of suggested product information.

[0654] Step 6: Presenting the proposed results

[0655] Input: Proposed product information.

[0656] process:

[0657] The server transmits the proposal results to the user terminal.

[0658] The user terminal displays a list of suggested product information to the user.

[0659] Output: A list of suggestion results shown to the user.

[0660] Step 7: Select and purchase products

[0661] Input: List of proposed product information.

[0662] process:

[0663] The user selects the items to purchase from the suggested products.

[0664] The user terminal transmits the selected product information and necessary purchase data to the server.

[0665] Output: Purchase data sent to the server.

[0666] Step 8: Support with checkout

[0667] Input: User-selected product information and purchase data.

[0668] process:

[0669] The server passes the purchase procedure to the online store's system.

[0670] The server sends a purchase completion notification to the user terminal, and the user confirms it.

[0671] Output: Notification and confirmation that the purchase has been completed.

[0672] (Application example 1)

[0673] 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."

[0674] Conventional fashion suggestion systems are limited to suggesting optimal styles based on a user's personal information, which is insufficient for improving the shopping experience in physical stores. Furthermore, most virtual try-on systems are limited to online stores, making it difficult to use in stores in real time. The present invention aims to solve these problems and make shopping in physical stores more intuitive and satisfying for users.

[0675] 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.

[0676] In this invention, the server includes means for collecting personal information of the user, means for determining the optimal style for the user based on the collected personal information using a machine learning algorithm, means for capturing an image of the user and generating a simulation image of the determined style, means for acquiring suggested product information from an online store, means for presenting the suggested product information to the user so that the user can select and purchase, means for capturing an image of the user in real time using a camera function of the smart glasses, and means for acquiring in-store inventory information and generating a product list to be suggested to the user. This allows the user to check the fashion items that are optimal for them in real time, improving the shopping experience in physical stores.

[0677] "User's personal information" refers to individual information about the user, such as the user's name, age, gender, height, weight, fashion preferences, and usage situation.

[0678] A "machine learning algorithm" is an artificial intelligence technique that uses data to train models to identify patterns and relationships and make predictions.

[0679] "Simulation video" is a video in which the judged style and outfit are superimposed on the user's video, giving the impression of virtually trying on the outfits.

[0680] An "online store" is a website or platform that sells products over the Internet.

[0681] "Smart glasses" are glasses-type wearable devices that have the function of displaying information in the user's field of vision.

[0682] "Camera function" refers to hardware and software that has the function of taking images and videos.

[0683] "Stock information" is information about the quantity and types of products available in the store.

[0684] A "product list" is a list of suggested products that is presented in a format that allows the user to select from them.

[0685] The system embodying this invention mainly collects personal information of users and suggests optimal fashion styles based on that information. Furthermore, this system is designed to enhance users' shopping experience in physical stores, and uses smart glasses to suggest optimal styles in real time.

[0686] Configuration and Operation Procedures

[0687] 1. Collection of User Information

[0688] Users input their personal information (such as name, age, gender, height, weight, preferred style, and usage situation) through smart glasses or other devices. This operation is carried out through a dedicated application.

[0689] 2. Body type diagnosis and personal color diagnosis

[0690] Users upload their own images and the system asks them to answer a number of questions to diagnose their body type and personal color. This information is also sent to the server and stored in a database.

[0691] 3. Determining the best style

[0692] The server uses machine learning algorithms based on the collected personal information to determine the best style for the user, using a generative AI model for this process.

[0693] 4. Real-time video capture and simulation

[0694] The camera function of the smart glasses is used to capture real-time footage of the user, and a simulated video is generated with the determined style overlaid on it, which the user can view through the smart glasses.

[0695] 5. Obtaining in-store inventory information

[0696] The server retrieves inventory information from physical stores and generates a list of products to suggest to users, allowing them to check the items available in the store in real time.

[0697] 6. Recommended styles and product suggestions

[0698] The server retrieves the best product information from online and physical stores and suggests it to the user, who can then review the suggestions through the smart glasses and make a purchase decision.

[0699] Specific examples

[0700] For example, when User A enters a physical store, the smart glasses capture User A's image in real time and suggest the best style based on the personal information input in advance. The server uses the results of User A's bone structure and personal color diagnosis to display a simulation image of an outfit that would suit User A.

[0701] The server then retrieves in-store inventory information and generates a list of products that are optimal for User A. User A can then view, select, and purchase items through the smart glasses.

[0702] Hardware and software used

[0703] Hardware: Smart glasses (with camera function), user devices (smartphones, tablets, PCs)

[0704] Software: Machine learning algorithms (generative AI models), image processing technology, online store API, store inventory management system

[0705] Prompt Sentence Examples

[0706] "Please suggest the best fashion style for user A based on their age, gender, build, and preferences. Also, please generate a virtual try-on image and display it in real time. User camera: user_image.jpg"

[0707] By using this prompt, the generative AI model can provide optimal fashion suggestions to users.

[0708] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0709] Step 1:

[0710] The user enters personal information using smart glasses or other devices. The user information input form includes name, age, gender, height, weight, fashion preferences, and usage situation. After input, this information is sent to the server. The entered data is stored in the server's database and used for further processing.

[0711] Step 2:

[0712] The user performs a bone structure diagnosis and a personal color diagnosis. The user uploads an image, and the system asks the user several questions along with the image, prompting the user to answer. This diagnostic information is also sent to the server and stored in a database. The server uses this data to analyze the user's body shape and skin color.

[0713] Step 3:

[0714] The server uses a machine learning algorithm to determine the best style for the user based on the collected personal information and diagnostic results. This data is input into a generative AI model, which then suggests the best style and color. The server then stores the generated style data in a database.

[0715] Step 4:

[0716] The user captures a real-time video of themselves using the camera function of their smart glasses. The device then sends the image captured by the camera to the server. The server then overlays the received image with a pre-determined style to generate a simulated video. The generated simulated video is then sent from the server to the user's smart glasses.

[0717] Step 5:

[0718] The server retrieves product information to be suggested from both online and physical stores. It searches for products that match the style suggested by the AI ​​through the online store's API and the physical store's inventory management system. The server organizes the retrieved product information and generates a list to suggest to the user. The list is then sent from the server to the user's smart glasses.

[0719] Step 6:

[0720] The user checks the suggested product information and selects it using the smart glasses. The user then selects the item they want from the list and proceeds with the purchase using the smart glasses. The device then sends the selected product information and the data required for the purchase to the server, which then forwards it to the online store to complete the purchase. The user can receive a confirmation message through the smart glasses.

[0721] Step 7:

[0722] The server stores the completed purchase information in a database and manages it as the user's purchase history. The user can use this history as reference for their next purchase. The server can also use this data to learn how to make more advanced personalized fashion suggestions.

[0723] 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.

[0724] The system of the present invention not only collects personal information of a user and suggests the most suitable fashion style, but also recognizes the user's emotions and adjusts the information and suggestions provided, and combines an emotion engine to improve the consumer experience. Hereinafter, embodiments for carrying out the present invention will be described in detail.

[0725] This system mainly consists of a user terminal, a server, an emotion engine, and an online store. Users access the system using their own smartphones or computers (user terminals).

[0726] Program processing

[0727] 1. Collection of User Information

[0728] The user launches the application and enters personal information

[0729] The user device displays a screen for entering basic information such as name, age, gender, height, weight, fashion preferences, and usage situation (e.g., business, casual).

[0730] The user performs a bone structure diagnosis and a personal color diagnosis.

[0731] The user terminal presents the user with a question using a plurality of images and prompts the user to input an answer.

[0732] The terminal transmits the input information to the server.

[0733] 2. Automatic judgment by AI

[0734] The server analyzes the user information

[0735] The server stores the received user information in a database.

[0736] The server then feeds the stored information into a machine learning algorithm to analyze the style and color that best suits the user.

[0737] The analysis results are saved in a database.

[0738] 3. Simulation using the person's own video

[0739] The user captures the video using the camera

[0740] The user activates the camera function of the user device to take a video of themselves.

[0741] The terminal transmits the captured video data to the server.

[0742] The server generates the simulation video

[0743] The server generates a simulation video by overlaying the captured user video with the optimal style information determined by machine learning.

[0744] The simulation video is sent to the user's device so that the user can view it.

[0745] 4. Use of Emotion Engine

[0746] User uses camera to recognize emotions

[0747] The user device uses a camera function to capture the user's facial expression and transmits the image to the server.

[0748] The server uses an emotion engine to recognize emotions from the user's facial expressions.

[0749] Emotion engine adjusts suggestions

[0750] Based on the recognized emotion data, the server adjusts the product information and simulation images it proposes to make suggestions that are appropriate for the user.

[0751] For example, if a user is feeling stressed, it will suggest fashion that will help them relax.

[0752] 5. AI suggests suitable clothing from apparel sites

[0753] The server acquires product information from the apparel site based on the proposal results.

[0754] The server searches the online store for products that match the proposed style and retrieves multiple options.

[0755] The server organizes the acquired product information and generates a list to suggest to the user.

[0756] A list of suggested product information is sent to the user's device.

[0757] 6. Users can purchase original items that suit their tastes

[0758] The user selects and purchases from the suggested products

[0759] The user selects the desired product from the product list displayed on the user terminal.

[0760] The terminal presents the user with a form for completing the purchase procedure and prompts the user to enter the necessary information.

[0761] The terminal transmits the input information to the server.

[0762] The server handles the purchase process

[0763] The server sends the user's selected product information and payment information to the online store to complete the purchase.

[0764] The server sends a purchase confirmation message to the user's terminal, allowing the user to confirm the purchase.

[0765] Specific examples

[0766] For example, suppose User B launches the application, enters personal information, and answers questions about bone structure and personal color. This information is sent to the server, where a machine learning algorithm determines the optimal style. Next, User B takes a video of themselves with a camera and checks which style suits them best in the simulation video sent from the server. At the same time, the emotion engine analyzes User B's facial expressions and suggests a casual style if they are relaxed, or a style that gives them a sense of security if they are nervous. This suggestion is based on information obtained from the online store, and User B selects and purchases the most suitable items. This process allows User B to achieve high satisfaction while reducing their environmental impact through purchases.

[0767] The processing flow will be explained below.

[0768] Step 1:

[0769] The user launches the application and enters personal information

[0770] The user launches the application on their device and operates a screen to enter basic information such as name, age, gender, height, weight, fashion preferences, and usage situation (e.g., business, casual).

[0771] The terminal stores the information entered by the user and transmits it to the server.

[0772] Step 2:

[0773] The user performs a bone structure diagnosis and a personal color diagnosis.

[0774] The user device displays multiple images and options for skeletal diagnosis and prompts the user to choose the one that best suits them.

[0775] Similarly, a number of questions and images are presented for personal color diagnosis, and the user answers them.

[0776] The terminal obtains the user's answer and sends it to the server.

[0777] Step 3:

[0778] The server analyzes the user information

[0779] The server stores the received personal information and diagnostic results in a database.

[0780] The server runs machine learning algorithms based on the stored information to analyze the style and color that best suits the user.

[0781] The analysis results are stored in a database for further processing.

[0782] Step 4:

[0783] The user captures the video using the camera

[0784] The user activates the camera function of the user device and takes an image of their current posture and face.

[0785] The terminal transmits the captured video data to the server.

[0786] Step 5:

[0787] The server generates the simulation video

[0788] The server generates a simulation video using the captured user video and optimal style information determined by machine learning.

[0789] The server transmits the generated simulation video to the user terminal so that the user can visually check it.

[0790] Step 6:

[0791] User uses camera to recognize emotions

[0792] The user captures their facial expression using the camera function of their device.

[0793] The terminal transmits the acquired video data to the server.

[0794] Step 7:

[0795] The server recognizes emotions using an emotion engine

[0796] The server analyzes the transmitted video data and uses an emotion engine to recognize emotions from the user's facial expressions.

[0797] The user's psychological state is determined based on the recognized emotional data.

[0798] Step 8:

[0799] Emotion engine adjusts suggestions

[0800] The server then adjusts the product information and simulation images it recommends based on the user's emotional data. For example, if it determines that the user is relaxed, it will suggest a casual, relaxed style.

[0801] The adjusted proposal content is sent to the user device.

[0802] Step 9:

[0803] The server acquires product information from the apparel site based on the proposal results.

[0804] The server retrieves multiple options from the online store via API, searching for products that match the user's best style.

[0805] The server analyzes the acquired product information and selects clothing candidates that are best suited to the user.

[0806] A list of suggested product information is sent to the user's device.

[0807] Step 10:

[0808] The user selects and purchases the suggested product

[0809] The user selects the desired product from the product list displayed on the user terminal.

[0810] The terminal displays a form for the user to complete the purchase procedure and prompts the user to enter the necessary information.

[0811] The terminal transmits the input information to the server.

[0812] Step 11:

[0813] The server handles the purchase process

[0814] The server sends the user's selected product information and payment information to the online store to complete the purchase.

[0815] The server sends a purchase confirmation message to the user's terminal, allowing the user to confirm the purchase.

[0816] This system allows users to receive suggestions for optimal fashion styles based on their personal information and emotional data, reducing unnecessary purchases and waste, and easing the burden on the environment.

[0817] Example 2

[0818] 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."

[0819] Conventional fashion suggestion systems only considered the user's personal information and preferences, and therefore did not provide flexible suggestions that took into account the user's real-time emotions and circumstances. Furthermore, they only provided fashion suggestions in the form of still images or text, and lacked a way for users to visually confirm how the fashion would look when actually worn. This led to problems such as lower user satisfaction and a decline in purchasing motivation.

[0820] 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 collecting personal information of the user, means for determining the optimal style for the user based on the collected personal information using a machine learning algorithm, means for capturing an image of the user and generating a simulation image of the determined style, means for analyzing the user's facial expression and recognizing emotions, means for adjusting the suggestions based on the recognized emotions, means for acquiring information on products to be suggested from an online store, and means for presenting the suggested product information to the user so that the user can select and purchase. This makes it possible to reflect the user's real-time emotions and provide an image of how the product will actually look when worn, thereby making it possible to make more personalized fashion suggestions and improve user satisfaction and purchasing motivation.

[0821] "User's personal information" refers to basic information about an individual, such as the user's name, age, gender, height, weight, fashion preferences, and usage situation.

[0822] "Machine learning algorithms" are algorithms that analyze optimal fashion styles and colors based on collected data, and primarily use technologies such as TensorFlow and PyTorch.

[0823] A "simulation video" is a moving or still image generated by superimposing a determined fashion style onto a user's video.

[0824] "Means for recognizing emotions" refers to technology that analyzes a user's facial expression data and identifies the user's current emotional state, such as using Microsoft Azure's Emotion API.

[0825] The "means for adjusting the content of suggestions" is a technology that appropriately changes or adjusts the fashion and product information suggestions based on the recognized user emotions.

[0826] An "online store" is a website that provides product information and sells products via the Internet, and examples include Amazon and Rakuten.

[0827] "Product information" refers to data about a product, such as its name, price, size, color, material, and photo, obtained from an online store.

[0828] MODE FOR CARRYING OUT THE INVENTION

[0829] The system of the present invention not only collects personal information of the user and suggests the most suitable fashion style, but also recognizes the user's emotions and adjusts the suggestions accordingly, and combines an emotion engine to improve the consumer experience. The following describes in detail the embodiments of the present invention.

[0830] System configuration

[0831] This system mainly consists of a user terminal, a server, an emotion engine, and an online store. Users access the system using their own smartphones or computers (user terminals).

[0832] Hardware and software used

[0833] User device: Uses a smartphone or computer. Provides an interface for users to input information and use a camera.

[0834] Server: Receives and stores information from users, processes and analyzes the data using machine learning algorithms and emotion engines.

[0835] Machine learning algorithms: using frameworks such as TensorFlow and PyTorch.

[0836] Emotion engine: Uses services such as Microsoft Azure's Emotion API.

[0837] Online store: Obtain product information from online e-commerce sites (e.g., Amazon, Rakuten).

[0838] Program processing

[0839] 1. Collection of User Information

[0840] The user starts the application and enters personal information (such as name, age, gender, height, weight, fashion preferences, and usage situation). Furthermore, the application performs a bone structure diagnosis and a personal color diagnosis, and answers questions using multiple images. This information is then sent from the user's device to the server.

[0841] 2. Automatic judgment by AI

[0842] The server stores the received user information in a database and uses machine learning algorithms to analyze the optimal style and color. The analysis results are then stored in the database.

[0843] 3. Simulation using the person's own video

[0844] The user captures a video of themselves using a camera, and the device sends the video data to the server. The server then overlays the captured user video with the optimal style information determined by machine learning to generate a simulation video, which is then sent to the user's device. This allows the user to visually check the style that suits them best.

[0845] 4. Use of Emotion Engine

[0846] The user captures their facial expressions using a camera, and the device sends the video to a server. The server then uses an emotion engine to recognize the emotion from the user's facial expressions and adjusts the recommendations based on the recognized emotion data. For example, if the user is feeling stressed, the server will suggest relaxing fashion.

[0847] 5. AI suggests suitable clothing from apparel sites

[0848] The server then searches online stores for matching product information based on the results of the suggestions, retrieves multiple options, and organizes the information before sending it to the user's device.

[0849] 6. Users can purchase original items that suit their tastes

[0850] The user selects from the suggested products and completes the purchase. The user's device displays a form for the purchase and asks them to enter the necessary information. The server then sends this information to the online store to complete the purchase.

[0851] Specific examples

[0852] For example, suppose User B launches the application, enters personal information, and answers questions about bone structure and personal color. This information is sent to the server, where a machine learning algorithm determines the optimal style. Next, User B takes a video of themselves with a camera and checks which style suits them best in the simulated video sent from the server. At the same time, the emotion engine analyzes User B's facial expressions and suggests a casual style if he is relaxed, or a style that gives him a sense of security if he is nervous. These suggestions are based on information obtained from the online store, and User B selects and purchases the most suitable items.

[0853] Prompt Sentence Examples

[0854] Here is an example of a prompt that allows the user to ask the system a specific question:

[0855] "I'm a 34-year-old man, 180cm tall and 75kg. I like casual style and am looking for fashion that I can wear in business casual situations. I took a recent photo of myself. Please suggest the best fashion style based on this photo. I'd also like you to use the emotion engine to suggest a style that takes my current mood into account."

[0856] Based on this prompt, the system collects and analyzes the user's information and suggests the most suitable fashion style and corresponding products.

[0857] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0858] Step 1: User launches application and enters personal information

[0859] Input: Basic information of the user (name, age, gender, height, weight, fashion preferences, usage situation, etc.).

[0860] Operation: The user launches the application on their smartphone or computer and displays the personal information entry screen. The user enters information for each item.

[0861] Data processing and calculation: The user terminal organizes the input information and converts it into an appropriate format.

[0862] Output: The organized personal information is sent to the server.

[0863] Step 2: User's procedure for performing bone structure diagnosis and personal color diagnosis

[0864] Input: User answers (answers to questions about bone structure and personal color).

[0865] Operation: The user terminal displays a number of questions to the user, who then enters answers to the displayed questions.

[0866] Data processing and calculation: The user terminal converts the input answers into a data format and extracts the necessary diagnostic data.

[0867] Output: The converted diagnostic data is sent to the server.

[0868] Step 3: The server analyzes the user information and determines the most suitable style

[0869] Input: Your personal and diagnostic data.

[0870] How it works: The server stores the received personal information and diagnostic data in a database, then inputs the stored information into a machine learning algorithm for analysis.

[0871] Data processing and calculation: Using machine learning algorithms (such as TensorFlow and PyTorch), we analyze the fashion style and color that best suits the user.

[0872] Output: The analysis results are saved in a database.

[0873] Step 4: User instructions for capturing video using the camera

[0874] Input: User's video (video data captured by a camera).

[0875] How it works: The user activates the device's camera and takes a video of themselves.

[0876] Data processing and calculation: The user device converts the captured video data into an appropriate format and adjusts the size and image quality.

[0877] Output: The converted video data is sent to the server.

[0878] Step 5: Procedure for the server to generate the simulation video

[0879] Input: User's video data and analysis results (optimal style information).

[0880] How it works: The server overlays style information determined by machine learning onto the captured user video.

[0881] Data processing and calculation: Using image processing technology, the user's video and style information are combined to generate a simulation video.

[0882] Output: The generated simulation video is sent to the user's device.

[0883] Step 6: User uses camera to capture facial expressions and recognize emotions

[0884] Input: User's facial expression video (video data captured by a camera).

[0885] Action: The user activates the device's camera and captures their facial expressions.

[0886] Data processing and calculation: The device converts the captured facial expression video into an appropriate format and sends it to the server.

[0887] Output: The converted facial expression video data is sent to the server.

[0888] Step 7: The server uses the emotion engine to recognize the user's emotions and adjust the suggestions.

[0889] Input: User's facial expression data.

[0890] How it works: The server inputs the received facial expression data into an emotion engine (such as Microsoft Azure's Emotion API) to recognize emotions.

[0891] Data processing and calculation: Analyzes emotional data to understand the user's current emotional state, and adjusts suggestions based on the analysis results.

[0892] Output: The adjusted proposal is sent to the user's device.

[0893] Step 8: Procedure for the server to obtain product information from the apparel site based on the proposal results

[0894] Input: Adjusted proposal.

[0895] How it works: The server searches online stores for matching products based on the suggested style.

[0896] Data processing and calculation: Utilizing the online store's API, we organize the obtained product information.

[0897] Output: The organized product information is sent to the user's terminal.

[0898] Step 9: User selects and purchases from the suggested products

[0899] Input: Suggested product information.

[0900] How it works: The user selects the product they want from a list of products displayed on the device, and the device displays a checkout form and asks them to enter the necessary information.

[0901] Data processing and calculation: The terminal sends the input information to the server, which then transmits it to the online store.

[0902] Output: A purchase confirmation message is sent to the user's device.

[0903] (Application example 2)

[0904] 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."

[0905] When shopping at traditional online or physical stores, it was difficult for users to fully reflect their personal information or their mood at the time when selecting the perfect fashion item. Furthermore, it often took time and effort for users to try on items, which often led to an unsatisfactory consumer experience. Furthermore, since appropriate suggestions were not made taking emotions into consideration, user satisfaction could decrease.

[0906] 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.

[0907] In this invention, the server includes means for collecting personal information of the user, means for determining the optimal style for the user based on the collected personal information using a machine learning algorithm, means for capturing an image of the user and generating a simulation image of the determined style, means for obtaining suggested product information from an online store, means for presenting the suggested product information to the user so that the user can select and purchase, means for analyzing the user's emotions and adjusting the suggested content based on the analysis results, and means for allowing the user to visually check a simulation of trying on the suggested items in real time. This enables the server to recommend optimal fashion items taking into account the user's personal information and emotions, and to provide an effective try-on experience.

[0908] "Personal information" is a general term for data necessary for fashion suggestions, such as personal information about the user, fashion preferences, body type diagnosis, and personal color diagnosis information.

[0909] "Machine learning algorithm" is an artificial intelligence technology that determines the best fashion style for a user based on collected personal information.

[0910] A "simulation video" is a video of a virtual try-on that is generated by overlaying the determined style onto a video of the user.

[0911] "Emotion analysis" is a technology that recognizes and analyzes a user's emotional state at any given time based on their facial expressions and behavior.

[0912] "Adjusting suggestion content" is the process of appropriately changing the fashion suggestions presented to the user based on the results of sentiment analysis.

[0913] "Real-time try-on simulation" is a technology that simulates the user trying on suggested items instantly, allowing them to visually confirm the experience.

[0914] "Acquisition of product information from online stores" is a data collection process in which suggested product information is acquired from online stores and provided to users.

[0915] "User Selection and Purchasing Instrument" means the interface and support system through which a user can review suggested product information and make a selection or purchase.

[0916] The system of the present invention is designed to suggest the most suitable fashion items to a user while they are shopping in a physical store using smart glasses. The details of the embodiment of the system are described below.

[0917] Program processing

[0918] Collection of User Information

[0919] The user puts on the smart glasses and launches the application. First, the user enters their personal information into the application. This information includes name, age, gender, height, weight, fashion preference, and usage situation (e.g., business, casual). This information is sent via Wi-Fi to the server and stored in a database.

[0920] User sentiment analysis

[0921] The smart glasses use a built-in camera to capture the user's facial expressions. The captured images are sent to a server, where an emotion recognition engine (e.g., IBM Watson or Microsoft Azure Emotion API) is used to analyze the user's emotional state. The analysis results are applied in real time and reflected in the recommendations.

[0922] Style detection using machine learning algorithms

[0923] The server uses machine learning algorithms (e.g., TensorFlow, PyTorch) to determine the best style for each user based on the collected personal information. The results of this style determination are stored in a database.

[0924] Adjusting the proposal

[0925] The server then adjusts the fashion suggestions it presents to the user based on the results of the emotion analysis. For example, if the user is relaxed, it will suggest a casual style, and if they are nervous, it will suggest a formal style.

[0926] Simulation video generation

[0927] When a user is interested in a particular item in a physical store, they look at the glasses and say, "Tell me more about this shirt." The server processes this request and retrieves the item's details. The server then combines the user's image with the defined style to generate a simulated image, which is then displayed on the smart glasses' display.

[0928] Product Information and Checkout

[0929] The server retrieves the suggested product information from the online store and displays it to the user. The user checks the product list through the smart glasses, selects, and completes the purchase. The result of the purchase is sent to the server, and the purchase is completed at the online store.

[0930] Specific examples

[0931] For example, User A wears smart glasses and uses the application in a physical store. User A finds a shirt he likes in the store and, while looking at the shirt, issues a voice command saying, "Tell me more about this shirt." The camera in the smart glasses captures User A's facial expression, and the server analyzes from the expression that User A is relaxed. Detailed information about the suggested shirt and a try-on simulation are displayed on the smart glasses, allowing User A to check whether the shirt suits him or her. As a result, User A selects the shirt and completes the purchase process through the smart glasses.

[0932] Example prompt sentence:

[0933] You are a user of an emotion-aware fashion advisor application using smart glasses. The app analyzes your emotions and suggests the best fashion items for you. Imagine staring at a particular item in a physical store and speaking to the smart glasses, saying, "Tell me more about this shirt." The smart glasses then display detailed information about the item and a simulated try-on.

[0934] In this way, the user can receive suggestions for the most suitable fashion items that take into consideration personal information and emotions, providing an effective try-on experience.

[0935] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0936] Step 1:

[0937] Entering user information

[0938] The user puts on the smart glasses and launches the application. The user enters personal information such as name, age, gender, height, weight, fashion preferences, and usage situation. This information is sent via Wi-Fi to the server, which stores the received information in a database for later processing.

[0939] Step 2:

[0940] Video capture for emotion analysis

[0941] The camera in the smart glasses captures the user's facial expressions in real time. The captured video is then sent to a server via Wi-Fi. The server then inputs the received video data into an emotion recognition engine (e.g., IBM Watson, Microsoft Azure Emotion API) to analyze the user's emotions. The analysis results are then returned to the server for use in the next step.

[0942] Step 3:

[0943] Style Determination

[0944] Based on the personal information collected in step 1, the server uses machine learning algorithms (e.g., TensorFlow, PyTorch) to determine the style that best suits the user. The results of this determination are stored in a database and used to adjust future recommendations. Specifically, the style is determined by analyzing multiple features using data such as height, weight, bone structure diagnosis, and personal color diagnosis results.

[0945] Step 4:

[0946] Adjusting the proposal

[0947] The server combines the results of the emotion analysis obtained in step 2 with the style information determined in step 3 to adjust the fashion item suggestions presented to the user. For example, if the user is relaxed, it will suggest a casual style, and if the user is nervous, it will suggest a formal style. This suggestion is important for providing the user with the optimal experience.

[0948] Step 5:

[0949] Simulation video generation

[0950] When a user is interested in a particular item through the smart glasses, they issue a voice command such as "Tell me more about this shirt." This request is sent to the server via Wi-Fi. The server processes the request and retrieves detailed information about the item from online stores (e.g., Amazon, Rakuten). Based on the retrieved information, the server combines the user's image and style information to generate a simulation image. This simulation image is then displayed on the smart glasses' display.

[0951] Step 6:

[0952] Product information and purchasing assistance

[0953] The server retrieves product information from the online store and displays it in a list for the user. The user checks the product information through the smart glasses and selects the desired product. The selected information is sent back to the server to assist in the purchase process. The server then sends the purchase information to the online store to complete the purchase process. Once the purchase is complete, a confirmation message is sent to the user.

[0954] In this way, users can receive recommendations for the most suitable fashion items that take into account their personal information and emotions, enabling an effective try-on experience and a smooth purchasing process.

[0955] 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.

[0956] 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.

[0957] 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.

[0958] [Third embodiment]

[0959] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0960] 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.

[0961] 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).

[0962] 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.

[0963] 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.

[0964] 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).

[0965] 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.

[0966] 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.

[0967] 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.

[0968] 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.

[0969] 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.

[0970] 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."

[0971] The system of the present invention collects personal information of a user and proposes an optimal fashion style, thereby providing a consumer-friendly and environmentally friendly approach. Hereinafter, an embodiment of the present invention will be described.

[0972] This system mainly consists of a user terminal, a server, and an online store. Users access the system using their own smartphones or computers (user terminals).

[0973] Program processing

[0974] 1. Collection of User Information

[0975] The user launches the application and enters personal information

[0976] The user device displays a screen for entering basic information such as name, age, gender, height, weight, fashion preferences, and usage situation (e.g., business, casual).

[0977] The user performs a bone structure diagnosis and a personal color diagnosis.

[0978] The user terminal presents the user with a question using a plurality of images and prompts the user to input an answer.

[0979] The server stores the collected data in a database and analyzes it.

[0980] 2. Automatic judgment by AI

[0981] The server proposes the best style based on the information collected

[0982] The server inputs the stored user information into a machine learning model to automatically determine the style and color that best suits the user.

[0983] The server stores the results of the assessment in a database and generates recommended styles tailored to each user.

[0984] 3. Simulation using the person's own video

[0985] The user uses the camera in the application to capture their own video.

[0986] The user device uses its camera function to capture images of the user's current posture and face.

[0987] The server runs the simulation

[0988] The user terminal transmits the captured video to the server.

[0989] The server combines the captured video with a pre-determined style to generate a simulation video in which the costume is superimposed on the user's image.

[0990] The server transmits the generated simulation video to the user terminal.

[0991] 4. AI recommends suitable clothing from apparel sites

[0992] The server acquires product information from the apparel site based on the proposal results.

[0993] The server searches the online store for products that match the proposed style and retrieves multiple options.

[0994] The server organizes the acquired product information and generates a list to suggest to the user.

[0995] Present the proposed results to the user

[0996] The user terminal displays a list of the proposal results received from the server, allowing the user to make a selection.

[0997] 5. Users can purchase original items that suit their tastes

[0998] The user selects and purchases from the suggested products

[0999] The user terminal provides an interface for the user to select items they wish to purchase from the suggested merchandise.

[1000] The server handles the purchase process

[1001] The user terminal transmits the selected product information and data required for the purchase procedure to the server.

[1002] The server sends the necessary information to the online store to proceed with the purchase, allowing the user to complete the purchase.

[1003] The server notifies the user terminal that the purchase has been completed and asks the user to confirm.

[1004] Specific examples

[1005] For example, suppose User A starts an application, enters personal information such as name, age, and height, and answers questions about bone structure and personal color diagnosis. The collected information is sent to the server, where a machine learning algorithm determines the optimal style. User A then takes a video of themselves with a camera and checks which style suits them best in the simulation video sent from the server. The server then retrieves product information from the online store that matches the suggested style and suggests it to User A. User A then selects and purchases the items they like from the presented list. Through this process, User A can select the optimal products based on their personal information and avoid unnecessary purchases.

[1006] This will enable consumers to enjoy a more satisfying purchasing experience and reduce the burden on the environment.

[1007] The processing flow will be explained below.

[1008] Step 1:

[1009] The user launches the application and enters personal information

[1010] Users enter basic information such as their name, age, gender, height, weight, fashion preferences, and usage situation (e.g., business, casual) on their device.

[1011] Step 2:

[1012] The user performs a bone structure diagnosis and a personal color diagnosis.

[1013] The user device shows the user multiple images for skeletal diagnosis and asks them to choose the one that most closely resembles their own.

[1014] Similarly, personal color diagnosis questions are presented and the user answers them.

[1015] The terminal transmits the input information to the server.

[1016] Step 3:

[1017] The server analyzes the user information

[1018] The server stores the received user information in a database.

[1019] The server then feeds the stored information into a machine learning algorithm to analyze the style and color that best suits the user.

[1020] The analysis results are saved in a database.

[1021] Step 4:

[1022] The user captures the video using the camera

[1023] The user activates the camera function of the user device to take a video of themselves.

[1024] The terminal transmits the captured video data to the server.

[1025] Step 5:

[1026] The server generates the simulation video

[1027] The server generates a simulation video by overlaying the captured user video with the optimal style information determined by machine learning.

[1028] The simulation video is sent to the user's device so that the user can view it.

[1029] Step 6:

[1030] The server will suggest suitable clothing items

[1031] Based on the generated style information, the server retrieves product information from the online store via API.

[1032] The server analyzes the acquired product information and selects clothing candidates that are best suited to the user.

[1033] A list of suggested product information is sent to the user's device.

[1034] Step 7:

[1035] The user selects and purchases the suggested product

[1036] The user selects the desired product from the product list displayed on the user terminal.

[1037] The terminal presents the user with a form to complete the purchase process and prompts them to enter the necessary information (e.g., payment information, etc.).

[1038] The terminal transmits the input information to the server.

[1039] Step 8:

[1040] The server handles the purchase process

[1041] The server sends the user's selected product information and payment information to the online store to complete the purchase.

[1042] The server sends a purchase confirmation message to the user's terminal, allowing the user to confirm the purchase.

[1043] The process at each step utilizes machine learning and simulation technology to provide optimal products tailored to user needs, preventing unnecessary purchases and reducing environmental impact.

[1044] Example 1

[1045] 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."

[1046] In modern society, consumers spend a lot of time and effort selecting the fashion style that best suits them. Furthermore, the increased purchase of inappropriate fashion items can have a negative impact on the environment. Furthermore, even with online shopping, consumers often feel dissatisfied after purchasing because they cannot actually try on the products. To solve these problems, a system is needed that can suggest optimal fashion styles tailored to individual consumers and perform a try-on simulation.

[1047] 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.

[1048] In this invention, the server includes means for collecting personal information of a user, means for determining the optimal style for the user based on the collected personal information using a machine learning algorithm, means for capturing an image of the user and generating a simulation image of the determined style, means for acquiring suggested product information from an online store, means for presenting the suggested product information to the user so that the user can select and purchase, means for saving the user's personal information and diagnostic information in a database and analyzing that information, means for capturing an image of the user's current posture and face when generating the simulation image, means for organizing the acquired product information and generating a list to suggest to the user, and means for supporting the purchase procedure based on the user's selection. This allows the user to efficiently select appropriate fashion items based on their personal information and enjoy a satisfying purchasing experience through a try-on simulation.

[1049] "User's personal information" refers to basic information such as the user's name, age, gender, height, weight, fashion preferences, and usage situation.

[1050] "Machine learning algorithm" refers to an algorithm that learns patterns from collected data and uses the results to suggest the best styles and colors for users.

[1051] "User's Images" refers to image and video data of the user's appearance, voice, and face captured by the user's camera using the application.

[1052] "Simulation video" refers to video data that provides a visual like trying on clothes, with the determined style superimposed on the user's video.

[1053] "Online store" refers to a store that sells products via the Internet.

[1054] A "database" refers to a system for organizing and storing data so that it can be searched and analyzed later.

[1055] A "web scraping tool" refers to software for automatically extracting specific data from web pages on the Internet.

[1056] "User terminal" refers to a device such as a smartphone or computer operated by a user.

[1057] "Checkout" refers to the series of steps (e.g., selection, payment, delivery arrangements) required by a User to purchase an item from an online store.

[1058] "Image processing technology" refers to the technology of processing and analyzing image data using a computer, and is used to generate simulation images.

[1059] "Judgment results" refer to the optimal fashion style and color combinations suggested to users based on analysis by machine learning algorithms.

[1060] "Product Information" refers to detailed product information (price, size, color, material, etc.) obtained from the online store.

[1061] MODE FOR CARRYING OUT THE INVENTION

[1062] The present invention is a system that collects personal information of a user and suggests an optimal fashion style. This system is mainly composed of a user terminal, a server, and an online store. Specific embodiments for carrying out the present invention will be described below.

[1063] Hardware and software used

[1064] User devices: Smartphones, computers, etc. These devices provide an interface for users to input information.

[1065] Server: Runs database software (e.g., MySQL) and machine learning models (e.g., TensorFlow).

[1066] Image processing software: such as OpenCV. Used to generate simulation images.

[1067] Web scraping tools, such as BeautifulSoup, are used to retrieve product information from online stores.

[1068] Program processing

[1069] Users access the system using a smartphone or computer and follow the process below.

[1070] 1. Collection of User Information

[1071] The user starts the application and enters basic information such as name, age, gender, height, weight, fashion preferences, and usage situation. The user's device sends this data to the server. The user also performs a bone structure diagnosis and personal color diagnosis, and sends the data to the server.

[1072] 2. Automatic judgment by AI

[1073] The server stores the collected personal information and diagnostic data in a database and uses machine learning algorithms to determine the best style and color for each user. The results are then stored in the database.

[1074] 3. Simulation using the person's own video

[1075] The user captures video of their posture and face through the application. The user device sends this video data to the server. The server combines the captured video with the determined style to generate a simulation video and sends it to the user device.

[1076] 4. AI recommends suitable clothing from apparel sites

[1077] The server searches the online store for products that match the proposed style, organizes the obtained product information, and generates a list to suggest to the user. This list is sent to the user's terminal and presented to the user.

[1078] 5. Users can purchase original items that suit their tastes

[1079] The user selects the item they wish to purchase from the list of suggested products and clicks the purchase button. The user's device sends the selected product information and data required for the purchase process to the server. The server then sends the information required to proceed with the purchase to the online store and notifies the user's device that the purchase is complete.

[1080] Specific examples

[1081] For example, User A starts the application, enters personal information such as name, age, and height, and answers questions about bone structure and personal color diagnosis. This information is sent to the server, and a machine learning algorithm determines the optimal style. User A then takes a video of themselves with a camera and checks which style suits them best in the simulation video sent from the server. The server then retrieves product information from the online store that matches the suggested style and suggests it to User A. User A then selects their preferred item from the list provided and purchases it.

[1082] This allows User A to select the most suitable product based on their personal information and avoid unnecessary purchases. Through this process, consumers can enjoy a more satisfying shopping experience and reduce their environmental impact.

[1083] Prompt Sentence Examples

[1084] Below are some example prompts to input to machine learning algorithms:

[1085] "User A is 25 years old, 160cm tall, weighs 50kg, and wants fashion suitable for business situations. His bone structure diagnosis is ectomorph, and his personal color is spring."

[1086] This allows the server to determine and suggest the best style and color for user A.

[1087] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1088] Program processing flow

[1089] Step 1: Collect user information

[1090] Input: User's personal information (name, age, gender, height, weight, fashion preferences, usage situation) and answers to the bone structure diagnosis and personal color diagnosis.

[1091] process:

[1092] The user launches the application and enters their basic information into the form that appears.

[1093] The user answers diagnostic questions.

[1094] The user terminal collects this information and sends it to the server.

[1095] Output: User personal and diagnostic information sent to the server.

[1096] Step 2: Data storage and analysis

[1097] Input: The user's personal and diagnostic information.

[1098] process:

[1099] The server stores the received data in a database.

[1100] The server inputs the data into the machine learning model and performs the analysis.

[1101] Machine learning algorithms use the collected data to determine the best fashion style and color.

[1102] Output: The result of the judgement (the best style and color combination for the user).

[1103] Step 3: Import your own video

[1104] Input: Video of the user's current pose and face.

[1105] process:

[1106] Users use the application to activate the camera and capture footage of themselves.

[1107] The user device sends the captured video to the server.

[1108] Output: User video data sent to the server.

[1109] Step 4: Generate simulation footage

[1110] Input: User video data and determined style information.

[1111] process:

[1112] The server generates a simulation video using the received video data and the determined style information.

[1113] The server uses image processing techniques (e.g. OpenCV) to overlay a style onto the user's video.

[1114] Output: Simulation video.

[1115] Step 5: Obtaining proposed product information

[1116] Input: Determined style information.

[1117] process:

[1118] The server searches the online store for product information that matches the suggested style.

[1119] The server uses a web scraping tool (e.g. BeautifulSoup) to retrieve and organize product information.

[1120] Output: A list of suggested product information.

[1121] Step 6: Presenting the proposed results

[1122] Input: Proposed product information.

[1123] process:

[1124] The server transmits the proposal results to the user terminal.

[1125] The user terminal displays a list of suggested product information to the user.

[1126] Output: A list of suggestion results shown to the user.

[1127] Step 7: Select and purchase products

[1128] Input: List of proposed product information.

[1129] process:

[1130] The user selects the items to purchase from the suggested products.

[1131] The user terminal transmits the selected product information and necessary purchase data to the server.

[1132] Output: Purchase data sent to the server.

[1133] Step 8: Support with checkout

[1134] Input: User-selected product information and purchase data.

[1135] process:

[1136] The server passes the purchase procedure to the online store's system.

[1137] The server sends a purchase completion notification to the user terminal, and the user confirms it.

[1138] Output: Notification and confirmation that the purchase has been completed.

[1139] (Application example 1)

[1140] 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."

[1141] Conventional fashion suggestion systems are limited to suggesting optimal styles based on a user's personal information, which is insufficient for improving the shopping experience in physical stores. Furthermore, most virtual try-on systems are limited to online stores, making it difficult to use in stores in real time. The present invention aims to solve these problems and make shopping in physical stores more intuitive and satisfying for users.

[1142] 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.

[1143] In this invention, the server includes means for collecting personal information of the user, means for determining the optimal style for the user based on the collected personal information using a machine learning algorithm, means for capturing an image of the user and generating a simulation image of the determined style, means for acquiring suggested product information from an online store, means for presenting the suggested product information to the user so that the user can select and purchase, means for capturing an image of the user in real time using a camera function of the smart glasses, and means for acquiring in-store inventory information and generating a product list to be suggested to the user. This allows the user to check the fashion items that are optimal for them in real time, improving the shopping experience in physical stores.

[1144] "User's personal information" refers to individual information about the user, such as the user's name, age, gender, height, weight, fashion preferences, and usage situation.

[1145] A "machine learning algorithm" is an artificial intelligence technique that uses data to train models to identify patterns and relationships and make predictions.

[1146] "Simulation video" is a video in which the judged style and outfit are superimposed on the user's video, giving the impression of virtually trying on the outfits.

[1147] An "online store" is a website or platform that sells products over the Internet.

[1148] "Smart glasses" are glasses-type wearable devices that have the function of displaying information in the user's field of vision.

[1149] "Camera function" refers to hardware and software that has the function of taking images and videos.

[1150] "Stock information" is information about the quantity and types of products available in the store.

[1151] A "product list" is a list of suggested products that is presented in a format that allows the user to select from them.

[1152] The system embodying this invention mainly collects personal information of users and suggests optimal fashion styles based on that information. Furthermore, this system is designed to enhance users' shopping experience in physical stores, and uses smart glasses to suggest optimal styles in real time.

[1153] Configuration and Operation Procedures

[1154] 1. Collection of User Information

[1155] Users input their personal information (such as name, age, gender, height, weight, preferred style, and usage situation) through smart glasses or other devices. This operation is carried out through a dedicated application.

[1156] 2. Body type diagnosis and personal color diagnosis

[1157] Users upload their own images and the system asks them to answer a number of questions to diagnose their body type and personal color. This information is also sent to the server and stored in a database.

[1158] 3. Determining the best style

[1159] The server uses machine learning algorithms based on the collected personal information to determine the best style for the user, using a generative AI model for this process.

[1160] 4. Real-time video capture and simulation

[1161] The camera function of the smart glasses is used to capture real-time footage of the user, and a simulated video is generated with the determined style overlaid on it, which the user can view through the smart glasses.

[1162] 5. Obtaining in-store inventory information

[1163] The server retrieves inventory information from physical stores and generates a list of products to suggest to users, allowing them to check the items available in the store in real time.

[1164] 6. Recommended styles and product suggestions

[1165] The server retrieves the best product information from online and physical stores and suggests it to the user, who can then review the suggestions through the smart glasses and make a purchase decision.

[1166] Specific examples

[1167] For example, when User A enters a physical store, the smart glasses capture User A's image in real time and suggest the best style based on the personal information input in advance. The server uses the results of User A's bone structure and personal color diagnosis to display a simulation image of an outfit that would suit User A.

[1168] The server then retrieves in-store inventory information and generates a list of products that are optimal for User A. User A can then view, select, and purchase items through the smart glasses.

[1169] Hardware and software used

[1170] Hardware: Smart glasses (with camera function), user devices (smartphones, tablets, PCs)

[1171] Software: Machine learning algorithms (generative AI models), image processing technology, online store API, store inventory management system

[1172] Prompt Sentence Examples

[1173] "Please suggest the best fashion style for user A based on their age, gender, build, and preferences. Also, please generate a virtual try-on image and display it in real time. User camera: user_image.jpg"

[1174] By using this prompt, the generative AI model can provide optimal fashion suggestions to users.

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

[1176] Step 1:

[1177] The user enters personal information using smart glasses or other devices. The user information input form includes name, age, gender, height, weight, fashion preferences, and usage situation. After input, this information is sent to the server. The entered data is stored in the server's database and used for further processing.

[1178] Step 2:

[1179] The user performs a bone structure diagnosis and a personal color diagnosis. The user uploads an image, and the system asks the user several questions along with the image, prompting the user to answer. This diagnostic information is also sent to the server and stored in a database. The server uses this data to analyze the user's body shape and skin color.

[1180] Step 3:

[1181] The server uses a machine learning algorithm to determine the best style for the user based on the collected personal information and diagnostic results. This data is input into a generative AI model, which then suggests the best style and color. The server then stores the generated style data in a database.

[1182] Step 4:

[1183] The user captures a real-time video of themselves using the camera function of their smart glasses. The device then sends the image captured by the camera to the server. The server then overlays the received image with a pre-determined style to generate a simulated video. The generated simulated video is then sent from the server to the user's smart glasses.

[1184] Step 5:

[1185] The server retrieves product information to be suggested from both online and physical stores. It searches for products that match the style suggested by the AI ​​through the online store's API and the physical store's inventory management system. The server organizes the retrieved product information and generates a list to suggest to the user. The list is then sent from the server to the user's smart glasses.

[1186] Step 6:

[1187] The user checks the suggested product information and selects it using the smart glasses. The user then selects the item they want from the list and proceeds with the purchase using the smart glasses. The device then sends the selected product information and the data required for the purchase to the server, which then forwards it to the online store to complete the purchase. The user can receive a confirmation message through the smart glasses.

[1188] Step 7:

[1189] The server stores the completed purchase information in a database and manages it as the user's purchase history. The user can use this history as reference for their next purchase. The server can also use this data to learn how to make more advanced personalized fashion suggestions.

[1190] 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.

[1191] The system of the present invention not only collects personal information of a user and suggests the most suitable fashion style, but also recognizes the user's emotions and adjusts the information and suggestions provided, and combines an emotion engine to improve the consumer experience. Hereinafter, embodiments for carrying out the present invention will be described in detail.

[1192] This system mainly consists of a user terminal, a server, an emotion engine, and an online store. Users access the system using their own smartphones or computers (user terminals).

[1193] Program processing

[1194] 1. Collection of User Information

[1195] The user launches the application and enters personal information

[1196] The user device displays a screen for entering basic information such as name, age, gender, height, weight, fashion preferences, and usage situation (e.g., business, casual).

[1197] The user performs a bone structure diagnosis and a personal color diagnosis.

[1198] The user terminal presents the user with a question using a plurality of images and prompts the user to input an answer.

[1199] The terminal transmits the input information to the server.

[1200] 2. Automatic judgment by AI

[1201] The server analyzes the user information

[1202] The server stores the received user information in a database.

[1203] The server then feeds the stored information into a machine learning algorithm to analyze the style and color that best suits the user.

[1204] The analysis results are saved in a database.

[1205] 3. Simulation using the person's own video

[1206] The user captures the video using the camera

[1207] The user activates the camera function of the user device to take a video of themselves.

[1208] The terminal transmits the captured video data to the server.

[1209] The server generates the simulation video

[1210] The server generates a simulation video by overlaying the captured user video with the optimal style information determined by machine learning.

[1211] The simulation video is sent to the user's device so that the user can view it.

[1212] 4. Use of Emotion Engine

[1213] User uses camera to recognize emotions

[1214] The user device uses a camera function to capture the user's facial expression and transmits the image to the server.

[1215] The server uses an emotion engine to recognize emotions from the user's facial expressions.

[1216] Emotion engine adjusts suggestions

[1217] Based on the recognized emotion data, the server adjusts the product information and simulation images it proposes to make suggestions that are appropriate for the user.

[1218] For example, if a user is feeling stressed, it will suggest fashion that will help them relax.

[1219] 5. AI suggests suitable clothing from apparel sites

[1220] The server acquires product information from the apparel site based on the proposal results.

[1221] The server searches the online store for products that match the proposed style and retrieves multiple options.

[1222] The server organizes the acquired product information and generates a list to suggest to the user.

[1223] A list of suggested product information is sent to the user's device.

[1224] 6. Users can purchase original items that suit their tastes

[1225] The user selects and purchases from the suggested products

[1226] The user selects the desired product from the product list displayed on the user terminal.

[1227] The terminal presents the user with a form for completing the purchase procedure and prompts the user to enter the necessary information.

[1228] The terminal transmits the input information to the server.

[1229] The server handles the purchase process

[1230] The server sends the user's selected product information and payment information to the online store to complete the purchase.

[1231] The server sends a purchase confirmation message to the user's terminal, allowing the user to confirm the purchase.

[1232] Specific examples

[1233] For example, suppose User B launches the application, enters personal information, and answers questions about bone structure and personal color. This information is sent to the server, where a machine learning algorithm determines the optimal style. Next, User B takes a video of themselves with a camera and checks which style suits them best in the simulation video sent from the server. At the same time, the emotion engine analyzes User B's facial expressions and suggests a casual style if they are relaxed, or a style that gives them a sense of security if they are nervous. This suggestion is based on information obtained from the online store, and User B selects and purchases the most suitable items. This process allows User B to achieve high satisfaction while reducing their environmental impact through purchases.

[1234] The processing flow will be explained below.

[1235] Step 1:

[1236] The user launches the application and enters personal information

[1237] The user launches the application on their device and operates a screen to enter basic information such as name, age, gender, height, weight, fashion preferences, and usage situation (e.g., business, casual).

[1238] The terminal stores the information entered by the user and transmits it to the server.

[1239] Step 2:

[1240] The user performs a bone structure diagnosis and a personal color diagnosis.

[1241] The user device displays multiple images and options for skeletal diagnosis and prompts the user to choose the one that best suits them.

[1242] Similarly, a number of questions and images are presented for personal color diagnosis, and the user answers them.

[1243] The terminal obtains the user's answer and sends it to the server.

[1244] Step 3:

[1245] The server analyzes the user information

[1246] The server stores the received personal information and diagnostic results in a database.

[1247] The server runs machine learning algorithms based on the stored information to analyze the style and color that best suits the user.

[1248] The analysis results are stored in a database for further processing.

[1249] Step 4:

[1250] The user captures the video using the camera

[1251] The user activates the camera function of the user device and takes an image of their current posture and face.

[1252] The terminal transmits the captured video data to the server.

[1253] Step 5:

[1254] The server generates the simulation video

[1255] The server generates a simulation video using the captured user video and optimal style information determined by machine learning.

[1256] The server transmits the generated simulation video to the user terminal so that the user can visually check it.

[1257] Step 6:

[1258] User uses camera to recognize emotions

[1259] The user captures their facial expression using the camera function of their device.

[1260] The terminal transmits the acquired video data to the server.

[1261] Step 7:

[1262] The server recognizes emotions using an emotion engine

[1263] The server analyzes the transmitted video data and uses an emotion engine to recognize emotions from the user's facial expressions.

[1264] The user's psychological state is determined based on the recognized emotional data.

[1265] Step 8:

[1266] Emotion engine adjusts suggestions

[1267] The server then adjusts the product information and simulation images it recommends based on the user's emotional data. For example, if it determines that the user is relaxed, it will suggest a casual, relaxed style.

[1268] The adjusted proposal content is sent to the user device.

[1269] Step 9:

[1270] The server acquires product information from the apparel site based on the proposal results.

[1271] The server retrieves multiple options from the online store via API, searching for products that match the user's best style.

[1272] The server analyzes the acquired product information and selects clothing candidates that are best suited to the user.

[1273] A list of suggested product information is sent to the user's device.

[1274] Step 10:

[1275] The user selects and purchases the suggested product

[1276] The user selects the desired product from the product list displayed on the user terminal.

[1277] The terminal displays a form for the user to complete the purchase procedure and prompts the user to enter the necessary information.

[1278] The terminal transmits the input information to the server.

[1279] Step 11:

[1280] The server handles the purchase process

[1281] The server sends the user's selected product information and payment information to the online store to complete the purchase.

[1282] The server sends a purchase confirmation message to the user's terminal, allowing the user to confirm the purchase.

[1283] This system allows users to receive suggestions for optimal fashion styles based on their personal information and emotional data, reducing unnecessary purchases and waste, and easing the burden on the environment.

[1284] Example 2

[1285] 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."

[1286] Conventional fashion suggestion systems only considered the user's personal information and preferences, and therefore did not provide flexible suggestions that took into account the user's real-time emotions and circumstances. Furthermore, they only provided fashion suggestions in the form of still images or text, and lacked a way for users to visually confirm how the fashion would look when actually worn. This led to problems such as lower user satisfaction and a decline in purchasing motivation.

[1287] 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 collecting personal information of the user, means for determining the optimal style for the user based on the collected personal information using a machine learning algorithm, means for capturing an image of the user and generating a simulation image of the determined style, means for analyzing the user's facial expression and recognizing emotions, means for adjusting the suggestions based on the recognized emotions, means for acquiring information on products to be suggested from an online store, and means for presenting the suggested product information to the user so that the user can select and purchase. This makes it possible to reflect the user's real-time emotions and provide an image of how the product will actually look when worn, thereby making it possible to make more personalized fashion suggestions and improve user satisfaction and purchasing motivation.

[1288] "User's personal information" refers to basic information about an individual, such as the user's name, age, gender, height, weight, fashion preferences, and usage situation.

[1289] "Machine learning algorithms" are algorithms that analyze optimal fashion styles and colors based on collected data, and primarily use technologies such as TensorFlow and PyTorch.

[1290] A "simulation video" is a moving or still image generated by superimposing a determined fashion style onto a user's video.

[1291] "Means for recognizing emotions" refers to technology that analyzes a user's facial expression data and identifies the user's current emotional state, such as using Microsoft Azure's Emotion API.

[1292] The "means for adjusting the content of suggestions" is a technology that appropriately changes or adjusts the fashion and product information suggestions based on the recognized user emotions.

[1293] An "online store" is a website that provides product information and sells products via the Internet, and examples include Amazon and Rakuten.

[1294] "Product information" refers to data about a product, such as its name, price, size, color, material, and photo, obtained from an online store.

[1295] MODE FOR CARRYING OUT THE INVENTION

[1296] The system of the present invention not only collects personal information of the user and suggests the most suitable fashion style, but also recognizes the user's emotions and adjusts the suggestions accordingly, and combines an emotion engine to improve the consumer experience. The following describes in detail the embodiments of the present invention.

[1297] System configuration

[1298] This system mainly consists of a user terminal, a server, an emotion engine, and an online store. Users access the system using their own smartphones or computers (user terminals).

[1299] Hardware and software used

[1300] User device: Uses a smartphone or computer. Provides an interface for users to input information and use a camera.

[1301] Server: Receives and stores information from users, processes and analyzes the data using machine learning algorithms and emotion engines.

[1302] Machine learning algorithms: using frameworks such as TensorFlow and PyTorch.

[1303] Emotion engine: Uses services such as Microsoft Azure's Emotion API.

[1304] Online store: Obtain product information from online e-commerce sites (e.g., Amazon, Rakuten).

[1305] Program processing

[1306] 1. Collection of User Information

[1307] The user starts the application and enters personal information (such as name, age, gender, height, weight, fashion preferences, and usage situation). Furthermore, the application performs a bone structure diagnosis and a personal color diagnosis, and answers questions using multiple images. This information is then sent from the user's device to the server.

[1308] 2. Automatic judgment by AI

[1309] The server stores the received user information in a database and uses machine learning algorithms to analyze the optimal style and color. The analysis results are then stored in the database.

[1310] 3. Simulation using the person's own video

[1311] The user captures a video of themselves using a camera, and the device sends the video data to the server. The server then overlays the captured user video with the optimal style information determined by machine learning to generate a simulation video, which is then sent to the user's device. This allows the user to visually check the style that suits them best.

[1312] 4. Use of Emotion Engine

[1313] The user captures their facial expressions using a camera, and the device sends the video to a server. The server then uses an emotion engine to recognize the emotion from the user's facial expressions and adjusts the recommendations based on the recognized emotion data. For example, if the user is feeling stressed, the server will suggest relaxing fashion.

[1314] 5. AI suggests suitable clothing from apparel sites

[1315] The server then searches online stores for matching product information based on the results of the suggestions, retrieves multiple options, and organizes the information before sending it to the user's device.

[1316] 6. Users can purchase original items that suit their tastes

[1317] The user selects from the suggested products and completes the purchase. The user's device displays a form for the purchase and asks them to enter the necessary information. The server then sends this information to the online store to complete the purchase.

[1318] Specific examples

[1319] For example, suppose User B launches the application, enters personal information, and answers questions about bone structure and personal color. This information is sent to the server, where a machine learning algorithm determines the optimal style. Next, User B takes a video of themselves with a camera and checks which style suits them best in the simulated video sent from the server. At the same time, the emotion engine analyzes User B's facial expressions and suggests a casual style if he is relaxed, or a style that gives him a sense of security if he is nervous. These suggestions are based on information obtained from the online store, and User B selects and purchases the most suitable items.

[1320] Prompt Sentence Examples

[1321] Here is an example of a prompt that allows the user to ask the system a specific question:

[1322] "I'm a 34-year-old man, 180cm tall and 75kg. I like casual style and am looking for fashion that I can wear in business casual situations. I took a recent photo of myself. Please suggest the best fashion style based on this photo. I'd also like you to use the emotion engine to suggest a style that takes my current mood into account."

[1323] Based on this prompt, the system collects and analyzes the user's information and suggests the most suitable fashion style and corresponding products.

[1324] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1325] Step 1: User launches application and enters personal information

[1326] Input: Basic information of the user (name, age, gender, height, weight, fashion preferences, usage situation, etc.).

[1327] Operation: The user launches the application on their smartphone or computer and displays the personal information entry screen. The user enters information for each item.

[1328] Data processing and calculation: The user terminal organizes the input information and converts it into an appropriate format.

[1329] Output: The organized personal information is sent to the server.

[1330] Step 2: User's procedure for performing bone structure diagnosis and personal color diagnosis

[1331] Input: User answers (answers to questions about bone structure and personal color).

[1332] Operation: The user terminal displays a number of questions to the user, who then enters answers to the displayed questions.

[1333] Data processing and calculation: The user terminal converts the input answers into a data format and extracts the necessary diagnostic data.

[1334] Output: The converted diagnostic data is sent to the server.

[1335] Step 3: The server analyzes the user information and determines the most suitable style

[1336] Input: Your personal and diagnostic data.

[1337] How it works: The server stores the received personal information and diagnostic data in a database, then inputs the stored information into a machine learning algorithm for analysis.

[1338] Data processing and calculation: Using machine learning algorithms (such as TensorFlow and PyTorch), we analyze the fashion style and color that best suits the user.

[1339] Output: The analysis results are saved in a database.

[1340] Step 4: User instructions for capturing video using the camera

[1341] Input: User's video (video data captured by a camera).

[1342] How it works: The user activates the device's camera and takes a video of themselves.

[1343] Data processing and calculation: The user device converts the captured video data into an appropriate format and adjusts the size and image quality.

[1344] Output: The converted video data is sent to the server.

[1345] Step 5: Procedure for the server to generate the simulation video

[1346] Input: User's video data and analysis results (optimal style information).

[1347] How it works: The server overlays style information determined by machine learning onto the captured user video.

[1348] Data processing and calculation: Using image processing technology, the user's video and style information are combined to generate a simulation video.

[1349] Output: The generated simulation video is sent to the user's device.

[1350] Step 6: User uses camera to capture facial expressions and recognize emotions

[1351] Input: User's facial expression video (video data captured by a camera).

[1352] Action: The user activates the device's camera and captures their facial expressions.

[1353] Data processing and calculation: The device converts the captured facial expression video into an appropriate format and sends it to the server.

[1354] Output: The converted facial expression video data is sent to the server.

[1355] Step 7: The server uses the emotion engine to recognize the user's emotions and adjust the suggestions.

[1356] Input: User's facial expression data.

[1357] How it works: The server inputs the received facial expression data into an emotion engine (such as Microsoft Azure's Emotion API) to recognize emotions.

[1358] Data processing and calculation: Analyzes emotional data to understand the user's current emotional state, and adjusts suggestions based on the analysis results.

[1359] Output: The adjusted proposal is sent to the user's device.

[1360] Step 8: Procedure for the server to obtain product information from the apparel site based on the proposal results

[1361] Input: Adjusted proposal.

[1362] How it works: The server searches online stores for matching products based on the suggested style.

[1363] Data processing and calculation: Utilizing the online store's API, we organize the obtained product information.

[1364] Output: The organized product information is sent to the user's terminal.

[1365] Step 9: User selects and purchases from the suggested products

[1366] Input: Suggested product information.

[1367] How it works: The user selects the product they want from a list of products displayed on the device, and the device displays a checkout form and asks them to enter the necessary information.

[1368] Data processing and calculation: The terminal sends the input information to the server, which then transmits it to the online store.

[1369] Output: A purchase confirmation message is sent to the user's device.

[1370] (Application example 2)

[1371] 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."

[1372] When shopping at traditional online or physical stores, it was difficult for users to fully reflect their personal information or their mood at the time when selecting the perfect fashion item. Furthermore, it often took time and effort for users to try on items, which often led to an unsatisfactory consumer experience. Furthermore, since appropriate suggestions were not made taking emotions into consideration, user satisfaction could decrease.

[1373] 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.

[1374] In this invention, the server includes means for collecting personal information of the user, means for determining the optimal style for the user based on the collected personal information using a machine learning algorithm, means for capturing an image of the user and generating a simulation image of the determined style, means for obtaining suggested product information from an online store, means for presenting the suggested product information to the user so that the user can select and purchase, means for analyzing the user's emotions and adjusting the suggested content based on the analysis results, and means for allowing the user to visually check a simulation of trying on the suggested items in real time. This enables the server to recommend optimal fashion items taking into account the user's personal information and emotions, and to provide an effective try-on experience.

[1375] "Personal information" is a general term for data necessary for fashion suggestions, such as personal information about the user, fashion preferences, body type diagnosis, and personal color diagnosis information.

[1376] "Machine learning algorithm" is an artificial intelligence technology that determines the best fashion style for a user based on collected personal information.

[1377] A "simulation video" is a video of a virtual try-on that is generated by overlaying the determined style onto a video of the user.

[1378] "Emotion analysis" is a technology that recognizes and analyzes a user's emotional state at any given time based on their facial expressions and behavior.

[1379] "Adjusting suggestion content" is the process of appropriately changing the fashion suggestions presented to the user based on the results of sentiment analysis.

[1380] "Real-time try-on simulation" is a technology that simulates the user trying on suggested items instantly, allowing them to visually confirm the experience.

[1381] "Acquisition of product information from online stores" is a data collection process in which suggested product information is acquired from online stores and provided to users.

[1382] "User Selection and Purchasing Instrument" means the interface and support system through which a user can review suggested product information and make a selection or purchase.

[1383] The system of the present invention is designed to suggest the most suitable fashion items to a user while they are shopping in a physical store using smart glasses. The details of the embodiment of the system are described below.

[1384] Program processing

[1385] Collection of User Information

[1386] The user puts on the smart glasses and launches the application. First, the user enters their personal information into the application. This information includes name, age, gender, height, weight, fashion preference, and usage situation (e.g., business, casual). This information is sent via Wi-Fi to the server and stored in a database.

[1387] User sentiment analysis

[1388] The smart glasses use a built-in camera to capture the user's facial expressions. The captured images are sent to a server, where an emotion recognition engine (e.g., IBM Watson or Microsoft Azure Emotion API) is used to analyze the user's emotional state. The analysis results are applied in real time and reflected in the recommendations.

[1389] Style detection using machine learning algorithms

[1390] The server uses machine learning algorithms (e.g., TensorFlow, PyTorch) to determine the best style for each user based on the collected personal information. The results of this style determination are stored in a database.

[1391] Adjusting the proposal

[1392] The server then adjusts the fashion suggestions it presents to the user based on the results of the emotion analysis. For example, if the user is relaxed, it will suggest a casual style, and if they are nervous, it will suggest a formal style.

[1393] Simulation video generation

[1394] When a user is interested in a particular item in a physical store, they look at the glasses and say, "Tell me more about this shirt." The server processes this request and retrieves the item's details. The server then combines the user's image with the defined style to generate a simulated image, which is then displayed on the smart glasses' display.

[1395] Product Information and Checkout

[1396] The server retrieves the suggested product information from the online store and displays it to the user. The user checks the product list through the smart glasses, selects, and completes the purchase. The result of the purchase is sent to the server, and the purchase is completed at the online store.

[1397] Specific examples

[1398] For example, User A wears smart glasses and uses the application in a physical store. User A finds a shirt he likes in the store and, while looking at the shirt, issues a voice command saying, "Tell me more about this shirt." The camera in the smart glasses captures User A's facial expression, and the server analyzes from the expression that User A is relaxed. Detailed information about the suggested shirt and a try-on simulation are displayed on the smart glasses, allowing User A to check whether the shirt suits him or her. As a result, User A selects the shirt and completes the purchase process through the smart glasses.

[1399] Example prompt sentence:

[1400] You are a user of an emotion-aware fashion advisor application using smart glasses. The app analyzes your emotions and suggests the best fashion items for you. Imagine staring at a particular item in a physical store and speaking to the smart glasses, saying, "Tell me more about this shirt." The smart glasses then display detailed information about the item and a simulated try-on.

[1401] In this way, the user can receive suggestions for the most suitable fashion items that take into consideration personal information and emotions, providing an effective try-on experience.

[1402] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1403] Step 1:

[1404] Entering user information

[1405] The user puts on the smart glasses and launches the application. The user enters personal information such as name, age, gender, height, weight, fashion preferences, and usage situation. This information is sent via Wi-Fi to the server, which stores the received information in a database for later processing.

[1406] Step 2:

[1407] Video capture for emotion analysis

[1408] The camera in the smart glasses captures the user's facial expressions in real time. The captured video is then sent to a server via Wi-Fi. The server then inputs the received video data into an emotion recognition engine (e.g., IBM Watson, Microsoft Azure Emotion API) to analyze the user's emotions. The analysis results are then returned to the server for use in the next step.

[1409] Step 3:

[1410] Style Determination

[1411] Based on the personal information collected in step 1, the server uses machine learning algorithms (e.g., TensorFlow, PyTorch) to determine the style that best suits the user. The results of this determination are stored in a database and used to adjust future recommendations. Specifically, the style is determined by analyzing multiple features using data such as height, weight, bone structure diagnosis, and personal color diagnosis results.

[1412] Step 4:

[1413] Adjusting the proposal

[1414] The server combines the results of the emotion analysis obtained in step 2 with the style information determined in step 3 to adjust the fashion item suggestions presented to the user. For example, if the user is relaxed, it will suggest a casual style, and if the user is nervous, it will suggest a formal style. This suggestion is important for providing the user with the optimal experience.

[1415] Step 5:

[1416] Simulation video generation

[1417] When a user is interested in a particular item through the smart glasses, they issue a voice command such as "Tell me more about this shirt." This request is sent to the server via Wi-Fi. The server processes the request and retrieves detailed information about the item from online stores (e.g., Amazon, Rakuten). Based on the retrieved information, the server combines the user's image and style information to generate a simulation image. This simulation image is then displayed on the smart glasses' display.

[1418] Step 6:

[1419] Product information and purchasing assistance

[1420] The server retrieves product information from the online store and displays it in a list for the user. The user checks the product information through the smart glasses and selects the desired product. The selected information is sent back to the server to assist in the purchase process. The server then sends the purchase information to the online store to complete the purchase process. Once the purchase is complete, a confirmation message is sent to the user.

[1421] In this way, users can receive recommendations for the most suitable fashion items that take into account their personal information and emotions, enabling an effective try-on experience and a smooth purchasing process.

[1422] 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.

[1423] 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.

[1424] 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.

[1425] [Fourth embodiment]

[1426] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1427] 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.

[1428] 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).

[1429] 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.

[1430] 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.

[1431] 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).

[1432] 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.

[1433] 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.

[1434] 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.

[1435] 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.

[1436] 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.

[1437] 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.

[1438] 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."

[1439] The system of the present invention collects personal information of a user and proposes an optimal fashion style, thereby providing a consumer-friendly and environmentally friendly approach. Hereinafter, an embodiment of the present invention will be described.

[1440] This system mainly consists of a user terminal, a server, and an online store. Users access the system using their own smartphones or computers (user terminals).

[1441] Program processing

[1442] 1. Collection of User Information

[1443] The user launches the application and enters personal information

[1444] The user device displays a screen for entering basic information such as name, age, gender, height, weight, fashion preferences, and usage situation (e.g., business, casual).

[1445] The user performs a bone structure diagnosis and a personal color diagnosis.

[1446] The user terminal presents the user with a question using a plurality of images and prompts the user to input an answer.

[1447] The server stores the collected data in a database and analyzes it.

[1448] 2. Automatic judgment by AI

[1449] The server proposes the best style based on the information collected

[1450] The server inputs the stored user information into a machine learning model to automatically determine the style and color that best suits the user.

[1451] The server stores the results of the assessment in a database and generates recommended styles tailored to each user.

[1452] 3. Simulation using the person's own video

[1453] The user uses the camera in the application to capture their own video.

[1454] The user device uses its camera function to capture images of the user's current posture and face.

[1455] The server runs the simulation

[1456] The user terminal transmits the captured video to the server.

[1457] The server combines the captured video with a pre-determined style to generate a simulation video in which the costume is superimposed on the user's image.

[1458] The server transmits the generated simulation video to the user terminal.

[1459] 4. AI recommends suitable clothing from apparel sites

[1460] The server acquires product information from the apparel site based on the proposal results.

[1461] The server searches the online store for products that match the proposed style and retrieves multiple options.

[1462] The server organizes the acquired product information and generates a list to suggest to the user.

[1463] Present the proposed results to the user

[1464] The user terminal displays a list of the proposal results received from the server, allowing the user to make a selection.

[1465] 5. Users can purchase original items that suit their tastes

[1466] The user selects and purchases from the suggested products

[1467] The user terminal provides an interface for the user to select items they wish to purchase from the suggested merchandise.

[1468] The server handles the purchase process

[1469] The user terminal transmits the selected product information and data required for the purchase procedure to the server.

[1470] The server sends the necessary information to the online store to proceed with the purchase, allowing the user to complete the purchase.

[1471] The server notifies the user terminal that the purchase has been completed and asks the user to confirm.

[1472] Specific examples

[1473] For example, suppose User A starts an application, enters personal information such as name, age, and height, and answers questions about bone structure and personal color diagnosis. The collected information is sent to the server, where a machine learning algorithm determines the optimal style. User A then takes a video of themselves with a camera and checks which style suits them best in the simulation video sent from the server. The server then retrieves product information from the online store that matches the suggested style and suggests it to User A. User A then selects and purchases the items they like from the presented list. Through this process, User A can select the optimal products based on their personal information and avoid unnecessary purchases.

[1474] This will enable consumers to enjoy a more satisfying purchasing experience and reduce the burden on the environment.

[1475] The processing flow will be explained below.

[1476] Step 1:

[1477] The user launches the application and enters personal information

[1478] Users enter basic information such as their name, age, gender, height, weight, fashion preferences, and usage situation (e.g., business, casual) on their device.

[1479] Step 2:

[1480] The user performs a bone structure diagnosis and a personal color diagnosis.

[1481] The user device shows the user multiple images for skeletal diagnosis and asks them to choose the one that most closely resembles their own.

[1482] Similarly, personal color diagnosis questions are presented and the user answers them.

[1483] The terminal transmits the input information to the server.

[1484] Step 3:

[1485] The server analyzes the user information

[1486] The server stores the received user information in a database.

[1487] The server then feeds the stored information into a machine learning algorithm to analyze the style and color that best suits the user.

[1488] The analysis results are saved in a database.

[1489] Step 4:

[1490] The user captures the video using the camera

[1491] The user activates the camera function of the user device to take a video of themselves.

[1492] The terminal transmits the captured video data to the server.

[1493] Step 5:

[1494] The server generates the simulation video

[1495] The server generates a simulation video by overlaying the captured user video with the optimal style information determined by machine learning.

[1496] The simulation video is sent to the user's device so that the user can view it.

[1497] Step 6:

[1498] The server will suggest suitable clothing items

[1499] Based on the generated style information, the server retrieves product information from the online store via API.

[1500] The server analyzes the acquired product information and selects clothing candidates that are best suited to the user.

[1501] A list of suggested product information is sent to the user's device.

[1502] Step 7:

[1503] The user selects and purchases the suggested product

[1504] The user selects the desired product from the product list displayed on the user terminal.

[1505] The terminal presents the user with a form to complete the purchase process and prompts them to enter the necessary information (e.g., payment information, etc.).

[1506] The terminal transmits the input information to the server.

[1507] Step 8:

[1508] The server handles the purchase process

[1509] The server sends the user's selected product information and payment information to the online store to complete the purchase.

[1510] The server sends a purchase confirmation message to the user's terminal, allowing the user to confirm the purchase.

[1511] The process at each step utilizes machine learning and simulation technology to provide optimal products tailored to user needs, preventing unnecessary purchases and reducing environmental impact.

[1512] Example 1

[1513] 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."

[1514] In modern society, consumers spend a lot of time and effort selecting the fashion style that best suits them. Furthermore, the increased purchase of inappropriate fashion items can have a negative impact on the environment. Furthermore, even with online shopping, consumers often feel dissatisfied after purchasing because they cannot actually try on the products. To solve these problems, a system is needed that can suggest optimal fashion styles tailored to individual consumers and perform a try-on simulation.

[1515] 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.

[1516] In this invention, the server includes means for collecting personal information of a user, means for determining the optimal style for the user based on the collected personal information using a machine learning algorithm, means for capturing an image of the user and generating a simulation image of the determined style, means for acquiring suggested product information from an online store, means for presenting the suggested product information to the user so that the user can select and purchase, means for saving the user's personal information and diagnostic information in a database and analyzing that information, means for capturing an image of the user's current posture and face when generating the simulation image, means for organizing the acquired product information and generating a list to suggest to the user, and means for supporting the purchase procedure based on the user's selection. This allows the user to efficiently select appropriate fashion items based on their personal information and enjoy a satisfying purchasing experience through a try-on simulation.

[1517] "User's personal information" refers to basic information such as the user's name, age, gender, height, weight, fashion preferences, and usage situation.

[1518] "Machine learning algorithm" refers to an algorithm that learns patterns from collected data and uses the results to suggest the best styles and colors for users.

[1519] "User's Images" refers to image and video data of the user's appearance, voice, and face captured by the user's camera using the application.

[1520] "Simulation video" refers to video data that provides a visual like trying on clothes, with the determined style superimposed on the user's video.

[1521] "Online store" refers to a store that sells products via the Internet.

[1522] A "database" refers to a system for organizing and storing data so that it can be searched and analyzed later.

[1523] A "web scraping tool" refers to software for automatically extracting specific data from web pages on the Internet.

[1524] "User terminal" refers to a device such as a smartphone or computer operated by a user.

[1525] "Checkout" refers to the series of steps (e.g., selection, payment, delivery arrangements) required by a User to purchase an item from an online store.

[1526] "Image processing technology" refers to the technology of processing and analyzing image data using a computer, and is used to generate simulation images.

[1527] "Judgment results" refer to the optimal fashion style and color combinations suggested to users based on analysis by machine learning algorithms.

[1528] "Product Information" refers to detailed product information (price, size, color, material, etc.) obtained from the online store.

[1529] MODE FOR CARRYING OUT THE INVENTION

[1530] The present invention is a system that collects personal information of a user and suggests an optimal fashion style. This system is mainly composed of a user terminal, a server, and an online store. Specific embodiments for carrying out the present invention will be described below.

[1531] Hardware and software used

[1532] User devices: Smartphones, computers, etc. These devices provide an interface for users to input information.

[1533] Server: Runs database software (e.g., MySQL) and machine learning models (e.g., TensorFlow).

[1534] Image processing software: such as OpenCV. Used to generate simulation images.

[1535] Web scraping tools, such as BeautifulSoup, are used to retrieve product information from online stores.

[1536] Program processing

[1537] Users access the system using a smartphone or computer and follow the process below.

[1538] 1. Collection of User Information

[1539] The user starts the application and enters basic information such as name, age, gender, height, weight, fashion preferences, and usage situation. The user's device sends this data to the server. The user also performs a bone structure diagnosis and personal color diagnosis, and sends the data to the server.

[1540] 2. Automatic judgment by AI

[1541] The server stores the collected personal information and diagnostic data in a database and uses machine learning algorithms to determine the best style and color for each user. The results are then stored in the database.

[1542] 3. Simulation using the person's own video

[1543] The user captures video of their posture and face through the application. The user device sends this video data to the server. The server combines the captured video with the determined style to generate a simulation video and sends it to the user device.

[1544] 4. AI recommends suitable clothing from apparel sites

[1545] The server searches the online store for products that match the proposed style, organizes the obtained product information, and generates a list to suggest to the user. This list is sent to the user's terminal and presented to the user.

[1546] 5. Users can purchase original items that suit their tastes

[1547] The user selects the item they wish to purchase from the list of suggested products and clicks the purchase button. The user's device sends the selected product information and data required for the purchase process to the server. The server then sends the information required to proceed with the purchase to the online store and notifies the user's device that the purchase is complete.

[1548] Specific examples

[1549] For example, User A starts the application, enters personal information such as name, age, and height, and answers questions about bone structure and personal color diagnosis. This information is sent to the server, and a machine learning algorithm determines the optimal style. User A then takes a video of themselves with a camera and checks which style suits them best in the simulation video sent from the server. The server then retrieves product information from the online store that matches the suggested style and suggests it to User A. User A then selects their preferred item from the list provided and purchases it.

[1550] This allows User A to select the most suitable product based on their personal information and avoid unnecessary purchases. Through this process, consumers can enjoy a more satisfying shopping experience and reduce their environmental impact.

[1551] Prompt Sentence Examples

[1552] Below are some example prompts to input to machine learning algorithms:

[1553] "User A is 25 years old, 160cm tall, weighs 50kg, and wants fashion suitable for business situations. His bone structure diagnosis is ectomorph, and his personal color is spring."

[1554] This allows the server to determine and suggest the best style and color for user A.

[1555] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1556] Program processing flow

[1557] Step 1: Collect user information

[1558] Input: User's personal information (name, age, gender, height, weight, fashion preferences, usage situation) and answers to the bone structure diagnosis and personal color diagnosis.

[1559] process:

[1560] The user launches the application and enters their basic information into the form that appears.

[1561] The user answers diagnostic questions.

[1562] The user terminal collects this information and sends it to the server.

[1563] Output: User personal and diagnostic information sent to the server.

[1564] Step 2: Data storage and analysis

[1565] Input: The user's personal and diagnostic information.

[1566] process:

[1567] The server stores the received data in a database.

[1568] The server inputs the data into the machine learning model and performs the analysis.

[1569] Machine learning algorithms use the collected data to determine the best fashion style and color.

[1570] Output: The result of the judgement (the best style and color combination for the user).

[1571] Step 3: Import your own video

[1572] Input: Video of the user's current pose and face.

[1573] process:

[1574] Users use the application to activate the camera and capture footage of themselves.

[1575] The user device sends the captured video to the server.

[1576] Output: User video data sent to the server.

[1577] Step 4: Generate simulation footage

[1578] Input: User video data and determined style information.

[1579] process:

[1580] The server generates a simulation video using the received video data and the determined style information.

[1581] The server uses image processing techniques (e.g. OpenCV) to overlay a style onto the user's video.

[1582] Output: Simulation video.

[1583] Step 5: Obtaining proposed product information

[1584] Input: Determined style information.

[1585] process:

[1586] The server searches the online store for product information that matches the suggested style.

[1587] The server uses a web scraping tool (e.g. BeautifulSoup) to retrieve and organize product information.

[1588] Output: A list of suggested product information.

[1589] Step 6: Presenting the proposed results

[1590] Input: Proposed product information.

[1591] process:

[1592] The server transmits the proposal results to the user terminal.

[1593] The user terminal displays a list of suggested product information to the user.

[1594] Output: A list of suggestion results shown to the user.

[1595] Step 7: Select and purchase products

[1596] Input: List of proposed product information.

[1597] process:

[1598] The user selects the items to purchase from the suggested products.

[1599] The user terminal transmits the selected product information and necessary purchase data to the server.

[1600] Output: Purchase data sent to the server.

[1601] Step 8: Support with checkout

[1602] Input: User-selected product information and purchase data.

[1603] process:

[1604] The server passes the purchase procedure to the online store's system.

[1605] The server sends a purchase completion notification to the user terminal, and the user confirms it.

[1606] Output: Notification and confirmation that the purchase has been completed.

[1607] (Application example 1)

[1608] 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."

[1609] Conventional fashion suggestion systems are limited to suggesting optimal styles based on a user's personal information, which is insufficient for improving the shopping experience in physical stores. Furthermore, most virtual try-on systems are limited to online stores, making it difficult to use in stores in real time. The present invention aims to solve these problems and make shopping in physical stores more intuitive and satisfying for users.

[1610] 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.

[1611] In this invention, the server includes means for collecting personal information of the user, means for determining the optimal style for the user based on the collected personal information using a machine learning algorithm, means for capturing an image of the user and generating a simulation image of the determined style, means for acquiring suggested product information from an online store, means for presenting the suggested product information to the user so that the user can select and purchase, means for capturing an image of the user in real time using a camera function of the smart glasses, and means for acquiring in-store inventory information and generating a product list to be suggested to the user. This allows the user to check the fashion items that are optimal for them in real time, improving the shopping experience in physical stores.

[1612] "User's personal information" refers to individual information about the user, such as the user's name, age, gender, height, weight, fashion preferences, and usage situation.

[1613] A "machine learning algorithm" is an artificial intelligence technique that uses data to train models to identify patterns and relationships and make predictions.

[1614] "Simulation video" is a video in which the judged style and outfit are superimposed on the user's video, giving the impression of virtually trying on the outfits.

[1615] An "online store" is a website or platform that sells products over the Internet.

[1616] "Smart glasses" are glasses-type wearable devices that have the function of displaying information in the user's field of vision.

[1617] "Camera function" refers to hardware and software that has the function of taking images and videos.

[1618] "Stock information" is information about the quantity and types of products available in the store.

[1619] A "product list" is a list of suggested products that is presented in a format that allows the user to select from them.

[1620] The system embodying this invention mainly collects personal information of users and suggests optimal fashion styles based on that information. Furthermore, this system is designed to enhance users' shopping experience in physical stores, and uses smart glasses to suggest optimal styles in real time.

[1621] Configuration and Operation Procedures

[1622] 1. Collection of User Information

[1623] Users input personal information (such as name, age, gender, height, weight, preferred style, and usage situation) through smart glasses or other devices. This operation is carried out through a dedicated application.

[1624] 2. Body type diagnosis and personal color diagnosis

[1625] Users upload their own images and the system asks them to answer a number of questions to diagnose their body type and personal color. This information is also sent to the server and stored in a database.

[1626] 3. Determining the best style

[1627] The server uses machine learning algorithms based on the collected personal information to determine the best style for the user, using a generative AI model for this process.

[1628] 4. Real-time video capture and simulation

[1629] The camera function of the smart glasses is used to capture real-time footage of the user, and a simulated video is generated with the determined style overlaid on it, which the user can view through the smart glasses.

[1630] 5. Obtaining in-store inventory information

[1631] The server retrieves inventory information from physical stores and generates a list of products to suggest to users, allowing them to check the items available in the store in real time.

[1632] 6. Recommended styles and product suggestions

[1633] The server retrieves the best product information from online and physical stores and suggests it to the user, who can then review the suggestions through the smart glasses and make a purchase decision.

[1634] Specific examples

[1635] For example, when User A enters a physical store, the smart glasses capture User A's image in real time and suggest the best style based on the personal information input in advance. The server uses the results of User A's bone structure and personal color diagnosis to display a simulation image of an outfit that would suit User A.

[1636] The server then retrieves in-store inventory information and generates a list of products that are optimal for User A. User A can then view, select, and purchase items through the smart glasses.

[1637] Hardware and software used

[1638] Hardware: Smart glasses (with camera function), user devices (smartphones, tablets, PCs)

[1639] Software: Machine learning algorithms (generative AI models), image processing technology, online store API, store inventory management system

[1640] Prompt Sentence Examples

[1641] "Please suggest the best fashion style for user A based on their age, gender, build, and preferences. Also, please generate a virtual try-on image and display it in real time. User camera: user_image.jpg"

[1642] By using this prompt, the generative AI model can provide optimal fashion suggestions to users.

[1643] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1644] Step 1:

[1645] The user enters personal information using smart glasses or other devices. The user information input form includes name, age, gender, height, weight, fashion preferences, and usage situation. After input, this information is sent to the server. The entered data is stored in the server's database and used for further processing.

[1646] Step 2:

[1647] The user performs a bone structure diagnosis and a personal color diagnosis. The user uploads an image, and the system asks the user several questions along with the image, prompting the user to answer. This diagnostic information is also sent to the server and stored in a database. The server uses this data to analyze the user's body shape and skin color.

[1648] Step 3:

[1649] The server uses a machine learning algorithm to determine the best style for the user based on the collected personal information and diagnostic results. This data is input into a generative AI model, which then suggests the best style and color. The server then stores the generated style data in a database.

[1650] Step 4:

[1651] The user captures a real-time video of themselves using the camera function of their smart glasses. The device then sends the image captured by the camera to the server. The server then overlays the received image with a pre-determined style to generate a simulated video. The generated simulated video is then sent from the server to the user's smart glasses.

[1652] Step 5:

[1653] The server retrieves product information to be suggested from both online and physical stores. It searches for products that match the style suggested by the AI ​​through the online store's API and the physical store's inventory management system. The server organizes the retrieved product information and generates a list to suggest to the user. The list is then sent from the server to the user's smart glasses.

[1654] Step 6:

[1655] The user checks the suggested product information and selects it using the smart glasses. The user then selects the item they want from the list and proceeds with the purchase using the smart glasses. The device then sends the selected product information and the data required for the purchase to the server, which then forwards it to the online store to complete the purchase. The user can receive a confirmation message through the smart glasses.

[1656] Step 7:

[1657] The server stores the completed purchase information in a database and manages it as the user's purchase history. The user can use this history as reference for their next purchase. The server can also use this data to learn how to make more advanced personalized fashion suggestions.

[1658] 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.

[1659] The system of the present invention not only collects personal information of a user and suggests the most suitable fashion style, but also recognizes the user's emotions and adjusts the information and suggestions provided, and combines an emotion engine to improve the consumer experience. Hereinafter, embodiments for carrying out the present invention will be described in detail.

[1660] This system mainly consists of a user terminal, a server, an emotion engine, and an online store. Users access the system using their own smartphones or computers (user terminals).

[1661] Program processing

[1662] 1. Collection of User Information

[1663] The user launches the application and enters personal information

[1664] The user device displays a screen for entering basic information such as name, age, gender, height, weight, fashion preferences, and usage situation (e.g., business, casual).

[1665] The user performs a bone structure diagnosis and a personal color diagnosis.

[1666] The user terminal presents the user with a question using a plurality of images and prompts the user to input an answer.

[1667] The terminal transmits the input information to the server.

[1668] 2. Automatic judgment by AI

[1669] The server analyzes the user information

[1670] The server stores the received user information in a database.

[1671] The server then feeds the stored information into a machine learning algorithm to analyze the style and color that best suits the user.

[1672] The analysis results are saved in a database.

[1673] 3. Simulation using the person's own video

[1674] The user captures the video using the camera

[1675] The user activates the camera function of the user device to take a video of themselves.

[1676] The terminal transmits the captured video data to the server.

[1677] The server generates the simulation video

[1678] The server generates a simulation video by overlaying the captured user video with the optimal style information determined by machine learning.

[1679] The simulation video is sent to the user's device so that the user can view it.

[1680] 4. Use of Emotion Engine

[1681] User uses camera to recognize emotions

[1682] The user device uses a camera function to capture the user's facial expression and transmits the image to the server.

[1683] The server uses an emotion engine to recognize emotions from the user's facial expressions.

[1684] Emotion engine adjusts suggestions

[1685] Based on the recognized emotion data, the server adjusts the product information and simulation images it proposes to make suggestions that are appropriate for the user.

[1686] For example, if a user is feeling stressed, it will suggest fashion that will help them relax.

[1687] 5. AI suggests suitable clothing from apparel sites

[1688] The server acquires product information from the apparel site based on the proposal results.

[1689] The server searches the online store for products that match the proposed style and retrieves multiple options.

[1690] The server organizes the acquired product information and generates a list to suggest to the user.

[1691] A list of suggested product information is sent to the user's device.

[1692] 6. Users can purchase original items that suit their tastes

[1693] The user selects and purchases from the suggested products

[1694] The user selects the desired product from the product list displayed on the user terminal.

[1695] The terminal presents the user with a form for completing the purchase procedure and prompts the user to enter the necessary information.

[1696] The terminal transmits the input information to the server.

[1697] The server handles the purchase process

[1698] The server sends the user's selected product information and payment information to the online store to complete the purchase.

[1699] The server sends a purchase confirmation message to the user's terminal, allowing the user to confirm the purchase.

[1700] Specific examples

[1701] For example, suppose User B launches the application, enters personal information, and answers questions about bone structure and personal color. This information is sent to the server, where a machine learning algorithm determines the optimal style. Next, User B takes a video of themselves with a camera and checks which style suits them best in the simulation video sent from the server. At the same time, the emotion engine analyzes User B's facial expressions and suggests a casual style if they are relaxed, or a style that gives them a sense of security if they are nervous. This suggestion is based on information obtained from the online store, and User B selects and purchases the most suitable items. This process allows User B to achieve high satisfaction while reducing their environmental impact through purchases.

[1702] The processing flow will be explained below.

[1703] Step 1:

[1704] The user launches the application and enters personal information

[1705] The user launches the application on their device and operates a screen to enter basic information such as name, age, gender, height, weight, fashion preferences, and usage situation (e.g., business, casual).

[1706] The terminal stores the information entered by the user and transmits it to the server.

[1707] Step 2:

[1708] The user performs a bone structure diagnosis and a personal color diagnosis.

[1709] The user device displays multiple images and options for skeletal diagnosis and prompts the user to choose the one that best suits them.

[1710] Similarly, a number of questions and images are presented for personal color diagnosis, and the user answers them.

[1711] The terminal obtains the user's answer and sends it to the server.

[1712] Step 3:

[1713] The server analyzes the user information

[1714] The server stores the received personal information and diagnostic results in a database.

[1715] The server runs machine learning algorithms based on the stored information to analyze the style and color that best suits the user.

[1716] The analysis results are stored in a database for further processing.

[1717] Step 4:

[1718] The user captures the video using the camera

[1719] The user activates the camera function of the user device and takes an image of their current posture and face.

[1720] The terminal transmits the captured video data to the server.

[1721] Step 5:

[1722] The server generates the simulation video

[1723] The server generates a simulation video using the captured user video and optimal style information determined by machine learning.

[1724] The server transmits the generated simulation video to the user terminal so that the user can visually check it.

[1725] Step 6:

[1726] User uses camera to recognize emotions

[1727] The user captures their facial expression using the camera function of their device.

[1728] The terminal transmits the acquired video data to the server.

[1729] Step 7:

[1730] The server recognizes emotions using an emotion engine

[1731] The server analyzes the transmitted video data and uses an emotion engine to recognize emotions from the user's facial expressions.

[1732] The user's psychological state is determined based on the recognized emotional data.

[1733] Step 8:

[1734] Emotion engine adjusts suggestions

[1735] The server then adjusts the product information and simulation images it recommends based on the user's emotional data. For example, if it determines that the user is relaxed, it will suggest a casual, relaxed style.

[1736] The adjusted proposal content is sent to the user device.

[1737] Step 9:

[1738] The server acquires product information from the apparel site based on the proposal results.

[1739] The server retrieves multiple options from the online store via API, searching for products that match the user's best style.

[1740] The server analyzes the acquired product information and selects clothing candidates that are best suited to the user.

[1741] A list of suggested product information is sent to the user's device.

[1742] Step 10:

[1743] The user selects and purchases the suggested product

[1744] The user selects the desired product from the product list displayed on the user terminal.

[1745] The terminal displays a form for the user to complete the purchase procedure and prompts the user to enter the necessary information.

[1746] The terminal transmits the input information to the server.

[1747] Step 11:

[1748] The server handles the purchase process

[1749] The server sends the user's selected product information and payment information to the online store to complete the purchase.

[1750] The server sends a purchase confirmation message to the user's terminal, allowing the user to confirm the purchase.

[1751] This system allows users to receive suggestions for optimal fashion styles based on their personal information and emotional data, reducing unnecessary purchases and waste, and easing the burden on the environment.

[1752] Example 2

[1753] 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."

[1754] Conventional fashion suggestion systems only considered the user's personal information and preferences, and therefore did not provide flexible suggestions that took into account the user's real-time emotions and circumstances. Furthermore, they only provided fashion suggestions in the form of still images or text, and lacked a way for users to visually confirm how the fashion would look when actually worn. This led to problems such as lower user satisfaction and a decline in purchasing motivation.

[1755] 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 collecting personal information of the user, means for determining the optimal style for the user based on the collected personal information using a machine learning algorithm, means for capturing an image of the user and generating a simulation image of the determined style, means for analyzing the user's facial expression and recognizing emotions, means for adjusting the suggestions based on the recognized emotions, means for acquiring information on products to be suggested from an online store, and means for presenting the suggested product information to the user so that the user can select and purchase. This makes it possible to reflect the user's real-time emotions and provide an image of how the product will actually look when worn, thereby making it possible to make more personalized fashion suggestions and improve user satisfaction and purchasing motivation.

[1756] "User's personal information" refers to basic information about an individual, such as the user's name, age, gender, height, weight, fashion preferences, and usage situation.

[1757] "Machine learning algorithms" are algorithms that analyze optimal fashion styles and colors based on collected data, and primarily use technologies such as TensorFlow and PyTorch.

[1758] A "simulation video" is a moving or still image generated by superimposing a determined fashion style onto a user's video.

[1759] "Means for recognizing emotions" refers to technology that analyzes a user's facial expression data and identifies the user's current emotional state, such as using Microsoft Azure's Emotion API.

[1760] The "means for adjusting the content of suggestions" is a technology that appropriately changes or adjusts the fashion and product information suggestions based on the recognized user emotions.

[1761] An "online store" is a website that provides product information and sells products via the Internet, and examples include Amazon and Rakuten.

[1762] "Product information" refers to data about a product, such as its name, price, size, color, material, and photo, obtained from an online store.

[1763] MODE FOR CARRYING OUT THE INVENTION

[1764] The system of the present invention not only collects personal information of the user and suggests the most suitable fashion style, but also recognizes the user's emotions and adjusts the suggestions accordingly, and combines an emotion engine to improve the consumer experience. The following describes in detail the embodiments of the present invention.

[1765] System configuration

[1766] This system mainly consists of a user terminal, a server, an emotion engine, and an online store. Users access the system using their own smartphones or computers (user terminals).

[1767] Hardware and software used

[1768] User device: Uses a smartphone or computer. Provides an interface for users to input information and use a camera.

[1769] Server: Receives and stores information from users, processes and analyzes the data using machine learning algorithms and emotion engines.

[1770] Machine learning algorithms: using frameworks such as TensorFlow and PyTorch.

[1771] Emotion engine: Uses services such as Microsoft Azure's Emotion API.

[1772] Online store: Obtain product information from online e-commerce sites (e.g., Amazon, Rakuten).

[1773] Program processing

[1774] 1. Collection of User Information

[1775] The user starts the application and enters personal information (such as name, age, gender, height, weight, fashion preferences, and usage situation). Furthermore, the application performs a bone structure diagnosis and a personal color diagnosis, and answers questions using multiple images. This information is then sent from the user's device to the server.

[1776] 2. Automatic judgment by AI

[1777] The server stores the received user information in a database and uses machine learning algorithms to analyze the optimal style and color. The analysis results are then stored in the database.

[1778] 3. Simulation using the person's own video

[1779] The user captures a video of themselves using a camera, and the device sends the video data to the server. The server then overlays the captured user video with the optimal style information determined by machine learning to generate a simulation video, which is then sent to the user's device. This allows the user to visually check the style that suits them best.

[1780] 4. Use of Emotion Engine

[1781] The user captures their facial expressions using a camera, and the device sends the video to a server. The server then uses an emotion engine to recognize the emotion from the user's facial expressions and adjusts the recommendations based on the recognized emotion data. For example, if the user is feeling stressed, the server will suggest relaxing fashion.

[1782] 5. AI suggests suitable clothing from apparel sites

[1783] The server then searches online stores for matching product information based on the results of the suggestions, retrieves multiple options, and organizes the information before sending it to the user's device.

[1784] 6. Users can purchase original items that suit their tastes

[1785] The user selects from the suggested products and completes the purchase. The user's device displays a form for the purchase and asks them to enter the necessary information. The server then sends this information to the online store to complete the purchase.

[1786] Specific examples

[1787] For example, suppose User B launches the application, enters personal information, and answers questions about bone structure and personal color. This information is sent to the server, where a machine learning algorithm determines the optimal style. Next, User B takes a video of themselves with a camera and checks which style suits them best in the simulated video sent from the server. At the same time, the emotion engine analyzes User B's facial expressions and suggests a casual style if he is relaxed, or a style that gives him a sense of security if he is nervous. These suggestions are based on information obtained from the online store, and User B selects and purchases the most suitable items.

[1788] Prompt Sentence Examples

[1789] Here is an example of a prompt that allows the user to ask the system a specific question:

[1790] "I'm a 34-year-old man, 180cm tall and 75kg. I like casual style and am looking for fashion that I can wear in business casual situations. I took a recent photo of myself. Please suggest the best fashion style based on this photo. I'd also like you to use the emotion engine to suggest a style that takes my current mood into account."

[1791] Based on this prompt, the system collects and analyzes the user's information and suggests the most suitable fashion style and corresponding products.

[1792] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1793] Step 1: User launches application and enters personal information

[1794] Input: Basic information of the user (name, age, gender, height, weight, fashion preferences, usage situation, etc.).

[1795] Operation: The user launches the application on their smartphone or computer and displays the personal information entry screen. The user enters information for each item.

[1796] Data processing and calculation: The user terminal organizes the input information and converts it into an appropriate format.

[1797] Output: The organized personal information is sent to the server.

[1798] Step 2: User's procedure for performing bone structure diagnosis and personal color diagnosis

[1799] Input: User answers (answers to questions about bone structure and personal color).

[1800] Operation: The user terminal displays a number of questions to the user, who then enters answers to the displayed questions.

[1801] Data processing and calculation: The user terminal converts the input answers into a data format and extracts the necessary diagnostic data.

[1802] Output: The converted diagnostic data is sent to the server.

[1803] Step 3: The server analyzes the user information and determines the most suitable style

[1804] Input: Your personal and diagnostic data.

[1805] How it works: The server stores the received personal information and diagnostic data in a database, then inputs the stored information into a machine learning algorithm for analysis.

[1806] Data processing and calculation: Using machine learning algorithms (such as TensorFlow and PyTorch), we analyze the fashion style and color that best suits the user.

[1807] Output: The analysis results are saved in a database.

[1808] Step 4: User instructions for capturing video using the camera

[1809] Input: User's video (video data captured by a camera).

[1810] How it works: The user activates the device's camera and takes a video of themselves.

[1811] Data processing and calculation: The user device converts the captured video data into an appropriate format and adjusts the size and image quality.

[1812] Output: The converted video data is sent to the server.

[1813] Step 5: Procedure for the server to generate the simulation video

[1814] Input: User's video data and analysis results (optimal style information).

[1815] How it works: The server overlays style information determined by machine learning onto the captured user video.

[1816] Data processing and calculation: Using image processing technology, the user's video and style information are combined to generate a simulation video.

[1817] Output: The generated simulation video is sent to the user's device.

[1818] Step 6: User uses camera to capture facial expressions and recognize emotions

[1819] Input: User's facial expression video (video data captured by a camera).

[1820] Action: The user activates the device's camera and captures their facial expressions.

[1821] Data processing and calculation: The device converts the captured facial expression video into an appropriate format and sends it to the server.

[1822] Output: The converted facial expression video data is sent to the server.

[1823] Step 7: The server uses the emotion engine to recognize the user's emotions and adjust the suggestions.

[1824] Input: User's facial expression data.

[1825] How it works: The server inputs the received facial expression data into an emotion engine (such as Microsoft Azure's Emotion API) to recognize emotions.

[1826] Data processing and calculation: Analyzes emotional data to understand the user's current emotional state, and adjusts suggestions based on the analysis results.

[1827] Output: The adjusted proposal is sent to the user's device.

[1828] Step 8: Procedure for the server to obtain product information from the apparel site based on the proposal results

[1829] Input: Adjusted proposal.

[1830] How it works: The server searches online stores for matching products based on the suggested style.

[1831] Data processing and calculation: Utilizing the online store's API, we organize the obtained product information.

[1832] Output: The organized product information is sent to the user's terminal.

[1833] Step 9: User selects and purchases from the suggested products

[1834] Input: Suggested product information.

[1835] How it works: The user selects the product they want from a list of products displayed on the device, and the device displays a checkout form and asks them to enter the necessary information.

[1836] Data processing and calculation: The terminal sends the input information to the server, which then transmits it to the online store.

[1837] Output: A purchase confirmation message is sent to the user's device.

[1838] (Application example 2)

[1839] 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."

[1840] When shopping at traditional online or physical stores, it was difficult for users to fully reflect their personal information or their mood at the time when selecting the perfect fashion item. Furthermore, it often took time and effort for users to try on items, which often led to an unsatisfactory consumer experience. Furthermore, since appropriate suggestions were not made taking emotions into consideration, user satisfaction could decrease.

[1841] 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.

[1842] In this invention, the server includes means for collecting personal information of the user, means for determining the optimal style for the user based on the collected personal information using a machine learning algorithm, means for capturing an image of the user and generating a simulation image of the determined style, means for obtaining suggested product information from an online store, means for presenting the suggested product information to the user so that the user can select and purchase, means for analyzing the user's emotions and adjusting the suggested content based on the analysis results, and means for allowing the user to visually check a simulation of trying on the suggested items in real time. This enables the server to recommend optimal fashion items taking into account the user's personal information and emotions, and to provide an effective try-on experience.

[1843] "Personal information" is a general term for data necessary for fashion suggestions, such as personal information about the user, fashion preferences, body type diagnosis, and personal color diagnosis information.

[1844] "Machine learning algorithm" is an artificial intelligence technology that determines the best fashion style for a user based on collected personal information.

[1845] A "simulation video" is a video of a virtual try-on that is generated by overlaying the determined style onto a video of the user.

[1846] "Emotion analysis" is a technology that recognizes and analyzes a user's emotional state at any given time based on their facial expressions and behavior.

[1847] "Adjusting suggestion content" is the process of appropriately changing the fashion suggestions presented to the user based on the results of sentiment analysis.

[1848] "Real-time try-on simulation" is a technology that simulates the user trying on suggested items instantly, allowing them to visually confirm the experience.

[1849] "Acquisition of product information from online stores" is a data collection process in which suggested product information is acquired from online stores and provided to users.

[1850] "User Selection and Purchasing Instrument" means the interface and support system through which a user can review suggested product information and make a selection or purchase.

[1851] The system of the present invention is designed to suggest the most suitable fashion items to a user while they are shopping in a physical store using smart glasses. The details of the embodiment of the system are described below.

[1852] Program processing

[1853] Collection of User Information

[1854] The user puts on the smart glasses and launches the application. First, the user enters their personal information into the application. This information includes name, age, gender, height, weight, fashion preference, and usage situation (e.g., business, casual). This information is sent via Wi-Fi to the server and stored in a database.

[1855] User sentiment analysis

[1856] The smart glasses use a built-in camera to capture the user's facial expressions. The captured images are sent to a server, where an emotion recognition engine (e.g., IBM Watson or Microsoft Azure Emotion API) is used to analyze the user's emotional state. The analysis results are applied in real time and reflected in the recommendations.

[1857] Style detection using machine learning algorithms

[1858] The server uses machine learning algorithms (e.g., TensorFlow, PyTorch) to determine the best style for each user based on the collected personal information. The results of this style determination are stored in a database.

[1859] Adjusting the proposal

[1860] The server then adjusts the fashion suggestions it presents to the user based on the results of the emotion analysis. For example, if the user is relaxed, it will suggest a casual style, and if they are nervous, it will suggest a formal style.

[1861] Simulation video generation

[1862] When a user is interested in a particular item in a physical store, they look at the glasses and say, "Tell me more about this shirt." The server processes this request and retrieves the item's details. The server then combines the user's image with the defined style to generate a simulated image, which is then displayed on the smart glasses' display.

[1863] Product Information and Checkout

[1864] The server retrieves the suggested product information from the online store and displays it to the user. The user checks the product list through the smart glasses, selects, and completes the purchase. The result of the purchase is sent to the server, and the purchase is completed at the online store.

[1865] Specific examples

[1866] For example, User A wears smart glasses and uses the application in a physical store. User A finds a shirt he likes in the store and, while looking at the shirt, issues a voice command saying, "Tell me more about this shirt." The camera in the smart glasses captures User A's facial expression, and the server analyzes from the expression that User A is relaxed. Detailed information about the suggested shirt and a try-on simulation are displayed on the smart glasses, allowing User A to check whether the shirt suits him or her. As a result, User A selects the shirt and completes the purchase process through the smart glasses.

[1867] Example prompt sentence:

[1868] You are a user of an emotion-aware fashion advisor application using smart glasses. The app analyzes your emotions and suggests the best fashion items for you. Imagine staring at a particular item in a physical store and speaking to the smart glasses, saying, "Tell me more about this shirt." The smart glasses then display detailed information about the item and a simulated try-on.

[1869] In this way, the user can receive suggestions for the most suitable fashion items that take into consideration personal information and emotions, providing an effective try-on experience.

[1870] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1871] Step 1:

[1872] Entering user information

[1873] The user puts on the smart glasses and launches the application. The user enters personal information such as name, age, gender, height, weight, fashion preferences, and usage situation. This information is sent via Wi-Fi to the server, which stores the received information in a database for later processing.

[1874] Step 2:

[1875] Video capture for emotion analysis

[1876] The camera in the smart glasses captures the user's facial expressions in real time. The captured video is then sent to a server via Wi-Fi. The server then inputs the received video data into an emotion recognition engine (e.g., IBM Watson, Microsoft Azure Emotion API) to analyze the user's emotions. The analysis results are then returned to the server for use in the next step.

[1877] Step 3:

[1878] Style Determination

[1879] Based on the personal information collected in step 1, the server uses machine learning algorithms (e.g., TensorFlow, PyTorch) to determine the style that best suits the user. The results of this determination are stored in a database and used to adjust future recommendations. Specifically, the style is determined by analyzing multiple features using data such as height, weight, bone structure diagnosis, and personal color diagnosis results.

[1880] Step 4:

[1881] Adjusting the proposal

[1882] The server combines the results of the emotion analysis obtained in step 2 with the style information determined in step 3 to adjust the fashion item suggestions presented to the user. For example, if the user is relaxed, it will suggest a casual style, and if the user is nervous, it will suggest a formal style. This suggestion is important for providing the user with the optimal experience.

[1883] Step 5:

[1884] Simulation video generation

[1885] When a user is interested in a particular item through the smart glasses, they issue a voice command such as "Tell me more about this shirt." This request is sent to the server via Wi-Fi. The server processes the request and retrieves detailed information about the item from online stores (e.g., Amazon, Rakuten). Based on the retrieved information, the server combines the user's image and style information to generate a simulation image. This simulation image is then displayed on the smart glasses' display.

[1886] Step 6:

[1887] Product information and purchasing assistance

[1888] The server retrieves product information from the online store and displays it in a list for the user. The user checks the product information through the smart glasses and selects the desired product. The selected information is sent back to the server to assist in the purchase process. The server then sends the purchase information to the online store to complete the purchase process. Once the purchase is complete, a confirmation message is sent to the user.

[1889] In this way, users can receive recommendations for the most suitable fashion items that take into account their personal information and emotions, enabling an effective try-on experience and a smooth purchasing process.

[1890] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1891] 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.

[1892] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1893] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1894] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1895] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1896] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1897] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1898] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1899] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1900] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1901] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1902] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1903] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1904] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1905] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1906] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1907] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1908] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1909] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1910] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1911] The following is further disclosed regarding the above embodiment.

[1912] (Claim 1)

[1913] means of collecting personal information about users;

[1914] A method for determining the best style for a user using machine learning algorithms based on collected personal information;

[1915] a means for capturing a user's video and generating a simulation video based on the determined style;

[1916] A means for obtaining product information to be proposed from an online store;

[1917] A means for presenting suggested product information to the user and allowing the user to select and purchase;

[1918] A system including:

[1919] (Claim 2)

[1920] 10. The system of claim 1, further comprising means for collecting a user's bone structure diagnosis and personal color diagnosis information.

[1921] (Claim 3)

[1922] 10. The system of claim 1, further comprising means for using image processing techniques to generate a simulated image by overlaying the determined style onto an image of the user.

[1923] "Example 1"

[1924] (Claim 1)

[1925] means of collecting personal information about users;

[1926] A method for determining the best style for a user using machine learning algorithms based on collected personal information;

[1927] a means for capturing a user's video and generating a simulation video based on the determined style;

[1928] A means for obtaining product information to be proposed from an online store;

[1929] A means for presenting suggested product information to the user and allowing the user to select and purchase;

[1930] a means for storing user personal and diagnostic information in a database and analyzing that information;

[1931] A means for capturing an image of the user's current posture and face when generating the simulation image;

[1932] A means for organizing the acquired product information and generating a list to suggest to the user;

[1933] A means to assist with checkout based on user selections;

[1934] A system including:

[1935] (Claim 2)

[1936] 10. The system of claim 1, further comprising means for collecting a user's bone structure diagnosis and personal color diagnosis information.

[1937] (Claim 3)

[1938] 10. The system of claim 1, further comprising means for using image processing techniques to generate a simulated image by overlaying the determined style onto an image of the user.

[1939] "Application Example 1"

[1940] (Claim 1)

[1941] means of collecting personal information about users;

[1942] A method for determining the best style for a user using machine learning algorithms based on collected personal information;

[1943] a means for capturing a user's video and generating a simulation video based on the determined style;

[1944] A means for obtaining product information to be proposed from an online store;

[1945] A means for presenting suggested product information to the user and allowing the user to select and purchase;

[1946] a means for capturing an image of a user in real time using a camera function of the smart glasses;

[1947] A means for acquiring in-store inventory information and generating a product list to be suggested to a user;

[1948] A system including:

[1949] (Claim 2)

[1950] 10. The system of claim 1, further comprising means for collecting a user's bone structure diagnosis and personal color diagnosis information.

[1951] (Claim 3)

[1952] 10. The system of claim 1, further comprising means for using image processing techniques to generate a simulated image by overlaying the determined style onto an image of the user.

[1953] "Example 2: Combining Emotion Engines"

[1954] (Claim 1)

[1955] means of collecting personal information about users;

[1956] A method for determining the best style for a user using machine learning algorithms based on collected personal information;

[1957] a means for capturing a user's video and generating a simulation video based on the determined style;

[1958] A means of analyzing the user's facial expressions and recognizing their emotions;

[1959] a means for tailoring recommendations based on the perceived sentiment;

[1960] A means for obtaining product information to be proposed from an online store;

[1961] A means for presenting suggested product information to the user and allowing the user to select and purchase;

[1962] A system including:

[1963] (Claim 2)

[1964] 10. The system of claim 1, further comprising means for collecting a user's bone structure diagnosis and personal color diagnosis information.

[1965] (Claim 3)

[1966] 10. The system of claim 1, further comprising means for using image processing techniques to generate a simulated image by overlaying the determined style onto an image of the user.

[1967] "Application example 2 when combining emotion engines"

[1968] (Claim 1)

[1969] means of collecting personal information about users;

[1970] A method for determining the best style for a user using machine learning algorithms based on collected personal information;

[1971] a means for capturing a user's video and generating a simulation video based on the determined style;

[1972] A means for obtaining product information to be proposed from an online store;

[1973] A means for presenting suggested product information to the user and allowing the user to select and purchase;

[1974] A means for analyzing user sentiment and adjusting the content of suggestions based on the analysis results;

[1975] a means for allowing the user to visually simulate trying on the suggested items in real time; and

[1976] A system including:

[1977] (Claim 2)

[1978] 10. The system of claim 1, further comprising means for collecting a user's bone structure diagnosis and personal color diagnosis information.

[1979] (Claim 3)

[1980] 10. The system of claim 1, further comprising means for using image processing techniques to generate a simulated image by overlaying the determined style onto an image of the user. [Explanation of symbols]

[1981] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means of collecting personal information about users; A method for determining the best style for a user using machine learning algorithms based on collected personal information; a means for capturing a user's video and generating a simulation video based on the determined style; A means for obtaining product information to be proposed from an online store; A means for presenting suggested product information to the user and allowing the user to select and purchase; A system including:

2. The system according to claim 1, further comprising means for collecting the user's bone structure diagnosis and personal color diagnosis information.

3. 10. The system of claim 1, further comprising means for using image processing techniques to generate a simulated image by superimposing the determined style onto an image of the user.

Images