system

Abstract

We provide the system. [Solution] Image processing means for processing image data obtained from a user to extract features of a person, An analysis means for analyzing the user's behavioral history data to identify their fashion preferences, A recommendation generation method that generates fashion suggestions based on identified characteristics and preferences, as well as current circumstances and uses, A presentation means that provides the user with fashion suggestions generated by the recommendation generation means, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern times, many people lack confidence in their sense of fashion choices and have difficulty choosing clothing suitable for social and personal scenes. Also, there is a problem that systems capable of providing fashion advice suitable for individual styling preferences, body types, and characteristics are limited, and it is impossible to obtain personalized and specific proposals.

Means for Solving the Problems

[0005] To address these challenges, the present invention provides a system that recognizes a person's unique characteristics based on their image data and identifies their individual fashion preferences by analyzing their behavioral history data. Furthermore, it provides a means of offering personalized advice to the user by suggesting fashion that is suitable for the current situation and purpose, according to the identified characteristics and preferences. As a result, users can choose the most appropriate fashion for the time, place, and occasion, thereby promoting self-expression and improving their social credibility.

[0006] A "user" is an individual who uses the system and provides image data and behavioral history data.

[0007] "Image data" refers to digital data containing visual information of a person, which is entered into the system by the user.

[0008] "Features" refer to data about a user's appearance extracted from image data, including information such as skin color, body type, and facial features.

[0009] "Behavioral history data" refers to digital information recorded based on a user's past actions and choices, including browsing history and purchase history.

[0010] "Analysis means" refers to a processing method or device for analyzing a user's behavioral history data and identifying their fashion preferences.

[0011] "Recommendation generation means" refers to a processing method or apparatus for generating fashion suggestions suitable for a user based on analyzed feature information and preference information.

[0012] "Presentation means" refers to methods or devices for providing generated fashion suggestions to users visually or audibly. [Brief explanation of the drawing]

[0013] [Figure 1]This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0019] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), etc.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the 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.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0027] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] The system according to the present invention allows a user to send images taken using their own device to a server, and then provides the user with optimal fashion suggestions based on those images and behavioral history data. First, the server receives the user's image data and processes it to analyze facial and body features. This analysis uses facial recognition technology and image processing technology. For example, individual features such as skin color, body type, and hairstyle are extracted. Based on this information, the system recommends the most suitable colors and styles for the user.

[0035] Meanwhile, the server collects user behavioral data and analyzes what fashion items the user has viewed and purchased in the past to reveal their style preferences. This analysis reveals trends in brands and items that the user frequently shows interest in.

[0036] Next, the server generates optimal fashion suggestions based on these analysis results and the current situation and purpose (TPO). These suggestions include clothing combinations and accessories that are likely to suit the user. For example, if the user is attending a casual event the next day, the server might suggest jeans and a brightly colored top.

[0037] The generated fashion suggestions are sent from the server to the user's terminal and presented to the user visually. Users can use these suggestions to make daily fashion choices and enhance their enjoyment of fashion by purchasing the suggested styles when shopping.

[0038] This system allows users to receive personalized fashion advice based on their own characteristics, making it easy to choose appropriate attire for different occasions.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The user launches a dedicated app on their device and takes or selects a full-body image of themselves. The captured image is uploaded to the server via the device.

[0042] Step 2:

[0043] The server receives images sent by users and applies image processing algorithms to analyze facial and body features. Specifically, skin color, body shape, and facial features are extracted.

[0044] Step 3:

[0045] The server retrieves user behavior history data from the database. This includes previously viewed fashion items, purchase history, and search queries.

[0046] Step 4:

[0047] The server analyzes the user's behavioral history to identify their fashion preferences. This analysis uses machine learning techniques to identify brands and styles that the user tends to favor.

[0048] Step 5:

[0049] The server takes into account the current time, location, and purpose (TPO) to generate fashion recommendations that reflect the user's characteristics and preferences. These recommendations include suggestions for specific clothing and accessories.

[0050] Step 6:

[0051] The server sends the generated recommendation information to the user's device. The user can review the suggestions received on their device and consider whether to adopt the suggested style.

[0052] (Example 1)

[0053] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0054] Modern consumers tend to seek personalized fashion suggestions based on their individual characteristics and personalities. However, conventional systems have struggled to generate suggestions that adequately reflect the individual characteristics and preferences of users, resulting in unsatisfactory recommendations. To address this challenge, there is a need for a method to generate fashion suggestions that fully take into account the user's characteristics and behavioral history.

[0055] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0056] In this invention, the server includes an image analysis means for processing image information acquired from the user to extract the person's features, a data analysis means for analyzing the user's behavioral history information to identify their fashion preferences, and a suggestion generation means for generating fashion suggestions that are tailored to the identified features and preferences, as well as the current conditions and intended use. This makes it possible to provide personalized fashion suggestions that take into account the individual characteristics and preferences of the user.

[0057] A "user" refers to a person who uses the system to receive fashion suggestions based on their own information.

[0058] "Image information" refers to photographs and image data taken by users, and is used to analyze the user's physical characteristics.

[0059] "Image analysis means" refers to technology that processes image information received from a user and extracts physical and visual characteristics.

[0060] "Behavioral history information" refers to data on fashion-related actions a user has taken in the past, such as browsing and purchasing.

[0061] "Data analysis methods" refer to processes and technologies used to analyze behavioral history information and identify a user's fashion preferences.

[0062] "Suggestion generation means" refers to the process of creating optimal fashion suggestions for the user based on information obtained from image analysis means and data analysis means.

[0063] "Display means" refers to methods or devices for visually presenting generated fashion suggestions to users.

[0064] This invention is a system for users to receive fashion suggestions based on their individual characteristics, and implements a process to suggest appropriate fashion styles based on the user's image information and behavioral history information.

[0065] First, the user prepares to receive fashion suggestions using their device. The user takes an image using the camera on their device and sends the image information to the server. To ensure high security, the server uses the HTTPS protocol to transmit the image information.

[0066] When the server receives image information from a user, it first processes it using image analysis tools. Here, the server executes scripts in programming languages ​​such as Python and utilizes image processing software like OpenCV to extract visual features such as facial shape, skin tone, and body type. Furthermore, the server uses a generative AI model to input prompt messages and perform individual fashion style analysis. A concrete example of a prompt message might be, "Create fashion suggestions for a woman with light-toned skin who usually prefers office casual attire."

[0067] The server also analyzes user behavior history information. The database stores users' fashion-related behavior, and the server analyzes this data using data analysis tools. Big data analysis tools such as Apache Spark are used to identify the brands and styles that users prefer.

[0068] Based on these analysis results, the server uses a suggestion generation mechanism to generate optimal fashion suggestions for the user. The generated suggestions include clothing combinations and accessory selections tailored to specific events or occasions. The generated suggestions are sent to the user's device and displayed visually. By viewing these visual suggestions, the user can make their daily fashion choices more enjoyable and make more appropriate choices.

[0069] This system provides technology that enhances the user experience, meets individual needs, and establishes a new standard for fashion proposals.

[0070] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0071] Step 1:

[0072] The user launches a camera app on their device and takes a picture to receive fashion suggestions. The input is image data captured by the device's camera, which is then sent to the server. The device securely transfers this image data to the server using the HTTPS protocol.

[0073] Step 2:

[0074] The server receives image data sent from the terminal. Using the received image data as input, the server uses image analysis tools. Here, image processing libraries such as OpenCV are used to analyze the image and extract the user's physical characteristics, such as face shape, skin color, and body type, as vector data. The output of this analysis, the obtained feature information, is passed to the next process.

[0075] Step 3:

[0076] The server retrieves user behavior history information from a database. This input includes past browsing and purchase history. Using data analysis tools, the server analyzes this data with big data processing tools such as Apache Spark to quantify user preferences. The results of the analysis are output as a list of the user's preferences and areas of interest.

[0077] Step 4:

[0078] The server uses a suggestion generation mechanism, taking feature information obtained through image analysis and preference information based on behavioral history as input. It utilizes a generation AI model to provide fashion suggestions using prompts. An example prompt used is, "Please create fashion suggestions for a woman with light skin tone who usually prefers office casual attire." The output is a fashion suggestion customized for the user.

[0079] Step 5:

[0080] The server sends the generated fashion suggestions to the user's device. The data is securely transferred using HTTPS, and the suggestions are displayed on the device's screen. The user visually confirms this output and performs actions to support their daily fashion choices. This allows the user to use the suggested styles as a reference when making purchase decisions at physical stores or online stores.

[0081] (Application Example 1)

[0082] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0083] In modern society, consumers are faced with a wide variety of fashion items to choose from, but selecting the appropriate fashion for any given situation is a particularly difficult challenge. Because there is a lack of real-time information on fashion that suits oneself, consumers spend a great deal of time and effort choosing the best outfit for themselves.

[0084] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0085] In this invention, the server includes information processing means for processing image data acquired from a user to extract the person's characteristics, data analysis means for analyzing the user's behavioral history data to identify preferences, and recommendation generation means for generating suggestion information according to the identified characteristics and preferences, as well as the situation and purpose. This allows the user to visually confirm fashion suggestions that suit them in real time and make appropriate choices quickly.

[0086] "Information processing means" refers to a technical device or function that analyzes image data obtained from a user and extracts human characteristics from the image.

[0087] "Data analysis means" refers to a technical device or function that investigates a user's behavioral history data and identifies their preferences and tastes based on that data.

[0088] A "recommendation generation method" is a technical device or function that generates optimal suggestion information for the user based on extracted characteristics and preferences, as well as the situation and application.

[0089] "Presentation means" refers to a technical device or function that provides generated proposal information to the user visually, for example, by displaying it in real time via a smart device.

[0090] The system implementing this invention involves the coordinated operation of a user, a terminal, and a server. The user acquires image data using a terminal such as smart glasses. The terminal is equipped with communication capabilities to transmit the image data to the server. The server analyzes the received image data using image processing software such as OpenCV to extract features such as the user's face shape, physique, and skin color.

[0091] The server further analyzes the user's past behavior history using data analysis tools such as Pandas to identify the user's preferred fashion trends from the database. This reveals specific brands and styles.

[0092] Based on these analysis results, the server uses generative AI models such as TENSORFLOW (registered trademark) to generate fashion suggestions that are best suited to the user. The user's characteristics, preferences, and current situation and purpose are considered during this process. An example of a prompt generated during this process would be, "Please suggest an outfit suitable for a 30-year-old woman, casual, and attending a cafe event."

[0093] The generated fashion suggestions are sent to the user's device in real time. The user can visually check the suggested clothing and styles on their device and make appropriate fashion choices based on that information.

[0094] As a concrete example, when a user participates in a casual book club at a cafe, a casual yet stylish combination of a denim jacket and a white shirt is suggested. This system allows users to easily choose the perfect outfit for themselves.

[0095] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0096] Step 1:

[0097] The user takes a picture of themselves using their device and sends that image to the server. Image data acquired by the device's camera becomes the input, and the image data is sent to the server via the communication function.

[0098] Step 2:

[0099] The server processes the received image data using OpenCV to extract features including the user's face shape, body type, and skin color. The input data is image data, and its features are analyzed using OpenCV's image processing techniques. The output provides the user's feature parameters.

[0100] Step 3:

[0101] The server uses Pandas to analyze user behavioral data and identify fashion preferences from past purchase and browsing history. The input data is behavioral data, which is analyzed using Pandas, and the output is a trend in preferences.

[0102] Step 4:

[0103] The server uses TensorFlow to run a generative AI model based on extracted features and preferences to generate optimal fashion suggestions for the user. In this process, feature parameters and preference data are used as input data, and specific fashion suggestions are generated as output.

[0104] Step 5:

[0105] The server sends the generated fashion suggestions to the user's device. The device visually displays the received fashion suggestions and provides the user with their content. The input data is the fashion suggestions, which are conveyed to the user visually in real time via the device's display function.

[0106] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0107] The system according to the present invention provides fashion suggestions based on the user's image data and behavioral history data, and further combines this with emotion analysis means to recognize the user's emotions. This system analyzes the user's facial and body features and obtains information based on the images when the user sends images taken with a terminal to a server. The server performs image processing to identify the user's skin color, body shape, and facial shape in particular.

[0108] In parallel, the server analyzes the user's behavioral history. This information includes fashion items previously viewed, items purchased, and frequently accessed brand pages. The analysis results are used to identify the user's fashion preferences.

[0109] Furthermore, this invention incorporates a new emotion analysis means. The server analyzes the user's facial expressions from the received image data and estimates the user's emotional state. For example, if the user is smiling, it is judged to be a positive emotion, and a more adventurous style of fashion suggestion may be appropriate. On the other hand, if a negative emotion is detected, a style that will reassure the user is provided.

[0110] The fashion suggestions generated in this way are sent by the server to the user's terminal and presented visually. The user can review the suggestions and decide whether to purchase new fashion items based on the suggested style.

[0111] This system allows users to receive personalized fashion advice tailored to their current emotions, characteristics, and preferences, resulting in a more satisfying shopping experience.

[0112] The following describes the processing flow.

[0113] Step 1:

[0114] Users launch a dedicated application on their device and take or select a full-body image that captures their facial expressions, then send it to the server. Users can also optionally add comments about their preferred style or current mood.

[0115] Step 2:

[0116] The server processes the received image data and performs face recognition and expression analysis. First, it detects facial features, and then uses an emotion analysis algorithm to identify the user's emotions. For example, it identifies positive or negative emotions from facial expressions such as smiles or confusion.

[0117] Step 3:

[0118] The server then extracts visual features from the image, such as skin tone, body shape, and facial features. This makes it easier to suggest colors and styles that suit the user. This data is also used to filter fashion items stored in the database.

[0119] Step 4:

[0120] The server retrieves user behavior history data. This data includes past purchase history, page viewing history, and favorited items. The server analyzes this data to identify trends in brands and styles that the user has previously preferred.

[0121] Step 5:

[0122] The server synthesizes the analysis results and generates fashion suggestions that reflect the user's characteristics, preferences, and current emotional state. For example, if the user has plans to go out, it will recommend active, brightly colored casual wear. If the user's emotions are positive, it may include suggestions for more adventurous styles.

[0123] Step 6:

[0124] The server sends the generated fashion suggestions to the user's device to visually present them. The user can then view the suggested items and styles on their device and access detailed information and purchase links.

[0125] This process allows users to receive fashion suggestions tailored to their mood and schedule for the day in real time, enabling them to enjoy a shopping experience that broadens their range of self-expression.

[0126] (Example 2)

[0127] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0128] Conventional fashion recommendation systems make suggestions based on limited information such as the user's basic characteristics and behavioral history, and have the drawback of not being able to provide personalized suggestions that take into account the user's emotional state at any given time. Furthermore, fashion recommendations often fail to fully adapt to the emotions and psychological state of individual users, making it difficult to increase satisfaction.

[0129] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0130] In this invention, the server includes processing means for processing image information acquired from the user to extract the person's characteristics, analysis means for analyzing the user's behavioral history information to identify fashion preferences, and generation means for recognizing emotional states from the image information and generating fashion suggestions based on those emotional states. This makes it possible to provide personalized fashion suggestions that take into account the user's behavioral history and emotional states.

[0131] "Image information" refers to photographic and video data that includes the user's facial and physical characteristics.

[0132] "Processing means" refers to devices or programs used to analyze digital information and extract specific parameters.

[0133] "Behavioral history information" refers to historical data such as what products a user has viewed or purchased in the past, and what brand websites they have visited.

[0134] "Analysis means" refers to devices or programs used to analyze acquired data and identify user preferences and trends.

[0135] "Emotional state" refers to the psychological state of the user at that time, inferred from their facial expressions, voice, etc.

[0136] "Generative means" refers to devices or programs used to create new data or proposals based on analysis results.

[0137] "Presentation means" refers to devices or programs that provide generated information to the user visually or audibly.

[0138] To implement this invention, the user first takes images of their face and body using the camera on their device. These images are then sent from the device to a server. The server uses image processing software to analyze the user's facial features, body shape, skin color, and other characteristics. Image processing libraries such as OpenCV are utilized in this process.

[0139] The server simultaneously retrieves and analyzes user behavior history information from a database. This behavior history information includes data such as online browsing history, purchase history, and visited brand websites. MySQL® or PostgreSQL can be used as the database management system for data analysis. Based on this data, the user's fashion preferences are identified.

[0140] Furthermore, the server analyzes the user's facial expressions from image data using an emotion analysis tool. An emotion analysis API can be used for emotion analysis. The system infers the user's emotional state and then uses a generative AI model to suggest a suitable fashion style. Here, an example of a prompt for the generative AI model is, "Suggest the best style for this user."

[0141] The server also utilizes this information to create fashion suggestions based on the user's characteristics, preferences, and emotional state. These suggestions are output as specific styles by a generative AI model and sent from the server to the user's device. The user can then review these suggestions on their device and consider their options.

[0142] This system allows users to receive personalized fashion advice tailored to their individual characteristics and preferences, resulting in a more satisfying shopping experience.

[0143] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0144] Step 1:

[0145] The user takes pictures of their face and body using the device's camera. The captured images are saved on the device in JPEG or PNG format and sent to the server via the internet connection. In this process, the input is the image data captured by the user, and the output is the image data sent to the server.

[0146] Step 2:

[0147] The server analyzes the received image data using image processing software. Specifically, it uses OpenCV to perform face detection and feature extraction. The input is the image data sent to the server, and the output is characteristic information such as the user's face shape, body type, and skin color.

[0148] Step 3:

[0149] The server retrieves user activity history information from the database. Here, a database management system (e.g., MySQL) is used to retrieve products the user has previously viewed and purchase history. The input is the user ID, and the output is the user's activity history data.

[0150] Step 4:

[0151] The server analyzes behavioral history data to identify the user's fashion preferences. It utilizes data mining techniques to analyze the patterns of brands and styles the user favors. The input is behavioral history data, and the output is information about the user's fashion preferences.

[0152] Step 5:

[0153] The server uses an emotion analysis API to analyze the user's facial expressions from image data and estimate their emotional state. Here, it analyzes emotions such as smiles, surprise, and sadness. The input is the user's image data, and the output is information indicating the user's emotional state.

[0154] Step 6:

[0155] Based on these analysis results, the server generates fashion suggestions using a generative AI model. Taking a prompt (e.g., "Suggest the best style for this user.") as input, the AI ​​model outputs specific fashion style suggestions. The input consists of analyzed characteristic information, emotional state, and preference data, while the output is fashion suggestion data.

[0156] Step 7:

[0157] The server sends the generated fashion suggestions to the user's terminal. The terminal visually displays these suggestions for the user to review. The input is the fashion suggestion data, and the output is the suggestion information displayed on the user's terminal.

[0158] (Application Example 2)

[0159] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0160] This invention aims to improve user satisfaction in conventional online shopping systems by providing optimal clothing suggestions that take into account the user's individual characteristics, behavioral history, and even emotional state. Furthermore, it aims to support rational purchasing decisions without actual try-on by providing an environment where users can virtually try on clothes.

[0161] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0162] In this invention, the server includes information processing means for processing image information acquired from the user to extract the person's characteristics; analysis means for analyzing the user's behavioral records to identify the user's preferences for items; recommendation generation means for generating clothing suggestions that are appropriate to the situation and purpose based on the identified characteristics and preferences, as well as emotional analysis; and visualization means having a function to virtually try on the suggested clothing. This makes it possible for the user to easily select products that suit their characteristics and emotional state, confirm the fit through virtual try-on, and obtain a highly satisfying shopping experience.

[0163] "Image information" refers to photos and video data provided by users, and is the basic data used to analyze the physical characteristics of individuals.

[0164] "Information processing means" refers to computer processing functions used to extract human characteristics from acquired image information.

[0165] "Behavioral data" refers to recorded data that reflects a user's interests and preferences, such as their past browsing history, purchase history, and frequently visited web pages.

[0166] "Analysis methods" refer to analytical techniques used to identify a person's preferences from behavioral records, and are implemented using machine learning algorithms and the like.

[0167] "Emotional analysis" is the process of estimating a user's current emotional state from image information, and primarily uses facial expression analysis technology.

[0168] "Situation and application" refers to the user's current environment and required functional needs, and the suitability of the proposal is judged based on this.

[0169] "Recommendation generation method" refers to technology that generates optimal product suggestions based on the characteristics, preferences, and circumstances of a specific individual.

[0170] "Visualization means" refers to technologies that provide a realistic fitting experience when users virtually try on products.

[0171] This invention provides a system that suggests optimal clothing based on user image information, behavioral records, and sentiment analysis. The system consists of a user terminal, a cloud server, and multiple analysis software components. The main functions of this system are described below in natural language.

[0172] The user first takes a photo with their device or uploads existing image data. The device sends this image information to a cloud server, which uses image processing tools to extract the user's personal features. Deep learning models such as OpenCV and Torch are used here.

[0173] Next, the server uses AI-based analysis tools to identify user preferences based on past purchase and browsing history from user behavior records. This process employs cluster analysis and collaborative filtering algorithms, and leverages generative AI models.

[0174] Furthermore, the server uses facial expression data acquired during the image processing process to analyze the user's emotional state. Emotion recognition technologies such as Emotion API and Face++ are used to suggest clothing appropriate to the user's current emotions.

[0175] Finally, the recommendation generation system within the server comprehensively analyzes this information and presents the suggested outfits to the user on a virtual model generated by the visualization system. This allows the user to improve the accuracy of their product selection through virtual try-on, resulting in a more satisfying shopping experience.

[0176] As a concrete example, let's assume a user is looking for clothes for a relaxing holiday. If the user uploads a photo of themselves smiling, the system will recognize this as a positive emotion and suggest casual, relaxed styles. On the other hand, if the user's expression is serious, the system will suggest calmer colors and designs.

[0177] Examples of prompts for a generative AI model:

[0178] "Consider the user's image information and behavioral records, and suggest the optimal fashion items based on sentiment analysis results."

[0179] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0180] Step 1:

[0181] The user takes or selects an image of themselves using their device and uploads it to the server. At this stage, image data is obtained as input information, and this data is transferred to the server via a communication protocol.

[0182] Step 2:

[0183] The server analyzes the received image data using information processing tools to extract features such as the user's skin color, build, and facial shape. A deep learning model using OpenCV or Torch handles this process, extracting features from the image data and outputting them as feature parameters.

[0184] Step 3:

[0185] The server collects user behavior records and identifies preferences using analytical tools. The collected data includes browsing history and purchase history, which are analyzed using cluster analysis and collaborative filtering, and then converted into user preference parameters for output.

[0186] Step 4:

[0187] The server analyzes the user's facial expressions using image data and estimates their emotional state using emotion recognition technology. Emotion API and Face++ are utilized to analyze the emotional data based on the image and output the estimated emotional state.

[0188] Step 5:

[0189] The server's recommendation generation method uses a generative AI model to generate optimal clothing suggestions based on the obtained feature parameters, preference parameters, and emotional state. The prompt used is "Suggest fashion items considering feature parameters, preference parameters, and emotional state," and as a result, a list of recommended clothing items is output.

[0190] Step 6:

[0191] The server uses visualization tools to display a simulation of the user trying on recommended clothing items on their virtual model. At this stage, a virtual avatar tool is used to visually present the suggestions to the user, and the final feedback is output.

[0192] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0193] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0194] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0195] [Second Embodiment]

[0196] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0197] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0198] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0199] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0200] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0201] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0202] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0203] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0204] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0205] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0206] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0207] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0208] The system according to the present invention allows a user to send images taken using their own device to a server, and then provides the user with optimal fashion suggestions based on those images and behavioral history data. First, the server receives the user's image data and processes it to analyze facial and body features. This analysis uses facial recognition technology and image processing technology. For example, individual features such as skin color, body type, and hairstyle are extracted. Based on this information, the system recommends the most suitable colors and styles for the user.

[0209] Meanwhile, the server collects user behavioral data and analyzes what fashion items the user has viewed and purchased in the past to reveal their style preferences. This analysis reveals trends in brands and items that the user frequently shows interest in.

[0210] Next, the server generates optimal fashion suggestions based on these analysis results and the current situation and purpose (TPO). These suggestions include clothing combinations and accessories that are likely to suit the user. For example, if the user is attending a casual event the next day, the server might suggest jeans and a brightly colored top.

[0211] The generated fashion suggestions are sent from the server to the user's terminal and presented to the user visually. Users can use these suggestions to make daily fashion choices and enhance their enjoyment of fashion by purchasing the suggested styles when shopping.

[0212] This system allows users to receive personalized fashion advice based on their own characteristics, making it easy to choose appropriate attire for different occasions.

[0213] The following describes the processing flow.

[0214] Step 1:

[0215] The user launches a dedicated app on their device and takes or selects a full-body image of themselves. The captured image is uploaded to the server via the device.

[0216] Step 2:

[0217] The server receives images sent by users and applies image processing algorithms to analyze facial and body features. Specifically, skin color, body shape, and facial features are extracted.

[0218] Step 3:

[0219] The server retrieves user behavior history data from the database. This includes previously viewed fashion items, purchase history, and search queries.

[0220] Step 4:

[0221] The server analyzes the user's behavioral history to identify their fashion preferences. This analysis uses machine learning techniques to identify brands and styles that the user tends to favor.

[0222] Step 5:

[0223] The server takes into account the current time, location, and purpose (TPO) to generate fashion recommendations that reflect the user's characteristics and preferences. These recommendations include suggestions for specific clothing and accessories.

[0224] Step 6:

[0225] The server sends the generated recommendation information to the user's device. The user can review the suggestions received on their device and consider whether to adopt the suggested style.

[0226] (Example 1)

[0227] Next, we will describe Example 1. 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."

[0228] Modern consumers tend to seek personalized fashion suggestions based on their individual characteristics and personalities. However, conventional systems have struggled to generate suggestions that adequately reflect the individual characteristics and preferences of users, resulting in unsatisfactory recommendations. To address this challenge, there is a need for a method to generate fashion suggestions that fully take into account the user's characteristics and behavioral history.

[0229] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0230] In this invention, the server includes an image analysis means for processing image information acquired from the user to extract the person's features, a data analysis means for analyzing the user's behavioral history information to identify their fashion preferences, and a suggestion generation means for generating fashion suggestions that are tailored to the identified features and preferences, as well as the current conditions and intended use. This makes it possible to provide personalized fashion suggestions that take into account the individual characteristics and preferences of the user.

[0231] A "user" refers to a person who uses the system to receive fashion suggestions based on their own information.

[0232] "Image information" refers to photographs and image data taken by users, and is used to analyze the user's physical characteristics.

[0233] "Image analysis means" refers to technology that processes image information received from a user and extracts physical and visual characteristics.

[0234] "Behavioral history information" refers to data on fashion-related actions a user has taken in the past, such as browsing and purchasing.

[0235] "Data analysis methods" refer to processes and technologies used to analyze behavioral history information and identify a user's fashion preferences.

[0236] "Suggestion generation means" refers to the process of creating optimal fashion suggestions for the user based on information obtained from image analysis means and data analysis means.

[0237] "Display means" refers to methods or devices for visually presenting generated fashion suggestions to users.

[0238] This invention is a system for users to receive fashion suggestions based on their individual characteristics, and implements a process to suggest appropriate fashion styles based on the user's image information and behavioral history information.

[0239] First, the user prepares to receive fashion suggestions using their device. The user takes an image using the camera on their device and sends the image information to the server. To ensure high security, the server uses the HTTPS protocol to transmit the image information.

[0240] When the server receives image information from a user, it first processes it using image analysis tools. Here, the server executes scripts in programming languages ​​such as Python and utilizes image processing software like OpenCV to extract visual features such as facial shape, skin tone, and body type. Furthermore, the server uses a generative AI model to input prompt messages and perform individual fashion style analysis. A concrete example of a prompt message might be, "Create fashion suggestions for a woman with light-toned skin who usually prefers office casual attire."

[0241] The server also analyzes user behavior history information. The database stores users' fashion-related behavior, and the server analyzes this data using data analysis tools. Big data analysis tools such as Apache Spark are used to identify the brands and styles that users prefer.

[0242] Based on these analysis results, the server uses a suggestion generation mechanism to generate optimal fashion suggestions for the user. The generated suggestions include clothing combinations and accessory selections tailored to specific events or occasions. The generated suggestions are sent to the user's device and displayed visually. By viewing these visual suggestions, the user can make their daily fashion choices more enjoyable and make more appropriate choices.

[0243] This system provides technology that enhances the user experience, meets individual needs, and establishes a new standard for fashion proposals.

[0244] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0245] Step 1:

[0246] The user launches a camera app on their device and takes a picture to receive fashion suggestions. The input is image data captured by the device's camera, which is then sent to the server. The device securely transfers this image data to the server using the HTTPS protocol.

[0247] Step 2:

[0248] The server receives image data sent from the terminal. Using the received image data as input, the server uses image analysis tools. Here, image processing libraries such as OpenCV are used to analyze the image and extract the user's physical characteristics, such as face shape, skin color, and body type, as vector data. The output of this analysis, the obtained feature information, is passed to the next process.

[0249] Step 3:

[0250] The server retrieves user behavior history information from a database. This input includes past browsing and purchase history. Using data analysis tools, the server analyzes this data with big data processing tools such as Apache Spark to quantify user preferences. The results of the analysis are output as a list of the user's preferences and areas of interest.

[0251] Step 4:

[0252] The server uses a suggestion generation mechanism, taking feature information obtained through image analysis and preference information based on behavioral history as input. It utilizes a generation AI model to provide fashion suggestions using prompts. An example prompt used is, "Please create fashion suggestions for a woman with light skin tone who usually prefers office casual attire." The output is a fashion suggestion customized for the user.

[0253] Step 5:

[0254] The server sends the generated fashion suggestions to the user's device. The data is securely transferred using HTTPS, and the suggestions are displayed on the device's screen. The user visually confirms this output and performs actions to support their daily fashion choices. This allows the user to use the suggested styles as a reference when making purchase decisions at physical stores or online stores.

[0255] (Application Example 1)

[0256] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0257] In modern society, consumers are faced with a wide variety of fashion items to choose from, but selecting the appropriate fashion for any given situation is a particularly difficult challenge. Because there is a lack of real-time information on fashion that suits oneself, consumers spend a great deal of time and effort choosing the best outfit for themselves.

[0258] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0259] In this invention, the server includes information processing means for processing image data acquired from a user to extract the person's characteristics, data analysis means for analyzing the user's behavioral history data to identify preferences, and recommendation generation means for generating suggestion information according to the identified characteristics and preferences, as well as the situation and purpose. This allows the user to visually confirm fashion suggestions that suit them in real time and make appropriate choices quickly.

[0260] "Information processing means" refers to a technical device or function that analyzes image data obtained from a user and extracts human characteristics from the image.

[0261] "Data analysis means" refers to a technical device or function that investigates a user's behavioral history data and identifies their preferences and tastes based on that data.

[0262] A "recommendation generation method" is a technical device or function that generates optimal suggestion information for the user based on extracted characteristics and preferences, as well as the situation and application.

[0263] "Presentation means" refers to a technical device or function that provides generated proposal information to the user visually, for example, by displaying it in real time via a smart device.

[0264] The system implementing this invention involves the coordinated operation of a user, a terminal, and a server. The user acquires image data using a terminal such as smart glasses. The terminal is equipped with communication capabilities to transmit the image data to the server. The server analyzes the received image data using image processing software such as OpenCV to extract features such as the user's face shape, physique, and skin color.

[0265] The server further analyzes the user's past behavior history using data analysis tools such as Pandas to identify the user's preferred fashion trends from the database. This reveals specific brands and styles.

[0266] Based on these analysis results, the server uses generative AI models such as TensorFlow to generate fashion suggestions best suited to the user. The user's characteristics, preferences, and current situation and purpose are all considered during this process. An example of a prompt generated during this process would be, "Please suggest an outfit suitable for a 30-year-old woman, casual, and attending a cafe event."

[0267] The generated fashion suggestions are sent to the user's device in real time. The user can visually check the suggested clothing and styles on their device and make appropriate fashion choices based on that information.

[0268] As a concrete example, when a user participates in a casual book club at a cafe, a casual yet stylish combination of a denim jacket and a white shirt is suggested. This system allows users to easily choose the perfect outfit for themselves.

[0269] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0270] Step 1:

[0271] The user takes a picture of themselves using their device and sends that image to the server. Image data acquired by the device's camera becomes the input, and the image data is sent to the server via the communication function.

[0272] Step 2:

[0273] The server processes the received image data using OpenCV to extract features including the user's face shape, body type, and skin color. The input data is image data, and its features are analyzed using OpenCV's image processing techniques. The output provides the user's feature parameters.

[0274] Step 3:

[0275] The server uses Pandas to analyze user behavioral data and identify fashion preferences from past purchase and browsing history. The input data is behavioral data, which is analyzed using Pandas, and the output is a trend in preferences.

[0276] Step 4:

[0277] The server uses TensorFlow to run a generative AI model based on extracted features and preferences to generate optimal fashion suggestions for the user. In this process, feature parameters and preference data are used as input data, and specific fashion suggestions are generated as output.

[0278] Step 5:

[0279] The server sends the generated fashion suggestions to the user's device. The device visually displays the received fashion suggestions and provides the user with their content. The input data is the fashion suggestions, which are conveyed to the user visually in real time via the device's display function.

[0280] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0281] The system according to the present invention provides fashion suggestions based on the user's image data and behavioral history data, and further combines this with emotion analysis means to recognize the user's emotions. This system analyzes the user's facial and body features and obtains information based on the images when the user sends images taken with a terminal to a server. The server performs image processing to identify the user's skin color, body shape, and facial shape in particular.

[0282] In parallel, the server analyzes the behavior history obtained from the user. This information includes fashion items viewed in the past, purchased items, brand pages frequently accessed, and the like. From the analysis results, the server identifies the user's fashion preferences.

[0283] Furthermore, the present invention newly incorporates sentiment analysis means. The server analyzes the user's expression from the received image data and estimates the user's emotional state. For example, when the user has a smiling face, it is determined as a positive emotion, and a more adventurous style fashion proposal may be suitable. On the other hand, when a negative emotion is detected, a style that makes the user feel at ease is provided.

[0284] The fashion proposal generated in this way is transmitted by the server to the user's terminal and provided visually. The user can view the proposal and decide whether to purchase new fashion items based on the proposed style.

[0285] With this system, the user can receive personalized fashion advice according to their emotions, characteristics, and preferences at any given time, realizing a more satisfying shopping experience.

[0286] The processing flow will be described below.

[0287] Step 1:

[0288] The user launches a dedicated application on the terminal, takes or selects a full-body image in which their expression is captured, and transmits it to the server. At this time, the user can optionally enter comments about their preferred style and current mood.

[0289] Step 2:

[0290] The server processes the received image data and performs face recognition and expression analysis. First, it detects facial features, and then uses an emotion analysis algorithm to identify the user's emotions. For example, it identifies positive or negative emotions from facial expressions such as smiles or confusion.

[0291] Step 3:

[0292] The server then extracts visual features from the image, such as skin tone, body shape, and facial features. This makes it easier to suggest colors and styles that suit the user. This data is also used to filter fashion items stored in the database.

[0293] Step 4:

[0294] The server retrieves user behavior history data. This data includes past purchase history, page viewing history, and favorited items. The server analyzes this data to identify trends in brands and styles that the user has previously preferred.

[0295] Step 5:

[0296] The server synthesizes the analysis results and generates fashion suggestions that reflect the user's characteristics, preferences, and current emotional state. For example, if the user has plans to go out, it will recommend active, brightly colored casual wear. If the user's emotions are positive, it may include suggestions for more adventurous styles.

[0297] Step 6:

[0298] The server sends the generated fashion suggestions to the user's device to visually present them. The user can then view the suggested items and styles on their device and access detailed information and purchase links.

[0299] This process allows users to receive fashion suggestions tailored to their mood and schedule for the day in real time, enabling them to enjoy a shopping experience that broadens their range of self-expression.

[0300] (Example 2)

[0301] Next, we will describe Example 2. 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".

[0302] Conventional fashion recommendation systems make suggestions based on limited information such as the user's basic characteristics and behavioral history, and have the drawback of not being able to provide personalized suggestions that take into account the user's emotional state at any given time. Furthermore, fashion recommendations often fail to fully adapt to the emotions and psychological state of individual users, making it difficult to increase satisfaction.

[0303] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0304] In this invention, the server includes processing means for processing image information acquired from the user to extract the person's characteristics, analysis means for analyzing the user's behavioral history information to identify fashion preferences, and generation means for recognizing emotional states from the image information and generating fashion suggestions based on those emotional states. This makes it possible to provide personalized fashion suggestions that take into account the user's behavioral history and emotional states.

[0305] "Image information" refers to photographic and video data that includes the user's facial and physical characteristics.

[0306] "Processing means" refers to devices or programs used to analyze digital information and extract specific parameters.

[0307] "Behavioral history information" refers to historical data such as what products a user has viewed or purchased in the past, and what brand websites they have visited.

[0308] The "analysis means" refers to a device or program for analyzing the acquired data to identify the user's preferences and tendencies.

[0309] The "emotional state" refers to the psychological state at that time inferred from the user's expression, voice, etc.

[0310] The "generation means" refers to a device or program for creating new data or proposals based on the analysis results.

[0311] The "presentation means" refers to a device or program for visually or audibly providing the generated information to the user.

[0312] To implement this invention, first, the user uses the camera of the terminal to take pictures of their own face and body. This image is transmitted from the terminal to the server. The server analyzes features such as the user's face shape, body shape, and skin color using image processing software. At this time, an image processing library such as OpenCV is utilized.

[0313] In parallel, the server acquires the user's behavior history information from the database and performs analysis. This behavior history information includes data such as online browsing history, purchase history, and visited brand sites. For data analysis, MySQL or PostgreSQL can be used as a database management system. Based on this data, the user's fashion preferences are identified.

[0314] Furthermore, the server analyzes the user's expression from the image data using an emotion analysis tool. For emotion analysis, an emotion analysis API can be utilized. The user's emotional state is inferred, and a fashion style suitable for it is proposed by a generation AI model. Here, as an example of the prompt sentence of the generation AI model, "Propose the most suitable style for this user." is input.

[0315] The server also utilizes this information to create fashion suggestions based on the user's characteristics, preferences, and emotional state. These suggestions are output as specific styles by a generative AI model and sent from the server to the user's device. The user can then review these suggestions on their device and consider their options.

[0316] This system allows users to receive personalized fashion advice tailored to their individual characteristics and preferences, resulting in a more satisfying shopping experience.

[0317] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0318] Step 1:

[0319] The user takes pictures of their face and body using the device's camera. The captured images are saved on the device in JPEG or PNG format and sent to the server via the internet connection. In this process, the input is the image data captured by the user, and the output is the image data sent to the server.

[0320] Step 2:

[0321] The server analyzes the received image data using image processing software. Specifically, it uses OpenCV to perform face detection and feature extraction. The input is the image data sent to the server, and the output is characteristic information such as the user's face shape, body type, and skin color.

[0322] Step 3:

[0323] The server retrieves user activity history information from the database. Here, a database management system (e.g., MySQL) is used to retrieve products the user has previously viewed and purchase history. The input is the user ID, and the output is the user's activity history data.

[0324] Step 4:

[0325] The server analyzes behavioral history data to identify the user's fashion preferences. It utilizes data mining techniques to analyze the patterns of brands and styles the user favors. The input is behavioral history data, and the output is information about the user's fashion preferences.

[0326] Step 5:

[0327] The server uses an emotion analysis API to analyze the user's facial expressions from image data and estimate their emotional state. Here, it analyzes emotions such as smiles, surprise, and sadness. The input is the user's image data, and the output is information indicating the user's emotional state.

[0328] Step 6:

[0329] Based on these analysis results, the server generates fashion suggestions using a generative AI model. Taking a prompt (e.g., "Suggest the best style for this user.") as input, the AI ​​model outputs specific fashion style suggestions. The input consists of analyzed characteristic information, emotional state, and preference data, while the output is fashion suggestion data.

[0330] Step 7:

[0331] The server sends the generated fashion suggestions to the user's terminal. The terminal visually displays these suggestions for the user to review. The input is the fashion suggestion data, and the output is the suggestion information displayed on the user's terminal.

[0332] (Application Example 2)

[0333] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0334] This invention aims to improve user satisfaction in conventional online shopping systems by providing optimal clothing suggestions that take into account the user's individual characteristics, behavioral history, and even emotional state. Furthermore, it aims to support rational purchasing decisions without actual try-on by providing an environment where users can virtually try on clothes.

[0335] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0336] In this invention, the server includes information processing means for processing image information acquired from the user to extract the person's characteristics; analysis means for analyzing the user's behavioral records to identify the user's preferences for items; recommendation generation means for generating clothing suggestions that are appropriate to the situation and purpose based on the identified characteristics and preferences, as well as emotional analysis; and visualization means having a function to virtually try on the suggested clothing. This makes it possible for the user to easily select products that suit their characteristics and emotional state, confirm the fit through virtual try-on, and obtain a highly satisfying shopping experience.

[0337] "Image information" refers to photos and video data provided by users, and is the basic data used to analyze the physical characteristics of individuals.

[0338] "Information processing means" refers to computer processing functions used to extract human characteristics from acquired image information.

[0339] "Behavioral data" refers to recorded data that reflects a user's interests and preferences, such as their past browsing history, purchase history, and frequently visited web pages.

[0340] "Analysis methods" refer to analytical techniques used to identify a person's preferences from behavioral records, and are implemented using machine learning algorithms and the like.

[0341] "Emotional analysis" is the process of estimating a user's current emotional state from image information, and primarily uses facial expression analysis technology.

[0342] "Situation and application" refers to the user's current environment and required functional needs, and the suitability of the proposal is judged based on this.

[0343] "Recommendation generation method" refers to technology that generates optimal product suggestions based on the characteristics, preferences, and circumstances of a specific individual.

[0344] "Visualization means" refers to technologies that provide a realistic fitting experience when users virtually try on products.

[0345] This invention provides a system that suggests optimal clothing based on user image information, behavioral records, and sentiment analysis. The system consists of a user terminal, a cloud server, and multiple analysis software components. The main functions of this system are described below in natural language.

[0346] The user first takes a photo with their device or uploads existing image data. The device sends this image information to a cloud server, which uses image processing tools to extract the user's personal features. Deep learning models such as OpenCV and Torch are used here.

[0347] Next, the server uses AI-based analysis tools to identify user preferences based on past purchase and browsing history from user behavior records. This process employs cluster analysis and collaborative filtering algorithms, and leverages generative AI models.

[0348] Furthermore, the server uses facial expression data acquired during the image processing process to analyze the user's emotional state. Emotion recognition technologies such as Emotion API and Face++ are used to suggest clothing appropriate to the user's current emotions.

[0349] Finally, the recommendation generation system within the server comprehensively analyzes this information and presents the suggested outfits to the user on a virtual model generated by the visualization system. This allows the user to improve the accuracy of their product selection through virtual try-on, resulting in a more satisfying shopping experience.

[0350] As a concrete example, let's assume a user is looking for clothes for a relaxing holiday. If the user uploads a photo of themselves smiling, the system will recognize this as a positive emotion and suggest casual, relaxed styles. On the other hand, if the user's expression is serious, the system will suggest calmer colors and designs.

[0351] Examples of prompts for a generative AI model:

[0352] "Consider the user's image information and behavioral records, and suggest the optimal fashion items based on sentiment analysis results."

[0353] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0354] Step 1:

[0355] The user takes or selects an image of themselves using their device and uploads it to the server. At this stage, image data is obtained as input information, and this data is transferred to the server via a communication protocol.

[0356] Step 2:

[0357] The server analyzes the received image data using information processing tools to extract features such as the user's skin color, build, and facial shape. A deep learning model using OpenCV or Torch handles this process, extracting features from the image data and outputting them as feature parameters.

[0358] Step 3:

[0359] The server collects user behavior records and identifies preferences using analytical tools. The collected data includes browsing history and purchase history, which are analyzed using cluster analysis and collaborative filtering, and then converted into user preference parameters for output.

[0360] Step 4:

[0361] The server analyzes the user's facial expressions using image data and estimates their emotional state using emotion recognition technology. Emotion API and Face++ are utilized to analyze the emotional data based on the image and output the estimated emotional state.

[0362] Step 5:

[0363] The server's recommendation generation method uses a generative AI model to generate optimal clothing suggestions based on the obtained feature parameters, preference parameters, and emotional state. The prompt used is "Suggest fashion items considering feature parameters, preference parameters, and emotional state," and as a result, a list of recommended clothing items is output.

[0364] Step 6:

[0365] The server uses visualization tools to display a simulation of the user trying on recommended clothing items on their virtual model. At this stage, a virtual avatar tool is used to visually present the suggestions to the user, and the final feedback is output.

[0366] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0367] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0368] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0369] [Third Embodiment]

[0370] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0371] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0372] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0373] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0374] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0375] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0376] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0377] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0378] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0379] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0380] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0381] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0382] The system according to the present invention allows a user to send images taken using their own device to a server, and then provides the user with optimal fashion suggestions based on those images and behavioral history data. First, the server receives the user's image data and processes it to analyze facial and body features. This analysis uses facial recognition technology and image processing technology. For example, individual features such as skin color, body type, and hairstyle are extracted. Based on this information, the system recommends the most suitable colors and styles for the user.

[0383] Meanwhile, the server collects user behavioral data and analyzes what fashion items the user has viewed and purchased in the past to reveal their style preferences. This analysis reveals trends in brands and items that the user frequently shows interest in.

[0384] Next, the server generates optimal fashion suggestions based on these analysis results and the current situation and purpose (TPO). These suggestions include clothing combinations and accessories that are likely to suit the user. For example, if the user is attending a casual event the next day, the server might suggest jeans and a brightly colored top.

[0385] The generated fashion suggestions are sent from the server to the user's terminal and presented to the user visually. Users can use these suggestions to make daily fashion choices and enhance their enjoyment of fashion by purchasing the suggested styles when shopping.

[0386] This system allows users to receive personalized fashion advice based on their own characteristics, making it easy to choose appropriate attire for different occasions.

[0387] The following describes the processing flow.

[0388] Step 1:

[0389] The user launches a dedicated app on their device and takes or selects a full-body image of themselves. The captured image is uploaded to the server via the device.

[0390] Step 2:

[0391] The server receives images sent by users and applies image processing algorithms to analyze facial and body features. Specifically, skin color, body shape, and facial features are extracted.

[0392] Step 3:

[0393] The server retrieves user behavior history data from the database. This includes previously viewed fashion items, purchase history, and search queries.

[0394] Step 4:

[0395] The server analyzes the user's behavioral history to identify their fashion preferences. This analysis uses machine learning techniques to identify brands and styles that the user tends to favor.

[0396] Step 5:

[0397] The server takes into account the current time, location, and purpose (TPO) to generate fashion recommendations that reflect the user's characteristics and preferences. These recommendations include suggestions for specific clothing and accessories.

[0398] Step 6:

[0399] The server sends the generated recommendation information to the user's device. The user can review the suggestions received on their device and consider whether to adopt the suggested style.

[0400] (Example 1)

[0401] Next, we will describe Example 1. 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."

[0402] Modern consumers tend to seek personalized fashion suggestions based on their individual characteristics and personalities. However, conventional systems have struggled to generate suggestions that adequately reflect the individual characteristics and preferences of users, resulting in unsatisfactory recommendations. To address this challenge, there is a need for a method to generate fashion suggestions that fully take into account the user's characteristics and behavioral history.

[0403] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0404] In this invention, the server includes an image analysis means for processing image information acquired from the user to extract the person's features, a data analysis means for analyzing the user's behavioral history information to identify their fashion preferences, and a suggestion generation means for generating fashion suggestions that are tailored to the identified features and preferences, as well as the current conditions and intended use. This makes it possible to provide personalized fashion suggestions that take into account the individual characteristics and preferences of the user.

[0405] A "user" refers to a person who uses the system to receive fashion suggestions based on their own information.

[0406] "Image information" refers to photographs and image data taken by users, and is used to analyze the user's physical characteristics.

[0407] "Image analysis means" refers to technology that processes image information received from a user and extracts physical and visual characteristics.

[0408] "Behavioral history information" refers to data on fashion-related actions a user has taken in the past, such as browsing and purchasing.

[0409] "Data analysis methods" refer to processes and technologies used to analyze behavioral history information and identify a user's fashion preferences.

[0410] "Suggestion generation means" refers to the process of creating optimal fashion suggestions for the user based on information obtained from image analysis means and data analysis means.

[0411] "Display means" refers to methods or devices for visually presenting generated fashion suggestions to users.

[0412] This invention is a system for users to receive fashion suggestions based on their individual characteristics, and implements a process to suggest appropriate fashion styles based on the user's image information and behavioral history information.

[0413] First, the user prepares to receive fashion suggestions using their device. The user takes an image using the camera on their device and sends the image information to the server. To ensure high security, the server uses the HTTPS protocol to transmit the image information.

[0414] When the server receives image information from a user, it first processes it using image analysis tools. Here, the server executes scripts in programming languages ​​such as Python and utilizes image processing software like OpenCV to extract visual features such as facial shape, skin tone, and body type. Furthermore, the server uses a generative AI model to input prompt messages and perform individual fashion style analysis. A concrete example of a prompt message might be, "Create fashion suggestions for a woman with light-toned skin who usually prefers office casual attire."

[0415] The server also analyzes user behavior history information. The database stores users' fashion-related behavior, and the server analyzes this data using data analysis tools. Big data analysis tools such as Apache Spark are used to identify the brands and styles that users prefer.

[0416] Based on these analysis results, the server uses a suggestion generation mechanism to generate optimal fashion suggestions for the user. The generated suggestions include clothing combinations and accessory selections tailored to specific events or occasions. The generated suggestions are sent to the user's device and displayed visually. By viewing these visual suggestions, the user can make their daily fashion choices more enjoyable and make more appropriate choices.

[0417] This system provides technology that enhances the user experience, meets individual needs, and establishes a new standard for fashion proposals.

[0418] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0419] Step 1:

[0420] The user launches a camera app on their device and takes a picture to receive fashion suggestions. The input is image data captured by the device's camera, which is then sent to the server. The device securely transfers this image data to the server using the HTTPS protocol.

[0421] Step 2:

[0422] The server receives image data sent from the terminal. Using the received image data as input, the server uses image analysis tools. Here, image processing libraries such as OpenCV are used to analyze the image and extract the user's physical characteristics, such as face shape, skin color, and body type, as vector data. The output of this analysis, the obtained feature information, is passed to the next process.

[0423] Step 3:

[0424] The server retrieves user behavior history information from a database. This input includes past browsing and purchase history. Using data analysis tools, the server analyzes this data with big data processing tools such as Apache Spark to quantify user preferences. The results of the analysis are output as a list of the user's preferences and areas of interest.

[0425] Step 4:

[0426] The server uses a suggestion generation mechanism, taking feature information obtained through image analysis and preference information based on behavioral history as input. It utilizes a generation AI model to provide fashion suggestions using prompts. An example prompt used is, "Please create fashion suggestions for a woman with light skin tone who usually prefers office casual attire." The output is a fashion suggestion customized for the user.

[0427] Step 5:

[0428] The server sends the generated fashion suggestions to the user's device. The data is securely transferred using HTTPS, and the suggestions are displayed on the device's screen. The user visually confirms this output and performs actions to support their daily fashion choices. This allows the user to use the suggested styles as a reference when making purchase decisions at physical stores or online stores.

[0429] (Application Example 1)

[0430] Next, we will explain Application Example 1. In the following explanation, 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."

[0431] In modern society, consumers are faced with a wide variety of fashion items to choose from, but selecting the appropriate fashion for any given situation is a particularly difficult challenge. Because there is a lack of real-time information on fashion that suits oneself, consumers spend a great deal of time and effort choosing the best outfit for themselves.

[0432] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0433] In this invention, the server includes information processing means for processing image data acquired from a user to extract the person's characteristics, data analysis means for analyzing the user's behavioral history data to identify preferences, and recommendation generation means for generating suggestion information according to the identified characteristics and preferences, as well as the situation and purpose. This allows the user to visually confirm fashion suggestions that suit them in real time and make appropriate choices quickly.

[0434] "Information processing means" refers to a technical device or function that analyzes image data obtained from a user and extracts human characteristics from the image.

[0435] "Data analysis means" refers to a technical device or function that investigates a user's behavioral history data and identifies their preferences and tastes based on that data.

[0436] A "recommendation generation method" is a technical device or function that generates optimal suggestion information for the user based on extracted characteristics and preferences, as well as the situation and application.

[0437] "Presentation means" refers to a technical device or function that provides generated proposal information to the user visually, for example, by displaying it in real time via a smart device.

[0438] The system implementing this invention involves the coordinated operation of a user, a terminal, and a server. The user acquires image data using a terminal such as smart glasses. The terminal is equipped with communication capabilities to transmit the image data to the server. The server analyzes the received image data using image processing software such as OpenCV to extract features such as the user's face shape, physique, and skin color.

[0439] The server further analyzes the user's past behavior history using data analysis tools such as Pandas to identify the user's preferred fashion trends from the database. This reveals specific brands and styles.

[0440] Based on these analysis results, the server uses generative AI models such as TensorFlow to generate fashion suggestions best suited to the user. The user's characteristics, preferences, and current situation and purpose are all considered during this process. An example of a prompt generated during this process would be, "Please suggest an outfit suitable for a 30-year-old woman, casual, and attending a cafe event."

[0441] The generated fashion suggestions are sent to the user's device in real time. The user can visually check the suggested clothing and styles on their device and make appropriate fashion choices based on that information.

[0442] As a concrete example, when a user participates in a casual book club at a cafe, a casual yet stylish combination of a denim jacket and a white shirt is suggested. This system allows users to easily choose the perfect outfit for themselves.

[0443] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0444] Step 1:

[0445] The user takes a picture of themselves using their device and sends that image to the server. Image data acquired by the device's camera becomes the input, and the image data is sent to the server via the communication function.

[0446] Step 2:

[0447] The server processes the received image data using OpenCV to extract features including the user's face shape, body type, and skin color. The input data is image data, and its features are analyzed using OpenCV's image processing techniques. The output provides the user's feature parameters.

[0448] Step 3:

[0449] The server uses Pandas to analyze user behavioral data and identify fashion preferences from past purchase and browsing history. The input data is behavioral data, which is analyzed using Pandas, and the output is a trend in preferences.

[0450] Step 4:

[0451] The server uses TensorFlow to run a generative AI model based on extracted features and preferences to generate optimal fashion suggestions for the user. In this process, feature parameters and preference data are used as input data, and specific fashion suggestions are generated as output.

[0452] Step 5:

[0453] The server sends the generated fashion suggestions to the user's device. The device visually displays the received fashion suggestions and provides the user with their content. The input data is the fashion suggestions, which are conveyed to the user visually in real time via the device's display function.

[0454] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0455] The system according to the present invention provides fashion suggestions based on the user's image data and behavioral history data, and further combines this with emotion analysis means to recognize the user's emotions. This system analyzes the user's facial and body features and obtains information based on the images when the user sends images taken with a terminal to a server. The server performs image processing to identify the user's skin color, body shape, and facial shape in particular.

[0456] In parallel, the server analyzes the user's behavioral history. This information includes fashion items previously viewed, items purchased, and frequently accessed brand pages. The analysis results are used to identify the user's fashion preferences.

[0457] Furthermore, this invention incorporates a new emotion analysis means. The server analyzes the user's facial expressions from the received image data and estimates the user's emotional state. For example, if the user is smiling, it is judged to be a positive emotion, and a more adventurous style of fashion suggestion may be appropriate. On the other hand, if a negative emotion is detected, a style that will reassure the user is provided.

[0458] The fashion suggestions generated in this way are sent by the server to the user's terminal and presented visually. The user can review the suggestions and decide whether to purchase new fashion items based on the suggested style.

[0459] This system allows users to receive personalized fashion advice tailored to their current emotions, characteristics, and preferences, resulting in a more satisfying shopping experience.

[0460] The following describes the processing flow.

[0461] Step 1:

[0462] Users launch a dedicated application on their device and take or select a full-body image that captures their facial expressions, then send it to the server. Users can also optionally add comments about their preferred style or current mood.

[0463] Step 2:

[0464] The server processes the received image data and performs face recognition and expression analysis. First, it detects facial features, and then uses an emotion analysis algorithm to identify the user's emotions. For example, it identifies positive or negative emotions from facial expressions such as smiles or confusion.

[0465] Step 3:

[0466] The server then extracts visual features from the image, such as skin tone, body shape, and facial features. This makes it easier to suggest colors and styles that suit the user. This data is also used to filter fashion items stored in the database.

[0467] Step 4:

[0468] The server retrieves user behavior history data. This data includes past purchase history, page viewing history, and favorited items. The server analyzes this data to identify trends in brands and styles that the user has previously preferred.

[0469] Step 5:

[0470] The server synthesizes the analysis results and generates fashion suggestions that reflect the user's characteristics, preferences, and current emotional state. For example, if the user has plans to go out, it will recommend active, brightly colored casual wear. If the user's emotions are positive, it may include suggestions for more adventurous styles.

[0471] Step 6:

[0472] The server sends the generated fashion suggestions to the user's device to visually present them. The user can then view the suggested items and styles on their device and access detailed information and purchase links.

[0473] This process allows users to receive fashion suggestions tailored to their mood and schedule for the day in real time, enabling them to enjoy a shopping experience that broadens their range of self-expression.

[0474] (Example 2)

[0475] Next, we will describe Example 2. 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."

[0476] Conventional fashion recommendation systems make suggestions based on limited information such as the user's basic characteristics and behavioral history, and have the drawback of not being able to provide personalized suggestions that take into account the user's emotional state at any given time. Furthermore, fashion recommendations often fail to fully adapt to the emotions and psychological state of individual users, making it difficult to increase satisfaction.

[0477] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0478] In this invention, the server includes processing means for processing image information acquired from the user to extract the person's characteristics, analysis means for analyzing the user's behavioral history information to identify fashion preferences, and generation means for recognizing emotional states from the image information and generating fashion suggestions based on those emotional states. This makes it possible to provide personalized fashion suggestions that take into account the user's behavioral history and emotional states.

[0479] "Image information" refers to photographic and video data that includes the user's facial and physical characteristics.

[0480] "Processing means" refers to devices or programs used to analyze digital information and extract specific parameters.

[0481] "Behavioral history information" refers to historical data such as what products a user has viewed or purchased in the past, and what brand websites they have visited.

[0482] "Analysis means" refers to devices or programs used to analyze acquired data and identify user preferences and trends.

[0483] "Emotional state" refers to the psychological state of the user at that time, inferred from their facial expressions, voice, etc.

[0484] "Generative means" refers to devices or programs used to create new data or proposals based on analysis results.

[0485] "Presentation means" refers to devices or programs that provide generated information to the user visually or audibly.

[0486] To implement this invention, the user first takes images of their face and body using the camera on their device. These images are then sent from the device to a server. The server uses image processing software to analyze the user's facial features, body shape, skin color, and other characteristics. Image processing libraries such as OpenCV are utilized in this process.

[0487] The server simultaneously retrieves and analyzes user behavior history information from a database. This behavior history information includes data such as online browsing history, purchase history, and visited brand websites. MySQL or PostgreSQL can be used as the database management system for data analysis. Based on this data, the user's fashion preferences are identified.

[0488] Furthermore, the server analyzes the user's facial expressions from image data using an emotion analysis tool. An emotion analysis API can be used for emotion analysis. The system infers the user's emotional state and then uses a generative AI model to suggest a suitable fashion style. Here, an example of a prompt for the generative AI model is, "Suggest the best style for this user."

[0489] The server also utilizes this information to create fashion suggestions based on the user's characteristics, preferences, and emotional state. These suggestions are output as specific styles by a generative AI model and sent from the server to the user's device. The user can then review these suggestions on their device and consider their options.

[0490] This system allows users to receive personalized fashion advice tailored to their individual characteristics and preferences, resulting in a more satisfying shopping experience.

[0491] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0492] Step 1:

[0493] The user takes pictures of their face and body using the device's camera. The captured images are saved on the device in JPEG or PNG format and sent to the server via the internet connection. In this process, the input is the image data captured by the user, and the output is the image data sent to the server.

[0494] Step 2:

[0495] The server analyzes the received image data using image processing software. Specifically, it uses OpenCV to perform face detection and feature extraction. The input is the image data sent to the server, and the output is characteristic information such as the user's face shape, body type, and skin color.

[0496] Step 3:

[0497] The server retrieves user activity history information from the database. Here, a database management system (e.g., MySQL) is used to retrieve products the user has previously viewed and purchase history. The input is the user ID, and the output is the user's activity history data.

[0498] Step 4:

[0499] The server analyzes behavioral history data to identify the user's fashion preferences. It utilizes data mining techniques to analyze the patterns of brands and styles the user favors. The input is behavioral history data, and the output is information about the user's fashion preferences.

[0500] Step 5:

[0501] The server uses an emotion analysis API to analyze the user's facial expressions from image data and estimate their emotional state. Here, it analyzes emotions such as smiles, surprise, and sadness. The input is the user's image data, and the output is information indicating the user's emotional state.

[0502] Step 6:

[0503] Based on these analysis results, the server generates fashion suggestions using a generative AI model. Taking a prompt (e.g., "Suggest the best style for this user.") as input, the AI ​​model outputs specific fashion style suggestions. The input consists of analyzed characteristic information, emotional state, and preference data, while the output is fashion suggestion data.

[0504] Step 7:

[0505] The server sends the generated fashion suggestions to the user's terminal. The terminal visually displays these suggestions for the user to review. The input is the fashion suggestion data, and the output is the suggestion information displayed on the user's terminal.

[0506] (Application Example 2)

[0507] Next, we will explain Application Example 2. In the following explanation, 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."

[0508] This invention aims to improve user satisfaction in conventional online shopping systems by providing optimal clothing suggestions that take into account the user's individual characteristics, behavioral history, and even emotional state. Furthermore, it aims to support rational purchasing decisions without actual try-on by providing an environment where users can virtually try on clothes.

[0509] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0510] In this invention, the server includes information processing means for processing image information acquired from the user to extract the person's characteristics; analysis means for analyzing the user's behavioral records to identify the user's preferences for items; recommendation generation means for generating clothing suggestions that are appropriate to the situation and purpose based on the identified characteristics and preferences, as well as emotional analysis; and visualization means having a function to virtually try on the suggested clothing. This makes it possible for the user to easily select products that suit their characteristics and emotional state, confirm the fit through virtual try-on, and obtain a highly satisfying shopping experience.

[0511] "Image information" refers to photos and video data provided by users, and is the basic data used to analyze the physical characteristics of individuals.

[0512] "Information processing means" refers to computer processing functions used to extract human characteristics from acquired image information.

[0513] "Behavioral data" refers to recorded data that reflects a user's interests and preferences, such as their past browsing history, purchase history, and frequently visited web pages.

[0514] "Analysis methods" refer to analytical techniques used to identify a person's preferences from behavioral records, and are implemented using machine learning algorithms and the like.

[0515] "Emotional analysis" is the process of estimating a user's current emotional state from image information, and primarily uses facial expression analysis technology.

[0516] "Situation and application" refers to the user's current environment and required functional needs, and the suitability of the proposal is judged based on this.

[0517] "Recommendation generation method" refers to technology that generates optimal product suggestions based on the characteristics, preferences, and circumstances of a specific individual.

[0518] "Visualization means" refers to technologies that provide a realistic fitting experience when users virtually try on products.

[0519] This invention provides a system that suggests optimal clothing based on user image information, behavioral records, and sentiment analysis. The system consists of a user terminal, a cloud server, and multiple analysis software components. The main functions of this system are described below in natural language.

[0520] The user first takes a photo with their device or uploads existing image data. The device sends this image information to a cloud server, which uses image processing tools to extract the user's personal features. Deep learning models such as OpenCV and Torch are used here.

[0521] Next, the server uses AI-based analysis tools to identify user preferences based on past purchase and browsing history from user behavior records. This process employs cluster analysis and collaborative filtering algorithms, and leverages generative AI models.

[0522] Furthermore, the server uses facial expression data acquired during the image processing process to analyze the user's emotional state. Emotion recognition technologies such as Emotion API and Face++ are used to suggest clothing appropriate to the user's current emotions.

[0523] Finally, the recommendation generation system within the server comprehensively analyzes this information and presents the suggested outfits to the user on a virtual model generated by the visualization system. This allows the user to improve the accuracy of their product selection through virtual try-on, resulting in a more satisfying shopping experience.

[0524] As a concrete example, let's assume a user is looking for clothes for a relaxing holiday. If the user uploads a photo of themselves smiling, the system will recognize this as a positive emotion and suggest casual, relaxed styles. On the other hand, if the user's expression is serious, the system will suggest calmer colors and designs.

[0525] Examples of prompts for a generative AI model:

[0526] "Consider the user's image information and behavioral records, and suggest the optimal fashion items based on sentiment analysis results."

[0527] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0528] Step 1:

[0529] The user takes or selects an image of themselves using their device and uploads it to the server. At this stage, image data is obtained as input information, and this data is transferred to the server via a communication protocol.

[0530] Step 2:

[0531] The server analyzes the received image data using information processing tools to extract features such as the user's skin color, build, and facial shape. A deep learning model using OpenCV or Torch handles this process, extracting features from the image data and outputting them as feature parameters.

[0532] Step 3:

[0533] The server collects user behavior records and identifies preferences using analytical tools. The collected data includes browsing history and purchase history, which are analyzed using cluster analysis and collaborative filtering, and then converted into user preference parameters for output.

[0534] Step 4:

[0535] The server analyzes the user's facial expressions using image data and estimates their emotional state using emotion recognition technology. Emotion API and Face++ are utilized to analyze the emotional data based on the image and output the estimated emotional state.

[0536] Step 5:

[0537] The server's recommendation generation method uses a generative AI model to generate optimal clothing suggestions based on the obtained feature parameters, preference parameters, and emotional state. The prompt used is "Suggest fashion items considering feature parameters, preference parameters, and emotional state," and as a result, a list of recommended clothing items is output.

[0538] Step 6:

[0539] The server uses visualization tools to display a simulation of the user trying on recommended clothing items on their virtual model. At this stage, a virtual avatar tool is used to visually present the suggestions to the user, and the final feedback is output.

[0540] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0541] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0542] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0543] [Fourth Embodiment]

[0544] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0545] As shown in Figure 7, the 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.

[0546] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0547] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0548] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0549] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0550] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0551] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0552] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0553] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0554] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0555] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0556] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0557] The system according to the present invention allows a user to send images taken using their own device to a server, and then provides the user with optimal fashion suggestions based on those images and behavioral history data. First, the server receives the user's image data and processes it to analyze facial and body features. This analysis uses facial recognition technology and image processing technology. For example, individual features such as skin color, body type, and hairstyle are extracted. Based on this information, the system recommends the most suitable colors and styles for the user.

[0558] Meanwhile, the server collects user behavioral data and analyzes what fashion items the user has viewed and purchased in the past to reveal their style preferences. This analysis reveals trends in brands and items that the user frequently shows interest in.

[0559] Next, the server generates optimal fashion suggestions based on these analysis results and the current situation and purpose (TPO). These suggestions include clothing combinations and accessories that are likely to suit the user. For example, if the user is attending a casual event the next day, the server might suggest jeans and a brightly colored top.

[0560] The generated fashion suggestions are sent from the server to the user's terminal and presented to the user visually. Users can use these suggestions to make daily fashion choices and enhance their enjoyment of fashion by purchasing the suggested styles when shopping.

[0561] This system allows users to receive personalized fashion advice based on their own characteristics, making it easy to choose appropriate attire for different occasions.

[0562] The following describes the processing flow.

[0563] Step 1:

[0564] The user launches a dedicated app on their device and takes or selects a full-body image of themselves. The captured image is uploaded to the server via the device.

[0565] Step 2:

[0566] The server receives images sent by users and applies image processing algorithms to analyze facial and body features. Specifically, skin color, body shape, and facial features are extracted.

[0567] Step 3:

[0568] The server retrieves user behavior history data from the database. This includes previously viewed fashion items, purchase history, and search queries.

[0569] Step 4:

[0570] The server analyzes the user's behavioral history to identify their fashion preferences. This analysis uses machine learning techniques to identify brands and styles that the user tends to favor.

[0571] Step 5:

[0572] The server takes into account the current time, location, and purpose (TPO) to generate fashion recommendations that reflect the user's characteristics and preferences. These recommendations include suggestions for specific clothing and accessories.

[0573] Step 6:

[0574] The server sends the generated recommendation information to the user's device. The user can review the suggestions received on their device and consider whether to adopt the suggested style.

[0575] (Example 1)

[0576] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0577] Modern consumers tend to seek personalized fashion suggestions based on their individual characteristics and personalities. However, conventional systems have struggled to generate suggestions that adequately reflect the individual characteristics and preferences of users, resulting in unsatisfactory recommendations. To address this challenge, there is a need for a method to generate fashion suggestions that fully take into account the user's characteristics and behavioral history.

[0578] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0579] In this invention, the server includes an image analysis means for processing image information acquired from the user to extract the person's features, a data analysis means for analyzing the user's behavioral history information to identify their fashion preferences, and a suggestion generation means for generating fashion suggestions that are tailored to the identified features and preferences, as well as the current conditions and intended use. This makes it possible to provide personalized fashion suggestions that take into account the individual characteristics and preferences of the user.

[0580] A "user" refers to a person who uses the system to receive fashion suggestions based on their own information.

[0581] "Image information" refers to photographs and image data taken by users, and is used to analyze the user's physical characteristics.

[0582] "Image analysis means" refers to technology that processes image information received from a user and extracts physical and visual characteristics.

[0583] "Behavioral history information" refers to data on fashion-related actions a user has taken in the past, such as browsing and purchasing.

[0584] "Data analysis methods" refer to processes and technologies used to analyze behavioral history information and identify a user's fashion preferences.

[0585] "Suggestion generation means" refers to the process of creating optimal fashion suggestions for the user based on information obtained from image analysis means and data analysis means.

[0586] "Display means" refers to methods or devices for visually presenting generated fashion suggestions to users.

[0587] This invention is a system for users to receive fashion suggestions based on their individual characteristics, and implements a process to suggest appropriate fashion styles based on the user's image information and behavioral history information.

[0588] First, the user prepares to receive fashion suggestions using their device. The user takes an image using the camera on their device and sends the image information to the server. To ensure high security, the server uses the HTTPS protocol to transmit the image information.

[0589] When the server receives image information from a user, it first processes it using image analysis tools. Here, the server executes scripts in programming languages ​​such as Python and utilizes image processing software like OpenCV to extract visual features such as facial shape, skin tone, and body type. Furthermore, the server uses a generative AI model to input prompt messages and perform individual fashion style analysis. A concrete example of a prompt message might be, "Create fashion suggestions for a woman with light-toned skin who usually prefers office casual attire."

[0590] The server also analyzes user behavior history information. The database stores users' fashion-related behavior, and the server analyzes this data using data analysis tools. Big data analysis tools such as Apache Spark are used to identify the brands and styles that users prefer.

[0591] Based on these analysis results, the server uses a suggestion generation mechanism to generate optimal fashion suggestions for the user. The generated suggestions include clothing combinations and accessory selections tailored to specific events or occasions. The generated suggestions are sent to the user's device and displayed visually. By viewing these visual suggestions, the user can make their daily fashion choices more enjoyable and make more appropriate choices.

[0592] This system provides technology that enhances the user experience, meets individual needs, and establishes a new standard for fashion proposals.

[0593] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0594] Step 1:

[0595] The user launches a camera app on their device and takes a picture to receive fashion suggestions. The input is image data captured by the device's camera, which is then sent to the server. The device securely transfers this image data to the server using the HTTPS protocol.

[0596] Step 2:

[0597] The server receives image data sent from the terminal. Using the received image data as input, the server uses image analysis tools. Here, image processing libraries such as OpenCV are used to analyze the image and extract the user's physical characteristics, such as face shape, skin color, and body type, as vector data. The output of this analysis, the obtained feature information, is passed to the next process.

[0598] Step 3:

[0599] The server retrieves user behavior history information from a database. This input includes past browsing and purchase history. Using data analysis tools, the server analyzes this data with big data processing tools such as Apache Spark to quantify user preferences. The results of the analysis are output as a list of the user's preferences and areas of interest.

[0600] Step 4:

[0601] The server uses a suggestion generation mechanism, taking feature information obtained through image analysis and preference information based on behavioral history as input. It utilizes a generation AI model to provide fashion suggestions using prompts. An example prompt used is, "Please create fashion suggestions for a woman with light skin tone who usually prefers office casual attire." The output is a fashion suggestion customized for the user.

[0602] Step 5:

[0603] The server sends the generated fashion suggestions to the user's device. The data is securely transferred using HTTPS, and the suggestions are displayed on the device's screen. The user visually confirms this output and performs actions to support their daily fashion choices. This allows the user to use the suggested styles as a reference when making purchase decisions at physical stores or online stores.

[0604] (Application Example 1)

[0605] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0606] In modern society, consumers are faced with a wide variety of fashion items to choose from, but selecting the appropriate fashion for any given situation is a particularly difficult challenge. Because there is a lack of real-time information on fashion that suits oneself, consumers spend a great deal of time and effort choosing the best outfit for themselves.

[0607] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0608] In this invention, the server includes information processing means for processing image data acquired from a user to extract the person's characteristics, data analysis means for analyzing the user's behavioral history data to identify preferences, and recommendation generation means for generating suggestion information according to the identified characteristics and preferences, as well as the situation and purpose. This allows the user to visually confirm fashion suggestions that suit them in real time and make appropriate choices quickly.

[0609] "Information processing means" refers to a technical device or function that analyzes image data obtained from a user and extracts human characteristics from the image.

[0610] "Data analysis means" refers to a technical device or function that investigates a user's behavioral history data and identifies their preferences and tastes based on that data.

[0611] A "recommendation generation method" is a technical device or function that generates optimal suggestion information for the user based on extracted characteristics and preferences, as well as the situation and application.

[0612] "Presentation means" refers to a technical device or function that provides generated proposal information to the user visually, for example, by displaying it in real time via a smart device.

[0613] The system implementing this invention involves the coordinated operation of a user, a terminal, and a server. The user acquires image data using a terminal such as smart glasses. The terminal is equipped with communication capabilities to transmit the image data to the server. The server analyzes the received image data using image processing software such as OpenCV to extract features such as the user's face shape, physique, and skin color.

[0614] The server further analyzes the user's past behavior history using data analysis tools such as Pandas to identify the user's preferred fashion trends from the database. This reveals specific brands and styles.

[0615] Based on these analysis results, the server uses generative AI models such as TensorFlow to generate fashion suggestions best suited to the user. The user's characteristics, preferences, and current situation and purpose are all considered during this process. An example of a prompt generated during this process would be, "Please suggest an outfit suitable for a 30-year-old woman, casual, and attending a cafe event."

[0616] The generated fashion suggestions are sent to the user's device in real time. The user can visually check the suggested clothing and styles on their device and make appropriate fashion choices based on that information.

[0617] As a concrete example, when a user participates in a casual book club at a cafe, a casual yet stylish combination of a denim jacket and a white shirt is suggested. This system allows users to easily choose the perfect outfit for themselves.

[0618] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0619] Step 1:

[0620] The user takes a picture of themselves using their device and sends that image to the server. Image data acquired by the device's camera becomes the input, and the image data is sent to the server via the communication function.

[0621] Step 2:

[0622] The server processes the received image data using OpenCV to extract features including the user's face shape, body type, and skin color. The input data is image data, and its features are analyzed using OpenCV's image processing techniques. The output provides the user's feature parameters.

[0623] Step 3:

[0624] The server uses Pandas to analyze user behavioral data and identify fashion preferences from past purchase and browsing history. The input data is behavioral data, which is analyzed using Pandas, and the output is a trend in preferences.

[0625] Step 4:

[0626] The server uses TensorFlow to run a generative AI model based on extracted features and preferences to generate optimal fashion suggestions for the user. In this process, feature parameters and preference data are used as input data, and specific fashion suggestions are generated as output.

[0627] Step 5:

[0628] The server sends the generated fashion suggestions to the user's device. The device visually displays the received fashion suggestions and provides the user with their content. The input data is the fashion suggestions, which are conveyed to the user visually in real time via the device's display function.

[0629] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0630] The system according to the present invention provides fashion suggestions based on the user's image data and behavioral history data, and further combines this with emotion analysis means to recognize the user's emotions. This system analyzes the user's facial and body features and obtains information based on the images when the user sends images taken with a terminal to a server. The server performs image processing to identify the user's skin color, body shape, and facial shape in particular.

[0631] In parallel, the server analyzes the user's behavioral history. This information includes fashion items previously viewed, items purchased, and frequently accessed brand pages. The analysis results are used to identify the user's fashion preferences.

[0632] Furthermore, this invention incorporates a new emotion analysis means. The server analyzes the user's facial expressions from the received image data and estimates the user's emotional state. For example, if the user is smiling, it is judged to be a positive emotion, and a more adventurous style of fashion suggestion may be appropriate. On the other hand, if a negative emotion is detected, a style that will reassure the user is provided.

[0633] The fashion suggestions generated in this way are sent by the server to the user's terminal and presented visually. The user can review the suggestions and decide whether to purchase new fashion items based on the suggested style.

[0634] This system allows users to receive personalized fashion advice tailored to their current emotions, characteristics, and preferences, resulting in a more satisfying shopping experience.

[0635] The following describes the processing flow.

[0636] Step 1:

[0637] Users launch a dedicated application on their device and take or select a full-body image that captures their facial expressions, then send it to the server. Users can also optionally add comments about their preferred style or current mood.

[0638] Step 2:

[0639] The server processes the received image data and performs face recognition and expression analysis. First, it detects facial features, and then uses an emotion analysis algorithm to identify the user's emotions. For example, it identifies positive or negative emotions from facial expressions such as smiles or confusion.

[0640] Step 3:

[0641] The server then extracts visual features from the image, such as skin tone, body shape, and facial features. This makes it easier to suggest colors and styles that suit the user. This data is also used to filter fashion items stored in the database.

[0642] Step 4:

[0643] The server retrieves user behavior history data. This data includes past purchase history, page viewing history, and favorited items. The server analyzes this data to identify trends in brands and styles that the user has previously preferred.

[0644] Step 5:

[0645] The server synthesizes the analysis results and generates fashion suggestions that reflect the user's characteristics, preferences, and current emotional state. For example, if the user has plans to go out, it will recommend active, brightly colored casual wear. If the user's emotions are positive, it may include suggestions for more adventurous styles.

[0646] Step 6:

[0647] The server sends the generated fashion suggestions to the user's device to visually present them. The user can then view the suggested items and styles on their device and access detailed information and purchase links.

[0648] This process allows users to receive fashion suggestions tailored to their mood and schedule for the day in real time, enabling them to enjoy a shopping experience that broadens their range of self-expression.

[0649] (Example 2)

[0650] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0651] Conventional fashion recommendation systems make suggestions based on limited information such as the user's basic characteristics and behavioral history, and have the drawback of not being able to provide personalized suggestions that take into account the user's emotional state at any given time. Furthermore, fashion recommendations often fail to fully adapt to the emotions and psychological state of individual users, making it difficult to increase satisfaction.

[0652] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0653] In this invention, the server includes processing means for processing image information acquired from the user to extract the person's characteristics, analysis means for analyzing the user's behavioral history information to identify fashion preferences, and generation means for recognizing emotional states from the image information and generating fashion suggestions based on those emotional states. This makes it possible to provide personalized fashion suggestions that take into account the user's behavioral history and emotional states.

[0654] "Image information" refers to photographic and video data that includes the user's facial and physical characteristics.

[0655] "Processing means" refers to devices or programs used to analyze digital information and extract specific parameters.

[0656] "Behavioral history information" refers to historical data such as what products a user has viewed or purchased in the past, and what brand websites they have visited.

[0657] "Analysis means" refers to devices or programs used to analyze acquired data and identify user preferences and trends.

[0658] "Emotional state" refers to the psychological state of the user at that time, inferred from their facial expressions, voice, etc.

[0659] "Generative means" refers to devices or programs used to create new data or proposals based on analysis results.

[0660] "Presentation means" refers to devices or programs that provide generated information to the user visually or audibly.

[0661] To implement this invention, the user first takes images of their face and body using the camera on their device. These images are then sent from the device to a server. The server uses image processing software to analyze the user's facial features, body shape, skin color, and other characteristics. Image processing libraries such as OpenCV are utilized in this process.

[0662] The server simultaneously retrieves and analyzes user behavior history information from a database. This behavior history information includes data such as online browsing history, purchase history, and visited brand websites. MySQL or PostgreSQL can be used as the database management system for data analysis. Based on this data, the user's fashion preferences are identified.

[0663] Furthermore, the server analyzes the user's facial expressions from image data using an emotion analysis tool. An emotion analysis API can be used for emotion analysis. The system infers the user's emotional state and then uses a generative AI model to suggest a suitable fashion style. Here, an example of a prompt for the generative AI model is, "Suggest the best style for this user."

[0664] The server also utilizes this information to create fashion suggestions based on the user's characteristics, preferences, and emotional state. These suggestions are output as specific styles by a generative AI model and sent from the server to the user's device. The user can then review these suggestions on their device and consider their options.

[0665] This system allows users to receive personalized fashion advice tailored to their individual characteristics and preferences, resulting in a more satisfying shopping experience.

[0666] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0667] Step 1:

[0668] The user takes pictures of their face and body using the device's camera. The captured images are saved on the device in JPEG or PNG format and sent to the server via the internet connection. In this process, the input is the image data captured by the user, and the output is the image data sent to the server.

[0669] Step 2:

[0670] The server analyzes the received image data using image processing software. Specifically, it uses OpenCV to perform face detection and feature extraction. The input is the image data sent to the server, and the output is characteristic information such as the user's face shape, body type, and skin color.

[0671] Step 3:

[0672] The server retrieves user activity history information from the database. Here, a database management system (e.g., MySQL) is used to retrieve products the user has previously viewed and purchase history. The input is the user ID, and the output is the user's activity history data.

[0673] Step 4:

[0674] The server analyzes behavioral history data to identify the user's fashion preferences. It utilizes data mining techniques to analyze the patterns of brands and styles the user favors. The input is behavioral history data, and the output is information about the user's fashion preferences.

[0675] Step 5:

[0676] The server uses an emotion analysis API to analyze the user's facial expressions from image data and estimate their emotional state. Here, it analyzes emotions such as smiles, surprise, and sadness. The input is the user's image data, and the output is information indicating the user's emotional state.

[0677] Step 6:

[0678] Based on these analysis results, the server generates fashion suggestions using a generative AI model. Taking a prompt (e.g., "Suggest the best style for this user.") as input, the AI ​​model outputs specific fashion style suggestions. The input consists of analyzed characteristic information, emotional state, and preference data, while the output is fashion suggestion data.

[0679] Step 7:

[0680] The server sends the generated fashion suggestions to the user's terminal. The terminal visually displays these suggestions for the user to review. The input is the fashion suggestion data, and the output is the suggestion information displayed on the user's terminal.

[0681] (Application Example 2)

[0682] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0683] This invention aims to improve user satisfaction in conventional online shopping systems by providing optimal clothing suggestions that take into account the user's individual characteristics, behavioral history, and even emotional state. Furthermore, it aims to support rational purchasing decisions without actual try-on by providing an environment where users can virtually try on clothes.

[0684] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0685] In this invention, the server includes information processing means for processing image information acquired from the user to extract the person's characteristics; analysis means for analyzing the user's behavioral records to identify the user's preferences for items; recommendation generation means for generating clothing suggestions that are appropriate to the situation and purpose based on the identified characteristics and preferences, as well as emotional analysis; and visualization means having a function to virtually try on the suggested clothing. This makes it possible for the user to easily select products that suit their characteristics and emotional state, confirm the fit through virtual try-on, and obtain a highly satisfying shopping experience.

[0686] "Image information" refers to photos and video data provided by users, and is the basic data used to analyze the physical characteristics of individuals.

[0687] "Information processing means" refers to computer processing functions used to extract human characteristics from acquired image information.

[0688] "Behavioral data" refers to recorded data that reflects a user's interests and preferences, such as their past browsing history, purchase history, and frequently visited web pages.

[0689] "Analysis methods" refer to analytical techniques used to identify a person's preferences from behavioral records, and are implemented using machine learning algorithms and the like.

[0690] "Emotional analysis" is the process of estimating a user's current emotional state from image information, and primarily uses facial expression analysis technology.

[0691] "Situation and application" refers to the user's current environment and required functional needs, and the suitability of the proposal is judged based on this.

[0692] "Recommendation generation method" refers to technology that generates optimal product suggestions based on the characteristics, preferences, and circumstances of a specific individual.

[0693] "Visualization means" refers to technologies that provide a realistic fitting experience when users virtually try on products.

[0694] This invention provides a system that suggests optimal clothing based on user image information, behavioral records, and sentiment analysis. The system consists of a user terminal, a cloud server, and multiple analysis software components. The main functions of this system are described below in natural language.

[0695] The user first takes a photo with their device or uploads existing image data. The device sends this image information to a cloud server, which uses image processing tools to extract the user's personal features. Deep learning models such as OpenCV and Torch are used here.

[0696] Next, the server uses AI-based analysis tools to identify user preferences based on past purchase and browsing history from user behavior records. This process employs cluster analysis and collaborative filtering algorithms, and leverages generative AI models.

[0697] Furthermore, the server uses facial expression data acquired during the image processing process to analyze the user's emotional state. Emotion recognition technologies such as Emotion API and Face++ are used to suggest clothing appropriate to the user's current emotions.

[0698] Finally, the recommendation generation system within the server comprehensively analyzes this information and presents the suggested outfits to the user on a virtual model generated by the visualization system. This allows the user to improve the accuracy of their product selection through virtual try-on, resulting in a more satisfying shopping experience.

[0699] As a concrete example, let's assume a user is looking for clothes for a relaxing holiday. If the user uploads a photo of themselves smiling, the system will recognize this as a positive emotion and suggest casual, relaxed styles. On the other hand, if the user's expression is serious, the system will suggest calmer colors and designs.

[0700] Examples of prompts for a generative AI model:

[0701] "Consider the user's image information and behavioral records, and suggest the optimal fashion items based on sentiment analysis results."

[0702] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0703] Step 1:

[0704] The user takes or selects an image of themselves using their device and uploads it to the server. At this stage, image data is obtained as input information, and this data is transferred to the server via a communication protocol.

[0705] Step 2:

[0706] The server analyzes the received image data using information processing tools to extract features such as the user's skin color, build, and facial shape. A deep learning model using OpenCV or Torch handles this process, extracting features from the image data and outputting them as feature parameters.

[0707] Step 3:

[0708] The server collects user behavior records and identifies preferences using analytical tools. The collected data includes browsing history and purchase history, which are analyzed using cluster analysis and collaborative filtering, and then converted into user preference parameters for output.

[0709] Step 4:

[0710] The server analyzes the user's facial expressions using image data and estimates their emotional state using emotion recognition technology. Emotion API and Face++ are utilized to analyze the emotional data based on the image and output the estimated emotional state.

[0711] Step 5:

[0712] The server's recommendation generation method uses a generative AI model to generate optimal clothing suggestions based on the obtained feature parameters, preference parameters, and emotional state. The prompt used is "Suggest fashion items considering feature parameters, preference parameters, and emotional state," and as a result, a list of recommended clothing items is output.

[0713] Step 6:

[0714] The server uses visualization tools to display a simulation of the user trying on recommended clothing items on their virtual model. At this stage, a virtual avatar tool is used to visually present the suggestions to the user, and the final feedback is output.

[0715] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0716] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0717] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0718] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0719] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0720] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0721] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0722] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0723] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0724] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0725] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0726] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0727] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0728] 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.

[0729] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0730] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0731] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0732] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0733] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0734] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0735] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0736] The following is further disclosed regarding the embodiments described above.

[0737] (Claim 1)

[0738] Image processing means for processing image data obtained from a user to extract features of a person,

[0739] An analysis means for analyzing the user's behavioral history data to identify their fashion preferences,

[0740] A recommendation generation method that generates fashion suggestions based on identified characteristics and preferences, as well as current circumstances and uses,

[0741] A presentation means that provides the user with fashion suggestions generated by the recommendation generation means,

[0742] A system that includes this.

[0743] (Claim 2)

[0744] The system according to claim 1, wherein the analysis means includes the step of extracting specific fashion brands and styles from the user's behavior history.

[0745] (Claim 3)

[0746] The system according to claim 1, wherein the image processing means includes the step of extracting the user's skin color, body shape, and facial shape as specific parameters.

[0747] "Example 1"

[0748] (Claim 1)

[0749] An image analysis means that processes image information obtained from a user to extract the features of a person,

[0750] A data analysis means that analyzes the user's behavioral history information to identify their fashion preferences,

[0751] A proposal generation means that generates fashion suggestions based on identified characteristics and preferences, as well as current conditions and uses,

[0752] A display means for providing the generated fashion suggestions to the user,

[0753] A system that includes this.

[0754] (Claim 2)

[0755] The system according to claim 1, wherein the data analysis means includes a step of extracting specific clothing brands and styles from the user's behavior history.

[0756] (Claim 3)

[0757] The system according to claim 1, wherein the image analysis means includes a step of extracting the user's skin tone, body shape, and facial shape as specific attributes.

[0758] "Application Example 1"

[0759] (Claim 1)

[0760] An information processing means for processing image data obtained from a user to extract the characteristics of a person,

[0761] A data analysis means for analyzing the user's behavioral history data to identify preferences,

[0762] A recommendation generation means that generates suggested information tailored to identified characteristics and preferences, as well as the situation and application,

[0763] A presentation means that provides the user with fashion suggestions generated by the recommendation generation means and displays them visually in real time,

[0764] A system that includes this.

[0765] (Claim 2)

[0766] The system according to claim 1, wherein the data analysis means includes the step of extracting specific product groups or forms from the user's behavior history.

[0767] (Claim 3)

[0768] The system according to claim 1, wherein the information processing means includes the step of extracting the user's skin color, body type, and facial shape as specific indicators.

[0769] "Example 2 of combining an emotion engine"

[0770] (Claim 1)

[0771] A processing means for extracting the characteristics of a person by processing image information obtained from a user,

[0772] An analysis means for analyzing the user's behavioral history information to identify their fashion preferences,

[0773] A generation means that recognizes an emotional state from the aforementioned image information and generates fashion suggestions based on that emotional state,

[0774] A presentation means that provides the user with fashion suggestions generated by the generation means,

[0775] A system that includes this.

[0776] (Claim 2)

[0777] The system according to claim 1, wherein the analysis means includes the step of extracting specific brands or styles from the user's behavior history.

[0778] (Claim 3)

[0779] The system according to claim 1, wherein the processing means includes a step of extracting the user's skin color, body shape, and facial shape as specific criteria.

[0780] "Application example 2 when combining with an emotional engine"

[0781] (Claim 1)

[0782] An information processing means that processes image information obtained from a user to extract the characteristics of a person,

[0783] An analysis means for analyzing the user's behavioral records to identify their preferences for items,

[0784] A recommendation generation method that generates clothing suggestions tailored to the situation and use based on identified characteristics and preferences, as well as sentiment analysis,

[0785] A presentation means that provides the user with clothing suggestions generated by the recommendation generation means,

[0786] A visualization means having a function for the user to virtually try on the proposed clothing,

[0787] A system that includes this.

[0788] (Claim 2)

[0789] The system according to claim 1, wherein the analysis means includes the step of extracting specific item brands and styles from the user's behavior record.

[0790] (Claim 3)

[0791] The system according to claim 1, wherein the information processing means includes the step of extracting the user's skin color, physique, and facial shape as specific parameters. [Explanation of Symbols]

[0792] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Image processing means for processing image data obtained from a user to extract features of a person, An analysis means for analyzing the user's behavioral history data to identify their fashion preferences, A recommendation generation method that generates fashion suggestions based on identified characteristics and preferences, as well as current circumstances and uses, A presentation means that provides the user with fashion suggestions generated by the recommendation generation means, A system that includes this.

2. The system according to claim 1, wherein the analysis means includes the step of extracting specific fashion brands and styles from the user's behavior history.

3. The system according to claim 1, wherein the image processing means includes the step of extracting the user's skin color, body shape, and facial shape as specific parameters.

Images