system

Abstract

A system is provided.SOLUTION: A system comprising: means for inputting and storing basic information of a user; means for analyzing an image of clothing and small articles possessed by the user and storing the information; means for acquiring and analyzing data from a social networking service and an electronic commerce site in order to analyze hobbies and preferences of the user; and means for generating a coordinate based on the basic information, clothing information, hobbies and preferences data, and the TPO guideline.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] People who normally do not have a strong interest in clothing often have difficulty choosing appropriate clothing for specific occasions (e.g., weddings, funerals, business meetings, leisure activities, etc.). There is also a need to avoid wearing clothes that are similar to others, and there is a need to address this need. Existing outfit suggestion systems have difficulty comprehensively proposing appropriate outfits that take into account the user's physique, hobbies, tastes, and specific occasions, and therefore are not yet able to help users establish rational, personalized outfits. [Means for solving the problem]

[0005] The present invention provides a system that enables even people who are not interested in clothing to easily select appropriate clothing for a specific occasion. This system includes a means for inputting and saving basic user information, a means for analyzing and saving images of clothing and accessories, a means for acquiring and analyzing data from social networking services and e-commerce sites, a means for acquiring TPO (Time, Place, Occasion) guidelines, a means for generating outfits based on this information, and a means for proposing the generated outfits and receiving feedback. This configuration allows users to easily select appropriate and personalized styling for a specific occasion.

[0006] "User" refers to a person who uses this system and provides basic information and hobbies and preferences in order to receive coordination suggestions.

[0007] "Basic information" refers to information necessary for suggesting outfits, including the user's physical information (height, weight, etc.) and account information for social networking services and e-commerce sites.

[0008] "Clothing" refers to the clothing and accessories owned by the user, and refers to all items that are the subject of coordination suggestions.

[0009] "Image analysis" refers to a technology that automatically identifies the color, type, brand, style, etc. of clothing or accessories from uploaded photos and extracts this information.

[0010] "Tastes and Interests" refers to information that indicates a user's preferences, such as patterns of style, brand, color, etc., analyzed from data on social networking services and e-commerce sites.

[0011] "TPO guidelines" are information that indicates appropriate standards for clothing in specific situations, providing styling guidelines according to the time, place, and occasion.

[0012] "Generative AI" refers to artificial intelligence that generates optimal outfits based on provided basic information, clothing information, hobby and taste data, and TPO guidelines.

[0013] "Coordination" refers to the combination of clothing and accessories suggested to users, and refers to styling appropriate for a particular scene.

[0014] "Feedback" refers to the evaluations and requests that users make of the proposed coordination, and new proposals are made based on this. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11]FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below with reference to the preferred embodiment. The system is composed of users, terminals, and a server, and each of the users plays a specific role in the system.

[0037] 1. User Registration

[0038] Fill out the registration form

[0039] First, a user launches the application and fills in the registration form with basic information such as name, email address, password, height, weight, etc. They also add account information for their favorite social networking services and e-commerce sites.

[0040] Sending and storing information

[0041] The entered information is sent from the terminal to the server, where it is securely encrypted and stored in a database.

[0042] 2. Collecting item data

[0043] Upload a photo

[0044] Next, the user takes photos of their own clothing and accessories and uploads them to the server through the application.

[0045] Image analysis and storage

[0046] The server analyzes the uploaded photos and automatically extracts details such as color, type, brand, style, etc. The extracted data is stored in a database.

[0047] 3. Analysis of hobbies and interests

[0048] Data Acquisition

[0049] The server automatically retrieves data such as browsing history, likes, and purchase history from social networking sites and e-commerce sites that users connect to.

[0050] Data analysis

[0051] The acquired data is analyzed to identify the user's preferences, such as preferred styles, brands, and colors. This information is clustered using machine learning algorithms and stored in a database.

[0052] 4. Select the scene and check the time, place, and occasion

[0053] Select a scene

[0054] The user selects a specific scene (e.g., wedding, casual date, business meeting, etc.) from a scene selection screen within the application.

[0055] Obtaining TPO guidelines

[0056] The server retrieves TPO guidelines from the database according to the selected scene, clarifying the appropriate clothing standards for that scene.

[0057] 5. Coordinate Generation

[0058] Coordinate generation

[0059] The server uses AI to generate optimal outfits based on the user's basic information, clothing information, hobbies and preferences, and TPO guidelines. This generation process determines the combination of items that are appropriate for the selected occasion.

[0060] Save your outfit

[0061] The generated coordinate information is stored again in the database.

[0062] 6. Coordination suggestions and feedback

[0063] Submit a proposal

[0064] The server sends the generated coordinate information to the user's terminal, which displays the information on its screen.

[0065] Receiving feedback

[0066] The user can check the proposed outfit and enter feedback as needed, such as requests like "more casual" or "different colors."

[0067] re-proposal

[0068] The server receives feedback from the user, uses the generative AI to revise the outfit and make a new suggestion. This cycle allows the user to achieve a style that is uniquely their own.

[0069] Specific examples

[0070] User registration example

[0071] Mr. Tanaka (user) registers as a new user, inputs his height of 175 cm and weight of 70 kg, and links his accounts for social networking service A, a commonly used SNS, and e-commerce site B.

[0072] Item Data Collection Example

[0073] Tanaka uploads photos of his personal items, such as shirts, pants, and shoes, to the app. The server analyzes these photos, extracts the necessary information, and stores it.

[0074] Example of analysis of hobbies and interests

[0075] The server retrieves Tanaka's browsing history and purchase history from social networking service A and e-commerce site B, and analyzes that he prefers casual and simple designs.

[0076] Scene selection example

[0077] Tanaka specifies on the app that she wants to choose an outfit to wear to attend a friend's wedding, and the server retrieves the appropriate TPO guidelines for the occasion.

[0078] Coordinate Generation Example

[0079] Based on Tanaka's basic information, clothing information, tastes, and TPO, the server uses generative AI to generate the optimal outfit, suggesting a combination of a simple black suit, a white shirt, and brown leather shoes.

[0080] Suggestions and Feedback Examples

[0081] Tanaka reviews this proposal and, if he prefers a different color or style, he sends feedback and the server makes a new proposal.

[0082] In this way, the system of the present invention allows the user to easily and accurately select a style that is appropriate and unique to the user for a particular scene.

[0083] The processing flow will be explained below.

[0084] User Registration

[0085] Step 1:

[0086] A user launches the application and enters basic information such as name, email address, password, height, and weight into the new registration form.

[0087] Step 2:

[0088] The user selects their preferred social networking services and e-commerce sites and enters their respective account information.

[0089] Step 3:

[0090] The device sends all the information entered in the registration form to the server.

[0091] Step 4:

[0092] The server receives the information sent and stores it securely in a database.

[0093] Item Data Collection

[0094] Step 1:

[0095] The user takes a photo of their own clothing and accessories.

[0096] Step 2:

[0097] The device uploads the photograph to the server.

[0098] Step 3:

[0099] The server sends the received photos to an image analysis service to extract information such as color, type, brand, and style.

[0100] Step 4:

[0101] The server stores the analysis results in a database.

[0102] Analysis of hobbies and interests

[0103] Step 1:

[0104] The server obtains data such as browsing history, likes, and purchase history from the social networking services and e-commerce sites that the user has connected to.

[0105] Step 2:

[0106] The server analyzes the data and uses machine learning algorithms to identify the user's preferences, such as preferred styles, brands, and colors.

[0107] Step 3:

[0108] The server stores the analysis results in a database.

[0109] Select the scene and check the time, place, and occasion

[0110] Step 1:

[0111] The user selects a specific scene (e.g., wedding, casual date, business meeting, etc.) from a scene selection screen within the application.

[0112] Step 2:

[0113] The server retrieves the TPO guidelines corresponding to the selected scene from the database.

[0114] Coordinate generation

[0115] Step 1:

[0116] The server sends the user's basic information, clothing information, hobbies and preferences, and TPO guidelines as input data to the generation AI.

[0117] Step 2:

[0118] The generative AI generates the optimal coordination based on the input data.

[0119] Step 3:

[0120] The server stores the generated coordinate information in a database.

[0121] Coordination suggestions and feedback

[0122] Step 1:

[0123] The server transmits the stored coordinate information to the user's terminal.

[0124] Step 2:

[0125] The device displays the suggested outfit to the user, along with images and detailed information (such as a list of combined items and options for replacing each item) on the screen.

[0126] Step 3:

[0127] Users can provide feedback on the proposed outfits, such as requests like "I want it to be more casual" or "I'd like a different color."

[0128] Step 4:

[0129] The server receives feedback from the user, and based on that, the generative AI revises the coordination and makes a new proposal.

[0130] The above is the specific processing flow for carrying out the invention.

[0131] Example 1

[0132] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0133] Conventional outfit suggestion systems were unable to fully utilize the user's basic information and clothing information, and had difficulty accurately analyzing the user's tastes and preferences to suggest outfits suitable for specific occasions. Furthermore, the process of reflecting user feedback and re-suggesting outfits was complicated and time-consuming. For these reasons, there was a demand for more accurate outfit suggestions and a system that could quickly reflect user feedback.

[0134] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0135] In this invention, the server includes means for inputting and saving basic information about a user, means for analyzing images of clothing and accessories owned by the user and saving the information, means for acquiring and analyzing data from social networking services and e-commerce sites to analyze the user's tastes and preferences and saving the results, means for acquiring TPO guidelines for specific occasions, means for using a generative AI model to generate outfits based on the basic information, clothing information, tastes and preferences data, and TPO guidelines, means for proposing the generated outfits to the user and receiving feedback as needed, and means for regenerating the outfits based on the feedback, thereby enabling highly accurate outfit suggestions to be made to the user and for the feedback to be reflected quickly and effectively.

[0136] "Basic user information" refers to personal information entered by the user, such as name, email address, password, height, and weight.

[0137] "Images of clothing and accessories owned by the user" refers to photos of clothing, accessories, etc. owned by the user.

[0138] An "image analysis library" refers to a software tool that analyzes images of clothing and accessories and extracts detailed information such as color, type, brand, and style.

[0139] "Social networking service" refers to a website or application that provides services that enable users to interact online.

[0140] "E-commerce site" refers to a website or platform used by users to purchase products online.

[0141] "Data for analyzing hobbies and tastes" refers to information including users' browsing history, likes, purchase history, etc.

[0142] "TPO guidelines for specific occasions" refers to standards and guidelines for appropriate attire for specific occasions or events.

[0143] A "generative AI model" refers to a model that uses artificial intelligence algorithms to generate new information or content based on data.

[0144] "Coordination" refers to clothing combinations suggested based on the user's basic information, clothing information, hobbies and preferences, and TPO guidelines.

[0145] "Feedback" refers to the user's thoughts and requests regarding the proposed coordination.

[0146] "Regeneration" refers to the process of regenerating coordinates based on received feedback.

[0147] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below with reference to the preferred embodiment. The system is composed of users, terminals, and a server, and each of the users plays a specific role in the system.

[0148] 1. User Registration

[0149] A user launches an application and fills in a registration form with basic information such as name, email address, password, height, weight, etc. They also enter account information for their favorite social networking services and e-commerce sites. The information is sent from the device to the server, where it is securely encrypted and stored in a database (e.g., MySQL or PostgreSQL).

[0150] Specific examples

[0151] For example, a user has a height of 175 cm, a weight of 70 kg, and inputs account information for a commonly used social networking service A and an e-commerce site B.

[0152] 2. Collecting item data

[0153] Users take photos of their clothing and accessories and upload them to the server through the application. The server then analyzes the uploaded photos using an image analysis library (e.g., OpenCV) and automatically extracts detailed information such as color, type, brand, and style. The extracted data is stored in a database.

[0154] Specific examples

[0155] For example, when a user uploads photos of their shirts, pants, shoes, etc. to the app, the server analyzes these photos, extracts the necessary information, and stores it.

[0156] 3. Analysis of hobbies and interests

[0157] The server automatically retrieves data from the user's connected social networking sites and e-commerce sites via API. The retrieved data is analyzed using machine learning algorithms (e.g., k-means clustering) to identify the user's preferences, such as preferred styles, brands, and colors. This information is also stored in a database.

[0158] Specific examples

[0159] For example, the server acquires the user's browsing history and purchase history from SNS A and e-commerce site B, and analyzes that the user prefers casual and simple designs.

[0160] 4. Select the scene and check the time, place, and occasion

[0161] The user selects a specific scene (e.g., wedding, casual date, business meeting, etc.) from the scene selection screen within the application. The server retrieves TPO guidelines from the database according to the selected scene and clarifies the appropriate attire standards for that scene.

[0162] Specific examples

[0163] For example, when a user selects an outfit to wear to a friend's wedding, the server obtains the TPO guidelines appropriate for that occasion.

[0164] 5. Coordinate Generation

[0165] The server uses a generative AI model (e.g., GPT-3) to generate optimal outfits based on the user's basic information, clothing information, hobbies and preferences, and TPO guidelines. The generated outfit information is stored in a database.

[0166] Prompt Sentence Examples

[0167] "User basic information: height 175cm, weight 70kg. Clothing information: black suit, white shirt, brown leather shoes. Preferred style: simple, casual. TPO: formal, like a wedding. Generate the optimal outfit based on this information."

[0168] Specific examples

[0169] For example, based on Tanaka's basic information, clothing information, tastes, and TPO, the server uses generative AI to generate the optimal outfit of a simple black suit, white shirt, and brown leather shoes.

[0170] 6. Coordination suggestions and feedback

[0171] The server sends the generated outfit information to the user's device, which displays it on the screen. The user reviews the suggested outfit and provides feedback as needed. The server receives the user's feedback, again modifies the outfit using the generative AI model, and re-proposes it. This cycle allows the user to achieve a style that is uniquely their own.

[0172] Specific examples

[0173] For example, if Tanaka checks the proposed outfit and sends feedback indicating a preference for a different color or style, the server will make a new suggestion.

[0174] In this way, the system of the present invention allows the user to easily and accurately select a style that is appropriate and unique to the user for a particular scene.

[0175] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0176] Step 1:

[0177] A user starts an application and enters basic information such as name, email address, password, height, and weight into a new registration form. In addition, the user also enters account information for frequently used social networking services and e-commerce sites. This input information is sent to the server as device input. The server securely encrypts the received information and stores it in a database (e.g., MySQL or PostgreSQL). The input from the device is basic information and linked account information, which is encrypted and stored by the server.

[0178] Step 2:

[0179] Users take photos of their clothing and accessories and upload them to the server through the application. This photo data is sent to the server via the device. The server then analyzes the uploaded photo using an image analysis library (e.g., OpenCV) and automatically extracts detailed information such as color, type, brand, and style. The analyzed information is stored in a database. The input is image data, and the information extracted through image analysis is the output.

[0180] Step 3:

[0181] The server automatically acquires data (browsing history, likes, purchase history, etc.) from linked social networking sites and e-commerce sites via API. This data becomes the input to the server. The acquired data is analyzed using a machine learning algorithm (e.g., k-means clustering). As a result, the user's preferences, such as preferred styles, brands, and colors, are identified. This identified preference information is stored in a database. The acquired data is the input, and the analyzed preference information is stored as the output.

[0182] Step 4:

[0183] The user selects a scene, such as a wedding, casual date, or business meeting, from the scene selection screen within the application. This selection is input from the device to the server. The server then retrieves TPO guidelines from the database according to the selected scene. This clarifies the appropriate clothing standards for a particular scene. The user's scene selection is the input, and the retrieved TPO guidelines are the output.

[0184] Step 5:

[0185] The server generates the optimal outfit using a generative AI model (e.g., GPT-3) based on the user's basic information, clothing information, taste data, and TPO guidelines. The following prompt sentences are used in this generation process:

[0186] "User basic information: height 175cm, weight 70kg. Clothing information: black suit, white shirt, brown leather shoes. Preferred style: simple, casual. TPO: formal, like a wedding. Generate the optimal outfit based on this information."

[0187] The generated coordination information is stored in a database. The input is basic information, clothing information, taste data, and TPO guidelines, and the output is the generated coordination.

[0188] Step 6:

[0189] The server sends the generated coordination information to the user's device. The device displays this information on the screen. The user checks the proposed coordination and enters feedback as needed. The feedback becomes input from the device to the server. The server receives this feedback, again uses the generative AI model to revise the coordination and make a new proposal. This provides the optimal coordination for the user. The generated coordination proposal is the output, and regeneration and re-proposition are performed based on the received feedback.

[0190] (Application example 1)

[0191] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0192] Conventional outfit suggestion systems often struggle to provide outfits that accurately reflect a user's tastes and preferences. Furthermore, it takes time and effort for users to visually select and purchase items based on the suggested outfits. Furthermore, there are issues with systems that make it difficult to select appropriate fashion items for specific occasions. As a result, problems arise in terms of low user satisfaction and a declining reuse rate.

[0193] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0194] In this invention, the server includes means for inputting and saving basic user information, means for analyzing images of clothing and accessories owned by the user and saving the information, means for acquiring and analyzing data from social networking services and e-commerce sites to analyze the user's hobbies and tastes and saving the results, means for acquiring TPO guidelines for specific occasions, means for generating outfits based on the basic information, clothing information, hobbies and tastes data, and TPO guidelines, means for proposing the generated outfits to the user and receiving feedback as needed, and means for providing links to online shopping sites to encourage the purchase of products related to the proposed outfits. This enables the system to propose outfits optimized based on the user's hobbies and tastes and to enable the user to purchase the proposed products quickly and easily.

[0195] "Basic user information" refers to personal identification information such as name, email address, password, height, and weight.

[0196] "Clothing and accessories" refers to fashion items such as clothing and accessories owned by the user.

[0197] "Means for analyzing images and storing the information" refers to technology that uses image analysis algorithms to extract information such as color, type, brand, and style from images of clothing and accessories, and stores the data.

[0198] "Means of acquiring data from social networking services and e-commerce sites, analyzing the data, and saving the results in order to analyze hobbies and preferences" refers to technology that acquires browsing history and purchase history from the social networking services and e-commerce sites that users connect to, and uses machine learning algorithms to identify and save the user's preferences.

[0199] "TPO guidelines" are standards for appropriate clothing for specific occasions.

[0200] The "means of generating coordination" is a technology that uses generative AI to create optimal fashion coordination based on the user's basic information, clothing information, hobbies and tastes, and TPO guidelines.

[0201] "Means for proposing the generated coordination to the user and receiving feedback as necessary" refers to a technology that displays the generated fashion coordination information to the user, receives request for changes from the user, and regenerates the coordinated information.

[0202] The "means for providing a link to a mail-order site" is a technology that provides the user with a URL to a purchase page on a mail-order site related to each item in the suggested outfit.

[0203] This invention is a system that collects and analyzes a user's basic information, clothing information, hobbies and tastes, etc., generates and suggests fashion coordinations for specific scenes, and provides links to purchase fashion items related to the coordinations on online shopping sites.

[0204] 1. User Registration

[0205] A user downloads the smartphone app, launches it, and enters basic information such as name, email address, password, height, and weight into the new registration form and submits it. This information is sent from the device to the server, where it is encrypted and stored in a database.

[0206] 2. Collecting item data

[0207] Users take photos of their clothing and accessories with their smartphones and upload them to the server via the app. The server then uses image analysis algorithms (e.g., OpenCV, TensorFlow) to extract detailed information such as color, type, brand, and style from the images and stores this data in a database.

[0208] 3. Analysis of hobbies and interests

[0209] The server automatically obtains browsing history, purchase history, and likes from the user's linked social networking service or e-commerce site (e.g., social networking service A, e-commerce site B). The server analyzes the data using machine learning algorithms (e.g., K-means clustering, deep learning models) to identify the user's preferences. The results of this analysis are also stored in a database.

[0210] 4. Coordination generation and proposal

[0211] When a user selects a specific scene (e.g., office, casual, party, etc.) within the app, the server retrieves TPO guidelines from the database. The server uses a generative AI model to generate an optimal outfit based on the basic information, clothing information, hobbies and tastes, and TPO guidelines. The generated outfit information is then saved back into the database and sent to the user's smartphone.

[0212] 5. Feedback and link to shopping site

[0213] The user can review the suggested outfits and, if necessary, send feedback via the app, such as "more casual" or "use a different color." The server then uses this feedback to regenerate outfits using a generative AI model and suggests them to the user. This process allows the user to choose the fashion that best suits their preferences and the occasion. In addition, links to online shopping sites for products related to the suggested outfits are provided, allowing the user to easily proceed to the purchase process.

[0214] Specific examples

[0215] User A enters the following information into the smartphone app:

[0216] Name: Tanaka

[0217] Email address: tanaka@example.com

[0218] Password:securepassword

[0219] Height: 175cm

[0220] Weight: 70kg

[0221] Frequently used SNS: Social networking service A (account linking)

[0222] Frequently used e-commerce site: E-commerce site B (account linkage)

[0223] Next, User A takes and uploads photos of his or her own shirts, pants, shoes, etc. The server analyzes these photos, extracts information such as color, type, brand, and style, and stores it in a database.

[0224] The server analyzes the browsing history and purchase history obtained from social networking service A and e-commerce site B to identify the preferences of user A. User A specifies an outfit for attending a friend's wedding using the app, and the server obtains the appropriate TPO guidelines for the occasion.

[0225] The server uses generative AI to generate the optimal outfit for User A, proposing a simple black suit with a white shirt and brown leather shoes. User A reviews this suggestion, and if they prefer a different color or style, they can submit feedback, and the server will regenerate the outfit. In this way, users can easily and accurately select an appropriate and personalized style for a particular occasion.

[0226] Prompt Sentence Examples

[0227] Please enter the following information into the new user registration form:

[0228] name

[0229] email address

[0230] password

[0231] height

[0232] body weight

[0233] Billed SNS account information: Social networking service A, e-commerce site B

[0234]

[0235] Take a photo of your clothing item and upload it through the app, and our server will extract details like color, type, brand, style, etc.

[0236] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0237] Step 1: User Registration

[0238] The user downloads the smartphone app and launches it. They enter basic information such as their name, email address, password, height, and weight into the new registration form and press the "Submit" button. This input data is sent from the device to the server. The server encrypts the received data and stores it in a database. Specifically, the form data containing the user information is sent to the server via a POST request, and the data is saved on the server side.

[0239] Step 2: Collect item data

[0240] Users take photos of their clothing and accessories and upload them to the server via the app. This photo data is sent from the device to the server. The server uses image analysis algorithms (OpenCV or TensorFlow) to extract detailed information from the image, such as color, type, brand, and style. The extracted data is stored in a database. Specifically, the user uploads a photo, and the server performs image analysis and stores the results in the database.

[0241] Step 3: Analysis of hobbies and interests

[0242] Data is acquired from social networking sites and e-commerce sites that users connect to. The server automatically acquires browsing history, purchase history, likes, and other information from these sites. Based on the acquired data, the server analyzes it using machine learning algorithms (K-means clustering and deep learning models) to identify the user's preferences. The analysis results are stored in a database. Specifically, data is collected by API calls, and a machine learning model is executed to analyze the collected data.

[0243] Step 4: Generate coordinates

[0244] The user selects a specific scene (e.g., office, casual, party, etc.) within the app. The device sends the selected scene information to the server. The server retrieves the TPO guidelines for that scene from the database. Based on the basic information, clothing information, hobby and taste data, and TPO guidelines, the server uses a generative AI model to generate an optimal outfit. The generated outfit information is then saved back into the database. Specifically, the server queries the database based on the scene selection information and runs the generative AI model to generate an outfit.

[0245] Step 5: Coordination suggestions and feedback

[0246] The server sends the generated coordination information to the device and displays it on the screen. The user reviews the proposed coordination and inputs feedback such as "more casual" or "use a different color" as needed. The device then sends the feedback information to the server. The server receives the feedback, again modifies the coordination using the generative AI model, and proposes a new coordination. Specific operations include displaying coordination information, inputting feedback, and regenerating the coordination.

[0247] Step 6: Provide a link to your online store

[0248] To encourage the purchase of products related to the suggested outfits, the server obtains a purchase link from the online shopping site and sends the link to the terminal. The user can easily complete the purchase procedure by clicking the link displayed on the screen to access the online shopping site. Specifically, the server generates a link containing the product's URL and provides it to the user.

[0249] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0250] The following is a detailed description of an embodiment of the present invention. This system is composed of a user, a terminal, a server, and an emotion engine, and each of these entities plays a specific role in the system.

[0251] 1. User Registration

[0252] Fill out the registration form

[0253] First, a user launches the application and fills in the registration form with basic information such as name, email address, password, height, weight, etc. They also add account information for their favorite social networking services and e-commerce sites.

[0254] Sending and storing information

[0255] The entered information is sent from the terminal to the server, where it is securely encrypted and stored in a database.

[0256] 2. Collecting item data

[0257] Upload a photo

[0258] Next, the user takes photos of their own clothing and accessories and uploads them to the server through the application.

[0259] Image analysis and storage

[0260] The server analyzes the uploaded photos and automatically extracts details such as color, type, brand, style, etc. The extracted data is stored in a database.

[0261] 3. Analysis of hobbies and interests

[0262] Data Acquisition

[0263] The server automatically retrieves data such as browsing history, likes, and purchase history from social networking sites and e-commerce sites that users connect to.

[0264] Data analysis

[0265] The acquired data is analyzed to identify the user's preferences, such as preferred styles, brands, and colors. This information is clustered using machine learning algorithms and stored in a database.

[0266] 4. Select the scene and check the time, place, and occasion

[0267] Select a scene

[0268] The user selects a specific scene (e.g., wedding, casual date, business meeting, etc.) from a scene selection screen within the application.

[0269] Obtaining TPO guidelines

[0270] The server retrieves TPO guidelines from the database according to the selected scene, clarifying the appropriate clothing standards for that scene.

[0271] 5. Coordinate Generation

[0272] Coordinate generation

[0273] The server uses AI to generate optimal outfits based on the user's basic information, clothing information, hobbies and preferences, and TPO guidelines. This generation process determines the combination of items that are appropriate for the selected occasion.

[0274] Save your outfit

[0275] The generated coordinate information is stored again in the database.

[0276] 6. Emotion recognition and suggestion adjustment

[0277] User Emotion Recognition

[0278] When confirming the proposed outfit, the device transmits the user's facial expressions and voice to the emotion engine, which analyzes the user's emotional state and transmits the results to the server.

[0279] Utilizing Emotional Data

[0280] The server uses data from the emotion engine to tailor its outfit suggestions to the user's emotional state. For example, if the user expresses positive emotions, it will suggest a different outfit based on that style.

[0281] 7. Coordination suggestions and feedback

[0282] Submit a proposal

[0283] The server sends the generated coordinate information and data adjusted by the emotion engine to the user's device, which displays this information on its screen.

[0284] Receiving feedback

[0285] The user checks the proposed outfit and enters feedback as needed, such as requests for something more casual or a different color. The emotion engine also analyzes the user's emotions in real time and reflects them on the server.

[0286] re-proposal

[0287] Based on user feedback and emotional data, the server uses the generative AI to revise and re-suggest outfits, allowing users to achieve their own unique style.

[0288] Specific examples

[0289] User registration example

[0290] Mr. Sato (user) registers as a new user, inputs his height as 160 cm and weight as 55 kg, and links his accounts for social networking service A and e-commerce site B as his frequently used SNSs.

[0291] Item Data Collection Example

[0292] Sato uploads photos of her dresses, accessories, shoes, etc. to the app, and the server analyzes the photos, extracts the necessary information, and stores it.

[0293] Example of analysis of hobbies and interests

[0294] The server retrieves Mr. Sato's browsing history and purchase history from social networking service A and e-commerce site B, and analyzes that he prefers elegant and simple designs.

[0295] Scene selection example

[0296] Sato specifies on the app that she wants to choose an outfit for attending dinner with friends, and the server retrieves TPO guidelines appropriate for the occasion.

[0297] Coordinate Generation Example

[0298] Based on Sato's basic information, clothing information, tastes, and TPO, the server uses generative AI to generate the optimal outfit, suggesting a combination of an elegant dress with simple accessories.

[0299] Example of emotion recognition and suggestion adjustment

[0300] When Sato checks the proposed outfit, the device sends Sato's facial expression to the emotion engine, and the server determines from the emotion data whether Sato is satisfied and further improves the proposal.

[0301] Suggestions and Feedback Examples

[0302] Mr. Sato reviews the proposal and, if he prefers a different color or style, he sends feedback and the emotion engine reflects his feelings back to the server. Based on this data, the server makes a new proposal.

[0303] In this way, the system of the present invention not only allows users to easily and accurately select appropriate and personal styling for specific occasions, but also uses an emotion engine to provide more personalized suggestions.

[0304] The processing flow will be explained below.

[0305] User Registration

[0306] Step 1:

[0307] A user launches the application and enters basic information such as name, email address, password, height, and weight into the new registration form.

[0308] Step 2:

[0309] The user selects their preferred social networking services and e-commerce sites and enters their respective account information.

[0310] Step 3:

[0311] The device sends all the information entered in the registration form to the server.

[0312] Step 4:

[0313] The server receives the information sent and stores it securely in a database.

[0314] Item Data Collection

[0315] Step 1:

[0316] The user takes a photo of their own clothing and accessories.

[0317] Step 2:

[0318] The device uploads the photograph to the server.

[0319] Step 3:

[0320] The server sends the received photos to an image analysis service to extract information such as color, type, brand, and style.

[0321] Step 4:

[0322] The server stores the analysis results in a database.

[0323] Analysis of hobbies and interests

[0324] Step 1:

[0325] The server obtains data such as browsing history, likes, and purchase history from the social networking services and e-commerce sites that the user has connected to.

[0326] Step 2:

[0327] The server analyzes the data and uses machine learning algorithms to identify the user's preferences, such as preferred styles, brands, and colors.

[0328] Step 3:

[0329] The server stores the analysis results in a database.

[0330] Select the scene and check the time, place, and occasion

[0331] Step 1:

[0332] The user selects a specific scene (e.g., wedding, casual date, business meeting, etc.) from a scene selection screen within the application.

[0333] Step 2:

[0334] The server retrieves the TPO guidelines corresponding to the selected scene from the database.

[0335] Coordinate generation

[0336] Step 1:

[0337] The server sends the user's basic information, clothing information, hobbies and preferences, and TPO guidelines as input data to the generation AI.

[0338] Step 2:

[0339] The generative AI generates the optimal coordination based on the input data.

[0340] Step 3:

[0341] The server stores the generated coordinate information in a database.

[0342] Emotion recognition and suggestion adjustment

[0343] Step 1:

[0344] When the user confirms the proposed outfit, the device sends the user's facial expressions and voice to the emotion engine.

[0345] Step 2:

[0346] The emotion engine analyzes the user's facial expressions and voice to recognize their emotional state, such as satisfaction, surprise, or dissatisfaction.

[0347] Step 3:

[0348] The emotion engine sends the analysis results to the server, which then adjusts the coordination according to the emotional state.

[0349] Coordination suggestions and feedback

[0350] Step 1:

[0351] The server transmits the adjusted coordinate information to the user's terminal.

[0352] Step 2:

[0353] The device displays the suggested outfit to the user, including images and detailed information (such as a list of combined items and substitution options for each item).

[0354] Step 3:

[0355] Users can provide feedback on the proposed outfits, such as requests like "I want it to be more casual" or "I'd like a different color."

[0356] Step 4:

[0357] Based on user feedback and emotional data, the server uses the generative AI to revise the outfit and make a new suggestion.

[0358] The above is the specific processing flow for carrying out the invention.

[0359] Example 2

[0360] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0361] Conventional styling suggestion systems have difficulty providing personalized outfits based on the user's hobbies, tastes, and emotions. Furthermore, when suggesting appropriate clothing for a specific occasion, they lack a mechanism for reflecting the user's real-time feedback and emotional state. This often results in users receiving unsatisfactory styling suggestions.

[0362] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0363] In this invention, the server includes means for inputting and saving basic information about a user, means for analyzing images of clothing and accessories owned by the user and saving the information, means for acquiring and analyzing data from social networking services and e-commerce sites to analyze the user's tastes and preferences and saving the results, means for acquiring TPO guidelines for specific occasions, means for using a generative AI model to generate outfits based on the basic information, clothing information, tastes and preferences data, and TPO guidelines, means for proposing the generated outfits to the user and receiving feedback as needed, and means for acquiring and analyzing the user's emotional data and adjusting the outfits based on the results. This allows personalized outfits based on the user's tastes and preferences and emotional state to be provided in real time, ensuring high satisfaction even for specific occasions.

[0364] "Basic user information" refers to personal information such as name, email address, password, height, and weight that a user enters into the application.

[0365] "Clothing information" refers to detailed information such as color, type, brand, and style obtained by analyzing images of clothing and accessories owned by the user.

[0366] "Hobbies and tastes data" refers to information such as a user's preferred styles, brands, and colors, obtained by analyzing data such as browsing history, likes, and purchase history obtained from social networking services and e-commerce sites.

[0367] "TPO guidelines" are information that indicates the standards and rules for appropriate clothing for specific occasions.

[0368] The "generative AI model" is a model that uses artificial intelligence technology to generate optimal outfits based on input basic information, clothing information, hobby and taste data, and TPO guidelines.

[0369] "Emotion data" is information that indicates the emotional state of a user, obtained from the user's facial expressions, voice, etc.

[0370] "Feedback" refers to opinions and requests provided by users regarding the proposed coordination.

[0371] This invention is a system that is composed mainly of a user, a terminal, a server, and an emotion engine, each of which plays a specific role and cooperates to provide personalized coordination.

[0372] User Registration

[0373] First, the user launches the application and enters their basic information (name, email address, password, height, weight, etc.) into the new registration form. This basic information includes account information for social networking sites and e-commerce sites. The entered information is sent from the device to the server, where it is securely encrypted and stored in a database. Specifically, the AES encryption algorithm is used for encryption, and MySQL is used for the database.

[0374] Item Data Collection

[0375] Next, users take photos of their clothing and accessories and upload them to the server through the application. The server uses the OpenCV library and YOLOv5 to analyze the photos and extract details such as color, type, brand, style, etc. The extracted data is converted to JSON format and stored in a database.

[0376] Analysis of hobbies and interests

[0377] The server automatically obtains data such as users' browsing history, likes, and purchase history from the social media and e-commerce sites they connect to using OAuth 2.0. The obtained data is analyzed using a machine learning algorithm (using Scikit-learn) to identify the user's preferences, such as preferred styles, brands, and colors. The results of this analysis are also stored in a database.

[0378] Select the scene and check the time, place, and occasion

[0379] The user selects a specific scene (e.g., wedding, casual date, business meeting, etc.) on the scene selection screen within the application. The server retrieves TPO guidelines from the database according to the selected scene and provides appropriate attire standards for that scene. In this process, the appropriate guidelines are retrieved from the database using SQL queries.

[0380] Coordinate generation

[0381] The server uses a generative AI model (using OpenAI's GPT model) to generate optimal outfits based on the user's basic information, clothing information, hobbies and preferences, and TPO guidelines. The generated outfits are then converted back to JSON format and stored in a database.

[0382] Emotion recognition and suggestion adjustment

[0383] When the user confirms the suggested outfit, the device sends the user's facial expressions and voice to the emotion engine. The emotion engine performs analysis using Microsoft Azure's emotion analysis API and sends the results to the server. The server uses this emotion data to adjust the suggested outfit according to the user's emotional state. If the user expresses positive emotions, the server will suggest a different outfit based on that style.

[0384] Coordination suggestions and feedback

[0385] The server sends the generated outfit information to the user's device, which displays the information on the screen. The user then inputs feedback on the proposed outfit (e.g., "more casual," "use a different color," etc.). The device then sends this feedback to the server, which again uses the generative AI model to revise the outfit and make a new suggestion.

[0386] Specific examples

[0387] User registration example:

[0388] A user registers as a new user, inputs their height (160 cm) and weight (55 kg), and links their frequently used SNS service to their account on the e-commerce site.

[0389] Example of collecting item data:

[0390] Users upload photos of their own dresses, accessories, shoes, etc. to the app, and the server analyzes these photos, extracts the necessary information, and stores it.

[0391] Example of hobbies and interests analysis:

[0392] The server obtains the user's browsing history and purchase history from social networking services and e-commerce sites, and analyzes that the user prefers elegant and simple designs.

[0393] Scene selection example:

[0394] The user specifies in the app that they want to choose an outfit for attending dinner with friends, and the server retrieves the TPO guidelines appropriate for that occasion.

[0395] Example of generating coordinates:

[0396] The server uses generative AI to suggest the optimal outfit based on the user's basic information, clothing information, tastes, and TPO, suggesting a combination of an elegant dress with simple accessories.

[0397] Example of emotion recognition and suggestion adjustment:

[0398] When the user checks the suggested outfits, the device sends the user's facial expression data to the emotion engine, and the server determines the satisfaction level and further improves the suggestions.

[0399] Examples of suggestions and feedback:

[0400] If the user checks the proposal and wants a different color or style, they can send feedback and have their emotions reflected in the emotion engine. Based on this information, the server will make a new proposal.

[0401] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0402] System program processing flow

[0403] Step 1: Enter your user registration information

[0404] The user enters their name, email address, password, height, weight, and account information for frequently used social networking sites and e-commerce sites into the new registration form. This becomes the input data. Specifically, the user enters information into the form and presses the "Register" button. This input data is sent to the server as registration information.

[0405] Step 2: Send and store user information

[0406] The terminal sends the entered user information to the server. The server receives this information and encrypts it using the AES encryption algorithm. It then stores this encrypted data in a MySQL database. The input is the user information, and the output is the encrypted information stored in the database.

[0407] Step 3: Upload item data

[0408] Users take photos of their clothing or accessories with their smartphone or tablet and upload them to the server via the app. Specifically, the user presses the "Upload" button, selects a photo in the file selection dialog, and uploads it. The input is the photo file, and the output is image data stored on the server.

[0409] Step 4: Image analysis and storage

[0410] The server receives the uploaded photo and performs image analysis using the OpenCV library and YOLOv5 to extract detailed information such as color, type, brand, and style. The extracted data is converted to JSON format and stored in a database. The input is the photo data, and the output is the analyzed detailed information.

[0411] Step 5: Acquire social media and e-commerce site data

[0412] The server uses OAuth 2.0 authentication to retrieve data from the user's connected social networking sites and e-commerce sites. The retrieved data includes browsing history, likes, purchase history, etc. The input is an OAuth 2.0 token, and the output is the retrieved user activity data.

[0413] Step 6: Analyze your hobbies and interests data

[0414] The server uses Scikit-learn to perform machine learning on the acquired data from social media and e-commerce sites, analyzing the user's preferred styles, brands, colors, etc. The analysis results are stored in a database. The input is activity data, and the output is data on the user's hobbies and preferences.

[0415] Step 7: Select a Scene

[0416] The user selects a specific scene from the scene selection screen of the app. Specifically, the user selects a scene from a drop-down menu and presses the "Next" button. The input is the scene selected by the user, and the output is the selected scene information.

[0417] Step 8: Obtain TPO guidelines

[0418] The server retrieves appropriate TPO guidelines from the database based on the scene selected by the user using an SQL query. The input is the scene information, and the output is the retrieved TPO guidelines.

[0419] Step 9: Generate coordinates

[0420] The server uses OpenAI's GPT model to generate optimal outfits based on the user's basic information, clothing information, hobbies and preferences, and TPO guidelines. The generated outfits are converted to JSON format and stored in a database. The input is a prompt to the generative AI model, and the output is the generated outfit information.

[0421] Step 10: Propose your outfit and receive feedback

[0422] The server sends the generated outfit information to the user's device, which displays this information on its screen. The user inputs feedback about the proposed outfit (e.g., "Make it more casual," "I'd like it in a different color," etc.), and the device sends this feedback to the server. The input is the outfit information and the user's feedback, and the output is the feedback sent to the server.

[0423] Step 11: Acquire and analyze emotion data

[0424] When the user confirms the proposed outfit, the device captures the user's facial expressions and voice and sends them to an emotion engine (e.g., Microsoft Azure's emotion analysis API). The emotion engine analyzes this data and sends the results to a server. The input is facial expression and voice data, and the output is the analysis results.

[0425] Step 12: Adjust your outfit

[0426] The server uses a generative AI model to regenerate the coordinates based on the feedback and emotion data. The input is the user's feedback and emotion data, and the output is the adjusted coordinates.

[0427] Step 13: Resubmit

[0428] The server sends the adjusted coordinates back to the terminal, which displays the information on its screen. This process is repeated until the user is satisfied. The input is the adjusted coordinates, and the output is the re-proposed coordinates.

[0429] (Application example 2)

[0430] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0431] With conventional technology, it was difficult for users to automatically and personalizedly select outfits suitable for specific occasions, and suggestions rarely took the user's emotions into consideration. As a result, suggested outfits did not necessarily match the user's preferences or the situation. Furthermore, the accuracy of re-suggestions based on feedback was low, leaving a need for improved user satisfaction.

[0432] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0433] In this invention, the server includes means for inputting and saving basic user information, means for analyzing images of clothing and accessories owned by the user and saving the information, means for acquiring and analyzing data from social networking services and e-commerce sites to analyze the user's hobbies and tastes and saving the results, means for acquiring TPO guidelines for specific occasions, means for generating outfits based on the basic information, clothing information, hobbies and tastes data, and TPO guidelines, means for proposing the generated outfits to the user and receiving feedback as needed, means for analyzing the user's reaction to the proposed outfits using an emotion analysis engine and adjusting the outfit suggestions based on the data, and means for re-proposing outfits based on the emotion data and feedback. This allows users to receive more personalized outfit suggestions that take into account their individual preferences and emotional state.

[0434] "Basic User Information" means the personal data provided by a User when registering for the Service, including basic profile information such as name, email address, password, height, and weight.

[0435] "Means for analyzing images of clothing and accessories" refers to technology that processes photos of clothing and accessories uploaded by users and automatically extracts detailed information from them, such as color, type, brand, and style.

[0436] "Means for analyzing hobbies and tastes" refers to technology for identifying and analyzing users' preferences and interests using data such as users' browsing history and purchase history obtained from social networking services and e-commerce sites.

[0437] "TPO guidelines" are guidelines that indicate standards for appropriate clothing and style for specific occasions (e.g., weddings, casual dates, business meetings, etc.).

[0438] "Generative AI" refers to artificial intelligence technology that automatically generates new items and outfits based on input data.

[0439] An "emotion analysis engine" is a technology that analyzes a user's reaction to a proposed outfit from input data such as images and voice, and automatically determines the user's emotional state.

[0440] "Feedback" refers to the user inputting their opinions and requests regarding the proposed outfits, and this feedback serves as reference information for the system to make more optimal suggestions.

[0441] "Means of re-proposing" refers to technology that uses generative AI to generate new coordination based on feedback from users and sentiment analysis data, and then re-proposes it to the user.

[0442] The system for implementing the present invention is mainly composed of a user, a terminal, a server, and an emotion analysis engine. Each of these components plays a specific role and realizes the functions of the invention.

[0443] 1. User Registration

[0444] Enter and save basic information

[0445] A user launches the application on their device and enters basic information such as their name, email address, password, height, and weight into the new registration form. They also add account information for their favorite social networking services and e-commerce sites. This information is sent from the device to the server, where it is securely encrypted and stored in a database.

[0446] 2. Collecting item data

[0447] Uploading an image

[0448] Users take photos of their clothing and accessories and upload them to the server through the application. The server analyzes these photos and automatically extracts details such as color, type, brand, and style, and stores them in a database. This process uses software such as PIL (Python Imaging Library) and OpenCV (an image processing library).

[0449] 3. Analysis of hobbies and interests

[0450] Data acquisition and analysis

[0451] The server automatically retrieves data such as browsing history, likes, and purchase history from the user's connected social networking services and e-commerce sites. The retrieved data is analyzed using machine learning algorithms (e.g., scikit-learn) to identify the user's preferences, such as preferred styles, brands, and colors. This information is then clustered and stored in a database.

[0452] 4. Selecting the scene and obtaining TPO guidelines

[0453] Select a scene

[0454] The user selects a specific scene (e.g., a business meeting, a casual date, a formal event, etc.) from the scene selection screen within the application. Depending on the selected scene, the server retrieves TPO guidelines from the database and clarifies the appropriate attire standards for that scene.

[0455] 5. Coordinate Generation

[0456] Creating and saving coordinates

[0457] The server uses a generative AI model (e.g., AIGenerate library) to generate the optimal outfit based on the user's basic information, clothing information, hobbies and preferences, and TPO guidelines. During this generation process, a combination of items appropriate for the selected scene is established. The generated outfit information is then saved back to the database.

[0458] 6. Emotion recognition and suggestion adjustment

[0459] Recognizing user emotions and tailoring suggestions

[0460] When the user confirms the suggested outfit, the device sends the user's facial expressions and voice to an emotion analysis engine. This emotion analysis engine analyzes the user's emotional state and sends the results to the server. The server then adjusts the outfit suggestions based on the user's emotional state based on the data from the emotion engine. For example, if the user expresses positive emotions, the server will suggest a new outfit based on that style.

[0461] 7. Coordination suggestions and feedback

[0462] Submitting suggestions and receiving feedback

[0463] The server sends the generated outfit information and data adjusted by the emotion analysis engine to the user's device, which then displays this information on the screen. The user checks the proposed outfit and enters feedback as needed. Based on the feedback and the user's emotional data at the time of display, the server again uses the generation AI to revise the outfit and make a new suggestion.

[0464] Specific examples

[0465] Example of user registration: Typically, a user enters their basic information and links their SNS account 1 with their e-commerce site account as their frequently used SNS.

[0466] Example of collecting item data: A user uploads photos of their dresses, accessories, shoes, etc. to the app. The server analyzes these photos, extracts the necessary information, and stores it.

[0467] Example of analyzing hobbies and tastes: The server obtains the user's browsing history and purchase history from social networking sites and e-commerce sites, and analyzes their preferred style.

[0468] Example of scene selection: A user selects a coordinate for a business meeting, and the server retrieves the TPO guidelines appropriate for the scene.

[0469] Example of outfit generation: The server uses a generative AI model to generate the optimal outfit based on the user's basic information, clothing information, tastes, and TPO, and suggests a business shirt and suit as an example.

[0470] Example of emotion recognition and suggestion adjustment: When the user confirms the suggested outfit, the device sends the user's facial expression to the emotion analysis engine, and the server analyzes the user's emotional state to improve the suggestion.

[0471] Example of suggestion and feedback: A user sends feedback requesting a different color, and the server reflects that sentiment through a sentiment analysis engine. Based on this data, the server makes a new suggestion.

[0472] Prompt Sentence Examples

[0473] user_data = {

[0474] 'name': 'Yamada Taro',

[0475] 'email': 'taro@example.com',

[0476] 'password': 'password123',

[0477] 'height': 170,

[0478] 'weight': 65,

[0479] 'sns_accounts': ['mySNSAccount1', 'mySNSAccount2']

[0480] }

[0481] response = requests.post('http: / / localhost:5000 / register', json=user_data)

[0482] The system of the present invention enables users to select styling that is appropriate for each scene with high accuracy and receive suggestions that are adapted to their own emotions and preferences.

[0483] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0484] Step 1:

[0485] Enter and save basic information

[0486] A user launches an application on their device and enters basic information (such as name, email address, password, height, and weight) into a new registration form. They then add account information for social networking services and e-commerce sites they frequently use. This information is sent from the device to a server. The server securely encrypts the received information and stores it in a database. The input data is the user's personal information, and the output is encrypted stored data.

[0487] Step 2:

[0488] Image upload and analysis

[0489] Users take photos of their clothing and accessories and upload them to the server through the application. The server receives the images and performs image analysis using PIL and OpenCV. Through this analysis, detailed information such as color, type, brand, and style is automatically extracted and stored in a database. The input data is the uploaded image, and the output is the data resulting from the image analysis.

[0490] Step 3:

[0491] Data collection and preference analysis

[0492] The server automatically retrieves data on users' browsing history, likes, and purchase history from the social networking services and e-commerce sites they connect to. The retrieved data is analyzed using machine learning algorithms such as scikit-learn to identify the user's preferences, such as preferred styles, brands, and colors. The analysis results are clustered and stored in a database. The input data is the retrieved browsing history and purchase history, and the output is the clustered preference data.

[0493] Step 4:

[0494] Selecting the scene and obtaining TPO guidelines

[0495] The user selects a specific scene, such as a business meeting, a casual date, or a formal event, from the scene selection screen within the application. Based on this selection, the server retrieves the corresponding TPO guidelines from the database and provides appropriate attire standards for that scene. The input data is the user's scene selection, and the output is the retrieved TPO guidelines.

[0496] Step 5:

[0497] Creating and saving coordinates

[0498] The server uses a generative AI model to generate optimal outfits based on the user's basic information, clothing information, taste data, and TPO guidelines. During this generation process, a combination of items appropriate for the selected occasion is established. The generated outfit information is stored in a database. The input data are basic information, clothing information, taste data, and TPO guidelines, and the output is the generated outfit.

[0499] Step 6:

[0500] Emotion recognition and suggestion adjustment

[0501] When the user confirms the suggested outfit, the device sends the user's facial expressions and voice to an emotion analysis engine in real time. The emotion analysis engine analyzes the user's emotional state and sends the results to the server. The server then adjusts the outfit suggestions based on the user's reaction based on the emotional data. For example, if the user expresses positive emotions, the server will make new suggestions based on that style. The input data is the user's emotional state data, and the output is the adjusted outfit suggestions.

[0502] Step 7:

[0503] Receiving suggestions and feedback

[0504] The server sends the generated coordination information and data adjusted by the emotion analysis engine to the user's device. The device displays this information on the screen, and the user confirms the proposed coordination. If necessary, feedback (e.g., "more casual," "I'd like it in a different color") is entered. Based on the feedback and the user's emotional data at the time of display, the server again uses the generation AI to revise the coordination and make a new proposal. The input data is the user's feedback and emotional data, and the output is the revised, re-proposed coordination.

[0505] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0506] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0507] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0508] [Second embodiment]

[0509] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0510] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0511] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0512] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0513] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0514] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0515] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0516] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0517] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0518] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0519] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0520] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0521] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below with reference to the preferred embodiment. The system is composed of users, terminals, and a server, and each of the users plays a specific role in the system.

[0522] 1. User Registration

[0523] Fill out the registration form

[0524] First, a user launches the application and fills in the registration form with basic information such as name, email address, password, height, weight, etc. They also add account information for their favorite social networking services and e-commerce sites.

[0525] Sending and storing information

[0526] The entered information is sent from the terminal to the server, where it is securely encrypted and stored in a database.

[0527] 2. Collecting item data

[0528] Upload a photo

[0529] Next, the user takes photos of their own clothing and accessories and uploads them to the server through the application.

[0530] Image analysis and storage

[0531] The server analyzes the uploaded photos and automatically extracts details such as color, type, brand, style, etc. The extracted data is stored in a database.

[0532] 3. Analysis of hobbies and interests

[0533] Data Acquisition

[0534] The server automatically retrieves data such as browsing history, likes, and purchase history from social networking sites and e-commerce sites that users connect to.

[0535] Data analysis

[0536] The acquired data is analyzed to identify the user's preferences, such as preferred styles, brands, and colors. This information is clustered using machine learning algorithms and stored in a database.

[0537] 4. Select the scene and check the time, place, and occasion

[0538] Select a scene

[0539] The user selects a specific scene (e.g., wedding, casual date, business meeting, etc.) from a scene selection screen within the application.

[0540] Obtaining TPO guidelines

[0541] The server retrieves TPO guidelines from the database according to the selected scene, clarifying the appropriate clothing standards for that scene.

[0542] 5. Coordinate Generation

[0543] Coordinate generation

[0544] The server uses AI to generate optimal outfits based on the user's basic information, clothing information, hobbies and preferences, and TPO guidelines. This generation process determines the combination of items that are appropriate for the selected occasion.

[0545] Save your outfit

[0546] The generated coordinate information is stored again in the database.

[0547] 6. Coordination suggestions and feedback

[0548] Submit a proposal

[0549] The server sends the generated coordinate information to the user's terminal, which displays the information on its screen.

[0550] Receiving feedback

[0551] The user can check the proposed outfit and enter feedback as needed, such as requests like "more casual" or "different colors."

[0552] re-proposal

[0553] The server receives feedback from the user, uses the generative AI to revise the outfit and make a new suggestion. This cycle allows the user to achieve a style that is uniquely their own.

[0554] Specific examples

[0555] User registration example

[0556] Mr. Tanaka (user) registers as a new user, inputs his height of 175 cm and weight of 70 kg, and links his accounts for social networking service A, a commonly used SNS, and e-commerce site B.

[0557] Item Data Collection Example

[0558] Tanaka uploads photos of his personal items, such as shirts, pants, and shoes, to the app. The server analyzes these photos, extracts the necessary information, and stores it.

[0559] Example of analysis of hobbies and interests

[0560] The server retrieves Tanaka's browsing history and purchase history from social networking service A and e-commerce site B, and analyzes that he prefers casual and simple designs.

[0561] Scene selection example

[0562] Tanaka specifies on the app that she wants to choose an outfit to wear to attend a friend's wedding, and the server retrieves the appropriate TPO guidelines for the occasion.

[0563] Coordinate Generation Example

[0564] Based on Tanaka's basic information, clothing information, tastes, and TPO, the server uses generative AI to generate the optimal outfit, suggesting a combination of a simple black suit, a white shirt, and brown leather shoes.

[0565] Suggestions and Feedback Examples

[0566] Tanaka reviews this proposal and, if he prefers a different color or style, he sends feedback and the server makes a new proposal.

[0567] In this way, the system of the present invention allows the user to easily and accurately select a style that is appropriate and unique to the user for a particular scene.

[0568] The processing flow will be explained below.

[0569] User Registration

[0570] Step 1:

[0571] A user launches the application and enters basic information such as name, email address, password, height, and weight into the new registration form.

[0572] Step 2:

[0573] The user selects their preferred social networking services and e-commerce sites and enters their respective account information.

[0574] Step 3:

[0575] The device sends all the information entered in the registration form to the server.

[0576] Step 4:

[0577] The server receives the information sent and stores it securely in a database.

[0578] Item Data Collection

[0579] Step 1:

[0580] The user takes a photo of their own clothing and accessories.

[0581] Step 2:

[0582] The device uploads the photograph to the server.

[0583] Step 3:

[0584] The server sends the received photos to an image analysis service to extract information such as color, type, brand, and style.

[0585] Step 4:

[0586] The server stores the analysis results in a database.

[0587] Analysis of hobbies and interests

[0588] Step 1:

[0589] The server obtains data such as browsing history, likes, and purchase history from the social networking services and e-commerce sites that the user has connected to.

[0590] Step 2:

[0591] The server analyzes the data and uses machine learning algorithms to identify the user's preferences, such as preferred styles, brands, and colors.

[0592] Step 3:

[0593] The server stores the analysis results in a database.

[0594] Select the scene and check the time, place, and occasion

[0595] Step 1:

[0596] The user selects a specific scene (e.g., wedding, casual date, business meeting, etc.) from a scene selection screen within the application.

[0597] Step 2:

[0598] The server retrieves the TPO guidelines corresponding to the selected scene from the database.

[0599] Coordinate generation

[0600] Step 1:

[0601] The server sends the user's basic information, clothing information, hobbies and preferences, and TPO guidelines as input data to the generation AI.

[0602] Step 2:

[0603] The generative AI generates the optimal coordination based on the input data.

[0604] Step 3:

[0605] The server stores the generated coordinate information in a database.

[0606] Coordination suggestions and feedback

[0607] Step 1:

[0608] The server transmits the stored coordinate information to the user's terminal.

[0609] Step 2:

[0610] The device displays the suggested outfit to the user, along with images and detailed information (such as a list of combined items and options for replacing each item) on the screen.

[0611] Step 3:

[0612] Users can provide feedback on the proposed outfits, such as requests like "I want it to be more casual" or "I'd like a different color."

[0613] Step 4:

[0614] The server receives feedback from the user, and based on that, the generative AI revises the coordination and makes a new proposal.

[0615] The above is the specific processing flow for carrying out the invention.

[0616] Example 1

[0617] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0618] Conventional outfit suggestion systems were unable to fully utilize the user's basic information and clothing information, and had difficulty accurately analyzing the user's tastes and preferences to suggest outfits suitable for specific occasions. Furthermore, the process of reflecting user feedback and re-suggesting outfits was complicated and time-consuming. For these reasons, there was a demand for more accurate outfit suggestions and a system that could quickly reflect user feedback.

[0619] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0620] In this invention, the server includes means for inputting and saving basic information about a user, means for analyzing images of clothing and accessories owned by the user and saving the information, means for acquiring and analyzing data from social networking services and e-commerce sites to analyze the user's tastes and preferences and saving the results, means for acquiring TPO guidelines for specific occasions, means for using a generative AI model to generate outfits based on the basic information, clothing information, tastes and preferences data, and TPO guidelines, means for proposing the generated outfits to the user and receiving feedback as needed, and means for regenerating the outfits based on the feedback, thereby enabling highly accurate outfit suggestions to be made to the user and for the feedback to be reflected quickly and effectively.

[0621] "Basic user information" refers to personal information entered by the user, such as name, email address, password, height, and weight.

[0622] "Images of clothing and accessories owned by the user" refers to photos of clothing, accessories, etc. owned by the user.

[0623] An "image analysis library" refers to a software tool that analyzes images of clothing and accessories and extracts detailed information such as color, type, brand, and style.

[0624] "Social networking service" refers to a website or application that provides services that enable users to interact online.

[0625] "E-commerce site" refers to a website or platform used by users to purchase products online.

[0626] "Data for analyzing hobbies and tastes" refers to information including users' browsing history, likes, purchase history, etc.

[0627] "TPO guidelines for specific occasions" refers to standards and guidelines for appropriate attire for specific occasions or events.

[0628] A "generative AI model" refers to a model that uses artificial intelligence algorithms to generate new information or content based on data.

[0629] "Coordination" refers to clothing combinations suggested based on the user's basic information, clothing information, hobbies and preferences, and TPO guidelines.

[0630] "Feedback" refers to the user's thoughts and requests regarding the proposed coordination.

[0631] "Regeneration" refers to the process of regenerating coordinates based on received feedback.

[0632] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below with reference to the preferred embodiment. The system is composed of users, terminals, and a server, and each of the users plays a specific role in the system.

[0633] 1. User Registration

[0634] A user launches an application and fills in a registration form with basic information such as name, email address, password, height, weight, etc. They also enter account information for their favorite social networking services and e-commerce sites. The information is sent from the device to the server, where it is securely encrypted and stored in a database (e.g., MySQL or PostgreSQL).

[0635] Specific examples

[0636] For example, a user has a height of 175 cm, a weight of 70 kg, and inputs account information for a commonly used social networking service A and an e-commerce site B.

[0637] 2. Collecting item data

[0638] Users take photos of their clothing and accessories and upload them to the server through the application. The server then analyzes the uploaded photos using an image analysis library (e.g., OpenCV) and automatically extracts detailed information such as color, type, brand, and style. The extracted data is stored in a database.

[0639] Specific examples

[0640] For example, when a user uploads photos of their shirts, pants, shoes, etc. to the app, the server analyzes these photos, extracts the necessary information, and stores it.

[0641] 3. Analysis of hobbies and interests

[0642] The server automatically retrieves data from the user's connected social networking sites and e-commerce sites via API. The retrieved data is analyzed using machine learning algorithms (e.g., k-means clustering) to identify the user's preferences, such as preferred styles, brands, and colors. This information is also stored in a database.

[0643] Specific examples

[0644] For example, the server acquires the user's browsing history and purchase history from SNS A and e-commerce site B, and analyzes that the user prefers casual and simple designs.

[0645] 4. Select the scene and check the time, place, and occasion

[0646] The user selects a specific scene (e.g., wedding, casual date, business meeting, etc.) from the scene selection screen within the application. The server retrieves TPO guidelines from the database according to the selected scene and clarifies the appropriate attire standards for that scene.

[0647] Specific examples

[0648] For example, when a user selects an outfit to wear to a friend's wedding, the server obtains the TPO guidelines appropriate for that occasion.

[0649] 5. Coordinate Generation

[0650] The server uses a generative AI model (e.g., GPT-3) to generate optimal outfits based on the user's basic information, clothing information, hobbies and preferences, and TPO guidelines. The generated outfit information is stored in a database.

[0651] Prompt Sentence Examples

[0652] "User basic information: height 175cm, weight 70kg. Clothing information: black suit, white shirt, brown leather shoes. Preferred style: simple, casual. TPO: formal, like a wedding. Generate the optimal outfit based on this information."

[0653] Specific examples

[0654] For example, based on Tanaka's basic information, clothing information, tastes, and TPO, the server uses generative AI to generate the optimal outfit of a simple black suit, white shirt, and brown leather shoes.

[0655] 6. Coordination suggestions and feedback

[0656] The server sends the generated outfit information to the user's device, which displays it on the screen. The user reviews the suggested outfit and provides feedback as needed. The server receives the user's feedback, again modifies the outfit using the generative AI model, and re-proposes it. This cycle allows the user to achieve a style that is uniquely their own.

[0657] Specific examples

[0658] For example, if Tanaka checks the proposed outfit and sends feedback indicating a preference for a different color or style, the server will make a new suggestion.

[0659] In this way, the system of the present invention allows the user to easily and accurately select a style that is appropriate and unique to the user for a particular scene.

[0660] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0661] Step 1:

[0662] A user starts an application and enters basic information such as name, email address, password, height, and weight into a new registration form. In addition, the user also enters account information for frequently used social networking services and e-commerce sites. This input information is sent to the server as device input. The server securely encrypts the received information and stores it in a database (e.g., MySQL or PostgreSQL). The input from the device is basic information and linked account information, which is encrypted and stored by the server.

[0663] Step 2:

[0664] Users take photos of their clothing and accessories and upload them to the server through the application. This photo data is sent to the server via the device. The server then analyzes the uploaded photo using an image analysis library (e.g., OpenCV) and automatically extracts detailed information such as color, type, brand, and style. The analyzed information is stored in a database. The input is image data, and the information extracted through image analysis is the output.

[0665] Step 3:

[0666] The server automatically acquires data (browsing history, likes, purchase history, etc.) from linked social networking sites and e-commerce sites via API. This data becomes the input to the server. The acquired data is analyzed using a machine learning algorithm (e.g., k-means clustering). As a result, the user's preferences, such as preferred styles, brands, and colors, are identified. This identified preference information is stored in a database. The acquired data is the input, and the analyzed preference information is stored as the output.

[0667] Step 4:

[0668] The user selects a scene, such as a wedding, casual date, or business meeting, from the scene selection screen within the application. This selection is input from the device to the server. The server then retrieves TPO guidelines from the database according to the selected scene. This clarifies the appropriate clothing standards for a particular scene. The user's scene selection is the input, and the retrieved TPO guidelines are the output.

[0669] Step 5:

[0670] The server generates the optimal outfit using a generative AI model (e.g., GPT-3) based on the user's basic information, clothing information, taste data, and TPO guidelines. The following prompt sentences are used in this generation process:

[0671] "User basic information: height 175cm, weight 70kg. Clothing information: black suit, white shirt, brown leather shoes. Preferred style: simple, casual. TPO: formal, like a wedding. Generate the optimal outfit based on this information."

[0672] The generated coordination information is stored in a database. The input is basic information, clothing information, taste data, and TPO guidelines, and the output is the generated coordination.

[0673] Step 6:

[0674] The server sends the generated coordination information to the user's device. The device displays this information on the screen. The user checks the proposed coordination and enters feedback as needed. The feedback becomes input from the device to the server. The server receives this feedback, again uses the generative AI model to revise the coordination and make a new proposal. This provides the optimal coordination for the user. The generated coordination proposal is the output, and regeneration and re-proposition are performed based on the received feedback.

[0675] (Application example 1)

[0676] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0677] Conventional outfit suggestion systems often struggle to provide outfits that accurately reflect a user's tastes and preferences. Furthermore, it takes time and effort for users to visually select and purchase items based on the suggested outfits. Furthermore, there are issues with systems that make it difficult to select appropriate fashion items for specific occasions. As a result, problems arise in terms of low user satisfaction and a declining reuse rate.

[0678] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0679] In this invention, the server includes means for inputting and saving basic user information, means for analyzing images of clothing and accessories owned by the user and saving the information, means for acquiring and analyzing data from social networking services and e-commerce sites to analyze the user's hobbies and tastes and saving the results, means for acquiring TPO guidelines for specific occasions, means for generating outfits based on the basic information, clothing information, hobbies and tastes data, and TPO guidelines, means for proposing the generated outfits to the user and receiving feedback as needed, and means for providing links to online shopping sites to encourage the purchase of products related to the proposed outfits. This enables the system to propose outfits optimized based on the user's hobbies and tastes and to enable the user to purchase the proposed products quickly and easily.

[0680] "Basic user information" refers to personal identification information such as name, email address, password, height, and weight.

[0681] "Clothing and accessories" refers to fashion items such as clothing and accessories owned by the user.

[0682] "Means for analyzing images and storing the information" refers to technology that uses image analysis algorithms to extract information such as color, type, brand, and style from images of clothing and accessories, and stores the data.

[0683] "Means of acquiring data from social networking services and e-commerce sites, analyzing the data, and saving the results in order to analyze hobbies and preferences" refers to technology that acquires browsing history and purchase history from the social networking services and e-commerce sites that users connect to, and uses machine learning algorithms to identify and save the user's preferences.

[0684] "TPO guidelines" are standards for appropriate clothing for specific occasions.

[0685] The "means of generating coordination" is a technology that uses generative AI to create optimal fashion coordination based on the user's basic information, clothing information, hobbies and tastes, and TPO guidelines.

[0686] "Means for proposing the generated coordination to the user and receiving feedback as necessary" refers to a technology that displays the generated fashion coordination information to the user, receives request for changes from the user, and regenerates the coordinated information.

[0687] The "means for providing a link to a mail-order site" is a technology that provides the user with a URL to a purchase page on a mail-order site related to each item in the suggested outfit.

[0688] This invention is a system that collects and analyzes a user's basic information, clothing information, hobbies and tastes, etc., generates and suggests fashion coordinations for specific scenes, and provides links to purchase fashion items related to the coordinations on online shopping sites.

[0689] 1. User Registration

[0690] A user downloads the smartphone app, launches it, and enters basic information such as name, email address, password, height, and weight into the new registration form and submits it. This information is sent from the device to the server, where it is encrypted and stored in a database.

[0691] 2. Collecting item data

[0692] Users take photos of their clothing and accessories with their smartphones and upload them to the server via the app. The server then uses image analysis algorithms (e.g., OpenCV, TensorFlow) to extract detailed information such as color, type, brand, and style from the images and stores this data in a database.

[0693] 3. Analysis of hobbies and interests

[0694] The server automatically obtains browsing history, purchase history, and likes from the user's linked social networking service or e-commerce site (e.g., social networking service A, e-commerce site B). The server analyzes the data using machine learning algorithms (e.g., K-means clustering, deep learning models) to identify the user's preferences. The results of this analysis are also stored in a database.

[0695] 4. Coordination generation and proposal

[0696] When a user selects a specific scene (e.g., office, casual, party, etc.) within the app, the server retrieves TPO guidelines from the database. The server uses a generative AI model to generate an optimal outfit based on the basic information, clothing information, hobbies and tastes, and TPO guidelines. The generated outfit information is then saved back into the database and sent to the user's smartphone.

[0697] 5. Feedback and link to shopping site

[0698] The user can review the suggested outfits and, if necessary, send feedback via the app, such as "more casual" or "use a different color." The server then uses this feedback to regenerate outfits using a generative AI model and suggests them to the user. This process allows the user to choose the fashion that best suits their preferences and the occasion. In addition, links to online shopping sites for products related to the suggested outfits are provided, allowing the user to easily proceed to the purchase process.

[0699] Specific examples

[0700] User A enters the following information into the smartphone app:

[0701] Name: Tanaka

[0702] Email address: tanaka@example.com

[0703] Password:securepassword

[0704] Height: 175cm

[0705] Weight: 70kg

[0706] Frequently used SNS: Social networking service A (account linking)

[0707] Frequently used e-commerce site: E-commerce site B (account linkage)

[0708] Next, User A takes and uploads photos of his or her own shirts, pants, shoes, etc. The server analyzes these photos, extracts information such as color, type, brand, and style, and stores it in a database.

[0709] The server analyzes the browsing history and purchase history obtained from social networking service A and e-commerce site B to identify the preferences of user A. User A specifies an outfit for attending a friend's wedding using the app, and the server obtains the appropriate TPO guidelines for the occasion.

[0710] The server uses generative AI to generate the optimal outfit for User A, proposing a simple black suit with a white shirt and brown leather shoes. User A reviews this suggestion, and if they prefer a different color or style, they can submit feedback, and the server will regenerate the outfit. In this way, users can easily and accurately select an appropriate and personalized style for a particular occasion.

[0711] Prompt Sentence Examples

[0712] Please enter the following information into the new user registration form:

[0713] name

[0714] email address

[0715] password

[0716] height

[0717] body weight

[0718] Billed SNS account information: Social networking service A, e-commerce site B

[0719]

[0720] Take a photo of your clothing item and upload it through the app, and our server will extract details like color, type, brand, style, etc.

[0721] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0722] Step 1: User Registration

[0723] The user downloads the smartphone app and launches it. They enter basic information such as their name, email address, password, height, and weight into the new registration form and press the "Submit" button. This input data is sent from the device to the server. The server encrypts the received data and stores it in a database. Specifically, the form data containing the user information is sent to the server via a POST request, and the data is saved on the server side.

[0724] Step 2: Collect item data

[0725] Users take photos of their clothing and accessories and upload them to the server via the app. This photo data is sent from the device to the server. The server uses image analysis algorithms (OpenCV or TensorFlow) to extract detailed information from the image, such as color, type, brand, and style. The extracted data is stored in a database. Specifically, the user uploads a photo, and the server performs image analysis and stores the results in the database.

[0726] Step 3: Analysis of hobbies and interests

[0727] Data is acquired from social networking sites and e-commerce sites that users connect to. The server automatically acquires browsing history, purchase history, likes, and other information from these sites. Based on the acquired data, the server analyzes it using machine learning algorithms (K-means clustering and deep learning models) to identify the user's preferences. The analysis results are stored in a database. Specifically, data is collected by API calls, and a machine learning model is executed to analyze the collected data.

[0728] Step 4: Generate coordinates

[0729] The user selects a specific scene (e.g., office, casual, party, etc.) within the app. The device sends the selected scene information to the server. The server retrieves the TPO guidelines for that scene from the database. Based on the basic information, clothing information, hobby and taste data, and TPO guidelines, the server uses a generative AI model to generate an optimal outfit. The generated outfit information is then saved back into the database. Specifically, the server queries the database based on the scene selection information and runs the generative AI model to generate an outfit.

[0730] Step 5: Coordination suggestions and feedback

[0731] The server sends the generated coordination information to the device and displays it on the screen. The user reviews the proposed coordination and inputs feedback such as "more casual" or "use a different color" as needed. The device then sends the feedback information to the server. The server receives the feedback, again modifies the coordination using the generative AI model, and proposes a new coordination. Specific operations include displaying coordination information, inputting feedback, and regenerating the coordination.

[0732] Step 6: Provide a link to your online store

[0733] To encourage the purchase of products related to the suggested outfits, the server obtains a purchase link from the online shopping site and sends the link to the terminal. The user can easily complete the purchase procedure by clicking the link displayed on the screen to access the online shopping site. Specifically, the server generates a link containing the product's URL and provides it to the user.

[0734] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0735] The following is a detailed description of an embodiment of the present invention. This system is composed of a user, a terminal, a server, and an emotion engine, and each of these entities plays a specific role in the system.

[0736] 1. User Registration

[0737] Fill out the registration form

[0738] First, a user launches the application and fills in the registration form with basic information such as name, email address, password, height, weight, etc. They also add account information for their favorite social networking services and e-commerce sites.

[0739] Sending and storing information

[0740] The entered information is sent from the terminal to the server, where it is securely encrypted and stored in a database.

[0741] 2. Collecting item data

[0742] Upload a photo

[0743] Next, the user takes photos of their own clothing and accessories and uploads them to the server through the application.

[0744] Image analysis and storage

[0745] The server analyzes the uploaded photos and automatically extracts details such as color, type, brand, style, etc. The extracted data is stored in a database.

[0746] 3. Analysis of hobbies and interests

[0747] Data Acquisition

[0748] The server automatically retrieves data such as browsing history, likes, and purchase history from social networking sites and e-commerce sites that users connect to.

[0749] Data analysis

[0750] The acquired data is analyzed to identify the user's preferences, such as preferred styles, brands, and colors. This information is clustered using machine learning algorithms and stored in a database.

[0751] 4. Select the scene and check the time, place, and occasion

[0752] Select a scene

[0753] The user selects a specific scene (e.g., wedding, casual date, business meeting, etc.) from a scene selection screen within the application.

[0754] Obtaining TPO guidelines

[0755] The server retrieves TPO guidelines from the database according to the selected scene, clarifying the appropriate clothing standards for that scene.

[0756] 5. Coordinate Generation

[0757] Coordinate generation

[0758] The server uses AI to generate optimal outfits based on the user's basic information, clothing information, hobbies and preferences, and TPO guidelines. This generation process determines the combination of items that are appropriate for the selected occasion.

[0759] Save your outfit

[0760] The generated coordinate information is stored again in the database.

[0761] 6. Emotion recognition and suggestion adjustment

[0762] User Emotion Recognition

[0763] When confirming the proposed outfit, the device transmits the user's facial expressions and voice to the emotion engine, which analyzes the user's emotional state and transmits the results to the server.

[0764] Utilizing Emotional Data

[0765] The server uses data from the emotion engine to tailor its outfit suggestions to the user's emotional state. For example, if the user expresses positive emotions, it will suggest a different outfit based on that style.

[0766] 7. Coordination suggestions and feedback

[0767] Submit a proposal

[0768] The server sends the generated coordinate information and data adjusted by the emotion engine to the user's device, which displays this information on its screen.

[0769] Receiving feedback

[0770] The user checks the proposed outfit and enters feedback as needed, such as requests for something more casual or a different color. The emotion engine also analyzes the user's emotions in real time and reflects them on the server.

[0771] re-proposal

[0772] Based on user feedback and emotional data, the server uses the generative AI to revise and re-suggest outfits, allowing users to achieve their own unique style.

[0773] Specific examples

[0774] User registration example

[0775] Mr. Sato (user) registers as a new user, inputs his height as 160 cm and weight as 55 kg, and links his accounts for social networking service A and e-commerce site B as his frequently used SNSs.

[0776] Item Data Collection Example

[0777] Sato uploads photos of her dresses, accessories, shoes, etc. to the app, and the server analyzes the photos, extracts the necessary information, and stores it.

[0778] Example of analysis of hobbies and interests

[0779] The server retrieves Mr. Sato's browsing history and purchase history from social networking service A and e-commerce site B, and analyzes that he prefers elegant and simple designs.

[0780] Scene selection example

[0781] Sato specifies on the app that she wants to choose an outfit for attending dinner with friends, and the server retrieves TPO guidelines appropriate for the occasion.

[0782] Coordinate Generation Example

[0783] Based on Sato's basic information, clothing information, tastes, and TPO, the server uses generative AI to generate the optimal outfit, suggesting a combination of an elegant dress with simple accessories.

[0784] Example of emotion recognition and suggestion adjustment

[0785] When Sato checks the proposed outfit, the device sends Sato's facial expression to the emotion engine, and the server determines from the emotion data whether Sato is satisfied and further improves the proposal.

[0786] Suggestions and Feedback Examples

[0787] Mr. Sato reviews the proposal and, if he prefers a different color or style, he sends feedback and the emotion engine reflects his feelings back to the server. Based on this data, the server makes a new proposal.

[0788] In this way, the system of the present invention not only allows users to easily and accurately select appropriate and personal styling for specific occasions, but also uses an emotion engine to provide more personalized suggestions.

[0789] The processing flow will be explained below.

[0790] User Registration

[0791] Step 1:

[0792] A user launches the application and enters basic information such as name, email address, password, height, and weight into the new registration form.

[0793] Step 2:

[0794] The user selects their preferred social networking services and e-commerce sites and enters their respective account information.

[0795] Step 3:

[0796] The device sends all the information entered in the registration form to the server.

[0797] Step 4:

[0798] The server receives the information sent and stores it securely in a database.

[0799] Item Data Collection

[0800] Step 1:

[0801] The user takes a photo of their own clothing and accessories.

[0802] Step 2:

[0803] The device uploads the photograph to the server.

[0804] Step 3:

[0805] The server sends the received photos to an image analysis service to extract information such as color, type, brand, and style.

[0806] Step 4:

[0807] The server stores the analysis results in a database.

[0808] Analysis of hobbies and interests

[0809] Step 1:

[0810] The server obtains data such as browsing history, likes, and purchase history from the social networking services and e-commerce sites that the user has connected to.

[0811] Step 2:

[0812] The server analyzes the data and uses machine learning algorithms to identify the user's preferences, such as preferred styles, brands, and colors.

[0813] Step 3:

[0814] The server stores the analysis results in a database.

[0815] Select the scene and check the time, place, and occasion

[0816] Step 1:

[0817] The user selects a specific scene (e.g., wedding, casual date, business meeting, etc.) from a scene selection screen within the application.

[0818] Step 2:

[0819] The server retrieves the TPO guidelines corresponding to the selected scene from the database.

[0820] Coordinate generation

[0821] Step 1:

[0822] The server sends the user's basic information, clothing information, hobbies and preferences, and TPO guidelines as input data to the generation AI.

[0823] Step 2:

[0824] The generative AI generates the optimal coordination based on the input data.

[0825] Step 3:

[0826] The server stores the generated coordinate information in a database.

[0827] Emotion recognition and suggestion adjustment

[0828] Step 1:

[0829] When the user confirms the proposed outfit, the device sends the user's facial expressions and voice to the emotion engine.

[0830] Step 2:

[0831] The emotion engine analyzes the user's facial expressions and voice to recognize their emotional state, such as satisfaction, surprise, or dissatisfaction.

[0832] Step 3:

[0833] The emotion engine sends the analysis results to the server, which then adjusts the coordination according to the emotional state.

[0834] Coordination suggestions and feedback

[0835] Step 1:

[0836] The server transmits the adjusted coordinate information to the user's terminal.

[0837] Step 2:

[0838] The device displays the suggested outfit to the user, including images and detailed information (such as a list of combined items and substitution options for each item).

[0839] Step 3:

[0840] Users can provide feedback on the proposed outfits, such as requests like "I want it to be more casual" or "I'd like a different color."

[0841] Step 4:

[0842] Based on user feedback and emotional data, the server uses the generative AI to revise the outfit and make a new suggestion.

[0843] The above is the specific processing flow for carrying out the invention.

[0844] Example 2

[0845] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0846] Conventional styling suggestion systems have difficulty providing personalized outfits based on the user's hobbies, tastes, and emotions. Furthermore, when suggesting appropriate clothing for a specific occasion, they lack a mechanism for reflecting the user's real-time feedback and emotional state. This often results in users receiving unsatisfactory styling suggestions.

[0847] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0848] In this invention, the server includes means for inputting and saving basic information about a user, means for analyzing images of clothing and accessories owned by the user and saving the information, means for acquiring and analyzing data from social networking services and e-commerce sites to analyze the user's tastes and preferences and saving the results, means for acquiring TPO guidelines for specific occasions, means for using a generative AI model to generate outfits based on the basic information, clothing information, tastes and preferences data, and TPO guidelines, means for proposing the generated outfits to the user and receiving feedback as needed, and means for acquiring and analyzing the user's emotional data and adjusting the outfits based on the results. This allows personalized outfits based on the user's tastes and preferences and emotional state to be provided in real time, ensuring high satisfaction even for specific occasions.

[0849] "Basic user information" refers to personal information such as name, email address, password, height, and weight that a user enters into the application.

[0850] "Clothing information" refers to detailed information such as color, type, brand, and style obtained by analyzing images of clothing and accessories owned by the user.

[0851] "Hobbies and tastes data" refers to information such as a user's preferred styles, brands, and colors, obtained by analyzing data such as browsing history, likes, and purchase history obtained from social networking services and e-commerce sites.

[0852] "TPO guidelines" are information that indicates the standards and rules for appropriate clothing for specific occasions.

[0853] The "generative AI model" is a model that uses artificial intelligence technology to generate optimal outfits based on input basic information, clothing information, hobby and taste data, and TPO guidelines.

[0854] "Emotion data" is information that indicates the emotional state of a user, obtained from the user's facial expressions, voice, etc.

[0855] "Feedback" refers to opinions and requests provided by users regarding the proposed coordination.

[0856] This invention is a system that is composed mainly of a user, a terminal, a server, and an emotion engine, each of which plays a specific role and cooperates to provide personalized coordination.

[0857] User Registration

[0858] First, the user launches the application and enters their basic information (name, email address, password, height, weight, etc.) into the new registration form. This basic information includes account information for social networking sites and e-commerce sites. The entered information is sent from the device to the server, where it is securely encrypted and stored in a database. Specifically, the AES encryption algorithm is used for encryption, and MySQL is used for the database.

[0859] Item Data Collection

[0860] Next, users take photos of their clothing and accessories and upload them to the server through the application. The server uses the OpenCV library and YOLOv5 to analyze the photos and extract details such as color, type, brand, style, etc. The extracted data is converted to JSON format and stored in a database.

[0861] Analysis of hobbies and interests

[0862] The server automatically obtains data such as users' browsing history, likes, and purchase history from the social media and e-commerce sites they connect to using OAuth 2.0. The obtained data is analyzed using a machine learning algorithm (using Scikit-learn) to identify the user's preferences, such as preferred styles, brands, and colors. The results of this analysis are also stored in a database.

[0863] Select the scene and check the time, place, and occasion

[0864] The user selects a specific scene (e.g., wedding, casual date, business meeting, etc.) on the scene selection screen within the application. The server retrieves TPO guidelines from the database according to the selected scene and provides appropriate attire standards for that scene. In this process, the appropriate guidelines are retrieved from the database using SQL queries.

[0865] Coordinate generation

[0866] The server uses a generative AI model (using OpenAI's GPT model) to generate optimal outfits based on the user's basic information, clothing information, hobbies and preferences, and TPO guidelines. The generated outfits are then converted back to JSON format and stored in a database.

[0867] Emotion recognition and suggestion adjustment

[0868] When the user confirms the suggested outfit, the device sends the user's facial expressions and voice to the emotion engine. The emotion engine performs analysis using Microsoft Azure's emotion analysis API and sends the results to the server. The server uses this emotion data to adjust the suggested outfit according to the user's emotional state. If the user expresses positive emotions, the server will suggest a different outfit based on that style.

[0869] Coordination suggestions and feedback

[0870] The server sends the generated outfit information to the user's device, which displays the information on the screen. The user then inputs feedback on the proposed outfit (e.g., "more casual," "use a different color," etc.). The device then sends this feedback to the server, which again uses the generative AI model to revise the outfit and make a new suggestion.

[0871] Specific examples

[0872] User registration example:

[0873] A user registers as a new user, inputs their height (160 cm) and weight (55 kg), and links their frequently used SNS service to their account on the e-commerce site.

[0874] Example of collecting item data:

[0875] Users upload photos of their own dresses, accessories, shoes, etc. to the app, and the server analyzes these photos, extracts the necessary information, and stores it.

[0876] Example of hobbies and interests analysis:

[0877] The server obtains the user's browsing history and purchase history from social networking services and e-commerce sites, and analyzes that the user prefers elegant and simple designs.

[0878] Scene selection example:

[0879] The user specifies in the app that they want to choose an outfit for attending dinner with friends, and the server retrieves the TPO guidelines appropriate for that occasion.

[0880] Example of generating coordinates:

[0881] The server uses generative AI to suggest the optimal outfit based on the user's basic information, clothing information, tastes, and TPO, suggesting a combination of an elegant dress with simple accessories.

[0882] Example of emotion recognition and suggestion adjustment:

[0883] When the user checks the suggested outfits, the device sends the user's facial expression data to the emotion engine, and the server determines the satisfaction level and further improves the suggestions.

[0884] Examples of suggestions and feedback:

[0885] If the user checks the proposal and wants a different color or style, they can send feedback and have their emotions reflected in the emotion engine. Based on this information, the server will make a new proposal.

[0886] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0887] System program processing flow

[0888] Step 1: Enter your user registration information

[0889] The user enters their name, email address, password, height, weight, and account information for frequently used social networking sites and e-commerce sites into the new registration form. This becomes the input data. Specifically, the user enters information into the form and presses the "Register" button. This input data is sent to the server as registration information.

[0890] Step 2: Send and store user information

[0891] The terminal sends the entered user information to the server. The server receives this information and encrypts it using the AES encryption algorithm. It then stores this encrypted data in a MySQL database. The input is the user information, and the output is the encrypted information stored in the database.

[0892] Step 3: Upload item data

[0893] Users take photos of their clothing or accessories with their smartphone or tablet and upload them to the server via the app. Specifically, the user presses the "Upload" button, selects a photo in the file selection dialog, and uploads it. The input is the photo file, and the output is image data stored on the server.

[0894] Step 4: Image analysis and storage

[0895] The server receives the uploaded photo and performs image analysis using the OpenCV library and YOLOv5 to extract detailed information such as color, type, brand, and style. The extracted data is converted to JSON format and stored in a database. The input is the photo data, and the output is the analyzed detailed information.

[0896] Step 5: Acquire social media and e-commerce site data

[0897] The server uses OAuth 2.0 authentication to retrieve data from the user's connected social networking sites and e-commerce sites. The retrieved data includes browsing history, likes, purchase history, etc. The input is an OAuth 2.0 token, and the output is the retrieved user activity data.

[0898] Step 6: Analyze your hobbies and interests data

[0899] The server uses Scikit-learn to perform machine learning on the acquired data from social media and e-commerce sites, analyzing the user's preferred styles, brands, colors, etc. The analysis results are stored in a database. The input is activity data, and the output is data on the user's hobbies and preferences.

[0900] Step 7: Select a Scene

[0901] The user selects a specific scene from the scene selection screen of the app. Specifically, the user selects a scene from a drop-down menu and presses the "Next" button. The input is the scene selected by the user, and the output is the selected scene information.

[0902] Step 8: Obtain TPO guidelines

[0903] The server retrieves appropriate TPO guidelines from the database based on the scene selected by the user using an SQL query. The input is the scene information, and the output is the retrieved TPO guidelines.

[0904] Step 9: Generate coordinates

[0905] The server uses OpenAI's GPT model to generate optimal outfits based on the user's basic information, clothing information, hobbies and preferences, and TPO guidelines. The generated outfits are converted to JSON format and stored in a database. The input is a prompt to the generative AI model, and the output is the generated outfit information.

[0906] Step 10: Propose your outfit and receive feedback

[0907] The server sends the generated outfit information to the user's device, which displays this information on its screen. The user inputs feedback about the proposed outfit (e.g., "Make it more casual," "I'd like it in a different color," etc.), and the device sends this feedback to the server. The input is the outfit information and the user's feedback, and the output is the feedback sent to the server.

[0908] Step 11: Acquire and analyze emotion data

[0909] When the user confirms the proposed outfit, the device captures the user's facial expressions and voice and sends them to an emotion engine (e.g., Microsoft Azure's emotion analysis API). The emotion engine analyzes this data and sends the results to a server. The input is facial expression and voice data, and the output is the analysis results.

[0910] Step 12: Adjust your outfit

[0911] The server uses a generative AI model to regenerate the coordinates based on the feedback and emotion data. The input is the user's feedback and emotion data, and the output is the adjusted coordinates.

[0912] Step 13: Resubmit

[0913] The server sends the adjusted coordinates back to the terminal, which displays the information on its screen. This process is repeated until the user is satisfied. The input is the adjusted coordinates, and the output is the re-proposed coordinates.

[0914] (Application example 2)

[0915] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0916] With conventional technology, it was difficult for users to automatically and personalizedly select outfits suitable for specific occasions, and suggestions rarely took the user's emotions into consideration. As a result, suggested outfits did not necessarily match the user's preferences or the situation. Furthermore, the accuracy of re-suggestions based on feedback was low, leaving a need for improved user satisfaction.

[0917] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0918] In this invention, the server includes means for inputting and saving basic user information, means for analyzing images of clothing and accessories owned by the user and saving the information, means for acquiring and analyzing data from social networking services and e-commerce sites to analyze the user's hobbies and tastes and saving the results, means for acquiring TPO guidelines for specific occasions, means for generating outfits based on the basic information, clothing information, hobbies and tastes data, and TPO guidelines, means for proposing the generated outfits to the user and receiving feedback as needed, means for analyzing the user's reaction to the proposed outfits using an emotion analysis engine and adjusting the outfit suggestions based on the data, and means for re-proposing outfits based on the emotion data and feedback. This allows users to receive more personalized outfit suggestions that take into account their individual preferences and emotional state.

[0919] "Basic User Information" means the personal data provided by a User when registering for the Service, including basic profile information such as name, email address, password, height, and weight.

[0920] "Means for analyzing images of clothing and accessories" refers to technology that processes photos of clothing and accessories uploaded by users and automatically extracts detailed information from them, such as color, type, brand, and style.

[0921] "Means for analyzing hobbies and tastes" refers to technology for identifying and analyzing users' preferences and interests using data such as users' browsing history and purchase history obtained from social networking services and e-commerce sites.

[0922] "TPO guidelines" are guidelines that indicate standards for appropriate clothing and style for specific occasions (e.g., weddings, casual dates, business meetings, etc.).

[0923] "Generative AI" refers to artificial intelligence technology that automatically generates new items and outfits based on input data.

[0924] An "emotion analysis engine" is a technology that analyzes a user's reaction to a proposed outfit from input data such as images and voice, and automatically determines the user's emotional state.

[0925] "Feedback" refers to the user inputting their opinions and requests regarding the proposed outfits, and this feedback serves as reference information for the system to make more optimal suggestions.

[0926] "Means of re-proposing" refers to technology that uses generative AI to generate new coordination based on feedback from users and sentiment analysis data, and then re-proposes it to the user.

[0927] The system for implementing the present invention is mainly composed of a user, a terminal, a server, and an emotion analysis engine. Each of these components plays a specific role and realizes the functions of the invention.

[0928] 1. User Registration

[0929] Enter and save basic information

[0930] A user launches the application on their device and enters basic information such as their name, email address, password, height, and weight into the new registration form. They also add account information for their favorite social networking services and e-commerce sites. This information is sent from the device to the server, where it is securely encrypted and stored in a database.

[0931] 2. Collecting item data

[0932] Uploading an image

[0933] Users take photos of their clothing and accessories and upload them to the server through the application. The server analyzes these photos and automatically extracts details such as color, type, brand, and style, and stores them in a database. This process uses software such as PIL (Python Imaging Library) and OpenCV (an image processing library).

[0934] 3. Analysis of hobbies and interests

[0935] Data acquisition and analysis

[0936] The server automatically retrieves data such as browsing history, likes, and purchase history from the user's connected social networking services and e-commerce sites. The retrieved data is analyzed using machine learning algorithms (e.g., scikit-learn) to identify the user's preferences, such as preferred styles, brands, and colors. This information is then clustered and stored in a database.

[0937] 4. Selecting the scene and obtaining TPO guidelines

[0938] Select a scene

[0939] The user selects a specific scene (e.g., a business meeting, a casual date, a formal event, etc.) from the scene selection screen within the application. Depending on the selected scene, the server retrieves TPO guidelines from the database and clarifies the appropriate attire standards for that scene.

[0940] 5. Coordinate Generation

[0941] Creating and saving coordinates

[0942] The server uses a generative AI model (e.g., AIGenerate library) to generate the optimal outfit based on the user's basic information, clothing information, hobbies and preferences, and TPO guidelines. During this generation process, a combination of items appropriate for the selected scene is established. The generated outfit information is then saved back to the database.

[0943] 6. Emotion recognition and suggestion adjustment

[0944] Recognizing user emotions and tailoring suggestions

[0945] When the user confirms the suggested outfit, the device sends the user's facial expressions and voice to an emotion analysis engine. This emotion analysis engine analyzes the user's emotional state and sends the results to the server. The server then adjusts the outfit suggestions based on the user's emotional state based on the data from the emotion engine. For example, if the user expresses positive emotions, the server will suggest a new outfit based on that style.

[0946] 7. Coordination suggestions and feedback

[0947] Submitting suggestions and receiving feedback

[0948] The server sends the generated outfit information and data adjusted by the emotion analysis engine to the user's device, which then displays this information on the screen. The user checks the proposed outfit and enters feedback as needed. Based on the feedback and the user's emotional data at the time of display, the server again uses the generation AI to revise the outfit and make a new suggestion.

[0949] Specific examples

[0950] Example of user registration: Typically, a user enters their basic information and links their SNS account 1 with their e-commerce site account as their frequently used SNS.

[0951] Example of collecting item data: A user uploads photos of their dresses, accessories, shoes, etc. to the app. The server analyzes these photos, extracts the necessary information, and stores it.

[0952] Example of analyzing hobbies and tastes: The server obtains the user's browsing history and purchase history from social networking sites and e-commerce sites, and analyzes their preferred style.

[0953] Example of scene selection: A user selects a coordinate for a business meeting, and the server retrieves the TPO guidelines appropriate for the scene.

[0954] Example of outfit generation: The server uses a generative AI model to generate the optimal outfit based on the user's basic information, clothing information, tastes, and TPO, and suggests a business shirt and suit as an example.

[0955] Example of emotion recognition and suggestion adjustment: When the user confirms the suggested outfit, the device sends the user's facial expression to the emotion analysis engine, and the server analyzes the user's emotional state to improve the suggestion.

[0956] Example of suggestion and feedback: A user sends feedback requesting a different color, and the server reflects that sentiment through a sentiment analysis engine. Based on this data, the server makes a new suggestion.

[0957] Prompt Sentence Examples

[0958] user_data = {

[0959] 'name': 'Yamada Taro',

[0960] 'email': 'taro@example.com',

[0961] 'password': 'password123',

[0962] 'height': 170,

[0963] 'weight': 65,

[0964] 'sns_accounts': ['mySNSAccount1', 'mySNSAccount2']

[0965] }

[0966] response = requests.post('http: / / localhost:5000 / register', json=user_data)

[0967] The system of the present invention enables users to select styling that is appropriate for each scene with high accuracy and receive suggestions that are adapted to their own emotions and preferences.

[0968] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0969] Step 1:

[0970] Enter and save basic information

[0971] A user launches an application on their device and enters basic information (such as name, email address, password, height, and weight) into a new registration form. They then add account information for social networking services and e-commerce sites they frequently use. This information is sent from the device to a server. The server securely encrypts the received information and stores it in a database. The input data is the user's personal information, and the output is encrypted stored data.

[0972] Step 2:

[0973] Image upload and analysis

[0974] Users take photos of their clothing and accessories and upload them to the server through the application. The server receives the images and performs image analysis using PIL and OpenCV. Through this analysis, detailed information such as color, type, brand, and style is automatically extracted and stored in a database. The input data is the uploaded image, and the output is the data resulting from the image analysis.

[0975] Step 3:

[0976] Data collection and preference analysis

[0977] The server automatically retrieves data on users' browsing history, likes, and purchase history from the social networking services and e-commerce sites they connect to. The retrieved data is analyzed using machine learning algorithms such as scikit-learn to identify the user's preferences, such as preferred styles, brands, and colors. The analysis results are clustered and stored in a database. The input data is the retrieved browsing history and purchase history, and the output is the clustered preference data.

[0978] Step 4:

[0979] Selecting the scene and obtaining TPO guidelines

[0980] The user selects a specific scene, such as a business meeting, a casual date, or a formal event, from the scene selection screen within the application. Based on this selection, the server retrieves the corresponding TPO guidelines from the database and provides appropriate attire standards for that scene. The input data is the user's scene selection, and the output is the retrieved TPO guidelines.

[0981] Step 5:

[0982] Creating and saving coordinates

[0983] The server uses a generative AI model to generate optimal outfits based on the user's basic information, clothing information, taste data, and TPO guidelines. During this generation process, a combination of items appropriate for the selected occasion is established. The generated outfit information is stored in a database. The input data are basic information, clothing information, taste data, and TPO guidelines, and the output is the generated outfit.

[0984] Step 6:

[0985] Emotion recognition and suggestion adjustment

[0986] When the user confirms the suggested outfit, the device sends the user's facial expressions and voice to an emotion analysis engine in real time. The emotion analysis engine analyzes the user's emotional state and sends the results to the server. The server then adjusts the outfit suggestions based on the user's reaction based on the emotional data. For example, if the user expresses positive emotions, the server will make new suggestions based on that style. The input data is the user's emotional state data, and the output is the adjusted outfit suggestions.

[0987] Step 7:

[0988] Receiving suggestions and feedback

[0989] The server sends the generated coordination information and data adjusted by the emotion analysis engine to the user's device. The device displays this information on the screen, and the user confirms the proposed coordination. If necessary, feedback (e.g., "more casual," "I'd like it in a different color") is entered. Based on the feedback and the user's emotional data at the time of display, the server again uses the generation AI to revise the coordination and make a new proposal. The input data is the user's feedback and emotional data, and the output is the revised, re-proposed coordination.

[0990] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0991] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0992] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0993] [Third embodiment]

[0994] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0995] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0996] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0997] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0998] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0999] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1000] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1001] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1002] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1003] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1004] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1005] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1006] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below with reference to the preferred embodiment. The system is composed of users, terminals, and a server, and each of the users plays a specific role in the system.

[1007] 1. User Registration

[1008] Fill out the registration form

[1009] First, a user launches the application and fills in the registration form with basic information such as name, email address, password, height, weight, etc. They also add account information for their favorite social networking services and e-commerce sites.

[1010] Sending and storing information

[1011] The entered information is sent from the terminal to the server, where it is securely encrypted and stored in a database.

[1012] 2. Collecting item data

[1013] Upload a photo

[1014] Next, the user takes photos of their own clothing and accessories and uploads them to the server through the application.

[1015] Image analysis and storage

[1016] The server analyzes the uploaded photos and automatically extracts details such as color, type, brand, style, etc. The extracted data is stored in a database.

[1017] 3. Analysis of hobbies and interests

[1018] Data Acquisition

[1019] The server automatically retrieves data such as browsing history, likes, and purchase history from social networking sites and e-commerce sites that users connect to.

[1020] Data analysis

[1021] The acquired data is analyzed to identify the user's preferences, such as preferred styles, brands, and colors. This information is clustered using machine learning algorithms and stored in a database.

[1022] 4. Select the scene and check the time, place, and occasion

[1023] Select a scene

[1024] The user selects a specific scene (e.g., wedding, casual date, business meeting, etc.) from a scene selection screen within the application.

[1025] Obtaining TPO guidelines

[1026] The server retrieves TPO guidelines from the database according to the selected scene, clarifying the appropriate clothing standards for that scene.

[1027] 5. Coordinate Generation

[1028] Coordinate generation

[1029] The server uses AI to generate optimal outfits based on the user's basic information, clothing information, hobbies and preferences, and TPO guidelines. This generation process determines the combination of items that are appropriate for the selected occasion.

[1030] Save your outfit

[1031] The generated coordinate information is stored again in the database.

[1032] 6. Coordination suggestions and feedback

[1033] Submit a proposal

[1034] The server sends the generated coordinate information to the user's terminal, which displays the information on its screen.

[1035] Receiving feedback

[1036] The user can check the proposed outfit and enter feedback as needed, such as requests like "more casual" or "different colors."

[1037] re-proposal

[1038] The server receives feedback from the user, uses the generative AI to revise the outfit and make a new suggestion. This cycle allows the user to achieve a style that is uniquely their own.

[1039] Specific examples

[1040] User registration example

[1041] Mr. Tanaka (user) registers as a new user, inputs his height of 175 cm and weight of 70 kg, and links his accounts for social networking service A, a commonly used SNS, and e-commerce site B.

[1042] Item Data Collection Example

[1043] Tanaka uploads photos of his personal items, such as shirts, pants, and shoes, to the app. The server analyzes these photos, extracts the necessary information, and stores it.

[1044] Example of analysis of hobbies and interests

[1045] The server retrieves Tanaka's browsing history and purchase history from social networking service A and e-commerce site B, and analyzes that he prefers casual and simple designs.

[1046] Scene selection example

[1047] Tanaka specifies on the app that she wants to choose an outfit to wear to attend a friend's wedding, and the server retrieves the appropriate TPO guidelines for the occasion.

[1048] Coordinate Generation Example

[1049] Based on Tanaka's basic information, clothing information, tastes, and TPO, the server uses generative AI to generate the optimal outfit, suggesting a combination of a simple black suit, a white shirt, and brown leather shoes.

[1050] Suggestions and Feedback Examples

[1051] Tanaka reviews this proposal and, if he prefers a different color or style, he sends feedback and the server makes a new proposal.

[1052] In this way, the system of the present invention allows the user to easily and accurately select a style that is appropriate and unique to the user for a particular scene.

[1053] The processing flow will be explained below.

[1054] User Registration

[1055] Step 1:

[1056] A user launches the application and enters basic information such as name, email address, password, height, and weight into the new registration form.

[1057] Step 2:

[1058] The user selects their preferred social networking services and e-commerce sites and enters their respective account information.

[1059] Step 3:

[1060] The device sends all the information entered in the registration form to the server.

[1061] Step 4:

[1062] The server receives the information sent and stores it securely in a database.

[1063] Item Data Collection

[1064] Step 1:

[1065] The user takes a photo of their own clothing and accessories.

[1066] Step 2:

[1067] The device uploads the photograph to the server.

[1068] Step 3:

[1069] The server sends the received photos to an image analysis service to extract information such as color, type, brand, and style.

[1070] Step 4:

[1071] The server stores the analysis results in a database.

[1072] Analysis of hobbies and interests

[1073] Step 1:

[1074] The server obtains data such as browsing history, likes, and purchase history from the social networking services and e-commerce sites that the user has connected to.

[1075] Step 2:

[1076] The server analyzes the data and uses machine learning algorithms to identify the user's preferences, such as preferred styles, brands, and colors.

[1077] Step 3:

[1078] The server stores the analysis results in a database.

[1079] Select the scene and check the time, place, and occasion

[1080] Step 1:

[1081] The user selects a specific scene (e.g., wedding, casual date, business meeting, etc.) from a scene selection screen within the application.

[1082] Step 2:

[1083] The server retrieves the TPO guidelines corresponding to the selected scene from the database.

[1084] Coordinate generation

[1085] Step 1:

[1086] The server sends the user's basic information, clothing information, hobbies and preferences, and TPO guidelines as input data to the generation AI.

[1087] Step 2:

[1088] The generative AI generates the optimal coordination based on the input data.

[1089] Step 3:

[1090] The server stores the generated coordinate information in a database.

[1091] Coordination suggestions and feedback

[1092] Step 1:

[1093] The server transmits the stored coordinate information to the user's terminal.

[1094] Step 2:

[1095] The device displays the suggested outfit to the user, along with images and detailed information (such as a list of combined items and options for replacing each item) on the screen.

[1096] Step 3:

[1097] Users can provide feedback on the proposed outfits, such as requests like "I want it to be more casual" or "I'd like a different color."

[1098] Step 4:

[1099] The server receives feedback from the user, and based on that, the generative AI revises the coordination and makes a new proposal.

[1100] The above is the specific processing flow for carrying out the invention.

[1101] Example 1

[1102] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1103] Conventional outfit suggestion systems were unable to fully utilize the user's basic information and clothing information, and had difficulty accurately analyzing the user's tastes and preferences to suggest outfits suitable for specific occasions. Furthermore, the process of reflecting user feedback and re-suggesting outfits was complicated and time-consuming. For these reasons, there was a demand for more accurate outfit suggestions and a system that could quickly reflect user feedback.

[1104] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1105] In this invention, the server includes means for inputting and saving basic information about a user, means for analyzing images of clothing and accessories owned by the user and saving the information, means for acquiring and analyzing data from social networking services and e-commerce sites to analyze the user's tastes and preferences and saving the results, means for acquiring TPO guidelines for specific occasions, means for using a generative AI model to generate outfits based on the basic information, clothing information, tastes and preferences data, and TPO guidelines, means for proposing the generated outfits to the user and receiving feedback as needed, and means for regenerating the outfits based on the feedback, thereby enabling highly accurate outfit suggestions to be made to the user and for the feedback to be reflected quickly and effectively.

[1106] "Basic user information" refers to personal information entered by the user, such as name, email address, password, height, and weight.

[1107] "Images of clothing and accessories owned by the user" refers to photos of clothing, accessories, etc. owned by the user.

[1108] An "image analysis library" refers to a software tool that analyzes images of clothing and accessories and extracts detailed information such as color, type, brand, and style.

[1109] "Social networking service" refers to a website or application that provides services that enable users to interact online.

[1110] "E-commerce site" refers to a website or platform used by users to purchase products online.

[1111] "Data for analyzing hobbies and tastes" refers to information including users' browsing history, likes, purchase history, etc.

[1112] "TPO guidelines for specific occasions" refers to standards and guidelines for appropriate attire for specific occasions or events.

[1113] A "generative AI model" refers to a model that uses artificial intelligence algorithms to generate new information or content based on data.

[1114] "Coordination" refers to clothing combinations suggested based on the user's basic information, clothing information, hobbies and preferences, and TPO guidelines.

[1115] "Feedback" refers to the user's thoughts and requests regarding the proposed coordination.

[1116] "Regeneration" refers to the process of regenerating coordinates based on received feedback.

[1117] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below with reference to the preferred embodiment. The system is composed of users, terminals, and a server, and each of the users plays a specific role in the system.

[1118] 1. User Registration

[1119] A user launches an application and fills in a registration form with basic information such as name, email address, password, height, weight, etc. They also enter account information for their favorite social networking services and e-commerce sites. The information is sent from the device to the server, where it is securely encrypted and stored in a database (e.g., MySQL or PostgreSQL).

[1120] Specific examples

[1121] For example, a user has a height of 175 cm, a weight of 70 kg, and inputs account information for a commonly used social networking service A and an e-commerce site B.

[1122] 2. Collecting item data

[1123] Users take photos of their clothing and accessories and upload them to the server through the application. The server then analyzes the uploaded photos using an image analysis library (e.g., OpenCV) and automatically extracts detailed information such as color, type, brand, and style. The extracted data is stored in a database.

[1124] Specific examples

[1125] For example, when a user uploads photos of their shirts, pants, shoes, etc. to the app, the server analyzes these photos, extracts the necessary information, and stores it.

[1126] 3. Analysis of hobbies and interests

[1127] The server automatically retrieves data from the user's connected social networking sites and e-commerce sites via API. The retrieved data is analyzed using machine learning algorithms (e.g., k-means clustering) to identify the user's preferences, such as preferred styles, brands, and colors. This information is also stored in a database.

[1128] Specific examples

[1129] For example, the server acquires the user's browsing history and purchase history from SNS A and e-commerce site B, and analyzes that the user prefers casual and simple designs.

[1130] 4. Select the scene and check the time, place, and occasion

[1131] The user selects a specific scene (e.g., wedding, casual date, business meeting, etc.) from the scene selection screen within the application. The server retrieves TPO guidelines from the database according to the selected scene and clarifies the appropriate attire standards for that scene.

[1132] Specific examples

[1133] For example, when a user selects an outfit to wear to a friend's wedding, the server obtains the TPO guidelines appropriate for that occasion.

[1134] 5. Coordinate Generation

[1135] The server uses a generative AI model (e.g., GPT-3) to generate optimal outfits based on the user's basic information, clothing information, hobbies and preferences, and TPO guidelines. The generated outfit information is stored in a database.

[1136] Prompt Sentence Examples

[1137] "User basic information: height 175cm, weight 70kg. Clothing information: black suit, white shirt, brown leather shoes. Preferred style: simple, casual. TPO: formal, like a wedding. Generate the optimal outfit based on this information."

[1138] Specific examples

[1139] For example, based on Tanaka's basic information, clothing information, tastes, and TPO, the server uses generative AI to generate the optimal outfit of a simple black suit, white shirt, and brown leather shoes.

[1140] 6. Coordination suggestions and feedback

[1141] The server sends the generated outfit information to the user's device, which displays it on the screen. The user reviews the suggested outfit and provides feedback as needed. The server receives the user's feedback, again modifies the outfit using the generative AI model, and re-proposes it. This cycle allows the user to achieve a style that is uniquely their own.

[1142] Specific examples

[1143] For example, if Tanaka checks the proposed outfit and sends feedback indicating a preference for a different color or style, the server will make a new suggestion.

[1144] In this way, the system of the present invention allows the user to easily and accurately select a style that is appropriate and unique to the user for a particular scene.

[1145] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1146] Step 1:

[1147] A user starts an application and enters basic information such as name, email address, password, height, and weight into a new registration form. In addition, the user also enters account information for frequently used social networking services and e-commerce sites. This input information is sent to the server as device input. The server securely encrypts the received information and stores it in a database (e.g., MySQL or PostgreSQL). The input from the device is basic information and linked account information, which is encrypted and stored by the server.

[1148] Step 2:

[1149] Users take photos of their clothing and accessories and upload them to the server through the application. This photo data is sent to the server via the device. The server then analyzes the uploaded photo using an image analysis library (e.g., OpenCV) and automatically extracts detailed information such as color, type, brand, and style. The analyzed information is stored in a database. The input is image data, and the information extracted through image analysis is the output.

[1150] Step 3:

[1151] The server automatically acquires data (browsing history, likes, purchase history, etc.) from linked social networking sites and e-commerce sites via API. This data becomes the input to the server. The acquired data is analyzed using a machine learning algorithm (e.g., k-means clustering). As a result, the user's preferences, such as preferred styles, brands, and colors, are identified. This identified preference information is stored in a database. The acquired data is the input, and the analyzed preference information is stored as the output.

[1152] Step 4:

[1153] The user selects a scene, such as a wedding, casual date, or business meeting, from the scene selection screen within the application. This selection is input from the device to the server. The server then retrieves TPO guidelines from the database according to the selected scene. This clarifies the appropriate clothing standards for a particular scene. The user's scene selection is the input, and the retrieved TPO guidelines are the output.

[1154] Step 5:

[1155] The server generates the optimal outfit using a generative AI model (e.g., GPT-3) based on the user's basic information, clothing information, taste data, and TPO guidelines. The following prompt sentences are used in this generation process:

[1156] "User basic information: height 175cm, weight 70kg. Clothing information: black suit, white shirt, brown leather shoes. Preferred style: simple, casual. TPO: formal, like a wedding. Generate the optimal outfit based on this information."

[1157] The generated coordination information is stored in a database. The input is basic information, clothing information, taste data, and TPO guidelines, and the output is the generated coordination.

[1158] Step 6:

[1159] The server sends the generated coordination information to the user's device. The device displays this information on the screen. The user checks the proposed coordination and enters feedback as needed. The feedback becomes input from the device to the server. The server receives this feedback, again uses the generative AI model to revise the coordination and make a new proposal. This provides the optimal coordination for the user. The generated coordination proposal is the output, and regeneration and re-proposition are performed based on the received feedback.

[1160] (Application example 1)

[1161] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1162] Conventional outfit suggestion systems often struggle to provide outfits that accurately reflect a user's tastes and preferences. Furthermore, it takes time and effort for users to visually select and purchase items based on the suggested outfits. Furthermore, there are issues with systems that make it difficult to select appropriate fashion items for specific occasions. As a result, problems arise in terms of low user satisfaction and a declining reuse rate.

[1163] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1164] In this invention, the server includes means for inputting and saving basic user information, means for analyzing images of clothing and accessories owned by the user and saving the information, means for acquiring and analyzing data from social networking services and e-commerce sites to analyze the user's hobbies and tastes and saving the results, means for acquiring TPO guidelines for specific occasions, means for generating outfits based on the basic information, clothing information, hobbies and tastes data, and TPO guidelines, means for proposing the generated outfits to the user and receiving feedback as needed, and means for providing links to online shopping sites to encourage the purchase of products related to the proposed outfits. This enables the system to propose outfits optimized based on the user's hobbies and tastes and to enable the user to purchase the proposed products quickly and easily.

[1165] "Basic user information" refers to personal identification information such as name, email address, password, height, and weight.

[1166] "Clothing and accessories" refers to fashion items such as clothing and accessories owned by the user.

[1167] "Means for analyzing images and storing the information" refers to technology that uses image analysis algorithms to extract information such as color, type, brand, and style from images of clothing and accessories, and stores the data.

[1168] "Means of acquiring data from social networking services and e-commerce sites, analyzing the data, and saving the results in order to analyze hobbies and preferences" refers to technology that acquires browsing history and purchase history from the social networking services and e-commerce sites that users connect to, and uses machine learning algorithms to identify and save the user's preferences.

[1169] "TPO guidelines" are standards for appropriate clothing for specific occasions.

[1170] The "means of generating coordination" is a technology that uses generative AI to create optimal fashion coordination based on the user's basic information, clothing information, hobbies and tastes, and TPO guidelines.

[1171] "Means for proposing the generated coordination to the user and receiving feedback as necessary" refers to a technology that displays the generated fashion coordination information to the user, receives request for changes from the user, and regenerates the coordinated information.

[1172] The "means for providing a link to a mail-order site" is a technology that provides the user with a URL to a purchase page on a mail-order site related to each item in the suggested outfit.

[1173] This invention is a system that collects and analyzes a user's basic information, clothing information, hobbies and tastes, etc., generates and suggests fashion coordinations for specific scenes, and provides links to purchase fashion items related to the coordinations on online shopping sites.

[1174] 1. User Registration

[1175] A user downloads the smartphone app, launches it, and enters basic information such as name, email address, password, height, and weight into the new registration form and submits it. This information is sent from the device to the server, where it is encrypted and stored in a database.

[1176] 2. Collecting item data

[1177] Users take photos of their clothing and accessories with their smartphones and upload them to the server via the app. The server then uses image analysis algorithms (e.g., OpenCV, TensorFlow) to extract detailed information such as color, type, brand, and style from the images and stores this data in a database.

[1178] 3. Analysis of hobbies and interests

[1179] The server automatically obtains browsing history, purchase history, and likes from the user's linked social networking service or e-commerce site (e.g., social networking service A, e-commerce site B). The server analyzes the data using machine learning algorithms (e.g., K-means clustering, deep learning models) to identify the user's preferences. The results of this analysis are also stored in a database.

[1180] 4. Coordination generation and proposal

[1181] When a user selects a specific scene (e.g., office, casual, party, etc.) within the app, the server retrieves TPO guidelines from the database. The server uses a generative AI model to generate an optimal outfit based on the basic information, clothing information, hobbies and tastes, and TPO guidelines. The generated outfit information is then saved back into the database and sent to the user's smartphone.

[1182] 5. Feedback and link to shopping site

[1183] The user can review the suggested outfits and, if necessary, send feedback via the app, such as "more casual" or "use a different color." The server then uses this feedback to regenerate outfits using a generative AI model and suggests them to the user. This process allows the user to choose the fashion that best suits their preferences and the occasion. In addition, links to online shopping sites for products related to the suggested outfits are provided, allowing the user to easily proceed to the purchase process.

[1184] Specific examples

[1185] User A enters the following information into the smartphone app:

[1186] Name: Tanaka

[1187] Email address: tanaka@example.com

[1188] Password:securepassword

[1189] Height: 175cm

[1190] Weight: 70kg

[1191] Frequently used SNS: Social networking service A (account linking)

[1192] Frequently used e-commerce site: E-commerce site B (account linkage)

[1193] Next, User A takes and uploads photos of his or her own shirts, pants, shoes, etc. The server analyzes these photos, extracts information such as color, type, brand, and style, and stores it in a database.

[1194] The server analyzes the browsing history and purchase history obtained from social networking service A and e-commerce site B to identify the preferences of user A. User A specifies an outfit for attending a friend's wedding using the app, and the server obtains the appropriate TPO guidelines for the occasion.

[1195] The server uses generative AI to generate the optimal outfit for User A, proposing a simple black suit with a white shirt and brown leather shoes. User A reviews this suggestion, and if they prefer a different color or style, they can submit feedback, and the server will regenerate the outfit. In this way, users can easily and accurately select an appropriate and personalized style for a particular occasion.

[1196] Prompt Sentence Examples

[1197] Please enter the following information into the new user registration form:

[1198] name

[1199] email address

[1200] password

[1201] height

[1202] body weight

[1203] Billed SNS account information: Social networking service A, e-commerce site B

[1204]

[1205] Take a photo of your clothing item and upload it through the app, and our server will extract details like color, type, brand, style, etc.

[1206] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1207] Step 1: User Registration

[1208] The user downloads the smartphone app and launches it. They enter basic information such as their name, email address, password, height, and weight into the new registration form and press the "Submit" button. This input data is sent from the device to the server. The server encrypts the received data and stores it in a database. Specifically, the form data containing the user information is sent to the server via a POST request, and the data is saved on the server side.

[1209] Step 2: Collect item data

[1210] Users take photos of their clothing and accessories and upload them to the server via the app. This photo data is sent from the device to the server. The server uses image analysis algorithms (OpenCV or TensorFlow) to extract detailed information from the image, such as color, type, brand, and style. The extracted data is stored in a database. Specifically, the user uploads a photo, and the server performs image analysis and stores the results in the database.

[1211] Step 3: Analysis of hobbies and interests

[1212] Data is acquired from social networking sites and e-commerce sites that users connect to. The server automatically acquires browsing history, purchase history, likes, and other information from these sites. Based on the acquired data, the server analyzes it using machine learning algorithms (K-means clustering and deep learning models) to identify the user's preferences. The analysis results are stored in a database. Specifically, data is collected by API calls, and a machine learning model is executed to analyze the collected data.

[1213] Step 4: Generate coordinates

[1214] The user selects a specific scene (e.g., office, casual, party, etc.) within the app. The device sends the selected scene information to the server. The server retrieves the TPO guidelines for that scene from the database. Based on the basic information, clothing information, hobby and taste data, and TPO guidelines, the server uses a generative AI model to generate an optimal outfit. The generated outfit information is then saved back into the database. Specifically, the server queries the database based on the scene selection information and runs the generative AI model to generate an outfit.

[1215] Step 5: Coordination suggestions and feedback

[1216] The server sends the generated coordination information to the device and displays it on the screen. The user reviews the proposed coordination and inputs feedback such as "more casual" or "use a different color" as needed. The device then sends the feedback information to the server. The server receives the feedback, again modifies the coordination using the generative AI model, and proposes a new coordination. Specific operations include displaying coordination information, inputting feedback, and regenerating the coordination.

[1217] Step 6: Provide a link to your online store

[1218] To encourage the purchase of products related to the suggested outfits, the server obtains a purchase link from the online shopping site and sends the link to the terminal. The user can easily complete the purchase procedure by clicking the link displayed on the screen to access the online shopping site. Specifically, the server generates a link containing the product's URL and provides it to the user.

[1219] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1220] The following is a detailed description of an embodiment of the present invention. This system is composed of a user, a terminal, a server, and an emotion engine, and each of these entities plays a specific role in the system.

[1221] 1. User Registration

[1222] Fill out the registration form

[1223] First, a user launches the application and fills in the registration form with basic information such as name, email address, password, height, weight, etc. They also add account information for their favorite social networking services and e-commerce sites.

[1224] Sending and storing information

[1225] The entered information is sent from the terminal to the server, where it is securely encrypted and stored in a database.

[1226] 2. Collecting item data

[1227] Upload a photo

[1228] Next, the user takes photos of their own clothing and accessories and uploads them to the server through the application.

[1229] Image analysis and storage

[1230] The server analyzes the uploaded photos and automatically extracts details such as color, type, brand, style, etc. The extracted data is stored in a database.

[1231] 3. Analysis of hobbies and interests

[1232] Data Acquisition

[1233] The server automatically retrieves data such as browsing history, likes, and purchase history from social networking sites and e-commerce sites that users connect to.

[1234] Data analysis

[1235] The acquired data is analyzed to identify the user's preferences, such as preferred styles, brands, and colors. This information is clustered using machine learning algorithms and stored in a database.

[1236] 4. Select the scene and check the time, place, and occasion

[1237] Select a scene

[1238] The user selects a specific scene (e.g., wedding, casual date, business meeting, etc.) from a scene selection screen within the application.

[1239] Obtaining TPO guidelines

[1240] The server retrieves TPO guidelines from the database according to the selected scene, clarifying the appropriate clothing standards for that scene.

[1241] 5. Coordinate Generation

[1242] Coordinate generation

[1243] The server uses AI to generate optimal outfits based on the user's basic information, clothing information, hobbies and preferences, and TPO guidelines. This generation process determines the combination of items that are appropriate for the selected occasion.

[1244] Save your outfit

[1245] The generated coordinate information is stored again in the database.

[1246] 6. Emotion recognition and suggestion adjustment

[1247] User Emotion Recognition

[1248] When confirming the proposed outfit, the device transmits the user's facial expressions and voice to the emotion engine, which analyzes the user's emotional state and transmits the results to the server.

[1249] Utilizing Emotional Data

[1250] The server uses data from the emotion engine to tailor its outfit suggestions to the user's emotional state. For example, if the user expresses positive emotions, it will suggest a different outfit based on that style.

[1251] 7. Coordination suggestions and feedback

[1252] Submit a proposal

[1253] The server sends the generated coordinate information and data adjusted by the emotion engine to the user's device, which displays this information on its screen.

[1254] Receiving feedback

[1255] The user checks the proposed outfit and enters feedback as needed, such as requests for something more casual or a different color. The emotion engine also analyzes the user's emotions in real time and reflects them on the server.

[1256] re-proposal

[1257] Based on user feedback and emotional data, the server uses the generative AI to revise and re-suggest outfits, allowing users to achieve their own unique style.

[1258] Specific examples

[1259] User registration example

[1260] Mr. Sato (user) registers as a new user, inputs his height as 160 cm and weight as 55 kg, and links his accounts for social networking service A and e-commerce site B as his frequently used SNSs.

[1261] Item Data Collection Example

[1262] Sato uploads photos of her dresses, accessories, shoes, etc. to the app, and the server analyzes the photos, extracts the necessary information, and stores it.

[1263] Example of analysis of hobbies and interests

[1264] The server retrieves Mr. Sato's browsing history and purchase history from social networking service A and e-commerce site B, and analyzes that he prefers elegant and simple designs.

[1265] Scene selection example

[1266] Sato specifies on the app that she wants to choose an outfit for attending dinner with friends, and the server retrieves TPO guidelines appropriate for the occasion.

[1267] Coordinate Generation Example

[1268] Based on Sato's basic information, clothing information, tastes, and TPO, the server uses generative AI to generate the optimal outfit, suggesting a combination of an elegant dress with simple accessories.

[1269] Example of emotion recognition and suggestion adjustment

[1270] When Sato checks the proposed outfit, the device sends Sato's facial expression to the emotion engine, and the server determines from the emotion data whether Sato is satisfied and further improves the proposal.

[1271] Suggestions and Feedback Examples

[1272] Mr. Sato reviews the proposal and, if he prefers a different color or style, he sends feedback and the emotion engine reflects his feelings back to the server. Based on this data, the server makes a new proposal.

[1273] In this way, the system of the present invention not only allows users to easily and accurately select appropriate and personal styling for specific occasions, but also uses an emotion engine to provide more personalized suggestions.

[1274] The processing flow will be explained below.

[1275] User Registration

[1276] Step 1:

[1277] A user launches the application and enters basic information such as name, email address, password, height, and weight into the new registration form.

[1278] Step 2:

[1279] The user selects their preferred social networking services and e-commerce sites and enters their respective account information.

[1280] Step 3:

[1281] The device sends all the information entered in the registration form to the server.

[1282] Step 4:

[1283] The server receives the information sent and stores it securely in a database.

[1284] Item Data Collection

[1285] Step 1:

[1286] The user takes a photo of their own clothing and accessories.

[1287] Step 2:

[1288] The device uploads the photograph to the server.

[1289] Step 3:

[1290] The server sends the received photos to an image analysis service to extract information such as color, type, brand, and style.

[1291] Step 4:

[1292] The server stores the analysis results in a database.

[1293] Analysis of hobbies and interests

[1294] Step 1:

[1295] The server obtains data such as browsing history, likes, and purchase history from the social networking services and e-commerce sites that the user has connected to.

[1296] Step 2:

[1297] The server analyzes the data and uses machine learning algorithms to identify the user's preferences, such as preferred styles, brands, and colors.

[1298] Step 3:

[1299] The server stores the analysis results in a database.

[1300] Select the scene and check the time, place, and occasion

[1301] Step 1:

[1302] The user selects a specific scene (e.g., wedding, casual date, business meeting, etc.) from a scene selection screen within the application.

[1303] Step 2:

[1304] The server retrieves the TPO guidelines corresponding to the selected scene from the database.

[1305] Coordinate generation

[1306] Step 1:

[1307] The server sends the user's basic information, clothing information, hobbies and preferences, and TPO guidelines as input data to the generation AI.

[1308] Step 2:

[1309] The generative AI generates the optimal coordination based on the input data.

[1310] Step 3:

[1311] The server stores the generated coordinate information in a database.

[1312] Emotion recognition and suggestion adjustment

[1313] Step 1:

[1314] When the user confirms the proposed outfit, the device sends the user's facial expressions and voice to the emotion engine.

[1315] Step 2:

[1316] The emotion engine analyzes the user's facial expressions and voice to recognize their emotional state, such as satisfaction, surprise, or dissatisfaction.

[1317] Step 3:

[1318] The emotion engine sends the analysis results to the server, which then adjusts the coordination according to the emotional state.

[1319] Coordination suggestions and feedback

[1320] Step 1:

[1321] The server transmits the adjusted coordinate information to the user's terminal.

[1322] Step 2:

[1323] The device displays the suggested outfit to the user, including images and detailed information (such as a list of combined items and substitution options for each item).

[1324] Step 3:

[1325] Users can provide feedback on the proposed outfits, such as requests like "I want it to be more casual" or "I'd like a different color."

[1326] Step 4:

[1327] Based on user feedback and emotional data, the server uses the generative AI to revise the outfit and make a new suggestion.

[1328] The above is the specific processing flow for carrying out the invention.

[1329] Example 2

[1330] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1331] Conventional styling suggestion systems have difficulty providing personalized outfits based on the user's hobbies, tastes, and emotions. Furthermore, when suggesting appropriate clothing for a specific occasion, they lack a mechanism for reflecting the user's real-time feedback and emotional state. This often results in users receiving unsatisfactory styling suggestions.

[1332] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1333] In this invention, the server includes means for inputting and saving basic information about a user, means for analyzing images of clothing and accessories owned by the user and saving the information, means for acquiring and analyzing data from social networking services and e-commerce sites to analyze the user's tastes and preferences and saving the results, means for acquiring TPO guidelines for specific occasions, means for using a generative AI model to generate outfits based on the basic information, clothing information, tastes and preferences data, and TPO guidelines, means for proposing the generated outfits to the user and receiving feedback as needed, and means for acquiring and analyzing the user's emotional data and adjusting the outfits based on the results. This allows personalized outfits based on the user's tastes and preferences and emotional state to be provided in real time, ensuring high satisfaction even for specific occasions.

[1334] "Basic user information" refers to personal information such as name, email address, password, height, and weight that a user enters into the application.

[1335] "Clothing information" refers to detailed information such as color, type, brand, and style obtained by analyzing images of clothing and accessories owned by the user.

[1336] "Hobbies and tastes data" refers to information such as a user's preferred styles, brands, and colors, obtained by analyzing data such as browsing history, likes, and purchase history obtained from social networking services and e-commerce sites.

[1337] "TPO guidelines" are information that indicates the standards and rules for appropriate clothing for specific occasions.

[1338] The "generative AI model" is a model that uses artificial intelligence technology to generate optimal outfits based on input basic information, clothing information, hobby and taste data, and TPO guidelines.

[1339] "Emotion data" is information that indicates the emotional state of a user, obtained from the user's facial expressions, voice, etc.

[1340] "Feedback" refers to opinions and requests provided by users regarding the proposed coordination.

[1341] This invention is a system that is composed mainly of a user, a terminal, a server, and an emotion engine, each of which plays a specific role and cooperates to provide personalized coordination.

[1342] User Registration

[1343] First, the user launches the application and enters their basic information (name, email address, password, height, weight, etc.) into the new registration form. This basic information includes account information for social networking sites and e-commerce sites. The entered information is sent from the device to the server, where it is securely encrypted and stored in a database. Specifically, the AES encryption algorithm is used for encryption, and MySQL is used for the database.

[1344] Item Data Collection

[1345] Next, users take photos of their clothing and accessories and upload them to the server through the application. The server uses the OpenCV library and YOLOv5 to analyze the photos and extract details such as color, type, brand, style, etc. The extracted data is converted to JSON format and stored in a database.

[1346] Analysis of hobbies and interests

[1347] The server automatically obtains data such as users' browsing history, likes, and purchase history from the social media and e-commerce sites they connect to using OAuth 2.0. The obtained data is analyzed using a machine learning algorithm (using Scikit-learn) to identify the user's preferences, such as preferred styles, brands, and colors. The results of this analysis are also stored in a database.

[1348] Select the scene and check the time, place, and occasion

[1349] The user selects a specific scene (e.g., wedding, casual date, business meeting, etc.) on the scene selection screen within the application. The server retrieves TPO guidelines from the database according to the selected scene and provides appropriate attire standards for that scene. In this process, the appropriate guidelines are retrieved from the database using SQL queries.

[1350] Coordinate generation

[1351] The server uses a generative AI model (using OpenAI's GPT model) to generate optimal outfits based on the user's basic information, clothing information, hobbies and preferences, and TPO guidelines. The generated outfits are then converted back to JSON format and stored in a database.

[1352] Emotion recognition and suggestion adjustment

[1353] When the user confirms the suggested outfit, the device sends the user's facial expressions and voice to the emotion engine. The emotion engine performs analysis using Microsoft Azure's emotion analysis API and sends the results to the server. The server uses this emotion data to adjust the suggested outfit according to the user's emotional state. If the user expresses positive emotions, the server will suggest a different outfit based on that style.

[1354] Coordination suggestions and feedback

[1355] The server sends the generated outfit information to the user's device, which displays the information on the screen. The user then inputs feedback on the proposed outfit (e.g., "more casual," "use a different color," etc.). The device then sends this feedback to the server, which again uses the generative AI model to revise the outfit and make a new suggestion.

[1356] Specific examples

[1357] User registration example:

[1358] A user registers as a new user, inputs their height (160 cm) and weight (55 kg), and links their frequently used SNS service to their account on the e-commerce site.

[1359] Example of collecting item data:

[1360] Users upload photos of their own dresses, accessories, shoes, etc. to the app, and the server analyzes these photos, extracts the necessary information, and stores it.

[1361] Example of hobbies and interests analysis:

[1362] The server obtains the user's browsing history and purchase history from social networking services and e-commerce sites, and analyzes that the user prefers elegant and simple designs.

[1363] Scene selection example:

[1364] The user specifies in the app that they want to choose an outfit for attending dinner with friends, and the server retrieves the TPO guidelines appropriate for that occasion.

[1365] Example of generating coordinates:

[1366] The server uses generative AI to suggest the optimal outfit based on the user's basic information, clothing information, tastes, and TPO, suggesting a combination of an elegant dress with simple accessories.

[1367] Example of emotion recognition and suggestion adjustment:

[1368] When the user checks the suggested outfits, the device sends the user's facial expression data to the emotion engine, and the server determines the satisfaction level and further improves the suggestions.

[1369] Examples of suggestions and feedback:

[1370] If the user checks the proposal and wants a different color or style, they can send feedback and have their emotions reflected in the emotion engine. Based on this information, the server will make a new proposal.

[1371] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1372] System program processing flow

[1373] Step 1: Enter your user registration information

[1374] The user enters their name, email address, password, height, weight, and account information for frequently used social networking sites and e-commerce sites into the new registration form. This becomes the input data. Specifically, the user enters information into the form and presses the "Register" button. This input data is sent to the server as registration information.

[1375] Step 2: Send and store user information

[1376] The terminal sends the entered user information to the server. The server receives this information and encrypts it using the AES encryption algorithm. It then stores this encrypted data in a MySQL database. The input is the user information, and the output is the encrypted information stored in the database.

[1377] Step 3: Upload item data

[1378] Users take photos of their clothing or accessories with their smartphone or tablet and upload them to the server via the app. Specifically, the user presses the "Upload" button, selects a photo in the file selection dialog, and uploads it. The input is the photo file, and the output is image data stored on the server.

[1379] Step 4: Image analysis and storage

[1380] The server receives the uploaded photo and performs image analysis using the OpenCV library and YOLOv5 to extract detailed information such as color, type, brand, and style. The extracted data is converted to JSON format and stored in a database. The input is the photo data, and the output is the analyzed detailed information.

[1381] Step 5: Acquire social media and e-commerce site data

[1382] The server uses OAuth 2.0 authentication to retrieve data from the user's connected social networking sites and e-commerce sites. The retrieved data includes browsing history, likes, purchase history, etc. The input is an OAuth 2.0 token, and the output is the retrieved user activity data.

[1383] Step 6: Analyze your hobbies and interests data

[1384] The server uses Scikit-learn to perform machine learning on the acquired data from social media and e-commerce sites, analyzing the user's preferred styles, brands, colors, etc. The analysis results are stored in a database. The input is activity data, and the output is data on the user's hobbies and preferences.

[1385] Step 7: Select a Scene

[1386] The user selects a specific scene from the scene selection screen of the app. Specifically, the user selects a scene from a drop-down menu and presses the "Next" button. The input is the scene selected by the user, and the output is the selected scene information.

[1387] Step 8: Obtain TPO guidelines

[1388] The server retrieves appropriate TPO guidelines from the database based on the scene selected by the user using an SQL query. The input is the scene information, and the output is the retrieved TPO guidelines.

[1389] Step 9: Generate coordinates

[1390] The server uses OpenAI's GPT model to generate optimal outfits based on the user's basic information, clothing information, hobbies and preferences, and TPO guidelines. The generated outfits are converted to JSON format and stored in a database. The input is a prompt to the generative AI model, and the output is the generated outfit information.

[1391] Step 10: Propose your outfit and receive feedback

[1392] The server sends the generated outfit information to the user's device, which displays this information on its screen. The user inputs feedback about the proposed outfit (e.g., "Make it more casual," "I'd like it in a different color," etc.), and the device sends this feedback to the server. The input is the outfit information and the user's feedback, and the output is the feedback sent to the server.

[1393] Step 11: Acquire and analyze emotion data

[1394] When the user confirms the proposed outfit, the device captures the user's facial expressions and voice and sends them to an emotion engine (e.g., Microsoft Azure's emotion analysis API). The emotion engine analyzes this data and sends the results to a server. The input is facial expression and voice data, and the output is the analysis results.

[1395] Step 12: Adjust your outfit

[1396] The server uses a generative AI model to regenerate the coordinates based on the feedback and emotion data. The input is the user's feedback and emotion data, and the output is the adjusted coordinates.

[1397] Step 13: Resubmit

[1398] The server sends the adjusted coordinates back to the terminal, which displays the information on its screen. This process is repeated until the user is satisfied. The input is the adjusted coordinates, and the output is the re-proposed coordinates.

[1399] (Application example 2)

[1400] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1401] With conventional technology, it was difficult for users to automatically and personalizedly select outfits suitable for specific occasions, and suggestions rarely took the user's emotions into consideration. As a result, suggested outfits did not necessarily match the user's preferences or the situation. Furthermore, the accuracy of re-suggestions based on feedback was low, leaving a need for improved user satisfaction.

[1402] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1403] In this invention, the server includes means for inputting and saving basic user information, means for analyzing images of clothing and accessories owned by the user and saving the information, means for acquiring and analyzing data from social networking services and e-commerce sites to analyze the user's hobbies and tastes and saving the results, means for acquiring TPO guidelines for specific occasions, means for generating outfits based on the basic information, clothing information, hobbies and tastes data, and TPO guidelines, means for proposing the generated outfits to the user and receiving feedback as needed, means for analyzing the user's reaction to the proposed outfits using an emotion analysis engine and adjusting the outfit suggestions based on the data, and means for re-proposing outfits based on the emotion data and feedback. This allows users to receive more personalized outfit suggestions that take into account their individual preferences and emotional state.

[1404] "Basic User Information" means the personal data provided by a User when registering for the Service, including basic profile information such as name, email address, password, height, and weight.

[1405] "Means for analyzing images of clothing and accessories" refers to technology that processes photos of clothing and accessories uploaded by users and automatically extracts detailed information from them, such as color, type, brand, and style.

[1406] "Means for analyzing hobbies and tastes" refers to technology for identifying and analyzing users' preferences and interests using data such as users' browsing history and purchase history obtained from social networking services and e-commerce sites.

[1407] "TPO guidelines" are guidelines that indicate standards for appropriate clothing and style for specific occasions (e.g., weddings, casual dates, business meetings, etc.).

[1408] "Generative AI" refers to artificial intelligence technology that automatically generates new items and outfits based on input data.

[1409] An "emotion analysis engine" is a technology that analyzes a user's reaction to a proposed outfit from input data such as images and voice, and automatically determines the user's emotional state.

[1410] "Feedback" refers to the user inputting their opinions and requests regarding the proposed outfits, and this feedback serves as reference information for the system to make more optimal suggestions.

[1411] "Means of re-proposing" refers to technology that uses generative AI to generate new coordination based on feedback from users and sentiment analysis data, and then re-proposes it to the user.

[1412] The system for implementing the present invention is mainly composed of a user, a terminal, a server, and an emotion analysis engine. Each of these components plays a specific role and realizes the functions of the invention.

[1413] 1. User Registration

[1414] Enter and save basic information

[1415] A user launches the application on their device and enters basic information such as their name, email address, password, height, and weight into the new registration form. They also add account information for their favorite social networking services and e-commerce sites. This information is sent from the device to the server, where it is securely encrypted and stored in a database.

[1416] 2. Collecting item data

[1417] Uploading an image

[1418] Users take photos of their clothing and accessories and upload them to the server through the application. The server analyzes these photos and automatically extracts details such as color, type, brand, and style, and stores them in a database. This process uses software such as PIL (Python Imaging Library) and OpenCV (an image processing library).

[1419] 3. Analysis of hobbies and interests

[1420] Data acquisition and analysis

[1421] The server automatically retrieves data such as browsing history, likes, and purchase history from the user's connected social networking services and e-commerce sites. The retrieved data is analyzed using machine learning algorithms (e.g., scikit-learn) to identify the user's preferences, such as preferred styles, brands, and colors. This information is then clustered and stored in a database.

[1422] 4. Selecting the scene and obtaining TPO guidelines

[1423] Select a scene

[1424] The user selects a specific scene (e.g., a business meeting, a casual date, a formal event, etc.) from the scene selection screen within the application. Depending on the selected scene, the server retrieves TPO guidelines from the database and clarifies the appropriate attire standards for that scene.

[1425] 5. Coordinate Generation

[1426] Creating and saving coordinates

[1427] The server uses a generative AI model (e.g., AIGenerate library) to generate the optimal outfit based on the user's basic information, clothing information, hobbies and preferences, and TPO guidelines. During this generation process, a combination of items appropriate for the selected scene is established. The generated outfit information is then saved back to the database.

[1428] 6. Emotion recognition and suggestion adjustment

[1429] Recognizing user emotions and tailoring suggestions

[1430] When the user confirms the suggested outfit, the device sends the user's facial expressions and voice to an emotion analysis engine. This emotion analysis engine analyzes the user's emotional state and sends the results to the server. The server then adjusts the outfit suggestions based on the user's emotional state based on the data from the emotion engine. For example, if the user expresses positive emotions, the server will suggest a new outfit based on that style.

[1431] 7. Coordination suggestions and feedback

[1432] Submitting suggestions and receiving feedback

[1433] The server sends the generated outfit information and data adjusted by the emotion analysis engine to the user's device, which then displays this information on the screen. The user checks the proposed outfit and enters feedback as needed. Based on the feedback and the user's emotional data at the time of display, the server again uses the generation AI to revise the outfit and make a new suggestion.

[1434] Specific examples

[1435] Example of user registration: Typically, a user enters their basic information and links their SNS account 1 with their e-commerce site account as their frequently used SNS.

[1436] Example of collecting item data: A user uploads photos of their dresses, accessories, shoes, etc. to the app. The server analyzes these photos, extracts the necessary information, and stores it.

[1437] Example of analyzing hobbies and tastes: The server obtains the user's browsing history and purchase history from social networking sites and e-commerce sites, and analyzes their preferred style.

[1438] Example of scene selection: A user selects a coordinate for a business meeting, and the server retrieves the TPO guidelines appropriate for the scene.

[1439] Example of outfit generation: The server uses a generative AI model to generate the optimal outfit based on the user's basic information, clothing information, tastes, and TPO, and suggests a business shirt and suit as an example.

[1440] Example of emotion recognition and suggestion adjustment: When the user confirms the suggested outfit, the device sends the user's facial expression to the emotion analysis engine, and the server analyzes the user's emotional state to improve the suggestion.

[1441] Example of suggestion and feedback: A user sends feedback requesting a different color, and the server reflects that sentiment through a sentiment analysis engine. Based on this data, the server makes a new suggestion.

[1442] Prompt Sentence Examples

[1443] user_data = {

[1444] 'name': 'Yamada Taro',

[1445] 'email': 'taro@example.com',

[1446] 'password': 'password123',

[1447] 'height': 170,

[1448] 'weight': 65,

[1449] 'sns_accounts': ['mySNSAccount1', 'mySNSAccount2']

[1450] }

[1451] response = requests.post('http: / / localhost:5000 / register', json=user_data)

[1452] The system of the present invention enables users to select styling that is appropriate for each scene with high accuracy and receive suggestions that are adapted to their own emotions and preferences.

[1453] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1454] Step 1:

[1455] Enter and save basic information

[1456] A user launches an application on their device and enters basic information (such as name, email address, password, height, and weight) into a new registration form. They then add account information for social networking services and e-commerce sites they frequently use. This information is sent from the device to a server. The server securely encrypts the received information and stores it in a database. The input data is the user's personal information, and the output is encrypted stored data.

[1457] Step 2:

[1458] Image upload and analysis

[1459] Users take photos of their clothing and accessories and upload them to the server through the application. The server receives the images and performs image analysis using PIL and OpenCV. Through this analysis, detailed information such as color, type, brand, and style is automatically extracted and stored in a database. The input data is the uploaded image, and the output is the data resulting from the image analysis.

[1460] Step 3:

[1461] Data collection and preference analysis

[1462] The server automatically retrieves data on users' browsing history, likes, and purchase history from the social networking services and e-commerce sites they connect to. The retrieved data is analyzed using machine learning algorithms such as scikit-learn to identify the user's preferences, such as preferred styles, brands, and colors. The analysis results are clustered and stored in a database. The input data is the retrieved browsing history and purchase history, and the output is the clustered preference data.

[1463] Step 4:

[1464] Selecting the scene and obtaining TPO guidelines

[1465] The user selects a specific scene, such as a business meeting, a casual date, or a formal event, from the scene selection screen within the application. Based on this selection, the server retrieves the corresponding TPO guidelines from the database and provides appropriate attire standards for that scene. The input data is the user's scene selection, and the output is the retrieved TPO guidelines.

[1466] Step 5:

[1467] Creating and saving coordinates

[1468] The server uses a generative AI model to generate optimal outfits based on the user's basic information, clothing information, taste data, and TPO guidelines. During this generation process, a combination of items appropriate for the selected occasion is established. The generated outfit information is stored in a database. The input data are basic information, clothing information, taste data, and TPO guidelines, and the output is the generated outfit.

[1469] Step 6:

[1470] Emotion recognition and suggestion adjustment

[1471] When the user confirms the suggested outfit, the device sends the user's facial expressions and voice to an emotion analysis engine in real time. The emotion analysis engine analyzes the user's emotional state and sends the results to the server. The server then adjusts the outfit suggestions based on the user's reaction based on the emotional data. For example, if the user expresses positive emotions, the server will make new suggestions based on that style. The input data is the user's emotional state data, and the output is the adjusted outfit suggestions.

[1472] Step 7:

[1473] Receiving suggestions and feedback

[1474] The server sends the generated coordination information and data adjusted by the emotion analysis engine to the user's device. The device displays this information on the screen, and the user confirms the proposed coordination. If necessary, feedback (e.g., "more casual," "I'd like it in a different color") is entered. Based on the feedback and the user's emotional data at the time of display, the server again uses the generation AI to revise the coordination and make a new proposal. The input data is the user's feedback and emotional data, and the output is the revised, re-proposed coordination.

[1475] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1476] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1477] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1478] [Fourth embodiment]

[1479] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1480] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1481] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1482] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1483] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1484] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1485] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1486] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1487] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1488] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1489] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1490] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1491] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1492] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below with reference to the preferred embodiment. The system is composed of users, terminals, and a server, and each of the users plays a specific role in the system.

[1493] 1. User Registration

[1494] Fill out the registration form

[1495] First, a user launches the application and fills in the registration form with basic information such as name, email address, password, height, weight, etc. They also add account information for their favorite social networking services and e-commerce sites.

[1496] Sending and storing information

[1497] The entered information is sent from the terminal to the server, where it is securely encrypted and stored in a database.

[1498] 2. Collecting item data

[1499] Upload a photo

[1500] Next, the user takes photos of their own clothing and accessories and uploads them to the server through the application.

[1501] Image analysis and storage

[1502] The server analyzes the uploaded photos and automatically extracts details such as color, type, brand, style, etc. The extracted data is stored in a database.

[1503] 3. Analysis of hobbies and interests

[1504] Data Acquisition

[1505] The server automatically retrieves data such as browsing history, likes, and purchase history from social networking sites and e-commerce sites that users connect to.

[1506] Data analysis

[1507] The acquired data is analyzed to identify the user's preferences, such as preferred styles, brands, and colors. This information is clustered using machine learning algorithms and stored in a database.

[1508] 4. Select the scene and check the time, place, and occasion

[1509] Select a scene

[1510] The user selects a specific scene (e.g., wedding, casual date, business meeting, etc.) from a scene selection screen within the application.

[1511] Obtaining TPO guidelines

[1512] The server retrieves TPO guidelines from the database according to the selected scene, clarifying the appropriate clothing standards for that scene.

[1513] 5. Coordinate Generation

[1514] Coordinate generation

[1515] The server uses AI to generate optimal outfits based on the user's basic information, clothing information, hobbies and preferences, and TPO guidelines. This generation process determines the combination of items that are appropriate for the selected occasion.

[1516] Save your outfit

[1517] The generated coordinate information is stored again in the database.

[1518] 6. Coordination suggestions and feedback

[1519] Submit a proposal

[1520] The server sends the generated coordinate information to the user's terminal, which displays the information on its screen.

[1521] Receiving feedback

[1522] The user can check the proposed outfit and enter feedback as needed, such as requests like "more casual" or "different colors."

[1523] re-proposal

[1524] The server receives feedback from the user, uses the generative AI to revise the outfit and make a new suggestion. This cycle allows the user to achieve a style that is uniquely their own.

[1525] Specific examples

[1526] User registration example

[1527] Mr. Tanaka (user) registers as a new user, inputs his height of 175 cm and weight of 70 kg, and links his accounts for social networking service A, a commonly used SNS, and e-commerce site B.

[1528] Item Data Collection Example

[1529] Tanaka uploads photos of his personal items, such as shirts, pants, and shoes, to the app. The server analyzes these photos, extracts the necessary information, and stores it.

[1530] Example of analysis of hobbies and interests

[1531] The server retrieves Tanaka's browsing history and purchase history from social networking service A and e-commerce site B, and analyzes that he prefers casual and simple designs.

[1532] Scene selection example

[1533] Tanaka specifies on the app that she wants to choose an outfit to wear to attend a friend's wedding, and the server retrieves the appropriate TPO guidelines for the occasion.

[1534] Coordinate Generation Example

[1535] Based on Tanaka's basic information, clothing information, tastes, and TPO, the server uses generative AI to generate the optimal outfit, suggesting a combination of a simple black suit, a white shirt, and brown leather shoes.

[1536] Suggestions and Feedback Examples

[1537] Tanaka reviews this proposal and, if he prefers a different color or style, he sends feedback and the server makes a new proposal.

[1538] In this way, the system of the present invention allows the user to easily and accurately select a style that is appropriate and unique to the user for a particular scene.

[1539] The processing flow will be explained below.

[1540] User Registration

[1541] Step 1:

[1542] A user launches the application and enters basic information such as name, email address, password, height, and weight into the new registration form.

[1543] Step 2:

[1544] The user selects their preferred social networking services and e-commerce sites and enters their respective account information.

[1545] Step 3:

[1546] The device sends all the information entered in the registration form to the server.

[1547] Step 4:

[1548] The server receives the information sent and stores it securely in a database.

[1549] Item Data Collection

[1550] Step 1:

[1551] The user takes a photo of their own clothing and accessories.

[1552] Step 2:

[1553] The device uploads the photograph to the server.

[1554] Step 3:

[1555] The server sends the received photos to an image analysis service to extract information such as color, type, brand, and style.

[1556] Step 4:

[1557] The server stores the analysis results in a database.

[1558] Analysis of hobbies and interests

[1559] Step 1:

[1560] The server obtains data such as browsing history, likes, and purchase history from the social networking services and e-commerce sites that the user has connected to.

[1561] Step 2:

[1562] The server analyzes the data and uses machine learning algorithms to identify the user's preferences, such as preferred styles, brands, and colors.

[1563] Step 3:

[1564] The server stores the analysis results in a database.

[1565] Select the scene and check the time, place, and occasion

[1566] Step 1:

[1567] The user selects a specific scene (e.g., wedding, casual date, business meeting, etc.) from a scene selection screen within the application.

[1568] Step 2:

[1569] The server retrieves the TPO guidelines corresponding to the selected scene from the database.

[1570] Coordinate generation

[1571] Step 1:

[1572] The server sends the user's basic information, clothing information, hobbies and preferences, and TPO guidelines as input data to the generation AI.

[1573] Step 2:

[1574] The generative AI generates the optimal coordination based on the input data.

[1575] Step 3:

[1576] The server stores the generated coordinate information in a database.

[1577] Coordination suggestions and feedback

[1578] Step 1:

[1579] The server transmits the stored coordinate information to the user's terminal.

[1580] Step 2:

[1581] The device displays the suggested outfit to the user, along with images and detailed information (such as a list of combined items and options for replacing each item) on the screen.

[1582] Step 3:

[1583] Users can provide feedback on the proposed outfits, such as requests like "I want it to be more casual" or "I'd like a different color."

[1584] Step 4:

[1585] The server receives feedback from the user, and based on that, the generative AI revises the coordination and makes a new proposal.

[1586] The above is the specific processing flow for carrying out the invention.

[1587] Example 1

[1588] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1589] Conventional outfit suggestion systems were unable to fully utilize the user's basic information and clothing information, and had difficulty accurately analyzing the user's tastes and preferences to suggest outfits suitable for specific occasions. Furthermore, the process of reflecting user feedback and re-suggesting outfits was complicated and time-consuming. For these reasons, there was a demand for more accurate outfit suggestions and a system that could quickly reflect user feedback.

[1590] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1591] In this invention, the server includes means for inputting and saving basic information about a user, means for analyzing images of clothing and accessories owned by the user and saving the information, means for acquiring and analyzing data from social networking services and e-commerce sites to analyze the user's tastes and preferences and saving the results, means for acquiring TPO guidelines for specific occasions, means for using a generative AI model to generate outfits based on the basic information, clothing information, tastes and preferences data, and TPO guidelines, means for proposing the generated outfits to the user and receiving feedback as needed, and means for regenerating the outfits based on the feedback, thereby enabling highly accurate outfit suggestions to be made to the user and for the feedback to be reflected quickly and effectively.

[1592] "Basic user information" refers to personal information entered by the user, such as name, email address, password, height, and weight.

[1593] "Images of clothing and accessories owned by the user" refers to photos of clothing, accessories, etc. owned by the user.

[1594] An "image analysis library" refers to a software tool that analyzes images of clothing and accessories and extracts detailed information such as color, type, brand, and style.

[1595] "Social networking service" refers to a website or application that provides services that enable users to interact online.

[1596] "E-commerce site" refers to a website or platform used by users to purchase products online.

[1597] "Data for analyzing hobbies and tastes" refers to information including users' browsing history, likes, purchase history, etc.

[1598] "TPO guidelines for specific occasions" refers to standards and guidelines for appropriate attire for specific occasions or events.

[1599] A "generative AI model" refers to a model that uses artificial intelligence algorithms to generate new information or content based on data.

[1600] "Coordination" refers to clothing combinations suggested based on the user's basic information, clothing information, hobbies and preferences, and TPO guidelines.

[1601] "Feedback" refers to the user's thoughts and requests regarding the proposed coordination.

[1602] "Regeneration" refers to the process of regenerating coordinates based on received feedback.

[1603] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below with reference to the preferred embodiment. The system is composed of users, terminals, and a server, and each of the users plays a specific role in the system.

[1604] 1. User Registration

[1605] A user launches an application and fills in a registration form with basic information such as name, email address, password, height, weight, etc. They also enter account information for their favorite social networking services and e-commerce sites. The information is sent from the device to the server, where it is securely encrypted and stored in a database (e.g., MySQL or PostgreSQL).

[1606] Specific examples

[1607] For example, a user has a height of 175 cm, a weight of 70 kg, and inputs account information for a commonly used social networking service A and an e-commerce site B.

[1608] 2. Collecting item data

[1609] Users take photos of their clothing and accessories and upload them to the server through the application. The server then analyzes the uploaded photos using an image analysis library (e.g., OpenCV) and automatically extracts detailed information such as color, type, brand, and style. The extracted data is stored in a database.

[1610] Specific examples

[1611] For example, when a user uploads photos of their shirts, pants, shoes, etc. to the app, the server analyzes these photos, extracts the necessary information, and stores it.

[1612] 3. Analysis of hobbies and interests

[1613] The server automatically retrieves data from the user's connected social networking sites and e-commerce sites via API. The retrieved data is analyzed using machine learning algorithms (e.g., k-means clustering) to identify the user's preferences, such as preferred styles, brands, and colors. This information is also stored in a database.

[1614] Specific examples

[1615] For example, the server acquires the user's browsing history and purchase history from SNS A and e-commerce site B, and analyzes that the user prefers casual and simple designs.

[1616] 4. Select the scene and check the time, place, and occasion

[1617] The user selects a specific scene (e.g., wedding, casual date, business meeting, etc.) from the scene selection screen within the application. The server retrieves TPO guidelines from the database according to the selected scene and clarifies the appropriate attire standards for that scene.

[1618] Specific examples

[1619] For example, when a user selects an outfit to wear to a friend's wedding, the server obtains the TPO guidelines appropriate for that occasion.

[1620] 5. Coordinate Generation

[1621] The server uses a generative AI model (e.g., GPT-3) to generate optimal outfits based on the user's basic information, clothing information, hobbies and preferences, and TPO guidelines. The generated outfit information is stored in a database.

[1622] Prompt Sentence Examples

[1623] "User basic information: height 175cm, weight 70kg. Clothing information: black suit, white shirt, brown leather shoes. Preferred style: simple, casual. TPO: formal, like a wedding. Generate the optimal outfit based on this information."

[1624] Specific examples

[1625] For example, based on Tanaka's basic information, clothing information, tastes, and TPO, the server uses generative AI to generate the optimal outfit of a simple black suit, white shirt, and brown leather shoes.

[1626] 6. Coordination suggestions and feedback

[1627] The server sends the generated outfit information to the user's device, which displays it on the screen. The user reviews the suggested outfit and provides feedback as needed. The server receives the user's feedback, again modifies the outfit using the generative AI model, and re-proposes it. This cycle allows the user to achieve a style that is uniquely their own.

[1628] Specific examples

[1629] For example, if Tanaka checks the proposed outfit and sends feedback indicating a preference for a different color or style, the server will make a new suggestion.

[1630] In this way, the system of the present invention allows the user to easily and accurately select a style that is appropriate and unique to the user for a particular scene.

[1631] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1632] Step 1:

[1633] A user starts an application and enters basic information such as name, email address, password, height, and weight into a new registration form. In addition, the user also enters account information for frequently used social networking services and e-commerce sites. This input information is sent to the server as device input. The server securely encrypts the received information and stores it in a database (e.g., MySQL or PostgreSQL). The input from the device is basic information and linked account information, which is encrypted and stored by the server.

[1634] Step 2:

[1635] Users take photos of their clothing and accessories and upload them to the server through the application. This photo data is sent to the server via the device. The server then analyzes the uploaded photo using an image analysis library (e.g., OpenCV) and automatically extracts detailed information such as color, type, brand, and style. The analyzed information is stored in a database. The input is image data, and the information extracted through image analysis is the output.

[1636] Step 3:

[1637] The server automatically acquires data (browsing history, likes, purchase history, etc.) from linked social networking sites and e-commerce sites via API. This data becomes the input to the server. The acquired data is analyzed using a machine learning algorithm (e.g., k-means clustering). As a result, the user's preferences, such as preferred styles, brands, and colors, are identified. This identified preference information is stored in a database. The acquired data is the input, and the analyzed preference information is stored as the output.

[1638] Step 4:

[1639] The user selects a scene, such as a wedding, casual date, or business meeting, from the scene selection screen within the application. This selection is input from the device to the server. The server then retrieves TPO guidelines from the database according to the selected scene. This clarifies the appropriate clothing standards for a particular scene. The user's scene selection is the input, and the retrieved TPO guidelines are the output.

[1640] Step 5:

[1641] The server generates the optimal outfit using a generative AI model (e.g., GPT-3) based on the user's basic information, clothing information, taste data, and TPO guidelines. The following prompt sentences are used in this generation process:

[1642] "User basic information: height 175cm, weight 70kg. Clothing information: black suit, white shirt, brown leather shoes. Preferred style: simple, casual. TPO: formal, like a wedding. Generate the optimal outfit based on this information."

[1643] The generated coordination information is stored in a database. The input is basic information, clothing information, taste data, and TPO guidelines, and the output is the generated coordination.

[1644] Step 6:

[1645] The server sends the generated coordination information to the user's device. The device displays this information on the screen. The user checks the proposed coordination and enters feedback as needed. The feedback becomes input from the device to the server. The server receives this feedback, again uses the generative AI model to revise the coordination and make a new proposal. This provides the optimal coordination for the user. The generated coordination proposal is the output, and regeneration and re-proposition are performed based on the received feedback.

[1646] (Application example 1)

[1647] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1648] Conventional outfit suggestion systems often struggle to provide outfits that accurately reflect a user's tastes and preferences. Furthermore, it takes time and effort for users to visually select and purchase items based on the suggested outfits. Furthermore, there are issues with systems that make it difficult to select appropriate fashion items for specific occasions. As a result, problems arise in terms of low user satisfaction and a declining reuse rate.

[1649] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1650] In this invention, the server includes means for inputting and saving basic user information, means for analyzing images of clothing and accessories owned by the user and saving the information, means for acquiring and analyzing data from social networking services and e-commerce sites to analyze the user's hobbies and tastes and saving the results, means for acquiring TPO guidelines for specific occasions, means for generating outfits based on the basic information, clothing information, hobbies and tastes data, and TPO guidelines, means for proposing the generated outfits to the user and receiving feedback as needed, and means for providing links to online shopping sites to encourage the purchase of products related to the proposed outfits. This enables the system to propose outfits optimized based on the user's hobbies and tastes and to enable the user to purchase the proposed products quickly and easily.

[1651] "Basic user information" refers to personal identification information such as name, email address, password, height, and weight.

[1652] "Clothing and accessories" refers to fashion items such as clothing and accessories owned by the user.

[1653] "Means for analyzing images and storing the information" refers to technology that uses image analysis algorithms to extract information such as color, type, brand, and style from images of clothing and accessories, and stores the data.

[1654] "Means of acquiring data from social networking services and e-commerce sites, analyzing the data, and saving the results in order to analyze hobbies and preferences" refers to technology that acquires browsing history and purchase history from the social networking services and e-commerce sites that users connect to, and uses machine learning algorithms to identify and save the user's preferences.

[1655] "TPO guidelines" are standards for appropriate clothing for specific occasions.

[1656] The "means of generating coordination" is a technology that uses generative AI to create optimal fashion coordination based on the user's basic information, clothing information, hobbies and tastes, and TPO guidelines.

[1657] "Means for proposing the generated coordination to the user and receiving feedback as necessary" refers to a technology that displays the generated fashion coordination information to the user, receives request for changes from the user, and regenerates the coordinated information.

[1658] The "means for providing a link to a mail-order site" is a technology that provides the user with a URL to a purchase page on a mail-order site related to each item in the suggested outfit.

[1659] This invention is a system that collects and analyzes a user's basic information, clothing information, hobbies and tastes, etc., generates and suggests fashion coordinations for specific scenes, and provides links to purchase fashion items related to the coordinations on online shopping sites.

[1660] 1. User Registration

[1661] A user downloads the smartphone app, launches it, and enters basic information such as name, email address, password, height, and weight into the new registration form and submits it. This information is sent from the device to the server, where it is encrypted and stored in a database.

[1662] 2. Collecting item data

[1663] Users take photos of their clothing and accessories with their smartphones and upload them to the server via the app. The server then uses image analysis algorithms (e.g., OpenCV, TensorFlow) to extract detailed information such as color, type, brand, and style from the images and stores this data in a database.

[1664] 3. Analysis of hobbies and interests

[1665] The server automatically obtains browsing history, purchase history, and likes from the user's linked social networking service or e-commerce site (e.g., social networking service A, e-commerce site B). The server analyzes the data using machine learning algorithms (e.g., K-means clustering, deep learning models) to identify the user's preferences. The results of this analysis are also stored in a database.

[1666] 4. Coordination generation and proposal

[1667] When a user selects a specific scene (e.g., office, casual, party, etc.) within the app, the server retrieves TPO guidelines from the database. The server uses a generative AI model to generate an optimal outfit based on the basic information, clothing information, hobbies and tastes, and TPO guidelines. The generated outfit information is then saved back into the database and sent to the user's smartphone.

[1668] 5. Feedback and link to shopping site

[1669] The user can review the suggested outfits and, if necessary, send feedback via the app, such as "more casual" or "use a different color." The server then uses this feedback to regenerate outfits using a generative AI model and suggests them to the user. This process allows the user to choose the fashion that best suits their preferences and the occasion. In addition, links to online shopping sites for products related to the suggested outfits are provided, allowing the user to easily proceed to the purchase process.

[1670] Specific examples

[1671] User A enters the following information into the smartphone app:

[1672] Name: Tanaka

[1673] Email address: tanaka@example.com

[1674] Password:securepassword

[1675] Height: 175cm

[1676] Weight: 70kg

[1677] Frequently used SNS: Social networking service A (account linking)

[1678] Frequently used e-commerce site: E-commerce site B (account linkage)

[1679] Next, User A takes and uploads photos of his or her own shirts, pants, shoes, etc. The server analyzes these photos, extracts information such as color, type, brand, and style, and stores it in a database.

[1680] The server analyzes the browsing history and purchase history obtained from social networking service A and e-commerce site B to identify the preferences of user A. User A specifies an outfit for attending a friend's wedding using the app, and the server obtains the appropriate TPO guidelines for the occasion.

[1681] The server uses generative AI to generate the optimal outfit for User A, proposing a simple black suit with a white shirt and brown leather shoes. User A reviews this suggestion, and if they prefer a different color or style, they can submit feedback, and the server will regenerate the outfit. In this way, users can easily and accurately select an appropriate and personalized style for a particular occasion.

[1682] Prompt Sentence Examples

[1683] Please enter the following information into the new user registration form:

[1684] name

[1685] email address

[1686] password

[1687] height

[1688] body weight

[1689] Billed SNS account information: Social networking service A, e-commerce site B

[1690]

[1691] Take a photo of your clothing item and upload it through the app, and our server will extract details like color, type, brand, style, etc.

[1692] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1693] Step 1: User Registration

[1694] The user downloads the smartphone app and launches it. They enter basic information such as their name, email address, password, height, and weight into the new registration form and press the "Submit" button. This input data is sent from the device to the server. The server encrypts the received data and stores it in a database. Specifically, the form data containing the user information is sent to the server via a POST request, and the data is saved on the server side.

[1695] Step 2: Collect item data

[1696] Users take photos of their clothing and accessories and upload them to the server via the app. This photo data is sent from the device to the server. The server uses image analysis algorithms (OpenCV or TensorFlow) to extract detailed information from the image, such as color, type, brand, and style. The extracted data is stored in a database. Specifically, the user uploads a photo, and the server performs image analysis and stores the results in the database.

[1697] Step 3: Analysis of hobbies and interests

[1698] Data is acquired from social networking sites and e-commerce sites that users connect to. The server automatically acquires browsing history, purchase history, likes, and other information from these sites. Based on the acquired data, the server analyzes it using machine learning algorithms (K-means clustering and deep learning models) to identify the user's preferences. The analysis results are stored in a database. Specifically, data is collected by API calls, and a machine learning model is executed to analyze the collected data.

[1699] Step 4: Generate coordinates

[1700] The user selects a specific scene (e.g., office, casual, party, etc.) within the app. The device sends the selected scene information to the server. The server retrieves the TPO guidelines for that scene from the database. Based on the basic information, clothing information, hobby and taste data, and TPO guidelines, the server uses a generative AI model to generate an optimal outfit. The generated outfit information is then saved back into the database. Specifically, the server queries the database based on the scene selection information and runs the generative AI model to generate an outfit.

[1701] Step 5: Coordination suggestions and feedback

[1702] The server sends the generated coordination information to the device and displays it on the screen. The user reviews the proposed coordination and inputs feedback such as "more casual" or "use a different color" as needed. The device then sends the feedback information to the server. The server receives the feedback, again modifies the coordination using the generative AI model, and proposes a new coordination. Specific operations include displaying coordination information, inputting feedback, and regenerating the coordination.

[1703] Step 6: Provide a link to your online store

[1704] To encourage the purchase of products related to the suggested outfits, the server obtains a purchase link from the online shopping site and sends the link to the terminal. The user can easily complete the purchase procedure by clicking the link displayed on the screen to access the online shopping site. Specifically, the server generates a link containing the product's URL and provides it to the user.

[1705] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1706] The following is a detailed description of an embodiment of the present invention. This system is composed of a user, a terminal, a server, and an emotion engine, and each of these entities plays a specific role in the system.

[1707] 1. User Registration

[1708] Fill out the registration form

[1709] First, a user launches the application and fills in the registration form with basic information such as name, email address, password, height, weight, etc. They also add account information for their favorite social networking services and e-commerce sites.

[1710] Sending and storing information

[1711] The entered information is sent from the terminal to the server, where it is securely encrypted and stored in a database.

[1712] 2. Collecting item data

[1713] Upload a photo

[1714] Next, the user takes photos of their own clothing and accessories and uploads them to the server through the application.

[1715] Image analysis and storage

[1716] The server analyzes the uploaded photos and automatically extracts details such as color, type, brand, style, etc. The extracted data is stored in a database.

[1717] 3. Analysis of hobbies and interests

[1718] Data Acquisition

[1719] The server automatically retrieves data such as browsing history, likes, and purchase history from social networking sites and e-commerce sites that users connect to.

[1720] Data analysis

[1721] The acquired data is analyzed to identify the user's preferences, such as preferred styles, brands, and colors. This information is clustered using machine learning algorithms and stored in a database.

[1722] 4. Select the scene and check the time, place, and occasion

[1723] Select a scene

[1724] The user selects a specific scene (e.g., wedding, casual date, business meeting, etc.) from a scene selection screen within the application.

[1725] Obtaining TPO guidelines

[1726] The server retrieves TPO guidelines from the database according to the selected scene, clarifying the appropriate clothing standards for that scene.

[1727] 5. Coordinate Generation

[1728] Coordinate generation

[1729] The server uses AI to generate optimal outfits based on the user's basic information, clothing information, hobbies and preferences, and TPO guidelines. This generation process determines the combination of items that are appropriate for the selected occasion.

[1730] Save your outfit

[1731] The generated coordinate information is stored again in the database.

[1732] 6. Emotion recognition and suggestion adjustment

[1733] User Emotion Recognition

[1734] When confirming the proposed outfit, the device transmits the user's facial expressions and voice to the emotion engine, which analyzes the user's emotional state and transmits the results to the server.

[1735] Utilizing Emotional Data

[1736] The server uses data from the emotion engine to tailor its outfit suggestions to the user's emotional state. For example, if the user expresses positive emotions, it will suggest a different outfit based on that style.

[1737] 7. Coordination suggestions and feedback

[1738] Submit a proposal

[1739] The server sends the generated coordinate information and data adjusted by the emotion engine to the user's device, which displays this information on its screen.

[1740] Receiving feedback

[1741] The user checks the proposed outfit and enters feedback as needed, such as requests for something more casual or a different color. The emotion engine also analyzes the user's emotions in real time and reflects them on the server.

[1742] re-proposal

[1743] Based on user feedback and emotional data, the server uses the generative AI to revise and re-suggest outfits, allowing users to achieve their own unique style.

[1744] Specific examples

[1745] User registration example

[1746] Mr. Sato (user) registers as a new user, inputs his height as 160 cm and weight as 55 kg, and links his accounts for social networking service A and e-commerce site B as his frequently used SNSs.

[1747] Item Data Collection Example

[1748] Sato uploads photos of her dresses, accessories, shoes, etc. to the app, and the server analyzes the photos, extracts the necessary information, and stores it.

[1749] Example of analysis of hobbies and interests

[1750] The server retrieves Mr. Sato's browsing history and purchase history from social networking service A and e-commerce site B, and analyzes that he prefers elegant and simple designs.

[1751] Scene selection example

[1752] Sato specifies on the app that she wants to choose an outfit for attending dinner with friends, and the server retrieves TPO guidelines appropriate for the occasion.

[1753] Coordinate Generation Example

[1754] Based on Sato's basic information, clothing information, tastes, and TPO, the server uses generative AI to generate the optimal outfit, suggesting a combination of an elegant dress with simple accessories.

[1755] Example of emotion recognition and suggestion adjustment

[1756] When Sato checks the proposed outfit, the device sends Sato's facial expression to the emotion engine, and the server determines from the emotion data whether Sato is satisfied and further improves the proposal.

[1757] Suggestions and Feedback Examples

[1758] Mr. Sato reviews the proposal and, if he prefers a different color or style, he sends feedback and the emotion engine reflects his feelings back to the server. Based on this data, the server makes a new proposal.

[1759] In this way, the system of the present invention not only allows users to easily and accurately select appropriate and personal styling for specific occasions, but also uses an emotion engine to provide more personalized suggestions.

[1760] The processing flow will be explained below.

[1761] User Registration

[1762] Step 1:

[1763] A user launches the application and enters basic information such as name, email address, password, height, and weight into the new registration form.

[1764] Step 2:

[1765] The user selects their preferred social networking services and e-commerce sites and enters their respective account information.

[1766] Step 3:

[1767] The device sends all the information entered in the registration form to the server.

[1768] Step 4:

[1769] The server receives the information sent and stores it securely in a database.

[1770] Item Data Collection

[1771] Step 1:

[1772] The user takes a photo of their own clothing and accessories.

[1773] Step 2:

[1774] The device uploads the photograph to the server.

[1775] Step 3:

[1776] The server sends the received photos to an image analysis service to extract information such as color, type, brand, and style.

[1777] Step 4:

[1778] The server stores the analysis results in a database.

[1779] Analysis of hobbies and interests

[1780] Step 1:

[1781] The server obtains data such as browsing history, likes, and purchase history from the social networking services and e-commerce sites that the user has connected to.

[1782] Step 2:

[1783] The server analyzes the data and uses machine learning algorithms to identify the user's preferences, such as preferred styles, brands, and colors.

[1784] Step 3:

[1785] The server stores the analysis results in a database.

[1786] Select the scene and check the time, place, and occasion

[1787] Step 1:

[1788] The user selects a specific scene (e.g., wedding, casual date, business meeting, etc.) from a scene selection screen within the application.

[1789] Step 2:

[1790] The server retrieves the TPO guidelines corresponding to the selected scene from the database.

[1791] Coordinate generation

[1792] Step 1:

[1793] The server sends the user's basic information, clothing information, hobbies and preferences, and TPO guidelines as input data to the generation AI.

[1794] Step 2:

[1795] The generative AI generates the optimal coordination based on the input data.

[1796] Step 3:

[1797] The server stores the generated coordinate information in a database.

[1798] Emotion recognition and suggestion adjustment

[1799] Step 1:

[1800] When the user confirms the proposed outfit, the device sends the user's facial expressions and voice to the emotion engine.

[1801] Step 2:

[1802] The emotion engine analyzes the user's facial expressions and voice to recognize their emotional state, such as satisfaction, surprise, or dissatisfaction.

[1803] Step 3:

[1804] The emotion engine sends the analysis results to the server, which then adjusts the coordination according to the emotional state.

[1805] Coordination suggestions and feedback

[1806] Step 1:

[1807] The server transmits the adjusted coordinate information to the user's terminal.

[1808] Step 2:

[1809] The device displays the suggested outfit to the user, including images and detailed information (such as a list of combined items and substitution options for each item).

[1810] Step 3:

[1811] Users can provide feedback on the proposed outfits, such as requests like "I want it to be more casual" or "I'd like a different color."

[1812] Step 4:

[1813] Based on user feedback and emotional data, the server uses the generative AI to revise the outfit and make a new suggestion.

[1814] The above is the specific processing flow for carrying out the invention.

[1815] Example 2

[1816] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1817] Conventional styling suggestion systems have difficulty providing personalized outfits based on the user's hobbies, tastes, and emotions. Furthermore, when suggesting appropriate clothing for a specific occasion, they lack a mechanism for reflecting the user's real-time feedback and emotional state. This often results in users receiving unsatisfactory styling suggestions.

[1818] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1819] In this invention, the server includes means for inputting and saving basic information about a user, means for analyzing images of clothing and accessories owned by the user and saving the information, means for acquiring and analyzing data from social networking services and e-commerce sites to analyze the user's tastes and preferences and saving the results, means for acquiring TPO guidelines for specific occasions, means for using a generative AI model to generate outfits based on the basic information, clothing information, tastes and preferences data, and TPO guidelines, means for proposing the generated outfits to the user and receiving feedback as needed, and means for acquiring and analyzing the user's emotional data and adjusting the outfits based on the results. This allows personalized outfits based on the user's tastes and preferences and emotional state to be provided in real time, ensuring high satisfaction even for specific occasions.

[1820] "Basic user information" refers to personal information such as name, email address, password, height, and weight that a user enters into the application.

[1821] "Clothing information" refers to detailed information such as color, type, brand, and style obtained by analyzing images of clothing and accessories owned by the user.

[1822] "Hobbies and tastes data" refers to information such as a user's preferred styles, brands, and colors, obtained by analyzing data such as browsing history, likes, and purchase history obtained from social networking services and e-commerce sites.

[1823] "TPO guidelines" are information that indicates the standards and rules for appropriate clothing for specific occasions.

[1824] The "generative AI model" is a model that uses artificial intelligence technology to generate optimal outfits based on input basic information, clothing information, hobby and taste data, and TPO guidelines.

[1825] "Emotion data" is information that indicates the emotional state of a user, obtained from the user's facial expressions, voice, etc.

[1826] "Feedback" refers to opinions and requests provided by users regarding the proposed coordination.

[1827] This invention is a system that is composed mainly of a user, a terminal, a server, and an emotion engine, each of which plays a specific role and cooperates to provide personalized coordination.

[1828] User Registration

[1829] First, the user launches the application and enters their basic information (name, email address, password, height, weight, etc.) into the new registration form. This basic information includes account information for social networking sites and e-commerce sites. The entered information is sent from the device to the server, where it is securely encrypted and stored in a database. Specifically, the AES encryption algorithm is used for encryption, and MySQL is used for the database.

[1830] Item Data Collection

[1831] Next, users take photos of their clothing and accessories and upload them to the server through the application. The server uses the OpenCV library and YOLOv5 to analyze the photos and extract details such as color, type, brand, style, etc. The extracted data is converted to JSON format and stored in a database.

[1832] Analysis of hobbies and interests

[1833] The server automatically obtains data such as users' browsing history, likes, and purchase history from the social media and e-commerce sites they connect to using OAuth 2.0. The obtained data is analyzed using a machine learning algorithm (using Scikit-learn) to identify the user's preferences, such as preferred styles, brands, and colors. The results of this analysis are also stored in a database.

[1834] Select the scene and check the time, place, and occasion

[1835] The user selects a specific scene (e.g., wedding, casual date, business meeting, etc.) on the scene selection screen within the application. The server retrieves TPO guidelines from the database according to the selected scene and provides appropriate attire standards for that scene. In this process, the appropriate guidelines are retrieved from the database using SQL queries.

[1836] Coordinate generation

[1837] The server uses a generative AI model (using OpenAI's GPT model) to generate optimal outfits based on the user's basic information, clothing information, hobbies and preferences, and TPO guidelines. The generated outfits are then converted back to JSON format and stored in a database.

[1838] Emotion recognition and suggestion adjustment

[1839] When the user confirms the suggested outfit, the device sends the user's facial expressions and voice to the emotion engine. The emotion engine performs analysis using Microsoft Azure's emotion analysis API and sends the results to the server. The server uses this emotion data to adjust the suggested outfit according to the user's emotional state. If the user expresses positive emotions, the server will suggest a different outfit based on that style.

[1840] Coordination suggestions and feedback

[1841] The server sends the generated outfit information to the user's device, which displays the information on the screen. The user then inputs feedback on the proposed outfit (e.g., "more casual," "use a different color," etc.). The device then sends this feedback to the server, which again uses the generative AI model to revise the outfit and make a new suggestion.

[1842] Specific examples

[1843] User registration example:

[1844] A user registers as a new user, inputs their height (160 cm) and weight (55 kg), and links their frequently used SNS service to their account on the e-commerce site.

[1845] Example of collecting item data:

[1846] Users upload photos of their own dresses, accessories, shoes, etc. to the app, and the server analyzes these photos, extracts the necessary information, and stores it.

[1847] Example of hobbies and interests analysis:

[1848] The server obtains the user's browsing history and purchase history from social networking services and e-commerce sites, and analyzes that the user prefers elegant and simple designs.

[1849] Scene selection example:

[1850] The user specifies in the app that they want to choose an outfit for attending dinner with friends, and the server retrieves the TPO guidelines appropriate for that occasion.

[1851] Example of generating coordinates:

[1852] The server uses generative AI to suggest the optimal outfit based on the user's basic information, clothing information, tastes, and TPO, suggesting a combination of an elegant dress with simple accessories.

[1853] Example of emotion recognition and suggestion adjustment:

[1854] When the user checks the suggested outfits, the device sends the user's facial expression data to the emotion engine, and the server determines the satisfaction level and further improves the suggestions.

[1855] Examples of suggestions and feedback:

[1856] If the user checks the proposal and wants a different color or style, they can send feedback and have their emotions reflected in the emotion engine. Based on this information, the server will make a new proposal.

[1857] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1858] System program processing flow

[1859] Step 1: Enter your user registration information

[1860] The user enters their name, email address, password, height, weight, and account information for frequently used social networking sites and e-commerce sites into the new registration form. This becomes the input data. Specifically, the user enters information into the form and presses the "Register" button. This input data is sent to the server as registration information.

[1861] Step 2: Send and store user information

[1862] The terminal sends the entered user information to the server. The server receives this information and encrypts it using the AES encryption algorithm. It then stores this encrypted data in a MySQL database. The input is the user information, and the output is the encrypted information stored in the database.

[1863] Step 3: Upload item data

[1864] Users take photos of their clothing or accessories with their smartphone or tablet and upload them to the server via the app. Specifically, the user presses the "Upload" button, selects a photo in the file selection dialog, and uploads it. The input is the photo file, and the output is image data stored on the server.

[1865] Step 4: Image analysis and storage

[1866] The server receives the uploaded photo and performs image analysis using the OpenCV library and YOLOv5 to extract detailed information such as color, type, brand, and style. The extracted data is converted to JSON format and stored in a database. The input is the photo data, and the output is the analyzed detailed information.

[1867] Step 5: Acquire social media and e-commerce site data

[1868] The server uses OAuth 2.0 authentication to retrieve data from the user's connected social networking sites and e-commerce sites. The retrieved data includes browsing history, likes, purchase history, etc. The input is an OAuth 2.0 token, and the output is the retrieved user activity data.

[1869] Step 6: Analyze your hobbies and interests data

[1870] The server uses Scikit-learn to perform machine learning on the acquired data from social media and e-commerce sites, analyzing the user's preferred styles, brands, colors, etc. The analysis results are stored in a database. The input is activity data, and the output is data on the user's hobbies and preferences.

[1871] Step 7: Select a Scene

[1872] The user selects a specific scene from the scene selection screen of the app. Specifically, the user selects a scene from a drop-down menu and presses the "Next" button. The input is the scene selected by the user, and the output is the selected scene information.

[1873] Step 8: Obtain TPO guidelines

[1874] The server retrieves appropriate TPO guidelines from the database based on the scene selected by the user using an SQL query. The input is the scene information, and the output is the retrieved TPO guidelines.

[1875] Step 9: Generate coordinates

[1876] The server uses OpenAI's GPT model to generate optimal outfits based on the user's basic information, clothing information, hobbies and preferences, and TPO guidelines. The generated outfits are converted to JSON format and stored in a database. The input is a prompt to the generative AI model, and the output is the generated outfit information.

[1877] Step 10: Propose your outfit and receive feedback

[1878] The server sends the generated outfit information to the user's device, which displays this information on its screen. The user inputs feedback about the proposed outfit (e.g., "Make it more casual," "I'd like it in a different color," etc.), and the device sends this feedback to the server. The input is the outfit information and the user's feedback, and the output is the feedback sent to the server.

[1879] Step 11: Acquire and analyze emotion data

[1880] When the user confirms the proposed outfit, the device captures the user's facial expressions and voice and sends them to an emotion engine (e.g., Microsoft Azure's emotion analysis API). The emotion engine analyzes this data and sends the results to a server. The input is facial expression and voice data, and the output is the analysis results.

[1881] Step 12: Adjust your outfit

[1882] The server uses a generative AI model to regenerate the coordinates based on the feedback and emotion data. The input is the user's feedback and emotion data, and the output is the adjusted coordinates.

[1883] Step 13: Resubmit

[1884] The server sends the adjusted coordinates back to the terminal, which displays the information on its screen. This process is repeated until the user is satisfied. The input is the adjusted coordinates, and the output is the re-proposed coordinates.

[1885] (Application example 2)

[1886] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1887] With conventional technology, it was difficult for users to automatically and personalizedly select outfits suitable for specific occasions, and suggestions rarely took the user's emotions into consideration. As a result, suggested outfits did not necessarily match the user's preferences or the situation. Furthermore, the accuracy of re-suggestions based on feedback was low, leaving a need for improved user satisfaction.

[1888] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1889] In this invention, the server includes means for inputting and saving basic user information, means for analyzing images of clothing and accessories owned by the user and saving the information, means for acquiring and analyzing data from social networking services and e-commerce sites to analyze the user's hobbies and tastes and saving the results, means for acquiring TPO guidelines for specific occasions, means for generating outfits based on the basic information, clothing information, hobbies and tastes data, and TPO guidelines, means for proposing the generated outfits to the user and receiving feedback as needed, means for analyzing the user's reaction to the proposed outfits using an emotion analysis engine and adjusting the outfit suggestions based on the data, and means for re-proposing outfits based on the emotion data and feedback. This allows users to receive more personalized outfit suggestions that take into account their individual preferences and emotional state.

[1890] "Basic User Information" means the personal data provided by a User when registering for the Service, including basic profile information such as name, email address, password, height, and weight.

[1891] "Means for analyzing images of clothing and accessories" refers to technology that processes photos of clothing and accessories uploaded by users and automatically extracts detailed information from them, such as color, type, brand, and style.

[1892] "Means for analyzing hobbies and tastes" refers to technology for identifying and analyzing users' preferences and interests using data such as users' browsing history and purchase history obtained from social networking services and e-commerce sites.

[1893] "TPO guidelines" are guidelines that indicate standards for appropriate clothing and style for specific occasions (e.g., weddings, casual dates, business meetings, etc.).

[1894] "Generative AI" refers to artificial intelligence technology that automatically generates new items and outfits based on input data.

[1895] An "emotion analysis engine" is a technology that analyzes a user's reaction to a proposed outfit from input data such as images and voice, and automatically determines the user's emotional state.

[1896] "Feedback" refers to the user inputting their opinions and requests regarding the proposed outfits, and this feedback serves as reference information for the system to make more optimal suggestions.

[1897] "Means of re-proposing" refers to technology that uses generative AI to generate new coordination based on feedback from users and sentiment analysis data, and then re-proposes it to the user.

[1898] The system for implementing the present invention is mainly composed of a user, a terminal, a server, and an emotion analysis engine. Each of these components plays a specific role and realizes the functions of the invention.

[1899] 1. User Registration

[1900] Enter and save basic information

[1901] A user launches the application on their device and enters basic information such as their name, email address, password, height, and weight into the new registration form. They also add account information for their favorite social networking services and e-commerce sites. This information is sent from the device to the server, where it is securely encrypted and stored in a database.

[1902] 2. Collecting item data

[1903] Uploading an image

[1904] Users take photos of their clothing and accessories and upload them to the server through the application. The server analyzes these photos and automatically extracts details such as color, type, brand, and style, and stores them in a database. This process uses software such as PIL (Python Imaging Library) and OpenCV (an image processing library).

[1905] 3. Analysis of hobbies and interests

[1906] Data acquisition and analysis

[1907] The server automatically retrieves data such as browsing history, likes, and purchase history from the user's connected social networking services and e-commerce sites. The retrieved data is analyzed using machine learning algorithms (e.g., scikit-learn) to identify the user's preferences, such as preferred styles, brands, and colors. This information is then clustered and stored in a database.

[1908] 4. Selecting the scene and obtaining TPO guidelines

[1909] Select a scene

[1910] The user selects a specific scene (e.g., a business meeting, a casual date, a formal event, etc.) from the scene selection screen within the application. Depending on the selected scene, the server retrieves TPO guidelines from the database and clarifies the appropriate attire standards for that scene.

[1911] 5. Coordinate Generation

[1912] Creating and saving coordinates

[1913] The server uses a generative AI model (e.g., AIGenerate library) to generate the optimal outfit based on the user's basic information, clothing information, hobbies and preferences, and TPO guidelines. During this generation process, a combination of items appropriate for the selected scene is established. The generated outfit information is then saved back to the database.

[1914] 6. Emotion recognition and suggestion adjustment

[1915] Recognizing user emotions and tailoring suggestions

[1916] When the user confirms the suggested outfit, the device sends the user's facial expressions and voice to an emotion analysis engine. This emotion analysis engine analyzes the user's emotional state and sends the results to the server. The server then adjusts the outfit suggestions based on the user's emotional state based on the data from the emotion engine. For example, if the user expresses positive emotions, the server will suggest a new outfit based on that style.

[1917] 7. Coordination suggestions and feedback

[1918] Submitting suggestions and receiving feedback

[1919] The server sends the generated outfit information and data adjusted by the emotion analysis engine to the user's device, which then displays this information on the screen. The user checks the proposed outfit and enters feedback as needed. Based on the feedback and the user's emotional data at the time of display, the server again uses the generation AI to revise the outfit and make a new suggestion.

[1920] Specific examples

[1921] Example of user registration: Typically, a user enters their basic information and links their SNS account 1 with their e-commerce site account as their frequently used SNS.

[1922] Example of collecting item data: A user uploads photos of their dresses, accessories, shoes, etc. to the app. The server analyzes these photos, extracts the necessary information, and stores it.

[1923] Example of analyzing hobbies and tastes: The server obtains the user's browsing history and purchase history from social networking sites and e-commerce sites, and analyzes their preferred style.

[1924] Example of scene selection: A user selects a coordinate for a business meeting, and the server retrieves the TPO guidelines appropriate for the scene.

[1925] Example of outfit generation: The server uses a generative AI model to generate the optimal outfit based on the user's basic information, clothing information, tastes, and TPO, and suggests a business shirt and suit as an example.

[1926] Example of emotion recognition and suggestion adjustment: When the user confirms the suggested outfit, the device sends the user's facial expression to the emotion analysis engine, and the server analyzes the user's emotional state to improve the suggestion.

[1927] Example of suggestion and feedback: A user sends feedback requesting a different color, and the server reflects that sentiment through a sentiment analysis engine. Based on this data, the server makes a new suggestion.

[1928] Prompt Sentence Examples

[1929] user_data = {

[1930] 'name': 'Yamada Taro',

[1931] 'email': 'taro@example.com',

[1932] 'password': 'password123',

[1933] 'height': 170,

[1934] 'weight': 65,

[1935] 'sns_accounts': ['mySNSAccount1', 'mySNSAccount2'] 【19...

Claims

1. A means for inputting and saving basic information of the user; A means for analyzing images of clothing and accessories owned by the user and storing the information; A means for acquiring data from social networking services and e-commerce sites, analyzing the data, and storing the results in order to analyze users' interests and tastes; A means to obtain TPO guidelines for specific occasions, A means for generating coordination based on the basic information, clothing information, hobby / taste data, and TPO guidelines; A means for proposing the generated coordination to users and receiving feedback as needed; A system including:

2. 2. The system according to claim 1, wherein an image analysis library is used as the means for acquiring the clothing information.

3. The system according to claim 1, further comprising a machine learning algorithm for analyzing hobbies and interests based on data obtained from the social networking service and the e-commerce site.

Images