System

Abstract

A system is provided.SOLUTION: A system comprising: means for a user to input an individual feature; means for transmitting the input feature to a server; means for storing the feature in the server; means for generating a suggestion using a generative AI model based on the feature; means for providing the generated suggestion to the user; means for collecting user feedback on the suggestion; and means for reflecting the collected feedback in the generative AI model.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] Currently, many users have difficulty finding the perfect style for themselves when choosing their hairstyle or fashion from the vast number of options and information available. It is also difficult to keep up with constantly changing fashion trends and provide suggestions tailored to each individual user. Furthermore, there are no systems that effectively collect user feedback and use it to improve the accuracy of style suggestions. The present invention aims to solve these problems and provide a system that suggests the best style for each user. [Means for solving the problem]

[0005] The present invention provides the following means: By providing a system including a means for a user to input individual characteristics (hair type, face shape, skin color, desired style, etc.), a means for transmitting the input characteristics to a server, a means for storing the characteristics on the server, a means for generating suggestions using a generative AI model based on the characteristics, a means for providing the generated suggestions to the user, a means for collecting user feedback on the suggestions, and a means for reflecting the collected feedback in the generative AI model, it is possible to provide appropriate and up-to-date hairstyle and fashion suggestions to individual users. Furthermore, by including a means for reflecting the recommended styles of brands frequently used by the user and affiliated stylists in the suggestions, more accurate suggestions can be made.

[0006] "User" refers to an individual who uses the system to receive suggestions for their hairstyle and fashion.

[0007] "Individual characteristics" refers to information about a user's appearance and preferences, such as the user's hair type, face shape, skin color, and desired style.

[0008] "Server" refers to the computer system that receives and stores information sent by users and uses generative AI models to make style suggestions.

[0009] "Terminal" refers to a device (e.g., smartphone, tablet, PC, etc.) through which a user inputs information and communicates with a server.

[0010] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to generate optimal hairstyle and fashion suggestions based on user information.

[0011] "Suggestions" refer to specific hairstyle and fashion style ideas generated by a generative AI model.

[0012] "Feedback" refers to the evaluations and opinions that users give to suggestions.

[0013] "Database" means an electronic information storage system for managing received and stored user information and feedback.

[0014] A "brand" refers to a group of fashion items offered by a particular company or manufacturer.

[0015] A "stylist" is a professional who has specialized knowledge about fashion and hair styling and provides advice and suggestions to users. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0024] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0037] ---

[0038] The present invention includes a hairstyle and fashion suggestion system called Style Core. This system is designed to provide users with hairstyles and fashion styles that are optimal for them, with the server, terminals, and users working together.

[0039] Overall system configuration

[0040] The system is implemented primarily by the following components:

[0041] 1. Entering user information: The user enters their individual characteristics (hair type, face shape, skin color, desired style, etc.) into the terminal.

[0042] 2. Transmission and storage of information: The information entered by the user is transmitted from the terminal to the server and stored in the server's database.

[0043] 3. Utilizing generative AI models: The server uses generative AI models based on stored user information to suggest optimal hairstyles and fashions.

[0044] 4. Sending and displaying proposals: The generated proposals are sent from the server to the terminal and displayed on the terminal.

[0045] 5. Feedback collection: Users provide feedback on the proposals, which is sent to the server, stored in a database, and used as training data for the generative AI model.

[0046] 6. Brand and stylist collaboration: Suggestions include ways to reflect the styles of brands and affiliated stylists that users frequent.

[0047] Program processing and specific examples

[0048] Below, the program processing in each component will be explained in natural language with specific examples.

[0049] Entering user information

[0050] Users access the Style Core application using a device such as a smartphone or PC, and enter information such as their hair type (e.g., straight hair), face shape (e.g., oval), skin color (e.g., olive skin), and desired style (e.g., casual) into a form displayed on the application screen.

[0051] Sending and storing information

[0052] When the user presses the "Submit" button, the terminal sends the entered information to the server, which receives it, validates it, and stores it in the database.

[0053] Leveraging generative AI models

[0054] The server launches a generative AI model based on the saved user information. The generative AI model learns the latest trends and design knowledge, and uses that information to generate optimal hairstyle and fashion suggestions for the user. For example, for a user with straight hair and an oval face, it might suggest a "short haircut with bangs" and a "casual striped shirt."

[0055] Submitting and Viewing Proposals

[0056] The server sends the generated suggestions to the user's device, which receives and analyzes them and then displays them on the application screen, where the user can check the suggested hairstyles and fashions.

[0057] Gathering feedback

[0058] Users can provide feedback on the proposed styles within the application, such as "I like it" or "I'd like a more casual style." The device sends this feedback to the server, which receives it and stores it in a database. The stored feedback is used as training data for the generative AI model.

[0059] Collaboration with brands and stylists

[0060] The server integrates information about the user's favorite brands and affiliated stylists as training data into the generative AI model, allowing suggestions to reflect items recommended by brands and stylists familiar to the user.

[0061] ---

[0062] The above is an embodiment of the present invention. This allows users to easily find hairstyles and fashion styles that suit them best, and it is expected that the accuracy of personalized suggestions will be further improved based on feedback.

[0063] The processing flow will be explained below.

[0064] Okay, so let's break down the program's processing into specific steps.

[0065] Step 1: User accesses the system

[0066] Users launch the StyleCore application from a device such as a smartphone or PC.

[0067] Step 2: User Enters Information

[0068] The user enters individual characteristics such as their hair type (e.g., straight hair), face shape (e.g., oval), skin color (e.g., olive skin), and desired style (e.g., casual) into a form on the application screen.

[0069] Step 3: The device sends the information

[0070] When the user enters information and presses the "send" button, the terminal sends the information to the server.

[0071] Step 4: The server receives and stores the information

[0072] The server receives the user information, checks the integrity of the data, and then stores it in the database. A validation process is performed to check for inappropriate data.

[0073] Step 5: The server launches the generative AI model

[0074] The server then launches a generative AI model based on the stored user information, which is trained on the latest trends and design knowledge.

[0075] Step 6: The server inputs the data into the generative AI model

[0076] The server inputs user information into a generative AI model, which then generates optimal hairstyle and fashion suggestions based on the user's characteristics.

[0077] Step 7: The server retrieves the generated proposal

[0078] The server receives the recommendations output by the generative AI model, such as a "short haircut with bangs" and a "casual striped shirt."

[0079] Step 8: Server sends proposal

[0080] The server then sends the generated suggestions to the user's device, often in a format such as JSON.

[0081] Step 9: Your device receives and displays the proposal

[0082] The device receives the suggestions sent from the server, analyzes them, and displays them on the application screen, where the user can check the suggested hairstyles and fashions.

[0083] Step 10: User Enters Feedback

[0084] Users can input their evaluations and opinions on the suggestions, such as "I like it" or "I'd like a more casual style."

[0085] Step 11: Device sends feedback

[0086] When the user inputs feedback and presses the "send" button, the terminal sends the feedback to the server.

[0087] Step 12: Server receives and stores feedback

[0088] The server receives the feedback and stores it in a database, which is later used as training data for the generative AI model.

[0089] Step 13: The server learns the brand and stylist information

[0090] The server collects information about the user's favorite brands and affiliated stylists and integrates it into a generative AI model.

[0091] Step 14: Your server will then reflect on your recommendations with compatible brands and stylists.

[0092] The server uses the generative AI model to generate recommendations based on the styles of brands and stylists familiar to the user, resulting in more accurate recommendations for the user.

[0093] The above is a description of the specific operation of each processing step in the Style Core system.

[0094] Example 1

[0095] 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."

[0096] The present invention relates to a system that proposes optimal hairstyles and fashions based on the individual characteristics of each user. Conventional proposal systems have difficulty responding to individual user characteristics in detail, and have faced challenges in improving the accuracy of proposals that appropriately reflect user feedback. In addition, it has been difficult to reflect the proposals of brands and stylists that users are familiar with, which has prevented users from achieving sufficient satisfaction. The present invention aims to solve these problems.

[0097] 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.

[0098] In this invention, the server includes means for a user to input individual characteristics, means for transmitting the input characteristics to a processing device, means for storing the characteristics in the processing device, means for generating proposals using a generative AI model based on the characteristics, means for providing the generated proposals to a user, means for collecting user feedback on the proposals, means for reflecting the collected feedback in the generative AI model, means for analyzing and displaying the proposal content, and means for validating the user's personal information in a database of the processing device. This enables highly accurate proposals based on the user's individual characteristics, improves the accuracy of proposals based on feedback, and further enables proposals that reflect styles recommended by brands and stylists familiar to the user.

[0099] "User" refers to an individual who utilizes the system to input their characteristics and receive suggestions.

[0100] "Characteristics" refers to personal information about a user, including hair type, face shape, skin color, desired style, and the like.

[0101] "Processing device" refers to hardware or software that receives, stores, and processes data sent by a user.

[0102] A "generative AI model" refers to an artificial intelligence model that generates optimal hairstyle and fashion suggestions based on a user's characteristics.

[0103] "Suggestions" refers to recommendations about hairstyles and fashion that are generated based on the user's characteristics using a generative AI model.

[0104] "Feedback" refers to the opinions and thoughts that users provide regarding suggestions.

[0105] "Validation" refers to the process of verifying that received data has the correct format and content.

[0106] "Database" refers to an information storage system for storing user characteristics and feedback.

[0107] A "brand" refers to a sign or name that identifies the products or services offered by a particular company or organization.

[0108] A "stylist" is a professional who gives advice and suggestions regarding fashion and hairstyles.

[0109] "Terminal" refers to a device, such as a computer or smartphone, that a user uses to access the system.

[0110] "User interface" refers to the screens and operating means that users use to operate a system.

[0111] "Communication protocol" refers to the rules and procedures used between a terminal and a server to send and receive information.

[0112] An "HTTP request" refers to the communication format used by a web browser or application to request data from a server or server.

[0113] "JSON format" is a lightweight data exchange format that is easy for humans to read and machines to parse.

[0114] A "trained neural network" refers to an artificial intelligence model that has been trained using a specific dataset.

[0115] This invention is a system that suggests optimal hairstyles and fashion styles to users, and this system makes suggestions using a generative AI model based on the user's characteristics. Users can access the system using a device such as a smartphone or PC and receive suggestions by inputting their own characteristics.

[0116] Overall system configuration

[0117] The system consists of the following main components:

[0118] 1. Enter your user information

[0119] 2. Transmission and storage of information

[0120] 3. Utilizing generative AI models

[0121] 4. Submitting and Displaying Proposals

[0122] 5. Gathering Feedback

[0123] 6. Collaboration with brands and stylists

[0124] Specific actions

[0125] The specific operation of each element will be described below.

[0126] Entering user information

[0127] Users input their own characteristic information (hair type, face shape, skin color, desired style, etc.) via a device such as a smartphone or PC. This information is then input and used by the user through an application on the device.

[0128] Sending and storing information

[0129] The characteristic information entered by the user is sent from the terminal to the server. The server validates the received data, confirming that it is in the correct format and content, and then stores it in a database. The database used here is a commonly used relational database (e.g., MySQL, PostgreSQL).

[0130] Leveraging generative AI models

[0131] The server then launches a generative AI model based on the stored user information. This model is built using machine learning frameworks such as TensorFlow and PyTorch, and makes suggestions for optimal hairstyles and fashion based on the user's characteristics. For example, suggestions are generated for information such as "straight hair," "oval face," "olive skin," and "casual style."

[0132] As a concrete example, the following prompt sentence is input to the generative AI model:

[0133] "Please suggest the best casual hairstyle and fashion for a user with straight hair, an oval face, and olive skin."

[0134] Submitting and Viewing Proposals

[0135] The server sends the generated suggestions to the user's device, which receives them, analyzes them, and displays them on the application screen. The user can then check the suggested hairstyles and fashions, and save or share them as needed.

[0136] Gathering feedback

[0137] Users can input feedback on the suggestions and send it to the server via their devices. The server stores the received feedback in a database, and this feedback is used as training data for the generative AI model, thereby improving the accuracy of the suggestions made by the AI ​​model.

[0138] Collaboration with brands and stylists

[0139] The server can reflect the recommended styles of brands and affiliated stylists frequently used by the user in its suggestions. Specifically, by storing information on brand items and stylist suggestion history in a database and adding this information to the training data of the AI ​​model, the server can make suggestions that are familiar to the user.

[0140] In this way, users can use a system that suggests optimal hairstyles and fashion styles based on their individual characteristics, thereby increasing user satisfaction and improving the accuracy of suggestions.

[0141] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0142] Step 1: Enter your user information

[0143] The user launches the Style Core application using a device such as a smartphone or PC. The user enters their characteristic information (hair type, face shape, skin color, desired style, etc.) into a form displayed on the application screen. For example, the user enters specific information such as "straight hair," "oval face," "olive skin," and "casual style." This input information becomes the data sent to the server in the next step.

[0144] Step 2: Send and save information

[0145] Data entered by the user, including characteristic information, is sent from the terminal to the server. The data input is sent using an HTTP request. The server validates the received data to ensure that it is in the correct format and content. Data that passes validation is stored in the server's database. The database used here is a relational database such as MySQL or PostgreSQL.

[0146] Step 3: Leveraging generative AI models

[0147] The server launches a generative AI model based on the stored user feature information. The user's feature information (e.g., "straight hair," "oval face," "olive skin," and "casual style") is used as input. The generative AI model is built using frameworks such as TensorFlow and PyTorch. This AI model analyzes the input user feature information and generates optimal hairstyle and fashion suggestions. For example, it might generate suggestions such as "short haircut with bangs" and "casual striped shirt." As a concrete example, the following prompt sentence is input to the generative AI model:

[0148] "Please suggest the best casual hairstyle and fashion for a user with straight hair, an oval face, and olive skin."

[0149] Step 4: Submit and view your proposal

[0150] The suggestions created by the generative AI model are sent from the server to the device in data format such as JSON. The device analyzes the data received from the server and displays it on the user interface. On the display screen, the user can check the suggested hairstyle, fashion, and specific item information (e.g., a short haircut with bangs, a casual striped shirt). This allows the user to confirm the suggestions and proceed to the next step.

[0151] Step 5: Gather feedback

[0152] The user inputs their thoughts and opinions about the suggestions (e.g., "I like it," "I'd like a more casual style," etc.). The input feedback is sent from the device to the server. The server stores the received feedback data in a database. The feedback data is used as training data for the generative AI model. This improves the accuracy of the next suggestion.

[0153] Step 6: Collaborate with brands and stylists

[0154] The server integrates information about the user's favorite brands and affiliated stylists into the generative AI model. Specifically, it imports information about brand items and stylist recommendation history as learning data and stores it in a database. For example, it reflects the latest collections of brands frequently purchased by the user and recommended items from affiliated stylists in the database. This ensures that suggestions include items from brands and stylists familiar to the user.

[0155] The above are the processing steps of the system and their specific operations. Data processing and calculations are carried out at each step, resulting in a system that provides optimal suggestions to users.

[0156] (Application example 1)

[0157] 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."

[0158] Today, there are many systems that suggest the best hairstyles and fashions for individual users, but these systems require users to manually input their own characteristics. In addition, they cannot confirm the suggestions in real time, and the feedback loop to reflect the suggestions in reality is incomplete. This limits the user experience and reduces satisfaction.

[0159] 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.

[0160] In this invention, the server includes: means for a user to input individual features; means for transmitting the input features to the server; means for storing the features in the server; means for generating suggestions using a generative AI model based on the features; means for providing the generated suggestions to the user; means for collecting user feedback on the suggestions; means for reflecting the collected feedback in the generative AI model; a camera for recognizing the user's features; means for transmitting data collected by the camera to a cloud server; means for the cloud server to analyze the data using the generative AI model and generate suggestions; and means for displaying the suggestions on the user's visual device in real time. This allows the user to see optimal hairstyle and fashion suggestions in real time without having to manually input their own features, and further allows feedback based on the suggestions to be reflected in the generative AI model.

[0161] "User" refers to a person who uses the system to receive hairstyle and fashion suggestions.

[0162] "Characteristics" refers to individual information such as the user's hair type, face shape, skin color, and desired style.

[0163] "Means" refers to a method or apparatus for achieving a specific function or operation.

[0164] "Server" refers to a device or system that receives and stores information sent by users and generates and provides suggestions using generative AI models.

[0165] A "generative AI model" refers to an artificial intelligence model that generates optimal hairstyle and fashion suggestions based on training data.

[0166] "Camera" refers to a photographic device for collecting data on a user's face and body.

[0167] "Cloud Server" refers to the remote server that analyzes the collected data and generates and sends recommendations to users.

[0168] A "visual device" is a device for displaying suggestions to a user, such as smart glasses.

[0169] System Overview

[0170] The present invention relates to a style suggestion system, specifically a system that recognizes a user's individual characteristics and uses a generative AI model to suggest optimal hairstyles and fashions. The system operates by including a user terminal, a server, and a visual device (e.g., smart glasses).

[0171] Program processing and natural language explanation

[0172] User information entry and automatic collection

[0173] The user wears the vision device and activates the system. The camera on the vision device captures the user's facial and body features in real time, and the data is sent from the user's device to a cloud server. This process uses facial recognition software (e.g., OpenCV).

[0174] Analyzing information and generating recommendations

[0175] The cloud server stores the received feature data and inputs it into a generative AI model (e.g., TensorFlow). The generative AI model generates optimal hairstyle and fashion suggestions based on the stored user feature data. For example, for a user with straight hair and an oval face, it might suggest a "short haircut with bangs" and a "casual striped shirt."

[0176] Submitting and Viewing Proposals

[0177] The cloud server sends the generated suggestions to the user's visual device in real time, where the visual device analyzes the received suggestions and displays them to the user. The user can then check the suggested hairstyles and fashions as if looking in a mirror through the visual device.

[0178] Gathering and implementing feedback

[0179] When the user provides feedback on the suggestions via the visual device, the feedback is again sent to the cloud server and stored, where it is used as training data for the generative AI model to improve the accuracy of subsequent suggestions.

[0180] Specific hardware and software names used

[0181] Hardware:

[0182] Smart glasses (e.g., general-purpose smart glasses devices)

[0183] camera

[0184] Cloud Server

[0185] software:

[0186] Facial recognition software (e.g. OpenCV)

[0187] AI models (e.g. TensorFlow)

[0188] Cloud services (e.g. AWS, GCP)

[0189] Front-end applications (e.g. HTML5, JavaScript)

[0190] Examples and prompts

[0191] For example, smart glasses automatically activate when a user enters a store and perform facial recognition. At this time, the following prompt sentence is input to the generative AI model:

[0192] "Based on the client's characteristics, suggest hairstyles and casual styles that would suit someone with straight hair and an oval face."

[0193] The generative AI model generates suggestions based on this prompt and displays them on a visual device, allowing users to see the best hairstyles and fashions in real time.

[0194] summary

[0195] The system automatically collects users' personal characteristics and allows them to receive personalized style suggestions in real time, while incorporating user feedback into the generative AI model to continuously improve the accuracy of the suggestions.

[0196] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0197] Step 1:

[0198] The user puts on the smart glasses and activates the system. The camera in the smart glasses captures the user's facial and body features and sends this data to the user's device. The input data is facial images and body proportion information, which are then analyzed in subsequent processing steps.

[0199] Step 2:

[0200] The user device transmits the captured feature data to the cloud server. This transmission process involves data conversion and compression. Specifically, the image data is converted to JPEG format and compressed for efficient transmission over the network. The input data is the captured image data, and the output is compressed image data.

[0201] Step 3:

[0202] The cloud server stores the received feature data in a database. At the same time, it analyzes the image data using facial recognition software (e.g., OpenCV). This analysis process extracts characteristics such as facial shape, hair type, and skin color. The input data is compressed image data, and the output data is analyzed feature data.

[0203] Step 4:

[0204] The cloud server inputs the analyzed feature data into the generative AI model. To create this prompt, text data is generated, such as "Please suggest a hairstyle and fashion that would suit a user with straight hair and an oval face." The generative AI model then generates optimal hairstyle and fashion suggestions based on this prompt. The input data is the analyzed feature data, and the output is optimal suggestion data.

[0205] Step 5:

[0206] The cloud server transmits the generated proposal data to the user's visual device in real time. Specifically, the proposal data is encoded using a dedicated protocol and transmitted to the visual device. The input data is the proposal data, and the output is the encoded data.

[0207] Step 6:

[0208] The visual device decodes the received suggestion data and displays it to the user. The user can check the suggested hairstyle and fashion on their own image. The input data is the encoded suggestion data, and the output is a display for the user's vision.

[0209] Step 7:

[0210] The user inputs feedback on the suggestions through a visual device. For example, they input opinions such as "cut your bangs a little shorter" or "dress more casually." The input data is the user's feedback, and the output is feedback data.

[0211] Step 8:

[0212] The vision device sends feedback data to a cloud server, which stores the received feedback in a database and uses it as training data for the generative AI model. This process improves the accuracy of subsequent suggestions. The input data is the feedback data, and the output is the stored data.

[0213] 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.

[0214] ---

[0215] This invention shows an embodiment for implementing "Style Core," a system that suggests optimal hairstyles and fashions based on the individual characteristics of a user. This system operates in cooperation with a server, terminals, and users, and by combining it with an emotion engine that recognizes the user's emotions, it achieves more accurate style suggestions and feedback collection.

[0216] Overall system configuration

[0217] The system is implemented by the following components:

[0218] 1. Input of user information: The user inputs his / her individual characteristics from the terminal.

[0219] 2. Sending and saving information: The device sends the entered information to the server, which saves it in a database.

[0220] 3. Utilizing generative AI models: The server generates suggestions using generative AI models based on the stored user information.

[0221] 4. Sending and displaying the proposal: The server sends the generated proposal to the terminal and it is displayed on the user's terminal.

[0222] 5. Feedback collection: The user provides feedback on the proposal, which is sent to the server and stored in a database.

[0223] 6. Collaboration with brands and stylists: Suggestions will reflect the recommended styles of brands and affiliated stylists that users frequently use.

[0224] 7. Utilizing an emotion engine: An emotion engine is used to recognize the user's emotions and reflect the results in the suggestions.

[0225] Program processing and specific examples

[0226] Below, the program processing in each component will be explained in natural language with specific examples.

[0227] Entering user information

[0228] Users access the Style Core application using a device such as a smartphone or PC, and enter information such as their hair type (e.g., straight hair), face shape (e.g., oval), skin color (e.g., olive skin), and desired style (e.g., casual) into the application form screen.

[0229] Sending and storing information

[0230] When the user presses the "Submit" button, the terminal sends the entered information to the server, which receives the information, validates it, and stores it in the database.

[0231] Leveraging generative AI models

[0232] The server launches a generative AI model based on the saved user information. The generative AI model learns the latest trends and design knowledge and generates optimal hairstyle and fashion suggestions based on the user information. For example, for a user with straight hair and an oval face, it would suggest a "short haircut with bangs" and a "casual striped shirt."

[0233] Submitting and Viewing Proposals

[0234] The server sends the generated suggestions to the user's device, which receives them and displays them on the application screen, where the user can check the suggested hairstyles and fashions.

[0235] Gathering feedback

[0236] Users can provide feedback on the suggested styles, such as "I like it" or "I'd like a more casual style." The device then sends this feedback to the server, which receives it and stores it in a database. The feedback is then used as training data for the generative AI model.

[0237] Collaboration with brands and stylists

[0238] The server integrates information about the user's favorite brands and affiliated stylists as training data into the generative AI model, allowing suggestions to reflect items recommended by brands and stylists familiar to the user.

[0239] Utilizing the Emotion Engine

[0240] The device is equipped with an emotion engine that recognizes emotions through the user's facial expressions and voice. The recognized emotion data is sent to a server, which then uses the data to adjust the generative AI model. For example, if the user smiles when viewing a suggestion, the emotion data is added to the feedback as a signal that the suggestion has been accepted. In this way, the suggestions are further personalized.

[0241] ---

[0242] The above is an embodiment of the present invention. This allows users to receive personalized suggestions for hairstyles and fashion styles based on their emotions. Furthermore, it is expected that the accuracy of suggestions will be further improved based on feedback.

[0243] The processing flow will be explained below.

[0244] Step 1: User accesses the system

[0245] Users launch StyleCore applications using devices such as smartphones and PCs.

[0246] Step 2: User Enters Information

[0247] The user enters their individual characteristics, such as their hair type (e.g., straight hair), face shape (e.g., oval), skin color (e.g., olive skin), and desired style (e.g., casual), into the application's form screen.

[0248] Step 3: The device sends the information

[0249] When the user inputs information and presses the "send" button, the terminal sends the input information to the server.

[0250] Step 4: The server receives and stores the information

[0251] The server receives the submitted user information, checks the data for consistency, and stores it in a database, for example by validating that the hair type is specified correctly and that the face shape is within the valid options.

[0252] Step 5: The server launches the generative AI model

[0253] The server then launches a generative AI model based on the stored user information, which uses the trend data and design knowledge it has learned to generate optimal hairstyle and fashion suggestions.

[0254] Step 6: The server inputs the data into the generative AI model

[0255] The server inputs user information into a generative AI model, which takes into account the user's hair type, face shape, skin color, etc. to calculate and generate optimal style suggestions.

[0256] Step 7: The server retrieves the generated proposal

[0257] The server receives the output of the generative AI model, generating specific style suggestions such as a "short haircut with bangs" and a "casual striped shirt."

[0258] Step 8: Server sends proposal

[0259] The server sends the generated proposal to the user's device, formatted in JSON or similar.

[0260] Step 9: Your device receives and displays the proposal

[0261] The device receives the suggestions sent from the server, analyzes them, and displays them on the application screen, where the user can check the suggested hairstyles and fashions.

[0262] Step 10: User Enters Feedback

[0263] Users can then rate and comment on the suggestions within the application, for example by entering feedback such as "I like it" or "I'd like a more casual style."

[0264] Step 11: Device sends feedback

[0265] When the user inputs feedback and presses the "send" button, the terminal sends the feedback to the server.

[0266] Step 12: Server receives and stores feedback

[0267] The server receives the feedback and stores it in a database, which is later used as training data for the generative AI model.

[0268] Step 13: The server learns the brand and stylist information

[0269] The server collects information about the user's favorite brands and affiliated stylists, stores it in a database, and then integrates this information into a generative AI model for training.

[0270] Step 14: Your server will then reflect on your recommendations with compatible brands and stylists.

[0271] The server uses a generative AI model to generate suggestions that reflect the brands and stylists familiar to the user, for example, by providing suggestions that include the latest collections from brands the user frequently purchases.

[0272] Step 15: Device captures real-time emotions

[0273] The device is equipped with an emotion engine that recognizes emotions through the user's real-time facial expressions and voice, for example, by using a camera and microphone to detect the user's smile and tone of voice.

[0274] Step 16: The device sends emotion data

[0275] The device sends the recognized emotion data to the server. For example, if the device recognizes a smile or a voice of joy from the user, the data is sent to the server.

[0276] Step 17: The server reflects the emotion data in the generative AI model

[0277] The server then feeds the received emotion data into the generative AI model, which then further adjusts the suggestions based on the user's emotion. If the emotion data is positive, the feedback is considered a positive evaluation.

[0278] The above is a concrete explanation of the operation of each processing step in the style core system including the emotion engine.

[0279] Example 2

[0280] 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."

[0281] Conventional style suggestion systems have difficulty providing personalized suggestions based on the individual characteristics of each user, which has led to issues with not being able to sufficiently increase user satisfaction. Furthermore, they lacked the functionality to appropriately reflect user feedback and emotions, making it impossible to improve the accuracy of suggestions for the next time. Furthermore, they were unable to reflect the recommended styles of brands frequently used by users or affiliated stylists in the suggestions, making it impossible to realize suggestions tailored to the user's preferences.

[0282] 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.

[0283] In this invention, the server includes means for a user to input individual features, means for transmitting the input features to the server, means for storing the features in the server, means for generating suggestions using a generative AI model based on the features, means for providing the generated suggestions to the user, means for collecting user feedback on the suggestions, means for reflecting the collected feedback in the generative AI model, and means for recognizing user emotions using an emotion engine and reflecting the emotions in the generated suggestions. This enables more personalized style suggestions based on the user's features, emotions, and past feedback.

[0284] "Characteristics" refers to individual attribute information such as the user's hair type, face shape, skin color, and desired style.

[0285] "Server" refers to a computer system for receiving, storing, and processing data from users.

[0286] "Generative AI model" refers to an artificial intelligence model designed to generate optimal suggestions based on user characteristics.

[0287] "Suggestion" refers to the recommendation of hairstyle or fashion style that the generative AI model generates based on the user's characteristics.

[0288] "Feedback" refers to reactions such as satisfaction, opinions, and requests provided by users in response to suggestions.

[0289] An "emotion engine" is an engine that recognizes emotions from the user's facial expressions and voice, and reflects that data in a generative AI model.

[0290] A "terminal" is a device that a user uses to input information or check suggestions, such as a smartphone or computer.

[0291] "Database" refers to the data storage system used by the Server to store and manage user characteristics and feedback.

[0292] "Brand" refers to the manufacturer or retailer that the user frequently uses.

[0293] A "stylist" is a professional who suggests hairstyles and fashion styles.

[0294] MODE FOR CARRYING OUT THE INVENTION

[0295] The present invention is a system that suggests optimal hairstyles and fashions based on the individual characteristics of a user, and detailed embodiments thereof are described below. This system operates in cooperation with a server, terminal, and user, and by combining it with an emotion engine that recognizes the user's emotions, it achieves more accurate style suggestions and feedback collection.

[0296] Overall system configuration

[0297] The system is implemented by the following components:

[0298] 1. A terminal for inputting user information

[0299] 2. Server that receives, processes, and stores information

[0300] 3. Generative AI model that generates suggestions

[0301] 4. Emotion engine that recognizes user emotions

[0302] Details of each component

[0303] Entering user information

[0304] Users access the Style Core application using a device such as a smartphone or PC. They enter information such as their hair type (e.g., straight hair), face shape (e.g., oval), skin color (e.g., olive skin), and desired style (e.g., casual) into the application's form screen. This information is entered through the application's user interface, and the user proceeds to the next step by pressing the submit button.

[0305] Sending and storing information

[0306] When the user presses the "Send" button, the terminal sends the entered information to the server. The server receives the sent information and checks (validates) the validity of the data format. Information that passes this check is saved in the database.

[0307] Leveraging generative AI models

[0308] The server launches a generative AI model based on the saved user information. The generative AI model learns the latest trends and fashion designs to generate optimal suggestions based on the conditions obtained from the user. For example, the server passes the following prompt text to the generative AI model: "The user's hair type is straight, their face shape is oval, their skin color is olive, and their desired style is casual. Please suggest the best hairstyle and fashion for this user."

[0309] Submitting and Viewing Proposals

[0310] The generated suggestions are sent from the server to the user's device, which receives them and displays them on the application screen, where the user can check in detail the hairstyles and fashions suggested by the generative AI model.

[0311] Gathering feedback

[0312] Users can provide feedback on the suggested styles, for example by rating "how satisfied I am with the suggested styles" on a scale of 1 to 5, or by entering specific requests in text, such as "I would like a more casual style." The device then sends this feedback data to the server, which stores the received feedback in a database. This feedback is then used as training data for the generative AI model.

[0313] Collaboration with brands and stylists

[0314] The server analyzes the user's past usage history and feedback information, and incorporates the user's preferred brands and the styles of affiliated stylists into the generative AI model as learning data, so that the next recommendation will include items recommended by brands and stylists familiar to the user.

[0315] Utilizing the Emotion Engine

[0316] The user's device is equipped with an emotion engine that analyzes the user's facial expressions and voice in real time via the built-in camera and microphone. For example, the emotion engine recognizes and analyzes changes in facial expression (e.g., smile or frown) and tone of voice (e.g., joy or dissatisfaction) when the user sees a proposed style. This emotion data is sent to the server in real time, and the server uses this data to adjust the generative AI model. For example, data is fed back so that information that indicates the user's satisfaction is reflected in the next proposal generation.

[0317] Specific examples

[0318] As a concrete example, suppose a user inputs the following information: hair type "straight hair," face shape "oval," skin color "olive skin," and desired style "casual." The information is sent from the device to the server, where it is saved, and then the generative AI model is launched. The server passes a prompt to the generative AI model, which displays the results on the user's device. The suggestions are "short haircut with bangs" and "casual striped shirt," which the user confirms on the device.

[0319] The user enters feedback on the suggestion, such as "I want a more casual style," and the device sends this feedback to the server. The server also collects the user's facial expression data from the emotion engine and reflects it in the generative AI model. The next suggestion will be further adjusted to better suit the user's preferences.

[0320] Example of a text prompt:

[0321] "This user has straight hair, an oval face, olive skin, and a casual style. What hairstyle and outfit would be best for this user?"

[0322] In this way, users can receive more personalized hairstyle and fashion style suggestions based on their emotions, and the accuracy of the suggestions can be improved based on feedback and emotional data.

[0323] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0324] Step 1:

[0325] Users access the Style Core application through a device such as a smartphone or PC. They enter information into a form screen, such as hair type (e.g., straight hair), face shape (e.g., oval), skin color (e.g., olive skin), and desired style (e.g., casual). This input data is collected using text boxes and drop-down menus in the application.

[0326] Input: Your individual characteristics (hair type, face shape, skin color, desired style)

[0327] Output: A dataset of the input features

[0328] Step 2:

[0329] When the user presses the "Submit" button, the terminal sends the entered information to the server. The server receives the sent information and checks the validity of the data format (validation). Information that passes validation is saved in the database.

[0330] Input: A dataset of input features

[0331] Output: Validated feature dataset (stored in a database)

[0332] Step 3:

[0333] The server launches a generative AI model based on the validated user information. The server passes the following prompt text to the generative AI model: "The user's hair type is straight, their face shape is oval, their skin color is olive, and their desired style is casual. Please suggest the best hairstyle and fashion for this user." The generative AI model processes and analyzes the data based on this prompt text, and generates optimal hairstyle and fashion suggestions.

[0334] Input: Validated feature dataset, prompt statement

[0335] Output: Data proposed by the generative AI model

[0336] Step 4:

[0337] The generated suggestion data is sent from the server to the user's device. The device receives the suggestion data and displays it on the application screen. Here, the user can check in detail the hairstyle and fashion suggested by the generative AI model.

[0338] Input: Data proposed by the generative AI model

[0339] Output: Proposal displayed on the device

[0340] Step 5:

[0341] The user provides feedback on the proposed style. For example, they input a specific request such as "I want a more casual style" and their satisfaction rating. The device sends this feedback data to the server, which then stores it in a database.

[0342] Input: User feedback on the proposal

[0343] Output: Saved feedback data

[0344] Step 6:

[0345] The server analyzes past usage history and feedback data and reflects it in the generative AI model. It processes and aggregates the data as necessary. This allows the generative AI model to learn the user's preferences and habits and reflect them in future suggestions.

[0346] Input: usage history data, feedback data

[0347] Output: A tuned and updated generative AI model

[0348] Step 7:

[0349] The user's device is equipped with an emotion engine that analyzes the user's facial expressions and voice in real time through the built-in camera and microphone. The emotion engine recognizes the user's emotions (e.g., joy, surprise, sadness) and sends the data to a server. The server then applies the emotion data to a generative AI model to provide more personalized suggestions.

[0350] Input: User's facial expression data, voice data

[0351] Output: Adjusting suggestions based on sentiment data

[0352] These are the specific program processing steps of this system. At each step, the user, device, and server play their respective roles, resulting in highly accurate style suggestions as a whole.

[0353] (Application example 2)

[0354] 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."

[0355] Conventional fashion suggestion systems make suggestions based on the user's individual characteristics, but they are unable to consider the user's emotions or real-time reactions, making it difficult to generate suggestions that truly satisfy the user. In particular, in the shopping experience at a physical store, it is necessary to reflect the user's emotions and feedback immediately. Our goal is to solve this problem and provide a system that allows users to receive more personalized, emotion-based suggestions.

[0356] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for a user to input individual characteristics, means for transmitting the input characteristics to the server, means for storing the characteristics in the server, means for generating proposals using a generative AI model based on the characteristics, means for providing the generated proposals to the user, means for collecting user feedback on the proposals, means for reflecting the collected feedback in the generative AI model, and means for analyzing the user's emotions using an emotion recognition engine and reflecting the emotions in the generative AI model. This makes it possible to realize more appropriate and personalized fashion proposals based on the user's individual characteristics and real-time emotional reactions.

[0357] "User individual characteristics" are individual identifying information input by the user or obtained by the system, such as hair type, face shape, skin color, desired style, etc.

[0358] A "server" is a computer system that transmits, receives, stores, and processes data.

[0359] A "generative AI model" is an artificial intelligence algorithm that uses machine learning to generate suggestions based on user information.

[0360] "Suggestions" are hairstyle and fashion style recommendations generated by the generative AI model and provided to the user.

[0361] "Feedback" is information indicating opinions and reactions provided by users to suggestions.

[0362] An "emotion recognition engine" is software or hardware that analyzes a user's facial expressions and voice to recognize their emotions.

[0363] "User emotion data" is data that indicates the user's emotional state and is output as a result of analysis by the emotion recognition engine.

[0364] A "terminal" is an electronic device that a user operates, such as a smartphone, smart glasses, a personal computer, or a head-mounted display.

[0365] A "database" is a system that allows a server to systematically store and manage data.

[0366] The present invention provides a system that proposes optimal fashion styles based on the user's individual characteristics and emotions. This system is configured to realize a series of steps: inputting user characteristics, recognizing emotions, generating suggestions, and collecting feedback.

[0367] Overall system configuration

[0368] The system is implemented by the following components:

[0369] 1. Enter your user information

[0370] Using a device such as a smartphone or smart glasses, users input their individual characteristics into the application, such as hair type, face shape, skin color, and desired style, which is then sent to a server and stored in a database.

[0371] 2. Emotion recognition

[0372] While a user is trying on fashion items, the smart glasses' camera and voice recognition function are used to analyze their emotions in real time. The emotion recognition engine uses Azure Face API to capture facial expression data such as smiles and surprise.

[0373] 3. Proposal generation

[0374] The server uses a generative AI model (e.g., OpenAI's GPT-4) to generate optimal fashion style suggestions based on the stored user feature information and real-time emotion data, and the generated suggestions are sent to the smart glasses or other devices and displayed to the user.

[0375] 4. Gathering Feedback

[0376] Users provide feedback on their impressions and requests regarding the proposed style, which is then sent to the server and stored as training data for the generative AI model.

[0377] 5. Collaboration between brands and stylists

[0378] The suggestions will reflect the styles recommended by the user's favorite brands and affiliated stylists, allowing for more personalized suggestions.

[0379] Processing Details

[0380] Hardware and Software Configuration

[0381] Smart glasses: Smart glasses such as HoloLens 2 are used and are equipped with a camera and voice input device.

[0382] Emotion recognition engine: Emotion analysis is performed using Azure Face API.

[0383] Generative AI model: We use OpenAI's GPT-4 to generate proposals.

[0384] Database: We use Microsoft Azure SQL Database to manage user information and feedback.

[0385] Data processing and calculation

[0386] 1. Enter and submit user information

[0387] The characteristic information entered by the user is sent from the device to the server and stored in Azure SQL Database.

[0388] 2. Emotion recognition

[0389] Facial images and voice data of the user trying on the items are captured by the camera and microphone of the smart glasses, and emotion analysis is performed using the Azure Face API.

[0390] 3. Proposal generation

[0391] The server accesses Azure SQL Database to retrieve stored user information and real-time emotion data.

[0392] This data is then input into the generative AI model GPT-4 to suggest the optimal fashion style.

[0393] 4. Submitting and Viewing Proposals

[0394] The generated suggestions are sent from the server to smart glasses or other devices and displayed to the user.

[0395] 5. Gathering Feedback

[0396] User feedback is sent from the device to the server, stored in Azure SQL Database, and used to improve the accuracy of the next suggestion.

[0397] Specific examples

[0398] Consider the "Style Guide Glasses" application in action. When a user tries on a dress in a store, the smart glasses capture the user's face and recognize their smile using the Azure Face API. This information is sent to a server, where, combined with stored profile information such as hair type and face shape, GPT-4 generates suggestions such as "What shoes would go well with this dress?" and displays them on the smart glasses' display.

[0399] Prompt Sentence Examples

[0400] Send a prompt like this to your generative AI model:

[0401] User profile information:

[0402] Hair type: Straight, Face shape: Oval, Skin tone: Olive, Desired style: Casual

[0403] Emotion data: Smile (positive)

[0404] Previous suggestion feedback: I liked it

[0405] Generate a proposal.

[0406] This concludes the detailed description of the invention, which allows users to receive more personalized, emotion-based fashion suggestions.

[0407] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0408] Step 1:

[0409] Users input their individual characteristics, such as hair type, face shape, skin color, and desired style, through a smartphone or smart glasses device, which then collects this information and sends it to a server.

[0410] Step 2:

[0411] The server receives the user characteristic information sent from the device, validates the received information (checks the format and range), and stores it in Azure SQL Database if there are no problems.

[0412] Step 3:

[0413] A user tries on fashion items in a physical store. The camera in the smart glasses captures the user's facial image and the microphone records the user's voice. This data is sent in real time to an emotion recognition engine (Azure Face API).

[0414] Step 4:

[0415] Using Azure Face API, the user's facial image and voice data are analyzed to obtain emotional data (e.g., smile, surprise, sadness), which is then transmitted from the smart glasses to the server.

[0416] Step 5:

[0417] The server combines the received emotion data with pre-stored user feature information. Based on this data, it creates a prompt for the generative AI model (GPT-4) and sends it as input data. An example of a specific prompt is as follows:

[0418] User profile information:

[0419] Hair type: Straight, Face shape: Oval, Skin tone: Olive, Desired style: Casual

[0420] Emotion data: Smile (positive)

[0421] Previous suggestion feedback: I liked it

[0422] Generate a proposal.

[0423] Step 6:

[0424] The generative AI model generates optimal fashion style suggestions based on the received prompt. These suggestions are returned to the server as text data. For example, a suggestion like, "How about some shoes that match this dress?"

[0425] Step 7:

[0426] The server receives the suggestions from the generative AI model and sends them to a device such as smart glasses or a smartphone, which then visually displays the received suggestions to the user.

[0427] Step 8:

[0428] The user can input feedback about the proposed fashion style, such as "I like it" or "I'd like you to suggest a more casual style" using the terminal.

[0429] Step 9:

[0430] The device sends user feedback to the server, which stores it in Azure SQL Database and uses it as training data for the generative AI model when generating the next recommendation.

[0431] This concludes the processing flow of the system program for implementing this application example, which allows users to receive personalized fashion suggestions in real time and collects feedback to improve the accuracy of the suggestions.

[0432] 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.

[0433] 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.

[0434] 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.

[0435] [Second embodiment]

[0436] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0437] 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.

[0438] 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).

[0439] 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.

[0440] 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.

[0441] 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).

[0442] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0443] 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.

[0444] 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.

[0445] 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.

[0446] 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.

[0447] 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."

[0448] ---

[0449] The present invention includes a hairstyle and fashion suggestion system called Style Core. This system is designed to provide users with hairstyles and fashion styles that are optimal for them, with the server, terminals, and users working together.

[0450] Overall system configuration

[0451] The system is implemented primarily by the following components:

[0452] 1. Entering user information: The user enters their individual characteristics (hair type, face shape, skin color, desired style, etc.) into the terminal.

[0453] 2. Transmission and storage of information: The information entered by the user is transmitted from the terminal to the server and stored in the server's database.

[0454] 3. Utilizing generative AI models: The server uses generative AI models based on stored user information to suggest optimal hairstyles and fashions.

[0455] 4. Sending and displaying proposals: The generated proposals are sent from the server to the terminal and displayed on the terminal.

[0456] 5. Feedback collection: Users provide feedback on the proposals, which is sent to the server, stored in a database, and used as training data for the generative AI model.

[0457] 6. Brand and stylist collaboration: Suggestions include ways to reflect the styles of brands and affiliated stylists that users frequent.

[0458] Program processing and specific examples

[0459] Below, the program processing in each component will be explained in natural language with specific examples.

[0460] Entering user information

[0461] Users access the Style Core application using a device such as a smartphone or PC, and enter information such as their hair type (e.g., straight hair), face shape (e.g., oval), skin color (e.g., olive skin), and desired style (e.g., casual) into a form displayed on the application screen.

[0462] Sending and storing information

[0463] When the user presses the "Submit" button, the terminal sends the entered information to the server, which receives it, validates it, and stores it in the database.

[0464] Leveraging generative AI models

[0465] The server launches a generative AI model based on the saved user information. The generative AI model learns the latest trends and design knowledge, and uses that information to generate optimal hairstyle and fashion suggestions for the user. For example, for a user with straight hair and an oval face, it might suggest a "short haircut with bangs" and a "casual striped shirt."

[0466] Submitting and Viewing Proposals

[0467] The server sends the generated suggestions to the user's device, which receives and analyzes them and then displays them on the application screen, where the user can check the suggested hairstyles and fashions.

[0468] Gathering feedback

[0469] Users can provide feedback on the proposed styles within the application, such as "I like it" or "I'd like a more casual style." The device sends this feedback to the server, which receives it and stores it in a database. The stored feedback is used as training data for the generative AI model.

[0470] Collaboration with brands and stylists

[0471] The server integrates information about the user's favorite brands and affiliated stylists as training data into the generative AI model, allowing suggestions to reflect items recommended by brands and stylists familiar to the user.

[0472] ---

[0473] The above is an embodiment of the present invention. This allows users to easily find hairstyles and fashion styles that suit them best, and it is expected that the accuracy of personalized suggestions will be further improved based on feedback.

[0474] The processing flow will be explained below.

[0475] Okay, so let's break down the program's processing into specific steps.

[0476] Step 1: User accesses the system

[0477] Users launch the StyleCore application from a device such as a smartphone or PC.

[0478] Step 2: User Enters Information

[0479] The user enters individual characteristics such as their hair type (e.g., straight hair), face shape (e.g., oval), skin color (e.g., olive skin), and desired style (e.g., casual) into a form on the application screen.

[0480] Step 3: The device sends the information

[0481] When the user enters information and presses the "send" button, the terminal sends the information to the server.

[0482] Step 4: The server receives and stores the information

[0483] The server receives the user information, checks the integrity of the data, and then stores it in the database. A validation process is performed to check for inappropriate data.

[0484] Step 5: The server launches the generative AI model

[0485] The server then launches a generative AI model based on the stored user information, which is trained on the latest trends and design knowledge.

[0486] Step 6: The server inputs the data into the generative AI model

[0487] The server inputs user information into a generative AI model, which then generates optimal hairstyle and fashion suggestions based on the user's characteristics.

[0488] Step 7: The server retrieves the generated proposal

[0489] The server receives the recommendations output by the generative AI model, such as a "short haircut with bangs" and a "casual striped shirt."

[0490] Step 8: Server sends proposal

[0491] The server then sends the generated suggestions to the user's device, often in a format such as JSON.

[0492] Step 9: Your device receives and displays the proposal

[0493] The device receives the suggestions sent from the server, analyzes them, and displays them on the application screen, where the user can check the suggested hairstyles and fashions.

[0494] Step 10: User Enters Feedback

[0495] Users can input their evaluations and opinions on the suggestions, such as "I like it" or "I'd like a more casual style."

[0496] Step 11: Device sends feedback

[0497] When the user inputs feedback and presses the "send" button, the terminal sends the feedback to the server.

[0498] Step 12: Server receives and stores feedback

[0499] The server receives the feedback and stores it in a database, which is later used as training data for the generative AI model.

[0500] Step 13: The server learns the brand and stylist information

[0501] The server collects information about the user's favorite brands and affiliated stylists and integrates it into a generative AI model.

[0502] Step 14: Your server will then reflect on your recommendations with compatible brands and stylists.

[0503] The server uses the generative AI model to generate recommendations based on the styles of brands and stylists familiar to the user, resulting in more accurate recommendations for the user.

[0504] The above is a description of the specific operation of each processing step in the Style Core system.

[0505] Example 1

[0506] 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."

[0507] The present invention relates to a system that proposes optimal hairstyles and fashions based on the individual characteristics of each user. Conventional proposal systems have difficulty responding to individual user characteristics in detail, and have faced challenges in improving the accuracy of proposals that appropriately reflect user feedback. In addition, it has been difficult to reflect the proposals of brands and stylists that users are familiar with, which has prevented users from achieving sufficient satisfaction. The present invention aims to solve these problems.

[0508] 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.

[0509] In this invention, the server includes means for a user to input individual characteristics, means for transmitting the input characteristics to a processing device, means for storing the characteristics in the processing device, means for generating proposals using a generative AI model based on the characteristics, means for providing the generated proposals to a user, means for collecting user feedback on the proposals, means for reflecting the collected feedback in the generative AI model, means for analyzing and displaying the proposal content, and means for validating the user's personal information in a database of the processing device. This enables highly accurate proposals based on the user's individual characteristics, improves the accuracy of proposals based on feedback, and further enables proposals that reflect styles recommended by brands and stylists familiar to the user.

[0510] "User" refers to an individual who utilizes the system to input their characteristics and receive suggestions.

[0511] "Characteristics" refers to personal information about a user, including hair type, face shape, skin color, desired style, and the like.

[0512] "Processing device" refers to hardware or software that receives, stores, and processes data sent by a user.

[0513] A "generative AI model" refers to an artificial intelligence model that generates optimal hairstyle and fashion suggestions based on a user's characteristics.

[0514] "Suggestions" refers to recommendations about hairstyles and fashion that are generated based on the user's characteristics using a generative AI model.

[0515] "Feedback" refers to the opinions and thoughts that users provide regarding suggestions.

[0516] "Validation" refers to the process of verifying that received data has the correct format and content.

[0517] "Database" refers to an information storage system for storing user characteristics and feedback.

[0518] A "brand" refers to a sign or name that identifies the products or services offered by a particular company or organization.

[0519] A "stylist" is a professional who gives advice and suggestions regarding fashion and hairstyles.

[0520] "Terminal" refers to a device, such as a computer or smartphone, that a user uses to access the system.

[0521] "User interface" refers to the screens and operating means that users use to operate a system.

[0522] "Communication protocol" refers to the rules and procedures used between a terminal and a server to send and receive information.

[0523] An "HTTP request" refers to the communication format used by a web browser or application to request data from a server or server.

[0524] "JSON format" is a lightweight data exchange format that is easy for humans to read and machines to parse.

[0525] A "trained neural network" refers to an artificial intelligence model that has been trained using a specific dataset.

[0526] This invention is a system that suggests optimal hairstyles and fashion styles to users, and this system makes suggestions using a generative AI model based on the user's characteristics. Users can access the system using a device such as a smartphone or PC and receive suggestions by inputting their own characteristics.

[0527] Overall system configuration

[0528] The system consists of the following main components:

[0529] 1. Enter your user information

[0530] 2. Transmission and storage of information

[0531] 3. Utilizing generative AI models

[0532] 4. Submitting and Displaying Proposals

[0533] 5. Gathering Feedback

[0534] 6. Collaboration with brands and stylists

[0535] Specific actions

[0536] The specific operation of each element will be described below.

[0537] Entering user information

[0538] Users input their own characteristic information (hair type, face shape, skin color, desired style, etc.) via a device such as a smartphone or PC. This information is then input and used by the user through an application on the device.

[0539] Sending and storing information

[0540] The characteristic information entered by the user is sent from the terminal to the server. The server validates the received data, confirming that it is in the correct format and content, and then stores it in a database. The database used here is a commonly used relational database (e.g., MySQL, PostgreSQL).

[0541] Leveraging generative AI models

[0542] The server then launches a generative AI model based on the stored user information. This model is built using machine learning frameworks such as TensorFlow and PyTorch, and makes suggestions for optimal hairstyles and fashion based on the user's characteristics. For example, suggestions are generated for information such as "straight hair," "oval face," "olive skin," and "casual style."

[0543] As a concrete example, the following prompt sentence is input to the generative AI model:

[0544] "Please suggest the best casual hairstyle and fashion for a user with straight hair, an oval face, and olive skin."

[0545] Submitting and Viewing Proposals

[0546] The server sends the generated suggestions to the user's device, which receives them, analyzes them, and displays them on the application screen. The user can then check the suggested hairstyles and fashions, and save or share them as needed.

[0547] Gathering feedback

[0548] Users can input feedback on the suggestions and send it to the server via their devices. The server stores the received feedback in a database, and this feedback is used as training data for the generative AI model, thereby improving the accuracy of the suggestions made by the AI ​​model.

[0549] Collaboration with brands and stylists

[0550] The server can reflect the recommended styles of brands and affiliated stylists frequently used by the user in its suggestions. Specifically, by storing information on brand items and stylist suggestion history in a database and adding this information to the training data of the AI ​​model, the server can make suggestions that are familiar to the user.

[0551] In this way, users can use a system that suggests optimal hairstyles and fashion styles based on their individual characteristics, thereby increasing user satisfaction and improving the accuracy of suggestions.

[0552] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0553] Step 1: Enter your user information

[0554] The user launches the Style Core application using a device such as a smartphone or PC. The user enters their characteristic information (hair type, face shape, skin color, desired style, etc.) into a form displayed on the application screen. For example, the user enters specific information such as "straight hair," "oval face," "olive skin," and "casual style." This input information becomes the data sent to the server in the next step.

[0555] Step 2: Send and save information

[0556] Data entered by the user, including characteristic information, is sent from the terminal to the server. The data input is sent using an HTTP request. The server validates the received data to ensure that it is in the correct format and content. Data that passes validation is stored in the server's database. The database used here is a relational database such as MySQL or PostgreSQL.

[0557] Step 3: Leveraging generative AI models

[0558] The server launches a generative AI model based on the stored user feature information. The user's feature information (e.g., "straight hair," "oval face," "olive skin," and "casual style") is used as input. The generative AI model is built using frameworks such as TensorFlow and PyTorch. This AI model analyzes the input user feature information and generates optimal hairstyle and fashion suggestions. For example, it might generate suggestions such as "short haircut with bangs" and "casual striped shirt." As a concrete example, the following prompt sentence is input to the generative AI model:

[0559] "Please suggest the best casual hairstyle and fashion for a user with straight hair, an oval face, and olive skin."

[0560] Step 4: Submit and view your proposal

[0561] The suggestions created by the generative AI model are sent from the server to the device in data format such as JSON. The device analyzes the data received from the server and displays it on the user interface. On the display screen, the user can check the suggested hairstyle, fashion, and specific item information (e.g., a short haircut with bangs, a casual striped shirt). This allows the user to confirm the suggestions and proceed to the next step.

[0562] Step 5: Gather feedback

[0563] The user inputs their thoughts and opinions about the suggestions (e.g., "I like it," "I'd like a more casual style," etc.). The input feedback is sent from the device to the server. The server stores the received feedback data in a database. The feedback data is used as training data for the generative AI model. This improves the accuracy of the next suggestion.

[0564] Step 6: Collaborate with brands and stylists

[0565] The server integrates information about the user's favorite brands and affiliated stylists into the generative AI model. Specifically, it imports information about brand items and stylist recommendation history as learning data and stores it in a database. For example, it reflects the latest collections of brands frequently purchased by the user and recommended items from affiliated stylists in the database. This ensures that suggestions include items from brands and stylists familiar to the user.

[0566] The above are the processing steps of the system and their specific operations. Data processing and calculations are carried out at each step, resulting in a system that provides optimal suggestions to users.

[0567] (Application example 1)

[0568] 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."

[0569] Today, there are many systems that suggest the best hairstyles and fashions for individual users, but these systems require users to manually input their own characteristics. In addition, they cannot confirm the suggestions in real time, and the feedback loop to reflect the suggestions in reality is incomplete. This limits the user experience and reduces satisfaction.

[0570] 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.

[0571] In this invention, the server includes: means for a user to input individual features; means for transmitting the input features to the server; means for storing the features in the server; means for generating suggestions using a generative AI model based on the features; means for providing the generated suggestions to the user; means for collecting user feedback on the suggestions; means for reflecting the collected feedback in the generative AI model; a camera for recognizing the user's features; means for transmitting data collected by the camera to a cloud server; means for the cloud server to analyze the data using the generative AI model and generate suggestions; and means for displaying the suggestions on the user's visual device in real time. This allows the user to see optimal hairstyle and fashion suggestions in real time without having to manually input their own features, and further allows feedback based on the suggestions to be reflected in the generative AI model.

[0572] "User" refers to a person who uses the system to receive hairstyle and fashion suggestions.

[0573] "Characteristics" refers to individual information such as the user's hair type, face shape, skin color, and desired style.

[0574] "Means" refers to a method or apparatus for achieving a specific function or operation.

[0575] "Server" refers to a device or system that receives and stores information sent by users and generates and provides suggestions using generative AI models.

[0576] A "generative AI model" refers to an artificial intelligence model that generates optimal hairstyle and fashion suggestions based on training data.

[0577] "Camera" refers to a photographic device for collecting data on a user's face and body.

[0578] "Cloud Server" refers to the remote server that analyzes the collected data and generates and sends recommendations to users.

[0579] A "visual device" is a device for displaying suggestions to a user, such as smart glasses.

[0580] System Overview

[0581] The present invention relates to a style suggestion system, specifically a system that recognizes a user's individual characteristics and uses a generative AI model to suggest optimal hairstyles and fashions. The system operates by including a user terminal, a server, and a visual device (e.g., smart glasses).

[0582] Program processing and natural language explanation

[0583] User information entry and automatic collection

[0584] The user wears the vision device and activates the system. The camera on the vision device captures the user's facial and body features in real time, and the data is sent from the user's device to a cloud server. This process uses facial recognition software (e.g., OpenCV).

[0585] Analyzing information and generating recommendations

[0586] The cloud server stores the received feature data and inputs it into a generative AI model (e.g., TensorFlow). The generative AI model generates optimal hairstyle and fashion suggestions based on the stored user feature data. For example, for a user with straight hair and an oval face, it might suggest a "short haircut with bangs" and a "casual striped shirt."

[0587] Submitting and Viewing Proposals

[0588] The cloud server sends the generated suggestions to the user's visual device in real time, where the visual device analyzes the received suggestions and displays them to the user. The user can then check the suggested hairstyles and fashions as if looking in a mirror through the visual device.

[0589] Gathering and implementing feedback

[0590] When the user provides feedback on the suggestions via the visual device, the feedback is again sent to the cloud server and stored, where it is used as training data for the generative AI model to improve the accuracy of subsequent suggestions.

[0591] Specific hardware and software names used

[0592] Hardware:

[0593] Smart glasses (e.g., general-purpose smart glasses devices)

[0594] camera

[0595] Cloud Server

[0596] software:

[0597] Facial recognition software (e.g. OpenCV)

[0598] AI models (e.g. TensorFlow)

[0599] Cloud services (e.g. AWS, GCP)

[0600] Front-end applications (e.g. HTML5, JavaScript)

[0601] Examples and prompts

[0602] For example, smart glasses automatically activate when a user enters a store and perform facial recognition. At this time, the following prompt sentence is input to the generative AI model:

[0603] "Based on the client's characteristics, suggest hairstyles and casual styles that would suit someone with straight hair and an oval face."

[0604] The generative AI model generates suggestions based on this prompt and displays them on a visual device, allowing users to see the best hairstyles and fashions in real time.

[0605] summary

[0606] The system automatically collects users' personal characteristics and allows them to receive personalized style suggestions in real time, while incorporating user feedback into the generative AI model to continuously improve the accuracy of the suggestions.

[0607] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0608] Step 1:

[0609] The user puts on the smart glasses and activates the system. The camera in the smart glasses captures the user's facial and body features and sends this data to the user's device. The input data is facial images and body proportion information, which are then analyzed in subsequent processing steps.

[0610] Step 2:

[0611] The user device transmits the captured feature data to the cloud server. This transmission process involves data conversion and compression. Specifically, the image data is converted to JPEG format and compressed for efficient transmission over the network. The input data is the captured image data, and the output is compressed image data.

[0612] Step 3:

[0613] The cloud server stores the received feature data in a database. At the same time, it analyzes the image data using facial recognition software (e.g., OpenCV). This analysis process extracts characteristics such as facial shape, hair type, and skin color. The input data is compressed image data, and the output data is analyzed feature data.

[0614] Step 4:

[0615] The cloud server inputs the analyzed feature data into the generative AI model. To create this prompt, text data is generated, such as "Please suggest a hairstyle and fashion that would suit a user with straight hair and an oval face." The generative AI model then generates optimal hairstyle and fashion suggestions based on this prompt. The input data is the analyzed feature data, and the output is optimal suggestion data.

[0616] Step 5:

[0617] The cloud server transmits the generated proposal data to the user's visual device in real time. Specifically, the proposal data is encoded using a dedicated protocol and transmitted to the visual device. The input data is the proposal data, and the output is the encoded data.

[0618] Step 6:

[0619] The visual device decodes the received suggestion data and displays it to the user. The user can check the suggested hairstyle and fashion on their own image. The input data is the encoded suggestion data, and the output is a display for the user's vision.

[0620] Step 7:

[0621] The user inputs feedback on the suggestions through a visual device. For example, they input opinions such as "cut your bangs a little shorter" or "dress more casually." The input data is the user's feedback, and the output is feedback data.

[0622] Step 8:

[0623] The vision device sends feedback data to a cloud server, which stores the received feedback in a database and uses it as training data for the generative AI model. This process improves the accuracy of subsequent suggestions. The input data is the feedback data, and the output is the stored data.

[0624] 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.

[0625] ---

[0626] This invention shows an embodiment for implementing "Style Core," a system that suggests optimal hairstyles and fashions based on the individual characteristics of a user. This system operates in cooperation with a server, terminals, and users, and by combining it with an emotion engine that recognizes the user's emotions, it achieves more accurate style suggestions and feedback collection.

[0627] Overall system configuration

[0628] The system is implemented by the following components:

[0629] 1. Input of user information: The user inputs his / her individual characteristics from the terminal.

[0630] 2. Sending and saving information: The device sends the entered information to the server, which saves it in a database.

[0631] 3. Utilizing generative AI models: The server generates suggestions using generative AI models based on the stored user information.

[0632] 4. Sending and displaying the proposal: The server sends the generated proposal to the terminal and it is displayed on the user's terminal.

[0633] 5. Feedback collection: The user provides feedback on the proposal, which is sent to the server and stored in a database.

[0634] 6. Collaboration with brands and stylists: Suggestions will reflect the recommended styles of brands and affiliated stylists that users frequently use.

[0635] 7. Utilizing an emotion engine: An emotion engine is used to recognize the user's emotions and reflect the results in the suggestions.

[0636] Program processing and specific examples

[0637] Below, the program processing in each component will be explained in natural language with specific examples.

[0638] Entering user information

[0639] Users access the Style Core application using a device such as a smartphone or PC, and enter information such as their hair type (e.g., straight hair), face shape (e.g., oval), skin color (e.g., olive skin), and desired style (e.g., casual) into the application form screen.

[0640] Sending and storing information

[0641] When the user presses the "Submit" button, the terminal sends the entered information to the server, which receives the information, validates it, and stores it in the database.

[0642] Leveraging generative AI models

[0643] The server launches a generative AI model based on the saved user information. The generative AI model learns the latest trends and design knowledge and generates optimal hairstyle and fashion suggestions based on the user information. For example, for a user with straight hair and an oval face, it would suggest a "short haircut with bangs" and a "casual striped shirt."

[0644] Submitting and Viewing Proposals

[0645] The server sends the generated suggestions to the user's device, which receives them and displays them on the application screen, where the user can check the suggested hairstyles and fashions.

[0646] Gathering feedback

[0647] Users can provide feedback on the suggested styles, such as "I like it" or "I'd like a more casual style." The device then sends this feedback to the server, which receives it and stores it in a database. The feedback is then used as training data for the generative AI model.

[0648] Collaboration with brands and stylists

[0649] The server integrates information about the user's favorite brands and affiliated stylists as training data into the generative AI model, allowing suggestions to reflect items recommended by brands and stylists familiar to the user.

[0650] Utilizing the Emotion Engine

[0651] The device is equipped with an emotion engine that recognizes emotions through the user's facial expressions and voice. The recognized emotion data is sent to a server, which then uses the data to adjust the generative AI model. For example, if the user smiles when viewing a suggestion, the emotion data is added to the feedback as a signal that the suggestion has been accepted. In this way, the suggestions are further personalized.

[0652] ---

[0653] The above is an embodiment of the present invention. This allows users to receive personalized suggestions for hairstyles and fashion styles based on their emotions. Furthermore, it is expected that the accuracy of suggestions will be further improved based on feedback.

[0654] The processing flow will be explained below.

[0655] Step 1: User accesses the system

[0656] Users launch StyleCore applications using devices such as smartphones and PCs.

[0657] Step 2: User Enters Information

[0658] The user enters their individual characteristics, such as their hair type (e.g., straight hair), face shape (e.g., oval), skin color (e.g., olive skin), and desired style (e.g., casual), into the application's form screen.

[0659] Step 3: The device sends the information

[0660] When the user inputs information and presses the "send" button, the terminal sends the input information to the server.

[0661] Step 4: The server receives and stores the information

[0662] The server receives the submitted user information, checks the data for consistency, and stores it in a database, for example by validating that the hair type is specified correctly and that the face shape is within the valid options.

[0663] Step 5: The server launches the generative AI model

[0664] The server then launches a generative AI model based on the stored user information, which uses the trend data and design knowledge it has learned to generate optimal hairstyle and fashion suggestions.

[0665] Step 6: The server inputs the data into the generative AI model

[0666] The server inputs user information into a generative AI model, which takes into account the user's hair type, face shape, skin color, etc. to calculate and generate optimal style suggestions.

[0667] Step 7: The server retrieves the generated proposal

[0668] The server receives the output of the generative AI model, generating specific style suggestions such as a "short haircut with bangs" and a "casual striped shirt."

[0669] Step 8: Server sends proposal

[0670] The server sends the generated proposal to the user's device, formatted in JSON or similar.

[0671] Step 9: Your device receives and displays the proposal

[0672] The device receives the suggestions sent from the server, analyzes them, and displays them on the application screen, where the user can check the suggested hairstyles and fashions.

[0673] Step 10: User Enters Feedback

[0674] Users can then rate and comment on the suggestions within the application, for example by entering feedback such as "I like it" or "I'd like a more casual style."

[0675] Step 11: Device sends feedback

[0676] When the user inputs feedback and presses the "send" button, the terminal sends the feedback to the server.

[0677] Step 12: Server receives and stores feedback

[0678] The server receives the feedback and stores it in a database, which is later used as training data for the generative AI model.

[0679] Step 13: The server learns the brand and stylist information

[0680] The server collects information about the user's favorite brands and affiliated stylists, stores it in a database, and then integrates this information into a generative AI model for training.

[0681] Step 14: Your server will then reflect on your recommendations with compatible brands and stylists.

[0682] The server uses a generative AI model to generate suggestions that reflect the brands and stylists familiar to the user, for example, by providing suggestions that include the latest collections from brands the user frequently purchases.

[0683] Step 15: Device captures real-time emotions

[0684] The device is equipped with an emotion engine that recognizes emotions through the user's real-time facial expressions and voice, for example, by using a camera and microphone to detect the user's smile and tone of voice.

[0685] Step 16: The device sends emotion data

[0686] The device sends the recognized emotion data to the server. For example, if the device recognizes a smile or a voice of joy from the user, the data is sent to the server.

[0687] Step 17: The server reflects the emotion data in the generative AI model

[0688] The server then feeds the received emotion data into the generative AI model, which then further adjusts the suggestions based on the user's emotion. If the emotion data is positive, the feedback is considered a positive evaluation.

[0689] The above is a concrete explanation of the operation of each processing step in the style core system including the emotion engine.

[0690] Example 2

[0691] 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."

[0692] Conventional style suggestion systems have difficulty providing personalized suggestions based on the individual characteristics of each user, which has led to issues with not being able to sufficiently increase user satisfaction. Furthermore, they lacked the functionality to appropriately reflect user feedback and emotions, making it impossible to improve the accuracy of suggestions for the next time. Furthermore, they were unable to reflect the recommended styles of brands frequently used by users or affiliated stylists in the suggestions, making it impossible to realize suggestions tailored to the user's preferences.

[0693] 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.

[0694] In this invention, the server includes means for a user to input individual features, means for transmitting the input features to the server, means for storing the features in the server, means for generating suggestions using a generative AI model based on the features, means for providing the generated suggestions to the user, means for collecting user feedback on the suggestions, means for reflecting the collected feedback in the generative AI model, and means for recognizing user emotions using an emotion engine and reflecting the emotions in the generated suggestions. This enables more personalized style suggestions based on the user's features, emotions, and past feedback.

[0695] "Characteristics" refers to individual attribute information such as the user's hair type, face shape, skin color, and desired style.

[0696] "Server" refers to a computer system for receiving, storing, and processing data from users.

[0697] "Generative AI model" refers to an artificial intelligence model designed to generate optimal suggestions based on user characteristics.

[0698] "Suggestion" refers to the recommendation of hairstyle or fashion style that the generative AI model generates based on the user's characteristics.

[0699] "Feedback" refers to reactions such as satisfaction, opinions, and requests provided by users in response to suggestions.

[0700] An "emotion engine" is an engine that recognizes emotions from the user's facial expressions and voice, and reflects that data in a generative AI model.

[0701] A "terminal" is a device that a user uses to input information or check suggestions, such as a smartphone or computer.

[0702] "Database" refers to the data storage system used by the Server to store and manage user characteristics and feedback.

[0703] "Brand" refers to the manufacturer or retailer that the user frequently uses.

[0704] A "stylist" is a professional who suggests hairstyles and fashion styles.

[0705] MODE FOR CARRYING OUT THE INVENTION

[0706] The present invention is a system that suggests optimal hairstyles and fashions based on the individual characteristics of a user, and detailed embodiments thereof are described below. This system operates in cooperation with a server, terminal, and user, and by combining it with an emotion engine that recognizes the user's emotions, it achieves more accurate style suggestions and feedback collection.

[0707] Overall system configuration

[0708] The system is implemented by the following components:

[0709] 1. A terminal for inputting user information

[0710] 2. Server that receives, processes, and stores information

[0711] 3. Generative AI model that generates suggestions

[0712] 4. Emotion engine that recognizes user emotions

[0713] Details of each component

[0714] Entering user information

[0715] Users access the Style Core application using a device such as a smartphone or PC. They enter information such as their hair type (e.g., straight hair), face shape (e.g., oval), skin color (e.g., olive skin), and desired style (e.g., casual) into the application's form screen. This information is entered through the application's user interface, and the user proceeds to the next step by pressing the submit button.

[0716] Sending and storing information

[0717] When the user presses the "Send" button, the terminal sends the entered information to the server. The server receives the sent information and checks (validates) the validity of the data format. Information that passes this check is saved in the database.

[0718] Leveraging generative AI models

[0719] The server launches a generative AI model based on the saved user information. The generative AI model learns the latest trends and fashion designs to generate optimal suggestions based on the conditions obtained from the user. For example, the server passes the following prompt text to the generative AI model: "The user's hair type is straight, their face shape is oval, their skin color is olive, and their desired style is casual. Please suggest the best hairstyle and fashion for this user."

[0720] Submitting and Viewing Proposals

[0721] The generated suggestions are sent from the server to the user's device, which receives them and displays them on the application screen, where the user can check in detail the hairstyles and fashions suggested by the generative AI model.

[0722] Gathering feedback

[0723] Users can provide feedback on the suggested styles, for example by rating "how satisfied I am with the suggested styles" on a scale of 1 to 5, or by entering specific requests in text, such as "I would like a more casual style." The device then sends this feedback data to the server, which stores the received feedback in a database. This feedback is then used as training data for the generative AI model.

[0724] Collaboration with brands and stylists

[0725] The server analyzes the user's past usage history and feedback information, and incorporates the user's preferred brands and the styles of affiliated stylists into the generative AI model as learning data, so that the next recommendation will include items recommended by brands and stylists familiar to the user.

[0726] Utilizing the Emotion Engine

[0727] The user's device is equipped with an emotion engine that analyzes the user's facial expressions and voice in real time via the built-in camera and microphone. For example, the emotion engine recognizes and analyzes changes in facial expression (e.g., smile or frown) and tone of voice (e.g., joy or dissatisfaction) when the user sees a proposed style. This emotion data is sent to the server in real time, and the server uses this data to adjust the generative AI model. For example, data is fed back so that information that indicates the user's satisfaction is reflected in the next proposal generation.

[0728] Specific examples

[0729] As a concrete example, suppose a user inputs the following information: hair type "straight hair," face shape "oval," skin color "olive skin," and desired style "casual." The information is sent from the device to the server, where it is saved, and then the generative AI model is launched. The server passes a prompt to the generative AI model, which displays the results on the user's device. The suggestions are "short haircut with bangs" and "casual striped shirt," which the user confirms on the device.

[0730] The user enters feedback on the suggestion, such as "I want a more casual style," and the device sends this feedback to the server. The server also collects the user's facial expression data from the emotion engine and reflects it in the generative AI model. The next suggestion will be further adjusted to better suit the user's preferences.

[0731] Example of a text prompt:

[0732] "This user has straight hair, an oval face, olive skin, and a casual style. What hairstyle and outfit would be best for this user?"

[0733] In this way, users can receive more personalized hairstyle and fashion style suggestions based on their emotions, and the accuracy of the suggestions can be improved based on feedback and emotional data.

[0734] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0735] Step 1:

[0736] Users access the Style Core application through a device such as a smartphone or PC. They enter information into a form screen, such as hair type (e.g., straight hair), face shape (e.g., oval), skin color (e.g., olive skin), and desired style (e.g., casual). This input data is collected using text boxes and drop-down menus in the application.

[0737] Input: Your individual characteristics (hair type, face shape, skin color, desired style)

[0738] Output: A dataset of the input features

[0739] Step 2:

[0740] When the user presses the "Submit" button, the terminal sends the entered information to the server. The server receives the sent information and checks the validity of the data format (validation). Information that passes validation is saved in the database.

[0741] Input: A dataset of input features

[0742] Output: Validated feature dataset (stored in a database)

[0743] Step 3:

[0744] The server launches a generative AI model based on the validated user information. The server passes the following prompt text to the generative AI model: "The user's hair type is straight, their face shape is oval, their skin color is olive, and their desired style is casual. Please suggest the best hairstyle and fashion for this user." The generative AI model processes and analyzes the data based on this prompt text, and generates optimal hairstyle and fashion suggestions.

[0745] Input: Validated feature dataset, prompt statement

[0746] Output: Data proposed by the generative AI model

[0747] Step 4:

[0748] The generated suggestion data is sent from the server to the user's device. The device receives the suggestion data and displays it on the application screen. Here, the user can check in detail the hairstyle and fashion suggested by the generative AI model.

[0749] Input: Data proposed by the generative AI model

[0750] Output: Proposal displayed on the device

[0751] Step 5:

[0752] The user provides feedback on the proposed style. For example, they input a specific request such as "I want a more casual style" and their satisfaction rating. The device sends this feedback data to the server, which then stores it in a database.

[0753] Input: User feedback on the proposal

[0754] Output: Saved feedback data

[0755] Step 6:

[0756] The server analyzes past usage history and feedback data and reflects it in the generative AI model. It processes and aggregates the data as necessary. This allows the generative AI model to learn the user's preferences and habits and reflect them in future suggestions.

[0757] Input: usage history data, feedback data

[0758] Output: A tuned and updated generative AI model

[0759] Step 7:

[0760] The user's device is equipped with an emotion engine that analyzes the user's facial expressions and voice in real time through the built-in camera and microphone. The emotion engine recognizes the user's emotions (e.g., joy, surprise, sadness) and sends the data to a server. The server then applies the emotion data to a generative AI model to provide more personalized suggestions.

[0761] Input: User's facial expression data, voice data

[0762] Output: Adjusting suggestions based on sentiment data

[0763] These are the specific program processing steps of this system. At each step, the user, device, and server play their respective roles, resulting in highly accurate style suggestions as a whole.

[0764] (Application example 2)

[0765] 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."

[0766] Conventional fashion suggestion systems make suggestions based on the user's individual characteristics, but they are unable to consider the user's emotions or real-time reactions, making it difficult to generate suggestions that truly satisfy the user. In particular, in the shopping experience at a physical store, it is necessary to reflect the user's emotions and feedback immediately. Our goal is to solve this problem and provide a system that allows users to receive more personalized, emotion-based suggestions.

[0767] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for a user to input individual characteristics, means for transmitting the input characteristics to the server, means for storing the characteristics in the server, means for generating proposals using a generative AI model based on the characteristics, means for providing the generated proposals to the user, means for collecting user feedback on the proposals, means for reflecting the collected feedback in the generative AI model, and means for analyzing the user's emotions using an emotion recognition engine and reflecting the emotions in the generative AI model. This makes it possible to realize more appropriate and personalized fashion proposals based on the user's individual characteristics and real-time emotional reactions.

[0768] "User individual characteristics" are individual identifying information input by the user or obtained by the system, such as hair type, face shape, skin color, desired style, etc.

[0769] A "server" is a computer system that transmits, receives, stores, and processes data.

[0770] A "generative AI model" is an artificial intelligence algorithm that uses machine learning to generate suggestions based on user information.

[0771] "Suggestions" are hairstyle and fashion style recommendations generated by the generative AI model and provided to the user.

[0772] "Feedback" is information indicating opinions and reactions provided by users to suggestions.

[0773] An "emotion recognition engine" is software or hardware that analyzes a user's facial expressions and voice to recognize their emotions.

[0774] "User emotion data" is data that indicates the user's emotional state and is output as a result of analysis by the emotion recognition engine.

[0775] A "terminal" is an electronic device that a user operates, such as a smartphone, smart glasses, a personal computer, or a head-mounted display.

[0776] A "database" is a system that allows a server to systematically store and manage data.

[0777] The present invention provides a system that proposes optimal fashion styles based on the user's individual characteristics and emotions. This system is configured to realize a series of steps: inputting user characteristics, recognizing emotions, generating suggestions, and collecting feedback.

[0778] Overall system configuration

[0779] The system is implemented by the following components:

[0780] 1. Enter your user information

[0781] Using a device such as a smartphone or smart glasses, users input their individual characteristics into the application, such as hair type, face shape, skin color, and desired style, which is then sent to a server and stored in a database.

[0782] 2. Emotion recognition

[0783] While a user is trying on fashion items, the smart glasses' camera and voice recognition function are used to analyze their emotions in real time. The emotion recognition engine uses Azure Face API to capture facial expression data such as smiles and surprise.

[0784] 3. Proposal generation

[0785] The server uses a generative AI model (e.g., OpenAI's GPT-4) to generate optimal fashion style suggestions based on the stored user feature information and real-time emotion data, and the generated suggestions are sent to the smart glasses or other devices and displayed to the user.

[0786] 4. Gathering Feedback

[0787] Users provide feedback on their impressions and requests regarding the proposed style, which is then sent to the server and stored as training data for the generative AI model.

[0788] 5. Collaboration between brands and stylists

[0789] The suggestions will reflect the styles recommended by the user's favorite brands and affiliated stylists, allowing for more personalized suggestions.

[0790] Processing Details

[0791] Hardware and Software Configuration

[0792] Smart glasses: Smart glasses such as HoloLens 2 are used and are equipped with a camera and voice input device.

[0793] Emotion recognition engine: Emotion analysis is performed using Azure Face API.

[0794] Generative AI model: We use OpenAI's GPT-4 to generate proposals.

[0795] Database: We use Microsoft Azure SQL Database to manage user information and feedback.

[0796] Data processing and calculation

[0797] 1. Enter and submit user information

[0798] The characteristic information entered by the user is sent from the device to the server and stored in Azure SQL Database.

[0799] 2. Emotion recognition

[0800] Facial images and voice data of the user trying on the items are captured by the camera and microphone of the smart glasses, and emotion analysis is performed using the Azure Face API.

[0801] 3. Proposal generation

[0802] The server accesses Azure SQL Database to retrieve stored user information and real-time emotion data.

[0803] This data is then input into the generative AI model GPT-4 to suggest the optimal fashion style.

[0804] 4. Submitting and Viewing Proposals

[0805] The generated suggestions are sent from the server to smart glasses or other devices and displayed to the user.

[0806] 5. Gathering Feedback

[0807] User feedback is sent from the device to the server, stored in Azure SQL Database, and used to improve the accuracy of the next suggestion.

[0808] Specific examples

[0809] Consider the "Style Guide Glasses" application in action. When a user tries on a dress in a store, the smart glasses capture the user's face and recognize their smile using the Azure Face API. This information is sent to a server, where, combined with stored profile information such as hair type and face shape, GPT-4 generates suggestions such as "What shoes would go well with this dress?" and displays them on the smart glasses' display.

[0810] Prompt Sentence Examples

[0811] Send a prompt like this to your generative AI model:

[0812] User profile information:

[0813] Hair type: Straight, Face shape: Oval, Skin tone: Olive, Desired style: Casual

[0814] Emotion data: Smile (positive)

[0815] Previous suggestion feedback: I liked it

[0816] Generate a proposal.

[0817] This concludes the detailed description of the invention, which allows users to receive more personalized, emotion-based fashion suggestions.

[0818] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0819] Step 1:

[0820] Users input their individual characteristics, such as hair type, face shape, skin color, and desired style, through a smartphone or smart glasses device, which then collects this information and sends it to a server.

[0821] Step 2:

[0822] The server receives the user characteristic information sent from the device, validates the received information (checks the format and range), and stores it in Azure SQL Database if there are no problems.

[0823] Step 3:

[0824] A user tries on fashion items in a physical store. The camera in the smart glasses captures the user's facial image and the microphone records the user's voice. This data is sent in real time to an emotion recognition engine (Azure Face API).

[0825] Step 4:

[0826] Using Azure Face API, the user's facial image and voice data are analyzed to obtain emotional data (e.g., smile, surprise, sadness), which is then transmitted from the smart glasses to the server.

[0827] Step 5:

[0828] The server combines the received emotion data with pre-stored user feature information. Based on this data, it creates a prompt for the generative AI model (GPT-4) and sends it as input data. An example of a specific prompt is as follows:

[0829] User profile information:

[0830] Hair type: Straight, Face shape: Oval, Skin tone: Olive, Desired style: Casual

[0831] Emotion data: Smile (positive)

[0832] Previous suggestion feedback: I liked it

[0833] Generate a proposal.

[0834] Step 6:

[0835] The generative AI model generates optimal fashion style suggestions based on the received prompt. These suggestions are returned to the server as text data. For example, a suggestion like, "How about some shoes that match this dress?"

[0836] Step 7:

[0837] The server receives the suggestions from the generative AI model and sends them to a device such as smart glasses or a smartphone, which then visually displays the received suggestions to the user.

[0838] Step 8:

[0839] The user can input feedback about the proposed fashion style, such as "I like it" or "I'd like you to suggest a more casual style" using the terminal.

[0840] Step 9:

[0841] The device sends user feedback to the server, which stores it in Azure SQL Database and uses it as training data for the generative AI model when generating the next recommendation.

[0842] This concludes the processing flow of the system program for implementing this application example, which allows users to receive personalized fashion suggestions in real time and collects feedback to improve the accuracy of the suggestions.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] [Third embodiment]

[0847] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0848] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0849] 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).

[0850] 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.

[0851] 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.

[0852] 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).

[0853] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0854] 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.

[0855] 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.

[0856] 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.

[0857] 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.

[0858] 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."

[0859] ---

[0860] The present invention includes a hairstyle and fashion suggestion system called Style Core. This system is designed to provide users with hairstyles and fashion styles that are optimal for them, with the server, terminals, and users working together.

[0861] Overall system configuration

[0862] The system is implemented primarily by the following components:

[0863] 1. Entering user information: The user enters their individual characteristics (hair type, face shape, skin color, desired style, etc.) into the terminal.

[0864] 2. Transmission and storage of information: The information entered by the user is transmitted from the terminal to the server and stored in the server's database.

[0865] 3. Utilizing generative AI models: The server uses generative AI models based on stored user information to suggest optimal hairstyles and fashions.

[0866] 4. Sending and displaying proposals: The generated proposals are sent from the server to the terminal and displayed on the terminal.

[0867] 5. Feedback collection: Users provide feedback on the proposals, which is sent to the server, stored in a database, and used as training data for the generative AI model.

[0868] 6. Brand and stylist collaboration: Suggestions include ways to reflect the styles of brands and affiliated stylists that users frequent.

[0869] Program processing and specific examples

[0870] Below, the program processing in each component will be explained in natural language with specific examples.

[0871] Entering user information

[0872] Users access the Style Core application using a device such as a smartphone or PC, and enter information such as their hair type (e.g., straight hair), face shape (e.g., oval), skin color (e.g., olive skin), and desired style (e.g., casual) into a form displayed on the application screen.

[0873] Sending and storing information

[0874] When the user presses the "Submit" button, the terminal sends the entered information to the server, which receives it, validates it, and stores it in the database.

[0875] Leveraging generative AI models

[0876] The server launches a generative AI model based on the saved user information. The generative AI model learns the latest trends and design knowledge, and uses that information to generate optimal hairstyle and fashion suggestions for the user. For example, for a user with straight hair and an oval face, it might suggest a "short haircut with bangs" and a "casual striped shirt."

[0877] Submitting and Viewing Proposals

[0878] The server sends the generated suggestions to the user's device, which receives and analyzes them and then displays them on the application screen, where the user can check the suggested hairstyles and fashions.

[0879] Gathering feedback

[0880] Users can provide feedback on the proposed styles within the application, such as "I like it" or "I'd like a more casual style." The device sends this feedback to the server, which receives it and stores it in a database. The stored feedback is used as training data for the generative AI model.

[0881] Collaboration with brands and stylists

[0882] The server integrates information about the user's favorite brands and affiliated stylists as training data into the generative AI model, allowing suggestions to reflect items recommended by brands and stylists familiar to the user.

[0883] ---

[0884] The above is an embodiment of the present invention. This allows users to easily find hairstyles and fashion styles that suit them best, and it is expected that the accuracy of personalized suggestions will be further improved based on feedback.

[0885] The processing flow will be explained below.

[0886] Okay, so let's break down the program's processing into specific steps.

[0887] Step 1: User accesses the system

[0888] Users launch the StyleCore application from a device such as a smartphone or PC.

[0889] Step 2: User Enters Information

[0890] The user enters individual characteristics such as their hair type (e.g., straight hair), face shape (e.g., oval), skin color (e.g., olive skin), and desired style (e.g., casual) into a form on the application screen.

[0891] Step 3: The device sends the information

[0892] When the user enters information and presses the "send" button, the terminal sends the information to the server.

[0893] Step 4: The server receives and stores the information

[0894] The server receives the user information, checks the integrity of the data, and then stores it in the database. A validation process is performed to check for inappropriate data.

[0895] Step 5: The server launches the generative AI model

[0896] The server then launches a generative AI model based on the stored user information, which is trained on the latest trends and design knowledge.

[0897] Step 6: The server inputs the data into the generative AI model

[0898] The server inputs user information into a generative AI model, which then generates optimal hairstyle and fashion suggestions based on the user's characteristics.

[0899] Step 7: The server retrieves the generated proposal

[0900] The server receives the recommendations output by the generative AI model, such as a "short haircut with bangs" and a "casual striped shirt."

[0901] Step 8: Server sends proposal

[0902] The server then sends the generated suggestions to the user's device, often in a format such as JSON.

[0903] Step 9: Your device receives and displays the proposal

[0904] The device receives the suggestions sent from the server, analyzes them, and displays them on the application screen, where the user can check the suggested hairstyles and fashions.

[0905] Step 10: User Enters Feedback

[0906] Users can input their evaluations and opinions on the suggestions, such as "I like it" or "I'd like a more casual style."

[0907] Step 11: Device sends feedback

[0908] When the user inputs feedback and presses the "send" button, the terminal sends the feedback to the server.

[0909] Step 12: Server receives and stores feedback

[0910] The server receives the feedback and stores it in a database, which is later used as training data for the generative AI model.

[0911] Step 13: The server learns the brand and stylist information

[0912] The server collects information about the user's favorite brands and affiliated stylists and integrates it into a generative AI model.

[0913] Step 14: Your server will then reflect on your recommendations with compatible brands and stylists.

[0914] The server uses the generative AI model to generate recommendations based on the styles of brands and stylists familiar to the user, resulting in more accurate recommendations for the user.

[0915] The above is a description of the specific operation of each processing step in the Style Core system.

[0916] Example 1

[0917] 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."

[0918] The present invention relates to a system that proposes optimal hairstyles and fashions based on the individual characteristics of each user. Conventional proposal systems have difficulty responding to individual user characteristics in detail, and have faced challenges in improving the accuracy of proposals that appropriately reflect user feedback. In addition, it has been difficult to reflect the proposals of brands and stylists that users are familiar with, which has prevented users from achieving sufficient satisfaction. The present invention aims to solve these problems.

[0919] 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.

[0920] In this invention, the server includes means for a user to input individual characteristics, means for transmitting the input characteristics to a processing device, means for storing the characteristics in the processing device, means for generating proposals using a generative AI model based on the characteristics, means for providing the generated proposals to a user, means for collecting user feedback on the proposals, means for reflecting the collected feedback in the generative AI model, means for analyzing and displaying the proposal content, and means for validating the user's personal information in a database of the processing device. This enables highly accurate proposals based on the user's individual characteristics, improves the accuracy of proposals based on feedback, and further enables proposals that reflect styles recommended by brands and stylists familiar to the user.

[0921] "User" refers to an individual who utilizes the system to input their characteristics and receive suggestions.

[0922] "Characteristics" refers to personal information about a user, including hair type, face shape, skin color, desired style, and the like.

[0923] "Processing device" refers to hardware or software that receives, stores, and processes data sent by a user.

[0924] A "generative AI model" refers to an artificial intelligence model that generates optimal hairstyle and fashion suggestions based on a user's characteristics.

[0925] "Suggestions" refers to recommendations about hairstyles and fashion that are generated based on the user's characteristics using a generative AI model.

[0926] "Feedback" refers to the opinions and thoughts that users provide regarding suggestions.

[0927] "Validation" refers to the process of verifying that received data has the correct format and content.

[0928] "Database" refers to an information storage system for storing user characteristics and feedback.

[0929] A "brand" refers to a sign or name that identifies the products or services offered by a particular company or organization.

[0930] A "stylist" is a professional who gives advice and suggestions regarding fashion and hairstyles.

[0931] "Terminal" refers to a device, such as a computer or smartphone, that a user uses to access the system.

[0932] "User interface" refers to the screens and operating means that users use to operate a system.

[0933] "Communication protocol" refers to the rules and procedures used between a terminal and a server to send and receive information.

[0934] An "HTTP request" refers to the communication format used by a web browser or application to request data from a server or server.

[0935] "JSON format" is a lightweight data exchange format that is easy for humans to read and machines to parse.

[0936] A "trained neural network" refers to an artificial intelligence model that has been trained using a specific dataset.

[0937] This invention is a system that suggests optimal hairstyles and fashion styles to users, and this system makes suggestions using a generative AI model based on the user's characteristics. Users can access the system using a device such as a smartphone or PC and receive suggestions by inputting their own characteristics.

[0938] Overall system configuration

[0939] The system consists of the following main components:

[0940] 1. Enter your user information

[0941] 2. Transmission and storage of information

[0942] 3. Utilizing generative AI models

[0943] 4. Submitting and Displaying Proposals

[0944] 5. Gathering Feedback

[0945] 6. Collaboration with brands and stylists

[0946] Specific actions

[0947] The specific operation of each element will be described below.

[0948] Entering user information

[0949] Users input their own characteristic information (hair type, face shape, skin color, desired style, etc.) via a device such as a smartphone or PC. This information is then input and used by the user through an application on the device.

[0950] Sending and storing information

[0951] The characteristic information entered by the user is sent from the terminal to the server. The server validates the received data, confirming that it is in the correct format and content, and then stores it in a database. The database used here is a commonly used relational database (e.g., MySQL, PostgreSQL).

[0952] Leveraging generative AI models

[0953] The server then launches a generative AI model based on the stored user information. This model is built using machine learning frameworks such as TensorFlow and PyTorch, and makes suggestions for optimal hairstyles and fashion based on the user's characteristics. For example, suggestions are generated for information such as "straight hair," "oval face," "olive skin," and "casual style."

[0954] As a concrete example, the following prompt sentence is input to the generative AI model:

[0955] "Please suggest the best casual hairstyle and fashion for a user with straight hair, an oval face, and olive skin."

[0956] Submitting and Viewing Proposals

[0957] The server sends the generated suggestions to the user's device, which receives them, analyzes them, and displays them on the application screen. The user can then check the suggested hairstyles and fashions, and save or share them as needed.

[0958] Gathering feedback

[0959] Users can input feedback on the suggestions and send it to the server via their devices. The server stores the received feedback in a database, and this feedback is used as training data for the generative AI model, thereby improving the accuracy of the suggestions made by the AI ​​model.

[0960] Collaboration with brands and stylists

[0961] The server can reflect the recommended styles of brands and affiliated stylists frequently used by the user in its suggestions. Specifically, by storing information on brand items and stylist suggestion history in a database and adding this information to the training data of the AI ​​model, the server can make suggestions that are familiar to the user.

[0962] In this way, users can use a system that suggests optimal hairstyles and fashion styles based on their individual characteristics, thereby increasing user satisfaction and improving the accuracy of suggestions.

[0963] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0964] Step 1: Enter your user information

[0965] The user launches the Style Core application using a device such as a smartphone or PC. The user enters their characteristic information (hair type, face shape, skin color, desired style, etc.) into a form displayed on the application screen. For example, the user enters specific information such as "straight hair," "oval face," "olive skin," and "casual style." This input information becomes the data sent to the server in the next step.

[0966] Step 2: Send and save information

[0967] Data entered by the user, including characteristic information, is sent from the terminal to the server. The data input is sent using an HTTP request. The server validates the received data to ensure that it is in the correct format and content. Data that passes validation is stored in the server's database. The database used here is a relational database such as MySQL or PostgreSQL.

[0968] Step 3: Leveraging generative AI models

[0969] The server launches a generative AI model based on the stored user feature information. The user's feature information (e.g., "straight hair," "oval face," "olive skin," and "casual style") is used as input. The generative AI model is built using frameworks such as TensorFlow and PyTorch. This AI model analyzes the input user feature information and generates optimal hairstyle and fashion suggestions. For example, it might generate suggestions such as "short haircut with bangs" and "casual striped shirt." As a concrete example, the following prompt sentence is input to the generative AI model:

[0970] "Please suggest the best casual hairstyle and fashion for a user with straight hair, an oval face, and olive skin."

[0971] Step 4: Submit and view your proposal

[0972] The suggestions created by the generative AI model are sent from the server to the device in data format such as JSON. The device analyzes the data received from the server and displays it on the user interface. On the display screen, the user can check the suggested hairstyle, fashion, and specific item information (e.g., a short haircut with bangs, a casual striped shirt). This allows the user to confirm the suggestions and proceed to the next step.

[0973] Step 5: Gather feedback

[0974] The user inputs their thoughts and opinions about the suggestions (e.g., "I like it," "I'd like a more casual style," etc.). The input feedback is sent from the device to the server. The server stores the received feedback data in a database. The feedback data is used as training data for the generative AI model. This improves the accuracy of the next suggestion.

[0975] Step 6: Collaborate with brands and stylists

[0976] The server integrates information about the user's favorite brands and affiliated stylists into the generative AI model. Specifically, it imports information about brand items and stylist recommendation history as learning data and stores it in a database. For example, it reflects the latest collections of brands frequently purchased by the user and recommended items from affiliated stylists in the database. This ensures that suggestions include items from brands and stylists familiar to the user.

[0977] The above are the processing steps of the system and their specific operations. Data processing and calculations are carried out at each step, resulting in a system that provides optimal suggestions to users.

[0978] (Application example 1)

[0979] 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."

[0980] Today, there are many systems that suggest the best hairstyles and fashions for individual users, but these systems require users to manually input their own characteristics. In addition, they cannot confirm the suggestions in real time, and the feedback loop to reflect the suggestions in reality is incomplete. This limits the user experience and reduces satisfaction.

[0981] 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.

[0982] In this invention, the server includes: means for a user to input individual features; means for transmitting the input features to the server; means for storing the features in the server; means for generating suggestions using a generative AI model based on the features; means for providing the generated suggestions to the user; means for collecting user feedback on the suggestions; means for reflecting the collected feedback in the generative AI model; a camera for recognizing the user's features; means for transmitting data collected by the camera to a cloud server; means for the cloud server to analyze the data using the generative AI model and generate suggestions; and means for displaying the suggestions on the user's visual device in real time. This allows the user to see optimal hairstyle and fashion suggestions in real time without having to manually input their own features, and further allows feedback based on the suggestions to be reflected in the generative AI model.

[0983] "User" refers to a person who uses the system to receive hairstyle and fashion suggestions.

[0984] "Characteristics" refers to individual information such as the user's hair type, face shape, skin color, and desired style.

[0985] "Means" refers to a method or apparatus for achieving a specific function or operation.

[0986] "Server" refers to a device or system that receives and stores information sent by users and generates and provides suggestions using generative AI models.

[0987] A "generative AI model" refers to an artificial intelligence model that generates optimal hairstyle and fashion suggestions based on training data.

[0988] "Camera" refers to a photographic device for collecting data on a user's face and body.

[0989] "Cloud Server" refers to the remote server that analyzes the collected data and generates and sends recommendations to users.

[0990] A "visual device" is a device for displaying suggestions to a user, such as smart glasses.

[0991] System Overview

[0992] The present invention relates to a style suggestion system, specifically a system that recognizes a user's individual characteristics and uses a generative AI model to suggest optimal hairstyles and fashions. The system operates by including a user terminal, a server, and a visual device (e.g., smart glasses).

[0993] Program processing and natural language explanation

[0994] User information entry and automatic collection

[0995] The user wears the vision device and activates the system. The camera on the vision device captures the user's facial and body features in real time, and the data is sent from the user's device to a cloud server. This process uses facial recognition software (e.g., OpenCV).

[0996] Analyzing information and generating recommendations

[0997] The cloud server stores the received feature data and inputs it into a generative AI model (e.g., TensorFlow). The generative AI model generates optimal hairstyle and fashion suggestions based on the stored user feature data. For example, for a user with straight hair and an oval face, it might suggest a "short haircut with bangs" and a "casual striped shirt."

[0998] Submitting and Viewing Proposals

[0999] The cloud server sends the generated suggestions to the user's visual device in real time, where the visual device analyzes the received suggestions and displays them to the user. The user can then check the suggested hairstyles and fashions as if looking in a mirror through the visual device.

[1000] Gathering and implementing feedback

[1001] When the user provides feedback on the suggestions via the visual device, the feedback is again sent to the cloud server and stored, where it is used as training data for the generative AI model to improve the accuracy of subsequent suggestions.

[1002] Specific hardware and software names used

[1003] Hardware:

[1004] Smart glasses (e.g., general-purpose smart glasses devices)

[1005] camera

[1006] Cloud Server

[1007] software:

[1008] Facial recognition software (e.g. OpenCV)

[1009] AI models (e.g. TensorFlow)

[1010] Cloud services (e.g. AWS, GCP)

[1011] Front-end applications (e.g. HTML5, JavaScript)

[1012] Examples and prompts

[1013] For example, smart glasses automatically activate when a user enters a store and perform facial recognition. At this time, the following prompt sentence is input to the generative AI model:

[1014] "Based on the client's characteristics, suggest hairstyles and casual styles that would suit someone with straight hair and an oval face."

[1015] The generative AI model generates suggestions based on this prompt and displays them on a visual device, allowing users to see the best hairstyles and fashions in real time.

[1016] summary

[1017] The system automatically collects users' personal characteristics and allows them to receive personalized style suggestions in real time, while incorporating user feedback into the generative AI model to continuously improve the accuracy of the suggestions.

[1018] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1019] Step 1:

[1020] The user puts on the smart glasses and activates the system. The camera in the smart glasses captures the user's facial and body features and sends this data to the user's device. The input data is facial images and body proportion information, which are then analyzed in subsequent processing steps.

[1021] Step 2:

[1022] The user device transmits the captured feature data to the cloud server. This transmission process involves data conversion and compression. Specifically, the image data is converted to JPEG format and compressed for efficient transmission over the network. The input data is the captured image data, and the output is compressed image data.

[1023] Step 3:

[1024] The cloud server stores the received feature data in a database. At the same time, it analyzes the image data using facial recognition software (e.g., OpenCV). This analysis process extracts characteristics such as facial shape, hair type, and skin color. The input data is compressed image data, and the output data is analyzed feature data.

[1025] Step 4:

[1026] The cloud server inputs the analyzed feature data into the generative AI model. To create this prompt, text data is generated, such as "Please suggest a hairstyle and fashion that would suit a user with straight hair and an oval face." The generative AI model then generates optimal hairstyle and fashion suggestions based on this prompt. The input data is the analyzed feature data, and the output is optimal suggestion data.

[1027] Step 5:

[1028] The cloud server transmits the generated proposal data to the user's visual device in real time. Specifically, the proposal data is encoded using a dedicated protocol and transmitted to the visual device. The input data is the proposal data, and the output is the encoded data.

[1029] Step 6:

[1030] The visual device decodes the received suggestion data and displays it to the user. The user can check the suggested hairstyle and fashion on their own image. The input data is the encoded suggestion data, and the output is a display for the user's vision.

[1031] Step 7:

[1032] The user inputs feedback on the suggestions through a visual device. For example, they input opinions such as "cut your bangs a little shorter" or "dress more casually." The input data is the user's feedback, and the output is feedback data.

[1033] Step 8:

[1034] The vision device sends feedback data to a cloud server, which stores the received feedback in a database and uses it as training data for the generative AI model. This process improves the accuracy of subsequent suggestions. The input data is the feedback data, and the output is the stored data.

[1035] 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.

[1036] ---

[1037] This invention shows an embodiment for implementing "Style Core," a system that suggests optimal hairstyles and fashions based on the individual characteristics of a user. This system operates in cooperation with a server, terminals, and users, and by combining it with an emotion engine that recognizes the user's emotions, it achieves more accurate style suggestions and feedback collection.

[1038] Overall system configuration

[1039] The system is implemented by the following components:

[1040] 1. Input of user information: The user inputs his / her individual characteristics from the terminal.

[1041] 2. Sending and saving information: The device sends the entered information to the server, which saves it in a database.

[1042] 3. Utilizing generative AI models: The server generates suggestions using generative AI models based on the stored user information.

[1043] 4. Sending and displaying the proposal: The server sends the generated proposal to the terminal and it is displayed on the user's terminal.

[1044] 5. Feedback collection: The user provides feedback on the proposal, which is sent to the server and stored in a database.

[1045] 6. Collaboration with brands and stylists: Suggestions will reflect the recommended styles of brands and affiliated stylists that users frequently use.

[1046] 7. Utilizing an emotion engine: An emotion engine is used to recognize the user's emotions and reflect the results in the suggestions.

[1047] Program processing and specific examples

[1048] Below, the program processing in each component will be explained in natural language with specific examples.

[1049] Entering user information

[1050] Users access the Style Core application using a device such as a smartphone or PC, and enter information such as their hair type (e.g., straight hair), face shape (e.g., oval), skin color (e.g., olive skin), and desired style (e.g., casual) into the application form screen.

[1051] Sending and storing information

[1052] When the user presses the "Submit" button, the terminal sends the entered information to the server, which receives the information, validates it, and stores it in the database.

[1053] Leveraging generative AI models

[1054] The server launches a generative AI model based on the saved user information. The generative AI model learns the latest trends and design knowledge and generates optimal hairstyle and fashion suggestions based on the user information. For example, for a user with straight hair and an oval face, it would suggest a "short haircut with bangs" and a "casual striped shirt."

[1055] Submitting and Viewing Proposals

[1056] The server sends the generated suggestions to the user's device, which receives them and displays them on the application screen, where the user can check the suggested hairstyles and fashions.

[1057] Gathering feedback

[1058] Users can provide feedback on the suggested styles, such as "I like it" or "I'd like a more casual style." The device then sends this feedback to the server, which receives it and stores it in a database. The feedback is then used as training data for the generative AI model.

[1059] Collaboration with brands and stylists

[1060] The server integrates information about the user's favorite brands and affiliated stylists as training data into the generative AI model, allowing suggestions to reflect items recommended by brands and stylists familiar to the user.

[1061] Utilizing the Emotion Engine

[1062] The device is equipped with an emotion engine that recognizes emotions through the user's facial expressions and voice. The recognized emotion data is sent to a server, which then uses the data to adjust the generative AI model. For example, if the user smiles when viewing a suggestion, the emotion data is added to the feedback as a signal that the suggestion has been accepted. In this way, the suggestions are further personalized.

[1063] ---

[1064] The above is an embodiment of the present invention. This allows users to receive personalized suggestions for hairstyles and fashion styles based on their emotions. Furthermore, it is expected that the accuracy of suggestions will be further improved based on feedback.

[1065] The processing flow will be explained below.

[1066] Step 1: User accesses the system

[1067] Users launch StyleCore applications using devices such as smartphones and PCs.

[1068] Step 2: User Enters Information

[1069] The user enters their individual characteristics, such as their hair type (e.g., straight hair), face shape (e.g., oval), skin color (e.g., olive skin), and desired style (e.g., casual), into the application's form screen.

[1070] Step 3: The device sends the information

[1071] When the user inputs information and presses the "send" button, the terminal sends the input information to the server.

[1072] Step 4: The server receives and stores the information

[1073] The server receives the submitted user information, checks the data for consistency, and stores it in a database, for example by validating that the hair type is specified correctly and that the face shape is within the valid options.

[1074] Step 5: The server launches the generative AI model

[1075] The server then launches a generative AI model based on the stored user information, which uses the trend data and design knowledge it has learned to generate optimal hairstyle and fashion suggestions.

[1076] Step 6: The server inputs the data into the generative AI model

[1077] The server inputs user information into a generative AI model, which takes into account the user's hair type, face shape, skin color, etc. to calculate and generate optimal style suggestions.

[1078] Step 7: The server retrieves the generated proposal

[1079] The server receives the output of the generative AI model, generating specific style suggestions such as a "short haircut with bangs" and a "casual striped shirt."

[1080] Step 8: Server sends proposal

[1081] The server sends the generated proposal to the user's device, formatted in JSON or similar.

[1082] Step 9: Your device receives and displays the proposal

[1083] The device receives the suggestions sent from the server, analyzes them, and displays them on the application screen, where the user can check the suggested hairstyles and fashions.

[1084] Step 10: User Enters Feedback

[1085] Users can then rate and comment on the suggestions within the application, for example by entering feedback such as "I like it" or "I'd like a more casual style."

[1086] Step 11: Device sends feedback

[1087] When the user inputs feedback and presses the "send" button, the terminal sends the feedback to the server.

[1088] Step 12: Server receives and stores feedback

[1089] The server receives the feedback and stores it in a database, which is later used as training data for the generative AI model.

[1090] Step 13: The server learns the brand and stylist information

[1091] The server collects information about the user's favorite brands and affiliated stylists, stores it in a database, and then integrates this information into a generative AI model for training.

[1092] Step 14: Your server will then reflect on your recommendations with compatible brands and stylists.

[1093] The server uses a generative AI model to generate suggestions that reflect the brands and stylists familiar to the user, for example, by providing suggestions that include the latest collections from brands the user frequently purchases.

[1094] Step 15: Device captures real-time emotions

[1095] The device is equipped with an emotion engine that recognizes emotions through the user's real-time facial expressions and voice, for example, by using a camera and microphone to detect the user's smile and tone of voice.

[1096] Step 16: The device sends emotion data

[1097] The device sends the recognized emotion data to the server. For example, if the device recognizes a smile or a voice of joy from the user, the data is sent to the server.

[1098] Step 17: The server reflects the emotion data in the generative AI model

[1099] The server then feeds the received emotion data into the generative AI model, which then further adjusts the suggestions based on the user's emotion. If the emotion data is positive, the feedback is considered a positive evaluation.

[1100] The above is a concrete explanation of the operation of each processing step in the style core system including the emotion engine.

[1101] Example 2

[1102] 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."

[1103] Conventional style suggestion systems have difficulty providing personalized suggestions based on the individual characteristics of each user, which has led to issues with not being able to sufficiently increase user satisfaction. Furthermore, they lacked the functionality to appropriately reflect user feedback and emotions, making it impossible to improve the accuracy of suggestions for the next time. Furthermore, they were unable to reflect the recommended styles of brands frequently used by users or affiliated stylists in the suggestions, making it impossible to realize suggestions tailored to the user's preferences.

[1104] 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.

[1105] In this invention, the server includes means for a user to input individual features, means for transmitting the input features to the server, means for storing the features in the server, means for generating suggestions using a generative AI model based on the features, means for providing the generated suggestions to the user, means for collecting user feedback on the suggestions, means for reflecting the collected feedback in the generative AI model, and means for recognizing user emotions using an emotion engine and reflecting the emotions in the generated suggestions. This enables more personalized style suggestions based on the user's features, emotions, and past feedback.

[1106] "Characteristics" refers to individual attribute information such as the user's hair type, face shape, skin color, and desired style.

[1107] "Server" refers to a computer system for receiving, storing, and processing data from users.

[1108] "Generative AI model" refers to an artificial intelligence model designed to generate optimal suggestions based on user characteristics.

[1109] "Suggestion" refers to the recommendation of hairstyle or fashion style that the generative AI model generates based on the user's characteristics.

[1110] "Feedback" refers to reactions such as satisfaction, opinions, and requests provided by users in response to suggestions.

[1111] An "emotion engine" is an engine that recognizes emotions from the user's facial expressions and voice, and reflects that data in a generative AI model.

[1112] A "terminal" is a device that a user uses to input information or check suggestions, such as a smartphone or computer.

[1113] "Database" refers to the data storage system used by the Server to store and manage user characteristics and feedback.

[1114] "Brand" refers to the manufacturer or retailer that the user frequently uses.

[1115] A "stylist" is a professional who suggests hairstyles and fashion styles.

[1116] MODE FOR CARRYING OUT THE INVENTION

[1117] The present invention is a system that suggests optimal hairstyles and fashions based on the individual characteristics of a user, and detailed embodiments thereof are described below. This system operates in cooperation with a server, terminal, and user, and by combining it with an emotion engine that recognizes the user's emotions, it achieves more accurate style suggestions and feedback collection.

[1118] Overall system configuration

[1119] The system is implemented by the following components:

[1120] 1. A terminal for inputting user information

[1121] 2. Server that receives, processes, and stores information

[1122] 3. Generative AI model that generates suggestions

[1123] 4. Emotion engine that recognizes user emotions

[1124] Details of each component

[1125] Entering user information

[1126] Users access the Style Core application using a device such as a smartphone or PC. They enter information such as their hair type (e.g., straight hair), face shape (e.g., oval), skin color (e.g., olive skin), and desired style (e.g., casual) into the application's form screen. This information is entered through the application's user interface, and the user proceeds to the next step by pressing the submit button.

[1127] Sending and storing information

[1128] When the user presses the "Send" button, the terminal sends the entered information to the server. The server receives the sent information and checks (validates) the validity of the data format. Information that passes this check is saved in the database.

[1129] Leveraging generative AI models

[1130] The server launches a generative AI model based on the saved user information. The generative AI model learns the latest trends and fashion designs to generate optimal suggestions based on the conditions obtained from the user. For example, the server passes the following prompt text to the generative AI model: "The user's hair type is straight, their face shape is oval, their skin color is olive, and their desired style is casual. Please suggest the best hairstyle and fashion for this user."

[1131] Submitting and Viewing Proposals

[1132] The generated suggestions are sent from the server to the user's device, which receives them and displays them on the application screen, where the user can check in detail the hairstyles and fashions suggested by the generative AI model.

[1133] Gathering feedback

[1134] Users can provide feedback on the suggested styles, for example by rating "how satisfied I am with the suggested styles" on a scale of 1 to 5, or by entering specific requests in text, such as "I would like a more casual style." The device then sends this feedback data to the server, which stores the received feedback in a database. This feedback is then used as training data for the generative AI model.

[1135] Collaboration with brands and stylists

[1136] The server analyzes the user's past usage history and feedback information, and incorporates the user's preferred brands and the styles of affiliated stylists into the generative AI model as learning data, so that the next recommendation will include items recommended by brands and stylists familiar to the user.

[1137] Utilizing the Emotion Engine

[1138] The user's device is equipped with an emotion engine that analyzes the user's facial expressions and voice in real time via the built-in camera and microphone. For example, the emotion engine recognizes and analyzes changes in facial expression (e.g., smile or frown) and tone of voice (e.g., joy or dissatisfaction) when the user sees a proposed style. This emotion data is sent to the server in real time, and the server uses this data to adjust the generative AI model. For example, data is fed back so that information that indicates the user's satisfaction is reflected in the next proposal generation.

[1139] Specific examples

[1140] As a concrete example, suppose a user inputs the following information: hair type "straight hair," face shape "oval," skin color "olive skin," and desired style "casual." The information is sent from the device to the server, where it is saved, and then the generative AI model is launched. The server passes a prompt to the generative AI model, which displays the results on the user's device. The suggestions are "short haircut with bangs" and "casual striped shirt," which the user confirms on the device.

[1141] The user enters feedback on the suggestion, such as "I want a more casual style," and the device sends this feedback to the server. The server also collects the user's facial expression data from the emotion engine and reflects it in the generative AI model. The next suggestion will be further adjusted to better suit the user's preferences.

[1142] Example of a text prompt:

[1143] "This user has straight hair, an oval face, olive skin, and a casual style. What hairstyle and outfit would be best for this user?"

[1144] In this way, users can receive more personalized hairstyle and fashion style suggestions based on their emotions, and the accuracy of the suggestions can be improved based on feedback and emotional data.

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

[1146] Step 1:

[1147] Users access the Style Core application through a device such as a smartphone or PC. They enter information into a form screen, such as hair type (e.g., straight hair), face shape (e.g., oval), skin color (e.g., olive skin), and desired style (e.g., casual). This input data is collected using text boxes and drop-down menus in the application.

[1148] Input: Your individual characteristics (hair type, face shape, skin color, desired style)

[1149] Output: A dataset of the input features

[1150] Step 2:

[1151] When the user presses the "Submit" button, the terminal sends the entered information to the server. The server receives the sent information and checks the validity of the data format (validation). Information that passes validation is saved in the database.

[1152] Input: A dataset of input features

[1153] Output: Validated feature dataset (stored in a database)

[1154] Step 3:

[1155] The server launches a generative AI model based on the validated user information. The server passes the following prompt text to the generative AI model: "The user's hair type is straight, their face shape is oval, their skin color is olive, and their desired style is casual. Please suggest the best hairstyle and fashion for this user." The generative AI model processes and analyzes the data based on this prompt text, and generates optimal hairstyle and fashion suggestions.

[1156] Input: Validated feature dataset, prompt statement

[1157] Output: Data proposed by the generative AI model

[1158] Step 4:

[1159] The generated suggestion data is sent from the server to the user's device. The device receives the suggestion data and displays it on the application screen. Here, the user can check in detail the hairstyle and fashion suggested by the generative AI model.

[1160] Input: Data proposed by the generative AI model

[1161] Output: Proposal displayed on the device

[1162] Step 5:

[1163] The user provides feedback on the proposed style. For example, they input a specific request such as "I want a more casual style" and their satisfaction rating. The device sends this feedback data to the server, which then stores it in a database.

[1164] Input: User feedback on the proposal

[1165] Output: Saved feedback data

[1166] Step 6:

[1167] The server analyzes past usage history and feedback data and reflects it in the generative AI model. It processes and aggregates the data as necessary. This allows the generative AI model to learn the user's preferences and habits and reflect them in future suggestions.

[1168] Input: usage history data, feedback data

[1169] Output: A tuned and updated generative AI model

[1170] Step 7:

[1171] The user's device is equipped with an emotion engine that analyzes the user's facial expressions and voice in real time through the built-in camera and microphone. The emotion engine recognizes the user's emotions (e.g., joy, surprise, sadness) and sends the data to a server. The server then applies the emotion data to a generative AI model to provide more personalized suggestions.

[1172] Input: User's facial expression data, voice data

[1173] Output: Adjusting suggestions based on sentiment data

[1174] These are the specific program processing steps of this system. At each step, the user, device, and server play their respective roles, resulting in highly accurate style suggestions as a whole.

[1175] (Application example 2)

[1176] 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."

[1177] Conventional fashion suggestion systems make suggestions based on the user's individual characteristics, but they are unable to consider the user's emotions or real-time reactions, making it difficult to generate suggestions that truly satisfy the user. In particular, in the shopping experience at a physical store, it is necessary to reflect the user's emotions and feedback immediately. Our goal is to solve this problem and provide a system that allows users to receive more personalized, emotion-based suggestions.

[1178] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for a user to input individual characteristics, means for transmitting the input characteristics to the server, means for storing the characteristics in the server, means for generating proposals using a generative AI model based on the characteristics, means for providing the generated proposals to the user, means for collecting user feedback on the proposals, means for reflecting the collected feedback in the generative AI model, and means for analyzing the user's emotions using an emotion recognition engine and reflecting the emotions in the generative AI model. This makes it possible to realize more appropriate and personalized fashion proposals based on the user's individual characteristics and real-time emotional reactions.

[1179] "User individual characteristics" are individual identifying information input by the user or obtained by the system, such as hair type, face shape, skin color, desired style, etc.

[1180] A "server" is a computer system that transmits, receives, stores, and processes data.

[1181] A "generative AI model" is an artificial intelligence algorithm that uses machine learning to generate suggestions based on user information.

[1182] "Suggestions" are hairstyle and fashion style recommendations generated by the generative AI model and provided to the user.

[1183] "Feedback" is information indicating opinions and reactions provided by users to suggestions.

[1184] An "emotion recognition engine" is software or hardware that analyzes a user's facial expressions and voice to recognize their emotions.

[1185] "User emotion data" is data that indicates the user's emotional state and is output as a result of analysis by the emotion recognition engine.

[1186] A "terminal" is an electronic device that a user operates, such as a smartphone, smart glasses, a personal computer, or a head-mounted display.

[1187] A "database" is a system that allows a server to systematically store and manage data.

[1188] The present invention provides a system that proposes optimal fashion styles based on the user's individual characteristics and emotions. This system is configured to realize a series of steps: inputting user characteristics, recognizing emotions, generating suggestions, and collecting feedback.

[1189] Overall system configuration

[1190] The system is implemented by the following components:

[1191] 1. Enter your user information

[1192] Using a device such as a smartphone or smart glasses, users input their individual characteristics into the application, such as hair type, face shape, skin color, and desired style, which is then sent to a server and stored in a database.

[1193] 2. Emotion recognition

[1194] While a user is trying on fashion items, the smart glasses' camera and voice recognition function are used to analyze their emotions in real time. The emotion recognition engine uses Azure Face API to capture facial expression data such as smiles and surprise.

[1195] 3. Proposal generation

[1196] The server uses a generative AI model (e.g., OpenAI's GPT-4) to generate optimal fashion style suggestions based on the stored user feature information and real-time emotion data, and the generated suggestions are sent to the smart glasses or other devices and displayed to the user.

[1197] 4. Gathering Feedback

[1198] Users provide feedback on their impressions and requests regarding the proposed style, which is then sent to the server and stored as training data for the generative AI model.

[1199] 5. Collaboration between brands and stylists

[1200] The suggestions will reflect the styles recommended by the user's favorite brands and affiliated stylists, allowing for more personalized suggestions.

[1201] Processing Details

[1202] Hardware and Software Configuration

[1203] Smart glasses: Smart glasses such as HoloLens 2 are used and are equipped with a camera and voice input device.

[1204] Emotion recognition engine: Emotion analysis is performed using Azure Face API.

[1205] Generative AI model: We use OpenAI's GPT-4 to generate proposals.

[1206] Database: We use Microsoft Azure SQL Database to manage user information and feedback.

[1207] Data processing and calculation

[1208] 1. Enter and submit user information

[1209] The characteristic information entered by the user is sent from the device to the server and stored in Azure SQL Database.

[1210] 2. Emotion recognition

[1211] Facial images and voice data of the user trying on the items are captured by the camera and microphone of the smart glasses, and emotion analysis is performed using the Azure Face API.

[1212] 3. Proposal generation

[1213] The server accesses Azure SQL Database to retrieve stored user information and real-time emotion data.

[1214] This data is then input into the generative AI model GPT-4 to suggest the optimal fashion style.

[1215] 4. Submitting and Viewing Proposals

[1216] The generated suggestions are sent from the server to smart glasses or other devices and displayed to the user.

[1217] 5. Gathering Feedback

[1218] User feedback is sent from the device to the server, stored in Azure SQL Database, and used to improve the accuracy of the next suggestion.

[1219] Specific examples

[1220] Consider the "Style Guide Glasses" application in action. When a user tries on a dress in a store, the smart glasses capture the user's face and recognize their smile using the Azure Face API. This information is sent to a server, where, combined with stored profile information such as hair type and face shape, GPT-4 generates suggestions such as "What shoes would go well with this dress?" and displays them on the smart glasses' display.

[1221] Prompt Sentence Examples

[1222] Send a prompt like this to your generative AI model:

[1223] User profile information:

[1224] Hair type: Straight, Face shape: Oval, Skin tone: Olive, Desired style: Casual

[1225] Emotion data: Smile (positive)

[1226] Previous suggestion feedback: I liked it

[1227] Generate a proposal.

[1228] This concludes the detailed description of the invention, which allows users to receive more personalized, emotion-based fashion suggestions.

[1229] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1230] Step 1:

[1231] Users input their individual characteristics, such as hair type, face shape, skin color, and desired style, through a smartphone or smart glasses device, which then collects this information and sends it to a server.

[1232] Step 2:

[1233] The server receives the user characteristic information sent from the device, validates the received information (checks the format and range), and stores it in Azure SQL Database if there are no problems.

[1234] Step 3:

[1235] A user tries on fashion items in a physical store. The camera in the smart glasses captures the user's facial image and the microphone records the user's voice. This data is sent in real time to an emotion recognition engine (Azure Face API).

[1236] Step 4:

[1237] Using Azure Face API, the user's facial image and voice data are analyzed to obtain emotional data (e.g., smile, surprise, sadness), which is then transmitted from the smart glasses to the server.

[1238] Step 5:

[1239] The server combines the received emotion data with pre-stored user feature information. Based on this data, it creates a prompt for the generative AI model (GPT-4) and sends it as input data. An example of a specific prompt is as follows:

[1240] User profile information:

[1241] Hair type: Straight, Face shape: Oval, Skin tone: Olive, Desired style: Casual

[1242] Emotion data: Smile (positive)

[1243] Previous suggestion feedback: I liked it

[1244] Generate a proposal.

[1245] Step 6:

[1246] The generative AI model generates optimal fashion style suggestions based on the received prompt. These suggestions are returned to the server as text data. For example, a suggestion like, "How about some shoes that match this dress?"

[1247] Step 7:

[1248] The server receives the suggestions from the generative AI model and sends them to a device such as smart glasses or a smartphone, which then visually displays the received suggestions to the user.

[1249] Step 8:

[1250] The user can input feedback about the proposed fashion style, such as "I like it" or "I'd like you to suggest a more casual style" using the terminal.

[1251] Step 9:

[1252] The device sends user feedback to the server, which stores it in Azure SQL Database and uses it as training data for the generative AI model when generating the next recommendation.

[1253] This concludes the processing flow of the system program for implementing this application example, which allows users to receive personalized fashion suggestions in real time and collects feedback to improve the accuracy of the suggestions.

[1254] 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.

[1255] 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.

[1256] 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.

[1257] [Fourth embodiment]

[1258] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1259] 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.

[1260] 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).

[1261] 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.

[1262] 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.

[1263] 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).

[1264] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1265] 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.

[1266] 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.

[1267] 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.

[1268] 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.

[1269] 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.

[1270] 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."

[1271] ---

[1272] The present invention includes a hairstyle and fashion suggestion system called Style Core. This system is designed to provide users with hairstyles and fashion styles that are optimal for them, with the server, terminals, and users working together.

[1273] Overall system configuration

[1274] The system is implemented primarily by the following components:

[1275] 1. Entering user information: The user enters their individual characteristics (hair type, face shape, skin color, desired style, etc.) into the terminal.

[1276] 2. Transmission and storage of information: The information entered by the user is transmitted from the terminal to the server and stored in the server's database.

[1277] 3. Utilizing generative AI models: The server uses generative AI models based on stored user information to suggest optimal hairstyles and fashions.

[1278] 4. Sending and displaying proposals: The generated proposals are sent from the server to the terminal and displayed on the terminal.

[1279] 5. Feedback collection: Users provide feedback on the proposals, which is sent to the server, stored in a database, and used as training data for the generative AI model.

[1280] 6. Brand and stylist collaboration: Suggestions include ways to reflect the styles of brands and affiliated stylists that users frequent.

[1281] Program processing and specific examples

[1282] Below, the program processing in each component will be explained in natural language with specific examples.

[1283] Entering user information

[1284] Users access the Style Core application using a device such as a smartphone or PC, and enter information such as their hair type (e.g., straight hair), face shape (e.g., oval), skin color (e.g., olive skin), and desired style (e.g., casual) into a form displayed on the application screen.

[1285] Sending and storing information

[1286] When the user presses the "Submit" button, the terminal sends the entered information to the server, which receives it, validates it, and stores it in the database.

[1287] Leveraging generative AI models

[1288] The server launches a generative AI model based on the saved user information. The generative AI model learns the latest trends and design knowledge, and uses that information to generate optimal hairstyle and fashion suggestions for the user. For example, for a user with straight hair and an oval face, it might suggest a "short haircut with bangs" and a "casual striped shirt."

[1289] Submitting and Viewing Proposals

[1290] The server sends the generated suggestions to the user's device, which receives and analyzes them and then displays them on the application screen, where the user can check the suggested hairstyles and fashions.

[1291] Gathering feedback

[1292] Users can provide feedback on the proposed styles within the application, such as "I like it" or "I'd like a more casual style." The device sends this feedback to the server, which receives it and stores it in a database. The stored feedback is used as training data for the generative AI model.

[1293] Collaboration with brands and stylists

[1294] The server integrates information about the user's favorite brands and affiliated stylists as training data into the generative AI model, allowing suggestions to reflect items recommended by brands and stylists familiar to the user.

[1295] ---

[1296] The above is an embodiment of the present invention. This allows users to easily find hairstyles and fashion styles that suit them best, and it is expected that the accuracy of personalized suggestions will be further improved based on feedback.

[1297] The processing flow will be explained below.

[1298] Okay, so let's break down the program's processing into specific steps.

[1299] Step 1: User accesses the system

[1300] Users launch the StyleCore application from a device such as a smartphone or PC.

[1301] Step 2: User Enters Information

[1302] The user enters individual characteristics such as their hair type (e.g., straight hair), face shape (e.g., oval), skin color (e.g., olive skin), and desired style (e.g., casual) into a form on the application screen.

[1303] Step 3: The device sends the information

[1304] When the user enters information and presses the "send" button, the terminal sends the information to the server.

[1305] Step 4: The server receives and stores the information

[1306] The server receives the user information, checks the integrity of the data, and then stores it in the database. A validation process is performed to check for inappropriate data.

[1307] Step 5: The server launches the generative AI model

[1308] The server then launches a generative AI model based on the stored user information, which is trained on the latest trends and design knowledge.

[1309] Step 6: The server inputs the data into the generative AI model

[1310] The server inputs user information into a generative AI model, which then generates optimal hairstyle and fashion suggestions based on the user's characteristics.

[1311] Step 7: The server retrieves the generated proposal

[1312] The server receives the recommendations output by the generative AI model, such as a "short haircut with bangs" and a "casual striped shirt."

[1313] Step 8: Server sends proposal

[1314] The server then sends the generated suggestions to the user's device, often in a format such as JSON.

[1315] Step 9: Your device receives and displays the proposal

[1316] The device receives the suggestions sent from the server, analyzes them, and displays them on the application screen, where the user can check the suggested hairstyles and fashions.

[1317] Step 10: User Enters Feedback

[1318] Users can input their evaluations and opinions on the suggestions, such as "I like it" or "I'd like a more casual style."

[1319] Step 11: Device sends feedback

[1320] When the user inputs feedback and presses the "send" button, the terminal sends the feedback to the server.

[1321] Step 12: Server receives and stores feedback

[1322] The server receives the feedback and stores it in a database, which is later used as training data for the generative AI model.

[1323] Step 13: The server learns the brand and stylist information

[1324] The server collects information about the user's favorite brands and affiliated stylists and integrates it into a generative AI model.

[1325] Step 14: Your server will then reflect on your recommendations with compatible brands and stylists.

[1326] The server uses the generative AI model to generate recommendations based on the styles of brands and stylists familiar to the user, resulting in more accurate recommendations for the user.

[1327] The above is a description of the specific operation of each processing step in the Style Core system.

[1328] Example 1

[1329] 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."

[1330] The present invention relates to a system that proposes optimal hairstyles and fashions based on the individual characteristics of each user. Conventional proposal systems have difficulty responding to individual user characteristics in detail, and have faced challenges in improving the accuracy of proposals that appropriately reflect user feedback. In addition, it has been difficult to reflect the proposals of brands and stylists that users are familiar with, which has prevented users from achieving sufficient satisfaction. The present invention aims to solve these problems.

[1331] 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.

[1332] In this invention, the server includes means for a user to input individual characteristics, means for transmitting the input characteristics to a processing device, means for storing the characteristics in the processing device, means for generating proposals using a generative AI model based on the characteristics, means for providing the generated proposals to a user, means for collecting user feedback on the proposals, means for reflecting the collected feedback in the generative AI model, means for analyzing and displaying the proposal content, and means for validating the user's personal information in a database of the processing device. This enables highly accurate proposals based on the user's individual characteristics, improves the accuracy of proposals based on feedback, and further enables proposals that reflect styles recommended by brands and stylists familiar to the user.

[1333] "User" refers to an individual who utilizes the system to input their characteristics and receive suggestions.

[1334] "Characteristics" refers to personal information about a user, including hair type, face shape, skin color, desired style, and the like.

[1335] "Processing device" refers to hardware or software that receives, stores, and processes data sent by a user.

[1336] A "generative AI model" refers to an artificial intelligence model that generates optimal hairstyle and fashion suggestions based on a user's characteristics.

[1337] "Suggestions" refers to recommendations about hairstyles and fashion that are generated based on the user's characteristics using a generative AI model.

[1338] "Feedback" refers to the opinions and thoughts that users provide regarding suggestions.

[1339] "Validation" refers to the process of verifying that received data has the correct format and content.

[1340] "Database" refers to an information storage system for storing user characteristics and feedback.

[1341] A "brand" refers to a sign or name that identifies the products or services offered by a particular company or organization.

[1342] A "stylist" is a professional who gives advice and suggestions regarding fashion and hairstyles.

[1343] "Terminal" refers to a device, such as a computer or smartphone, that a user uses to access the system.

[1344] "User interface" refers to the screens and operating means that users use to operate a system.

[1345] "Communication protocol" refers to the rules and procedures used between a terminal and a server to send and receive information.

[1346] An "HTTP request" refers to the communication format used by a web browser or application to request data from a server or server.

[1347] "JSON format" is a lightweight data exchange format that is easy for humans to read and machines to parse.

[1348] A "trained neural network" refers to an artificial intelligence model that has been trained using a specific dataset.

[1349] This invention is a system that suggests optimal hairstyles and fashion styles to users, and this system makes suggestions using a generative AI model based on the user's characteristics. Users can access the system using a device such as a smartphone or PC and receive suggestions by inputting their own characteristics.

[1350] Overall system configuration

[1351] The system consists of the following main components:

[1352] 1. Enter your user information

[1353] 2. Transmission and storage of information

[1354] 3. Utilizing generative AI models

[1355] 4. Submitting and Displaying Proposals

[1356] 5. Gathering Feedback

[1357] 6. Collaboration with brands and stylists

[1358] Specific actions

[1359] The specific operation of each element will be described below.

[1360] Entering user information

[1361] Users input their own characteristic information (hair type, face shape, skin color, desired style, etc.) via a device such as a smartphone or PC. This information is then input and used by the user through an application on the device.

[1362] Sending and storing information

[1363] The characteristic information entered by the user is sent from the terminal to the server. The server validates the received data, confirming that it is in the correct format and content, and then stores it in a database. The database used here is a commonly used relational database (e.g., MySQL, PostgreSQL).

[1364] Leveraging generative AI models

[1365] The server then launches a generative AI model based on the stored user information. This model is built using machine learning frameworks such as TensorFlow and PyTorch, and makes suggestions for optimal hairstyles and fashion based on the user's characteristics. For example, suggestions are generated for information such as "straight hair," "oval face," "olive skin," and "casual style."

[1366] As a concrete example, the following prompt sentence is input to the generative AI model:

[1367] "Please suggest the best casual hairstyle and fashion for a user with straight hair, an oval face, and olive skin."

[1368] Submitting and Viewing Proposals

[1369] The server sends the generated suggestions to the user's device, which receives them, analyzes them, and displays them on the application screen. The user can then check the suggested hairstyles and fashions, and save or share them as needed.

[1370] Gathering feedback

[1371] Users can input feedback on the suggestions and send it to the server via their devices. The server stores the received feedback in a database, and this feedback is used as training data for the generative AI model, thereby improving the accuracy of the suggestions made by the AI ​​model.

[1372] Collaboration with brands and stylists

[1373] The server can reflect the recommended styles of brands and affiliated stylists frequently used by the user in its suggestions. Specifically, by storing information on brand items and stylist suggestion history in a database and adding this information to the training data of the AI ​​model, the server can make suggestions that are familiar to the user.

[1374] In this way, users can use a system that suggests optimal hairstyles and fashion styles based on their individual characteristics, thereby increasing user satisfaction and improving the accuracy of suggestions.

[1375] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1376] Step 1: Enter your user information

[1377] The user launches the Style Core application using a device such as a smartphone or PC. The user enters their characteristic information (hair type, face shape, skin color, desired style, etc.) into a form displayed on the application screen. For example, the user enters specific information such as "straight hair," "oval face," "olive skin," and "casual style." This input information becomes the data sent to the server in the next step.

[1378] Step 2: Send and save information

[1379] Data entered by the user, including characteristic information, is sent from the terminal to the server. The data input is sent using an HTTP request. The server validates the received data to ensure that it is in the correct format and content. Data that passes validation is stored in the server's database. The database used here is a relational database such as MySQL or PostgreSQL.

[1380] Step 3: Leveraging generative AI models

[1381] The server launches a generative AI model based on the stored user feature information. The user's feature information (e.g., "straight hair," "oval face," "olive skin," and "casual style") is used as input. The generative AI model is built using frameworks such as TensorFlow and PyTorch. This AI model analyzes the input user feature information and generates optimal hairstyle and fashion suggestions. For example, it might generate suggestions such as "short haircut with bangs" and "casual striped shirt." As a concrete example, the following prompt sentence is input to the generative AI model:

[1382] "Please suggest the best casual hairstyle and fashion for a user with straight hair, an oval face, and olive skin."

[1383] Step 4: Submit and view your proposal

[1384] The suggestions created by the generative AI model are sent from the server to the device in data format such as JSON. The device analyzes the data received from the server and displays it on the user interface. On the display screen, the user can check the suggested hairstyle, fashion, and specific item information (e.g., a short haircut with bangs, a casual striped shirt). This allows the user to confirm the suggestions and proceed to the next step.

[1385] Step 5: Gather feedback

[1386] The user inputs their thoughts and opinions about the suggestions (e.g., "I like it," "I'd like a more casual style," etc.). The input feedback is sent from the device to the server. The server stores the received feedback data in a database. The feedback data is used as training data for the generative AI model. This improves the accuracy of the next suggestion.

[1387] Step 6: Collaborate with brands and stylists

[1388] The server integrates information about the user's favorite brands and affiliated stylists into the generative AI model. Specifically, it imports information about brand items and stylist recommendation history as learning data and stores it in a database. For example, it reflects the latest collections of brands frequently purchased by the user and recommended items from affiliated stylists in the database. This ensures that suggestions include items from brands and stylists familiar to the user.

[1389] The above are the processing steps of the system and their specific operations. Data processing and calculations are carried out at each step, resulting in a system that provides optimal suggestions to users.

[1390] (Application example 1)

[1391] 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."

[1392] Today, there are many systems that suggest the best hairstyles and fashions for individual users, but these systems require users to manually input their own characteristics. In addition, they cannot confirm the suggestions in real time, and the feedback loop to reflect the suggestions in reality is incomplete. This limits the user experience and reduces satisfaction.

[1393] 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.

[1394] In this invention, the server includes: means for a user to input individual features; means for transmitting the input features to the server; means for storing the features in the server; means for generating suggestions using a generative AI model based on the features; means for providing the generated suggestions to the user; means for collecting user feedback on the suggestions; means for reflecting the collected feedback in the generative AI model; a camera for recognizing the user's features; means for transmitting data collected by the camera to a cloud server; means for the cloud server to analyze the data using the generative AI model and generate suggestions; and means for displaying the suggestions on the user's visual device in real time. This allows the user to see optimal hairstyle and fashion suggestions in real time without having to manually input their own features, and further allows feedback based on the suggestions to be reflected in the generative AI model.

[1395] "User" refers to a person who uses the system to receive hairstyle and fashion suggestions.

[1396] "Characteristics" refers to individual information such as the user's hair type, face shape, skin color, and desired style.

[1397] "Means" refers to a method or apparatus for achieving a specific function or operation.

[1398] "Server" refers to a device or system that receives and stores information sent by users and generates and provides suggestions using generative AI models.

[1399] A "generative AI model" refers to an artificial intelligence model that generates optimal hairstyle and fashion suggestions based on training data.

[1400] "Camera" refers to a photographic device for collecting data on a user's face and body.

[1401] "Cloud Server" refers to the remote server that analyzes the collected data and generates and sends recommendations to users.

[1402] A "visual device" is a device for displaying suggestions to a user, such as smart glasses.

[1403] System Overview

[1404] The present invention relates to a style suggestion system, specifically a system that recognizes a user's individual characteristics and uses a generative AI model to suggest optimal hairstyles and fashions. The system operates by including a user terminal, a server, and a visual device (e.g., smart glasses).

[1405] Program processing and natural language explanation

[1406] User information entry and automatic collection

[1407] The user wears the vision device and activates the system. The camera on the vision device captures the user's facial and body features in real time, and the data is sent from the user's device to a cloud server. This process uses facial recognition software (e.g., OpenCV).

[1408] Analyzing information and generating recommendations

[1409] The cloud server stores the received feature data and inputs it into a generative AI model (e.g., TensorFlow). The generative AI model generates optimal hairstyle and fashion suggestions based on the stored user feature data. For example, for a user with straight hair and an oval face, it might suggest a "short haircut with bangs" and a "casual striped shirt."

[1410] Submitting and Viewing Proposals

[1411] The cloud server sends the generated suggestions to the user's visual device in real time, where the visual device analyzes the received suggestions and displays them to the user. The user can then check the suggested hairstyles and fashions as if looking in a mirror through the visual device.

[1412] Gathering and implementing feedback

[1413] When the user provides feedback on the suggestions via the visual device, the feedback is again sent to the cloud server and stored, where it is used as training data for the generative AI model to improve the accuracy of subsequent suggestions.

[1414] Specific hardware and software names used

[1415] Hardware:

[1416] Smart glasses (e.g., general-purpose smart glasses devices)

[1417] camera

[1418] Cloud Server

[1419] software:

[1420] Facial recognition software (e.g. OpenCV)

[1421] AI models (e.g. TensorFlow)

[1422] Cloud services (e.g. AWS, GCP)

[1423] Front-end applications (e.g. HTML5, JavaScript)

[1424] Examples and prompts

[1425] For example, smart glasses automatically activate when a user enters a store and perform facial recognition. At this time, the following prompt sentence is input to the generative AI model:

[1426] "Based on the client's characteristics, suggest hairstyles and casual styles that would suit someone with straight hair and an oval face."

[1427] The generative AI model generates suggestions based on this prompt and displays them on a visual device, allowing users to see the best hairstyles and fashions in real time.

[1428] summary

[1429] The system automatically collects users' personal characteristics and allows them to receive personalized style suggestions in real time, while incorporating user feedback into the generative AI model to continuously improve the accuracy of the suggestions.

[1430] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1431] Step 1:

[1432] The user puts on the smart glasses and activates the system. The camera in the smart glasses captures the user's facial and body features and sends this data to the user's device. The input data is facial images and body proportion information, which are then analyzed in subsequent processing steps.

[1433] Step 2:

[1434] The user device transmits the captured feature data to the cloud server. This transmission process involves data conversion and compression. Specifically, the image data is converted to JPEG format and compressed for efficient transmission over the network. The input data is the captured image data, and the output is compressed image data.

[1435] Step 3:

[1436] The cloud server stores the received feature data in a database. At the same time, it analyzes the image data using facial recognition software (e.g., OpenCV). This analysis process extracts characteristics such as facial shape, hair type, and skin color. The input data is compressed image data, and the output data is analyzed feature data.

[1437] Step 4:

[1438] The cloud server inputs the analyzed feature data into the generative AI model. To create this prompt, text data is generated, such as "Please suggest a hairstyle and fashion that would suit a user with straight hair and an oval face." The generative AI model then generates optimal hairstyle and fashion suggestions based on this prompt. The input data is the analyzed feature data, and the output is optimal suggestion data.

[1439] Step 5:

[1440] The cloud server transmits the generated proposal data to the user's visual device in real time. Specifically, the proposal data is encoded using a dedicated protocol and transmitted to the visual device. The input data is the proposal data, and the output is the encoded data.

[1441] Step 6:

[1442] The visual device decodes the received suggestion data and displays it to the user. The user can check the suggested hairstyle and fashion on their own image. The input data is the encoded suggestion data, and the output is a display for the user's vision.

[1443] Step 7:

[1444] The user inputs feedback on the suggestions through a visual device. For example, they input opinions such as "cut your bangs a little shorter" or "dress more casually." The input data is the user's feedback, and the output is feedback data.

[1445] Step 8:

[1446] The vision device sends feedback data to a cloud server, which stores the received feedback in a database and uses it as training data for the generative AI model. This process improves the accuracy of subsequent suggestions. The input data is the feedback data, and the output is the stored data.

[1447] 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.

[1448] ---

[1449] This invention shows an embodiment for implementing "Style Core," a system that suggests optimal hairstyles and fashions based on the individual characteristics of a user. This system operates in cooperation with a server, terminals, and users, and by combining it with an emotion engine that recognizes the user's emotions, it achieves more accurate style suggestions and feedback collection.

[1450] Overall system configuration

[1451] The system is implemented by the following components:

[1452] 1. Input of user information: The user inputs his / her individual characteristics from the terminal.

[1453] 2. Sending and saving information: The device sends the entered information to the server, which saves it in a database.

[1454] 3. Utilizing generative AI models: The server generates suggestions using generative AI models based on the stored user information.

[1455] 4. Sending and displaying the proposal: The server sends the generated proposal to the terminal and it is displayed on the user's terminal.

[1456] 5. Feedback collection: The user provides feedback on the proposal, which is sent to the server and stored in a database.

[1457] 6. Collaboration with brands and stylists: Suggestions will reflect the recommended styles of brands and affiliated stylists that users frequently use.

[1458] 7. Utilizing an emotion engine: An emotion engine is used to recognize the user's emotions and reflect the results in the suggestions.

[1459] Program processing and specific examples

[1460] Below, the program processing in each component will be explained in natural language with specific examples.

[1461] Entering user information

[1462] Users access the Style Core application using a device such as a smartphone or PC, and enter information such as their hair type (e.g., straight hair), face shape (e.g., oval), skin color (e.g., olive skin), and desired style (e.g., casual) into the application form screen.

[1463] Sending and storing information

[1464] When the user presses the "Submit" button, the terminal sends the entered information to the server, which receives the information, validates it, and stores it in the database.

[1465] Leveraging generative AI models

[1466] The server launches a generative AI model based on the saved user information. The generative AI model learns the latest trends and design knowledge and generates optimal hairstyle and fashion suggestions based on the user information. For example, for a user with straight hair and an oval face, it would suggest a "short haircut with bangs" and a "casual striped shirt."

[1467] Submitting and Viewing Proposals

[1468] The server sends the generated suggestions to the user's device, which receives them and displays them on the application screen, where the user can check the suggested hairstyles and fashions.

[1469] Gathering feedback

[1470] Users can provide feedback on the suggested styles, such as "I like it" or "I'd like a more casual style." The device then sends this feedback to the server, which receives it and stores it in a database. The feedback is then used as training data for the generative AI model.

[1471] Collaboration with brands and stylists

[1472] The server integrates information about the user's favorite brands and affiliated stylists as training data into the generative AI model, allowing suggestions to reflect items recommended by brands and stylists familiar to the user.

[1473] Utilizing the Emotion Engine

[1474] The device is equipped with an emotion engine that recognizes emotions through the user's facial expressions and voice. The recognized emotion data is sent to a server, which then uses the data to adjust the generative AI model. For example, if the user smiles when viewing a suggestion, the emotion data is added to the feedback as a signal that the suggestion has been accepted. In this way, the suggestions are further personalized.

[1475] ---

[1476] The above is an embodiment of the present invention. This allows users to receive personalized suggestions for hairstyles and fashion styles based on their emotions. Furthermore, it is expected that the accuracy of suggestions will be further improved based on feedback.

[1477] The processing flow will be explained below.

[1478] Step 1: User accesses the system

[1479] Users launch StyleCore applications using devices such as smartphones and PCs.

[1480] Step 2: User Enters Information

[1481] The user enters their individual characteristics, such as their hair type (e.g., straight hair), face shape (e.g., oval), skin color (e.g., olive skin), and desired style (e.g., casual), into the application's form screen.

[1482] Step 3: The device sends the information

[1483] When the user inputs information and presses the "send" button, the terminal sends the input information to the server.

[1484] Step 4: The server receives and stores the information

[1485] The server receives the submitted user information, checks the data for consistency, and stores it in a database, for example by validating that the hair type is specified correctly and that the face shape is within the valid options.

[1486] Step 5: The server launches the generative AI model

[1487] The server then launches a generative AI model based on the stored user information, which uses the trend data and design knowledge it has learned to generate optimal hairstyle and fashion suggestions.

[1488] Step 6: The server inputs the data into the generative AI model

[1489] The server inputs user information into a generative AI model, which takes into account the user's hair type, face shape, skin color, etc. to calculate and generate optimal style suggestions.

[1490] Step 7: The server retrieves the generated proposal

[1491] The server receives the output of the generative AI model, generating specific style suggestions such as a "short haircut with bangs" and a "casual striped shirt."

[1492] Step 8: Server sends proposal

[1493] The server sends the generated proposal to the user's device, formatted in JSON or similar.

[1494] Step 9: Your device receives and displays the proposal

[1495] The device receives the suggestions sent from the server, analyzes them, and displays them on the application screen, where the user can check the suggested hairstyles and fashions.

[1496] Step 10: User Enters Feedback

[1497] Users can then rate and comment on the suggestions within the application, for example by entering feedback such as "I like it" or "I'd like a more casual style."

[1498] Step 11: Device sends feedback

[1499] When the user inputs feedback and presses the "send" button, the terminal sends the feedback to the server.

[1500] Step 12: Server receives and stores feedback

[1501] The server receives the feedback and stores it in a database, which is later used as training data for the generative AI model.

[1502] Step 13: The server learns the brand and stylist information

[1503] The server collects information about the user's favorite brands and affiliated stylists, stores it in a database, and then integrates this information into a generative AI model for training.

[1504] Step 14: Your server will then reflect on your recommendations with compatible brands and stylists.

[1505] The server uses a generative AI model to generate suggestions that reflect the brands and stylists familiar to the user, for example, by providing suggestions that include the latest collections from brands the user frequently purchases.

[1506] Step 15: Device captures real-time emotions

[1507] The device is equipped with an emotion engine that recognizes emotions through the user's real-time facial expressions and voice, for example, by using a camera and microphone to detect the user's smile and tone of voice.

[1508] Step 16: The device sends emotion data

[1509] The device sends the recognized emotion data to the server. For example, if the device recognizes a smile or a voice of joy from the user, the data is sent to the server.

[1510] Step 17: The server reflects the emotion data in the generative AI model

[1511] The server then feeds the received emotion data into the generative AI model, which then further adjusts the suggestions based on the user's emotion. If the emotion data is positive, the feedback is considered a positive evaluation.

[1512] The above is a concrete explanation of the operation of each processing step in the style core system including the emotion engine.

[1513] Example 2

[1514] 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."

[1515] Conventional style suggestion systems have difficulty providing personalized suggestions based on the individual characteristics of each user, which has led to issues with not being able to sufficiently increase user satisfaction. Furthermore, they lacked the functionality to appropriately reflect user feedback and emotions, making it impossible to improve the accuracy of suggestions for the next time. Furthermore, they were unable to reflect the recommended styles of brands frequently used by users or affiliated stylists in the suggestions, making it impossible to realize suggestions tailored to the user's preferences.

[1516] 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.

[1517] In this invention, the server includes means for a user to input individual features, means for transmitting the input features to the server, means for storing the features in the server, means for generating suggestions using a generative AI model based on the features, means for providing the generated suggestions to the user, means for collecting user feedback on the suggestions, means for reflecting the collected feedback in the generative AI model, and means for recognizing user emotions using an emotion engine and reflecting the emotions in the generated suggestions. This enables more personalized style suggestions based on the user's features, emotions, and past feedback.

[1518] "Characteristics" refers to individual attribute information such as the user's hair type, face shape, skin color, and desired style.

[1519] "Server" refers to a computer system for receiving, storing, and processing data from users.

[1520] "Generative AI model" refers to an artificial intelligence model designed to generate optimal suggestions based on user characteristics.

[1521] "Suggestion" refers to the recommendation of hairstyle or fashion style that the generative AI model generates based on the user's characteristics.

[1522] "Feedback" refers to reactions such as satisfaction, opinions, and requests provided by users in response to suggestions.

[1523] An "emotion engine" is an engine that recognizes emotions from the user's facial expressions and voice, and reflects that data in a generative AI model.

[1524] A "terminal" is a device that a user uses to input information or check suggestions, such as a smartphone or computer.

[1525] "Database" refers to the data storage system used by the Server to store and manage user characteristics and feedback.

[1526] "Brand" refers to the manufacturer or retailer that the user frequently uses.

[1527] A "stylist" is a professional who suggests hairstyles and fashion styles.

[1528] MODE FOR CARRYING OUT THE INVENTION

[1529] The present invention is a system that suggests optimal hairstyles and fashions based on the individual characteristics of a user, and detailed embodiments thereof are described below. This system operates in cooperation with a server, terminal, and user, and by combining it with an emotion engine that recognizes the user's emotions, it achieves more accurate style suggestions and feedback collection.

[1530] Overall system configuration

[1531] The system is implemented by the following components:

[1532] 1. A terminal for inputting user information

[1533] 2. Server that receives, processes, and stores information

[1534] 3. Generative AI model that generates suggestions

[1535] 4. Emotion engine that recognizes user emotions

[1536] Details of each component

[1537] Entering user information

[1538] Users access the Style Core application using a device such as a smartphone or PC. They enter information such as their hair type (e.g., straight hair), face shape (e.g., oval), skin color (e.g., olive skin), and desired style (e.g., casual) into the application's form screen. This information is entered through the application's user interface, and the user proceeds to the next step by pressing the submit button.

[1539] Sending and storing information

[1540] When the user presses the "Send" button, the terminal sends the entered information to the server. The server receives the sent information and checks (validates) the validity of the data format. Information that passes this check is saved in the database.

[1541] Leveraging generative AI models

[1542] The server launches a generative AI model based on the saved user information. The generative AI model learns the latest trends and fashion designs to generate optimal suggestions based on the conditions obtained from the user. For example, the server passes the following prompt text to the generative AI model: "The user's hair type is straight, their face shape is oval, their skin color is olive, and their desired style is casual. Please suggest the best hairstyle and fashion for this user."

[1543] Submitting and Viewing Proposals

[1544] The generated suggestions are sent from the server to the user's device, which receives them and displays them on the application screen, where the user can check in detail the hairstyles and fashions suggested by the generative AI model.

[1545] Gathering feedback

[1546] Users can provide feedback on the suggested styles, for example by rating "how satisfied I am with the suggested styles" on a scale of 1 to 5, or by entering specific requests in text, such as "I would like a more casual style." The device then sends this feedback data to the server, which stores the received feedback in a database. This feedback is then used as training data for the generative AI model.

[1547] Collaboration with brands and stylists

[1548] The server analyzes the user's past usage history and feedback information, and incorporates the user's preferred brands and the styles of affiliated stylists into the generative AI model as learning data, so that the next recommendation will include items recommended by brands and stylists familiar to the user.

[1549] Utilizing the Emotion Engine

[1550] The user's device is equipped with an emotion engine that analyzes the user's facial expressions and voice in real time via the built-in camera and microphone. For example, the emotion engine recognizes and analyzes changes in facial expression (e.g., smile or frown) and tone of voice (e.g., joy or dissatisfaction) when the user sees a proposed style. This emotion data is sent to the server in real time, and the server uses this data to adjust the generative AI model. For example, data is fed back so that information that indicates the user's satisfaction is reflected in the next proposal generation.

[1551] Specific examples

[1552] As a concrete example, suppose a user inputs the following information: hair type "straight hair," face shape "oval," skin color "olive skin," and desired style "casual." The information is sent from the device to the server, where it is saved, and then the generative AI model is launched. The server passes a prompt to the generative AI model, which displays the results on the user's device. The suggestions are "short haircut with bangs" and "casual striped shirt," which the user confirms on the device.

[1553] The user enters feedback on the suggestion, such as "I want a more casual style," and the device sends this feedback to the server. The server also collects the user's facial expression data from the emotion engine and reflects it in the generative AI model. The next suggestion will be further adjusted to better suit the user's preferences.

[1554] Example of a text prompt:

[1555] "This user has straight hair, an oval face, olive skin, and a casual style. What hairstyle and outfit would be best for this user?"

[1556] In this way, users can receive more personalized hairstyle and fashion style suggestions based on their emotions, and the accuracy of the suggestions can be improved based on feedback and emotional data.

[1557] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1558] Step 1:

[1559] Users access the Style Core application through a device such as a smartphone or PC. They enter information into a form screen, such as hair type (e.g., straight hair), face shape (e.g., oval), skin color (e.g., olive skin), and desired style (e.g., casual). This input data is collected using text boxes and drop-down menus in the application.

[1560] Input: Your individual characteristics (hair type, face shape, skin color, desired style)

[1561] Output: A dataset of the input features

[1562] Step 2:

[1563] When the user presses the "Submit" button, the terminal sends the entered information to the server. The server receives the sent information and checks the validity of the data format (validation). Information that passes validation is saved in the database.

[1564] Input: A dataset of input features

[1565] Output: Validated feature dataset (stored in a database)

[1566] Step 3:

[1567] The server launches a generative AI model based on the validated user information. The server passes the following prompt text to the generative AI model: "The user's hair type is straight, their face shape is oval, their skin color is olive, and their desired style is casual. Please suggest the best hairstyle and fashion for this user." The generative AI model processes and analyzes the data based on this prompt text, and generates optimal hairstyle and fashion suggestions.

[1568] Input: Validated feature dataset, prompt statement

[1569] Output: Data proposed by the generative AI model

[1570] Step 4:

[1571] The generated suggestion data is sent from the server to the user's device. The device receives the suggestion data and displays it on the application screen. Here, the user can check in detail the hairstyle and fashion suggested by the generative AI model.

[1572] Input: Data proposed by the generative AI model

[1573] Output: Proposal displayed on the device

[1574] Step 5:

[1575] The user provides feedback on the proposed style. For example, they input a specific request such as "I want a more casual style" and their satisfaction rating. The device sends this feedback data to the server, which then stores it in a database.

[1576] Input: User feedback on the proposal

[1577] Output: Saved feedback data

[1578] Step 6:

[1579] The server analyzes past usage history and feedback data and reflects it in the generative AI model. It processes and aggregates the data as necessary. This allows the generative AI model to learn the user's preferences and habits and reflect them in future suggestions.

[1580] Input: usage history data, feedback data

[1581] Output: A tuned and updated generative AI model

[1582] Step 7:

[1583] The user's device is equipped with an emotion engine that analyzes the user's facial expressions and voice in real time through the built-in camera and microphone. The emotion engine recognizes the user's emotions (e.g., joy, surprise, sadness) and sends the data to a server. The server then applies the emotion data to a generative AI model to provide more personalized suggestions.

[1584] Input: User's facial expression data, voice data

[1585] Output: Adjusting suggestions based on sentiment data

[1586] These are the specific program processing steps of this system. At each step, the user, device, and server play their respective roles, resulting in highly accurate style suggestions as a whole.

[1587] (Application example 2)

[1588] 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."

[1589] Conventional fashion suggestion systems make suggestions based on the user's individual characteristics, but they are unable to consider the user's emotions or real-time reactions, making it difficult to generate suggestions that truly satisfy the user. In particular, in the shopping experience at a physical store, it is necessary to reflect the user's emotions and feedback immediately. Our goal is to solve this problem and provide a system that allows users to receive more personalized, emotion-based suggestions.

[1590] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for a user to input individual characteristics, means for transmitting the input characteristics to the server, means for storing the characteristics in the server, means for generating proposals using a generative AI model based on the characteristics, means for providing the generated proposals to the user, means for collecting user feedback on the proposals, means for reflecting the collected feedback in the generative AI model, and means for analyzing the user's emotions using an emotion recognition engine and reflecting the emotions in the generative AI model. This makes it possible to realize more appropriate and personalized fashion proposals based on the user's individual characteristics and real-time emotional reactions.

[1591] "User individual characteristics" are individual identifying information input by the user or obtained by the system, such as hair type, face shape, skin color, desired style, etc.

[1592] A "server" is a computer system that transmits, receives, stores, and processes data.

[1593] A "generative AI model" is an artificial intelligence algorithm that uses machine learning to generate suggestions based on user information.

[1594] "Suggestions" are hairstyle and fashion style recommendations generated by the generative AI model and provided to the user.

[1595] "Feedback" is information indicating opinions and reactions provided by users to suggestions.

[1596] An "emotion recognition engine" is software or hardware that analyzes a user's facial expressions and voice to recognize their emotions.

[1597] "User emotion data" is data that indicates the user's emotional state and is output as a result of analysis by the emotion recognition engine.

[1598] A "terminal" is an electronic device that a user operates, such as a smartphone, smart glasses, a personal computer, or a head-mounted display.

[1599] A "database" is a system that allows a server to systematically store and manage data.

[1600] The present invention provides a system that proposes optimal fashion styles based on the user's individual characteristics and emotions. This system is configured to realize a series of steps: inputting user characteristics, recognizing emotions, generating suggestions, and collecting feedback.

[1601] Overall system configuration

[1602] The system is implemented by the following components:

[1603] 1. Enter your user information

[1604] Using a device such as a smartphone or smart glasses, users input their individual characteristics into the application, such as hair type, face shape, skin color, and desired style, which is then sent to a server and stored in a database.

[1605] 2. Emotion recognition

[1606] While a user is trying on fashion items, the smart glasses' camera and voice recognition function are used to analyze their emotions in real time. The emotion recognition engine uses Azure Face API to capture facial expression data such as smiles and surprise.

[1607] 3. Proposal generation

[1608] The server uses a generative AI model (e.g., OpenAI's GPT-4) to generate optimal fashion style suggestions based on the stored user feature information and real-time emotion data, and the generated suggestions are sent to the smart glasses or other devices and displayed to the user.

[1609] 4. Gathering Feedback

[1610] Users provide feedback on their impressions and requests regarding the proposed style, which is then sent to the server and stored as training data for the generative AI model.

[1611] 5. Collaboration between brands and stylists

[1612] The suggestions will reflect the styles recommended by the user's favorite brands and affiliated stylists, allowing for more personalized suggestions.

[1613] Processing Details

[1614] Hardware and Software Configuration

[1615] Smart glasses: Smart glasses such as HoloLens 2 are used and are equipped with a camera and voice input device.

[1616] Emotion recognition engine: Emotion analysis is performed using Azure Face API.

[1617] Generative AI model: We use OpenAI's GPT-4 to generate proposals.

[1618] Database: We use Microsoft Azure SQL Database to manage user information and feedback.

[1619] Data processing and calculation

[1620] 1. Enter and submit user information

[1621] The characteristic information entered by the user is sent from the device to the server and stored in Azure SQL Database.

[1622] 2. Emotion recognition

[1623] Facial images and voice data of the user trying on the items are captured by the camera and microphone of the smart glasses, and emotion analysis is performed using the Azure Face API.

[1624] 3. Proposal generation

[1625] The server accesses Azure SQL Database to retrieve stored user information and real-time emotion data.

[1626] This data is then input into the generative AI model GPT-4 to suggest the optimal fashion style.

[1627] 4. Submitting and Viewing Proposals

[1628] The generated suggestions are sent from the server to smart glasses or other devices and displayed to the user.

[1629] 5. Gathering Feedback

[1630] User feedback is sent from the device to the server, stored in Azure SQL Database, and used to improve the accuracy of the next suggestion.

[1631] Specific examples

[1632] Consider the "Style Guide Glasses" application in action. When a user tries on a dress in a store, the smart glasses capture the user's face and recognize their smile using the Azure Face API. This information is sent to a server, where, combined with stored profile information such as hair type and face shape, GPT-4 generates suggestions such as "What shoes would go well with this dress?" and displays them on the smart glasses' display.

[1633] Prompt Sentence Examples

[1634] Send a prompt like this to your generative AI model:

[1635] User profile information:

[1636] Hair type: Straight, Face shape: Oval, Skin tone: Olive, Desired style: Casual

[1637] Emotion data: Smile (positive)

[1638] Previous suggestion feedback: I liked it

[1639] Generate a proposal.

[1640] This concludes the detailed description of the invention, which allows users to receive more personalized, emotion-based fashion suggestions.

[1641] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1642] Step 1:

[1643] Users input their individual characteristics, such as hair type, face shape, skin color, and desired style, through a smartphone or smart glasses device, which then collects this information and sends it to a server.

[1644] Step 2:

[1645] The server receives the user characteristic information sent from the device, validates the received information (checks the format and range), and stores it in Azure SQL Database if there are no problems.

[1646] Step 3:

[1647] A user tries on fashion items in a physical store. The camera in the smart glasses captures the user's facial image and the microphone records the user's voice. This data is sent in real time to an emotion recognition engine (Azure Face API).

[1648] Step 4:

[1649] Using Azure Face API, the user's facial image and voice data are analyzed to obtain emotional data (e.g., smile, surprise, sadness), which is then transmitted from the smart glasses to the server.

[1650] Step 5:

[1651] The server combines the received emotion data with pre-stored user feature information. Based on this data, it creates a prompt for the generative AI model (GPT-4) and sends it as input data. An example of a specific prompt is as follows:

[1652] User profile information:

[1653] Hair type: Straight, Face shape: Oval, Skin tone: Olive, Desired style: Casual

[1654] Emotion data: Smile (positive)

[1655] Previous suggestion feedback: I liked it

[1656] Generate a proposal.

[1657] Step 6:

[1658] The generative AI model generates optimal fashion style suggestions based on the received prompt. These suggestions are returned to the server as text data. For example, a suggestion like, "How about some shoes that match this dress?"

[1659] Step 7:

[1660] The server receives the suggestions from the generative AI model and sends them to a device such as smart glasses or a smartphone, which then visually displays the received suggestions to the user.

[1661] Step 8:

[1662] The user can input feedback about the proposed fashion style, such as "I like it" or "I'd like you to suggest a more casual style" using the terminal.

[1663] Step 9:

[1664] The device sends user feedback to the server, which stores it in Azure SQL Database and uses it as training data for the generative AI model when generating the next recommendation.

[1665] This concludes the processing flow of the system program for implementing this application example, which allows users to receive personalized fashion suggestions in real time and collects feedback to improve the accuracy of the suggestions.

[1666] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1667] 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.

[1668] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1669] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1670] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1671] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1672] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1673] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1674] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1675] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1676] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1677] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1678] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1679] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1680] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1681] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1682] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1683] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1684] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1685] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1686] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1687] The following is further disclosed regarding the above embodiment.

[1688] (Claim 1)

[1689] a means for a user to input individual characteristics;

[1690] means for transmitting the input characteristics to a server;

[1691] means for storing said characteristics on a server;

[1692] means for generating suggestions using a generative AI model based on the features;

[1693] means for providing the generated suggestions to a user;

[1694] means for collecting user feedback on said suggestions;

[1695] A means for incorporating the collected feedback into a generative AI model;

[1696] A system including:

[1697] (Claim 2)

[1698] The system according to claim 1, further comprising means for reflecting in the suggestions recommended styles of brands frequently used by the user and affiliated stylists.

[1699] (Claim 3)

[1700] means for inputting data based on the features into a generative AI model;

[1701] means for transmitting the generated proposal to a user's terminal;

[1702] 2. The system of claim 1, wherein the terminal includes means for displaying the transmitted proposal.

[1703] "Example 1"

[1704] (Claim 1)

[1705] a means for a user to input individual characteristics;

[1706] means for transmitting the input characteristics to a processing unit;

[1707] means for storing said characteristics in a processing device;

[1708] means for generating suggestions using a generative AI model based on the features;

[1709] means for providing the generated suggestions to a user;

[1710] means for collecting user feedback on said suggestions;

[1711] A means for incorporating the collected feedback into a generative AI model;

[1712] a means for analyzing and displaying the proposal;

[1713] means for validating the user's personal information in a database of the processing device;

[1714] A system including:

[1715] (Claim 2)

[1716] The system according to claim 1, further comprising means for reflecting in the suggestions recommended styles of brands frequently used by the user and affiliated stylists.

[1717] (Claim 3)

[1718] means for inputting data based on the features into a generative AI model;

[1719] means for transmitting the generated proposal to a user's terminal;

[1720] 2. The system of claim 1, wherein the terminal includes means for displaying the transmitted proposal.

[1721] "Application Example 1"

[1722] (Claim 1)

[1723] a means for a user to input individual characteristics;

[1724] means for transmitting the input characteristics to a server;

[1725] means for storing said characteristics on a server;

[1726] means for generating suggestions using a generative AI model based on the features;

[1727] means for providing the generated suggestions to a user;

[1728] means for collecting user feedback on said suggestions;

[1729] A means for incorporating the collected feedback into a generative AI model;

[1730] a camera for recognizing user characteristics;

[1731] means for transmitting data collected by the camera to a cloud server;

[1732] A means for the cloud server to analyze using a generating AI model and generate a proposal;

[1733] means for displaying said suggestions in real time on a user's visual device;

[1734] A system including:

[1735] (Claim 2)

[1736] The system according to claim 1, further comprising means for reflecting in the suggestions recommended styles of brands frequently used by the user and affiliated stylists.

[1737] (Claim 3)

[1738] means for inputting data based on the features into a generative AI model;

[1739] means for transmitting the generated proposal to a user's terminal;

[1740] 2. The system of claim 1, wherein the terminal includes means for displaying the transmitted proposal.

[1741] "Example 2: Combining Emotion Engines"

[1742] (Claim 1)

[1743] a means for a user to input individual characteristics;

[1744] means for transmitting the input characteristics to a server;

[1745] means for storing said characteristics on a server;

[1746] means for generating suggestions using a generative AI model based on the features;

[1747] means for providing the generated suggestions to a user;

[1748] means for collecting user feedback on said suggestions;

[1749] A means for incorporating the collected feedback into a generative AI model;

[1750] means for recognizing a user's emotion using an emotion engine and reflecting the emotion in the generated suggestions;

[1751] A system including:

[1752] (Claim 2)

[1753] The system according to claim 1, further comprising means for reflecting in the suggestions recommended styles of brands frequently used by the user and affiliated stylists.

[1754] (Claim 3)

[1755] means for inputting data based on the features into a generative AI model;

[1756] means for transmitting the generated proposal to a user's terminal;

[1757] 2. The system of claim 1, wherein the terminal includes means for displaying the transmitted proposal.

[1758] "Application example 2 when combining emotion engines"

[1759] (Claim 1)

[1760] a means for a user to input individual characteristics;

[1761] means for transmitting the input characteristics to a server;

[1762] means for storing said characteristics on a server;

[1763] means for generating suggestions using a generative AI model based on the features;

[1764] means for providing the generated suggestions to a user;

[1765] means for collecting user feedback on said suggestions;

[1766] A means for incorporating the collected feedback into a generative AI model;

[1767] A system including:

[1768] (Claim 2)

[1769] The system according to claim 1, further comprising means for reflecting in the suggestions recommended styles of brands frequently used by the user and affiliated stylists.

[1770] (Claim 3)

[1771] means for inputting data based on the features into a generative AI model;

[1772] means for transmitting the generated proposal to a user's terminal;

[1773] 2. The system of claim 1, wherein the terminal includes means for displaying the transmitted proposal.

[1774] New invention content

[1775] (Claim 1)

[1776] a means for a user to input individual characteristics;

[1777] means for transmitting the input characteristics to a server;

[1778] means for storing said characteristics on a server;

[1779] means for generating suggestions using a generative AI model based on the features;

[1780] means for providing the generated suggestions to a user;

[1781] means for collecting user feedback on said suggestions;

[1782] A means for incorporating the collected feedback into a generative AI model;

[1783] A means for analyzing a user's emotions using an emotion recognition engine and reflecting the emotions in the generative AI model;

[1784] A system including:

[1785] (Claim 2)

[1786] The system according to claim 1, further comprising means for reflecting in the suggestions recommended styles of brands frequently used by the user and affiliated stylists.

[1787] (Claim 3)

[1788] means for inputting the feature-based data and user emotion data into a generative AI model;

[1789] means for transmitting the generated proposal to a user's terminal;

[1790] 2. The system of claim 1, wherein the terminal includes means for displaying the transmitted proposal. [Explanation of symbols]

[1791] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for a user to input individual characteristics; means for transmitting the input characteristics to a server; means for storing said characteristics on a server; means for generating suggestions using a generative AI model based on the features; means for providing the generated suggestions to a user; means for collecting user feedback on said suggestions; A means for incorporating the collected feedback into a generative AI model; A system including:

2. The system according to claim 1 , further comprising means for reflecting in the suggestions recommended styles of brands frequently used by the user and affiliated stylists.

3. means for inputting data based on the features into a generative AI model; means for transmitting the generated proposal to a user's terminal; 2. The system of claim 1, wherein said terminal includes means for displaying said transmitted proposals.

Images