system

Abstract

We provide the system. [Solution] A means for inputting information about the user, A means of collecting users' fashion preferences, A means of suggesting fashion items based on the above-mentioned information about the user and the above-mentioned user's fashion preferences, Means for providing a virtual fitting room, A means of providing purchase links for the above fashion items, Means for collecting user feedback, Based on the above feedback, we will develop a means to optimize the next proposal, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a conventional fashion coordination proposal system, there is a problem that it cannot sufficiently meet the individual preferences and needs of users. In addition, there are deficiencies in virtual fitting rooms and the reflection of user feedback, and there is a problem that it is difficult to make personalized fashion proposals. Furthermore, affiliate marketing cannot be combined as an effective monetization means, and the practicality of the entire system is low, so the development of a system that better meets user demands has been required.

Means for Solving the Problems

[0005] To solve the above problems, the present invention provides the following means: a system including means for inputting information about the user, means for collecting the user's fashion preferences, means for suggesting fashion items based on the user's information and preferences, means for providing a virtual fitting room, means for providing purchase links for fashion items, means for collecting user feedback, and means for optimizing the next suggestion based on the feedback. Furthermore, by including a natural language processing engine for analyzing the user's input information and a database for storing user information and feedback information, the system appropriately responds to the user's individual needs and realizes personalized fashion suggestions. In addition, the practicality of the entire system is improved by monetizing it through affiliate marketing.

[0006] "User information" refers to basic personal information that users enter into the system, including, for example, name, age, gender, fashion preferences, and budget.

[0007] "Fashion preferences" refer to information about the styles, colors, and designs that users like, and include detailed preferences specified by the user in a chat format.

[0008] "Fashion item suggestion means" refers to a function that allows the system to generate and suggest the most suitable fashion items based on user information and fashion preferences.

[0009] A "virtual fitting room" refers to a feature that allows users to have a virtual model try on fashion items they have selected, enabling them to visually confirm the fit.

[0010] A "purchase link" is a link to an online shopping site that allows users to actually purchase the suggested fashion items.

[0011] "Feedback" refers to information such as satisfaction levels, opinions, and impressions that users provide after purchasing a product or using a system.

[0012] A "natural language processing engine" refers to an algorithm and system that analyzes text data entered by users in a chat format and understands its meaning.

[0013] A "database" is an information storage system that structurally stores user information, fashion preferences, feedback information, etc., and allows access to it as needed. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] System Overview

[0036] This invention is a system that provides personalized fashion advice to users, suggesting optimal outfits using user information, fashion preferences, and trend information. Its aim is to comprehensively support users' fashion choices through features such as virtual fitting rooms, product purchase assistance, and feedback collection.

[0037] Key components of the system

[0038] 1. User information input means

[0039] Users enter personal information such as their name, age, gender, fashion preferences, and budget using the application.

[0040] The device collects this information and sends it to the server.

[0041] The server stores the received information in a database.

[0042] 2. Methods for collecting fashion preferences

[0043] Users specify their preferred style, color, and items through a chat interface.

[0044] The terminal sends this conversation data to the server.

[0045] The server uses a natural language processing engine to analyze the input data and saves the user's preferences to a database.

[0046] 3. Means of proposing fashion items

[0047] The server generates optimal fashion coordinates by matching user information and preference data with trend information.

[0048] The terminal displays this to the user.

[0049] 4. Virtual fitting room means

[0050] The user requests to virtually try on the suggested outfit.

[0051] The terminal sends 3D model data for virtual try-on to the server.

[0052] The server uses a 3D rendering engine to generate a 3D model for virtual try-on and sends it to the terminal.

[0053] The device displays the results of the virtual try-on to the user.

[0054] 5. Means of providing purchase links

[0055] The server generates purchase links (e.g., affiliate links to partner online shops) for the suggested fashion items.

[0056] The terminal displays this to the user.

[0057] 6. Methods for collecting feedback

[0058] Users fill out a form to provide feedback after purchasing or trying on an item.

[0059] The device sends feedback data to the server.

[0060] The server saves the feedback information to a database and incorporates it into future proposals.

[0061] Specific example

[0062] User registration and initial outfit suggestion

[0063] 1. The user opens the application for the first time and enters their name, age, gender, fashion preference (e.g., casual, elegant), and budget (e.g., less than 30,000 yen per month).

[0064] 2. The terminal sends the entered information to the server, and the server stores it in the database.

[0065] 3. The user uses the chat interface to enter their favorite color (e.g., blue) and the type of clothing they usually wear (e.g., jeans or a T-shirt).

[0066] 4. The terminal sends conversation data to the server, which uses a natural language processing engine to analyze the user's information and record it in a database.

[0067] 5. Based on user preference data and trend data, the server generates a casual yet elegant style outfit (e.g., white blouse, black skinny jeans, red pumps) and sends it to the terminal.

[0068] 6. The device displays recommended outfits to the user, and the user requests a virtual try-on.

[0069] 7. The device sends a virtual try-on request to the server, the server generates a virtual model using a 3D rendering engine, and sends it to the device.

[0070] 8. The device displays the results of the virtual try-on to the user, and the user clicks the purchase link for the items they like.

[0071] 9. The device proceeds with the purchase process, the server stores the purchase data, and the affiliate commission is earned.

[0072] 10. One week after purchase, the server sends a follow-up message to the user, who then provides feedback.

[0073] 11. The server saves the feedback to a database and incorporates it into future suggestions.

[0074] In this way, each component works together to provide users with a personalized fashion experience.

[0075] The following describes the processing flow.

[0076] Step 1:

[0077] The user opens the application and enters basic information such as their name, age, gender, fashion preferences, and budget.

[0078] Step 2:

[0079] The terminal sends the entered information to the server. Specifically, it sends user data to the server via an API.

[0080] Step 3:

[0081] The server saves the received information to the database. The database stores the information in the user profile table.

[0082] Step 4:

[0083] Users specify their preferred style, colors, and the types of clothes they usually wear through a chat interface.

[0084] Step 5:

[0085] The terminal sends the input dialogue data to the server. The dialogue data is sent in text format and passed to the server via an API.

[0086] Step 6:

[0087] The server uses a natural language processing engine to analyze the user's input data. The analysis results are recorded in a database as the user's preferences and needs.

[0088] Step 7:

[0089] The server analyzes user information and preference data, along with trend information, to generate the optimal fashion coordinate. For example, the coordinate might consist of a white blouse, black skinny jeans, and red pumps.

[0090] Step 8:

[0091] The server sends the generated outfit to the device. Specifically, the outfit data is passed to the device via an API.

[0092] Step 9:

[0093] The device displays outfit suggestions to the user. The user can review these and choose to virtually try them on.

[0094] Step 10:

[0095] The user selects a virtual try-on, and the device sends a virtual try-on request to the server. The request includes information about the selected outfit.

[0096] Step 11:

[0097] The server uses a 3D rendering engine to generate a 3D model of the virtual try-on garment. The model data for the virtual try-on garment is prepared.

[0098] Step 12:

[0099] The server sends the generated 3D model data to the terminal. The terminal receives the model data upon request.

[0100] Step 13:

[0101] The device displays the results of the virtual try-on to the user. The user reviews the results and decides which items they like.

[0102] Step 14:

[0103] The user clicks the purchase link and proceeds with the purchase of the item they like. The device sends the purchase data to the server.

[0104] Step 15:

[0105] The server receives purchase data and stores it in the database. Simultaneously, it records the commissions for affiliate marketing.

[0106] Step 16:

[0107] One week after purchase, the server will send a follow-up message to the user. The message will include a link to a feedback form.

[0108] Step 17:

[0109] The user submits their opinions and feedback by filling out a feedback form. The device then sends the entered feedback data to the server.

[0110] Step 18:

[0111] The server receives the feedback and stores it in the database. The feedback will be incorporated into the next proposal.

[0112] Step 19:

[0113] The server optimizes the next outfit suggestion based on collected feedback and user profiles. The server generates a new outfit and sends it to the device.

[0114] This series of processes makes it possible to provide users with a personalized fashion experience.

[0115] (Example 1)

[0116] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0117] Traditional fashion suggestion systems struggled to provide personalized recommendations that fully reflected user preferences and trend information. Furthermore, the lack of integrated features such as virtual try-on functionality, purchase links, feedback collection, and the ability to incorporate feedback into future suggestions resulted in a fragmented user experience, making it difficult to provide optimal outfits.

[0118] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0119] In this invention, the server includes means for inputting information about the user, means for collecting the user's fashion preferences, means for suggesting fashion items based on the user information and the user's fashion preferences, means for providing a virtual fitting room, means for providing purchase links for the fashion items, means for collecting user feedback, means for optimizing the next suggestion based on the feedback, means for analyzing user input using a natural language processing engine, means for using a generative AI model that suggests the optimal fashion items by matching user information, preference data, and trend information, and means for using a three-dimensional rendering engine that generates a three-dimensional model of the virtual fitting. This enables highly personalized fashion suggestions tailored to the user's preferences, resulting in an integrated user experience and a system that is efficient and easy to use.

[0120] A "user" refers to a person who uses this system and is the entity that provides personal information such as name, age, gender, fashion preferences, and budget.

[0121] A "user information input method" is a means for users to input personal information such as their name, age, gender, fashion preferences, and budget.

[0122] A "fashion preference collection method" refers to a means of collecting a user's preferred style, colors, items, etc.

[0123] "Fashion item suggestion means" refers to a means for suggesting fashion items based on the above-mentioned information about the user and the user's fashion preferences.

[0124] A "virtual fitting room system" is a means for users to virtually try on suggested fashion items.

[0125] "Method of providing purchase links" refers to a means of providing purchase links for proposed fashion items (for example, affiliate links to partner online shops).

[0126] "Feedback collection methods" refer to methods for collecting user feedback and obtaining information to optimize future proposals based on this feedback.

[0127] A "natural language processing engine" is an engine used to analyze user input information and has the function of analyzing the meaning of text.

[0128] A "generative AI model" is an artificial intelligence model used to suggest the most suitable fashion items by matching user information, preference data, and trend information.

[0129] A "three-dimensional rendering engine" is an engine used to generate three-dimensional models for virtual try-on.

[0130] This invention is a system that provides personalized fashion advice to users. It uses user information, fashion preferences, and trend information to suggest optimal outfits, and provides support for virtual fitting rooms, product purchases, and feedback collection. This invention consists of the following main components:

[0131] User information input means

[0132] The user uses the application to enter personal information such as name, age, gender, fashion preferences, and budget. The device collects this information and sends it to the server. The server stores the received information in a database.

[0133] Fashion preferences and collecting methods

[0134] Users specify their preferred style, color, and items using a chat interface. The device sends this conversational data to a server, which uses a natural language processing engine (e.g., Google® Cloud Natural Language API) to analyze the input data and store the user's preferences in a database.

[0135] Fashion Item Proposal Method

[0136] The server generates the optimal fashion coordinate based on user information and preference data, matching it with trend information (e.g., the latest fashion magazine data). Specifically, a generative AI model is used to generate the fashion coordinate. The generated coordinate is sent to the terminal, which then displays it to the user.

[0137] Virtual fitting room method

[0138] The user sends a request to virtually try on the suggested outfit. The device sends 3D model data for the virtual try-on to the server, which generates a 3D model of the virtual try-on using a 3D rendering engine (e.g., Unity3D) and sends it back to the device. The device then displays the results of the virtual try-on to the user.

[0139] Purchase link provision method

[0140] The server generates a purchase link (e.g., an affiliate link to a partner online shop) for the suggested fashion item. The terminal then displays this to the user.

[0141] Feedback collection methods

[0142] The user fills out a form to provide feedback after purchase or trying on an item. The device sends the feedback data to the server, which stores the feedback information in a database. The stored feedback is then used to inform future suggestions.

[0143] Specific example

[0144] User registration and initial outfit suggestion

[0145] 1. The user opens the application for the first time and enters their name, age, gender, fashion preference (e.g., casual, elegant), and budget (e.g., less than 30,000 yen per month). The device sends the entered information to the server, which stores it in a database.

[0146] 2. The user uses the chat interface to input their favorite color (e.g., blue) and the type of clothing they usually wear (e.g., jeans or a T-shirt). The terminal sends the conversation data to the server, which uses a natural language processing engine to analyze the user's information and record it in a database.

[0147] 3. Based on user preference data and trend data, the server generates a casual yet elegant style outfit (e.g., white blouse, black skinny jeans, red pumps) and sends it to the terminal.

[0148] 4. The device displays recommended outfits to the user, and the user requests a virtual try-on. The device sends a virtual try-on request to the server, which generates a virtual model using a 3D rendering engine and sends it to the device.

[0149] 5. The terminal displays the results of the virtual try-on to the user, and the user clicks the purchase link for the items they like. The terminal proceeds with the purchase process, the server saves the purchase data, and earns affiliate commissions. One week after the purchase, the server sends a follow-up message to the user, who provides feedback. The server saves the feedback in its database and uses it to improve future recommendations.

[0150] In this way, each component works together to provide users with a personalized fashion experience.

[0151] Example of a prompt

[0152] "Please tell us your favorite fashion style, colors, and items."

[0153] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0154] Step 1: Collecting User Information

[0155] 1-1. The user launches the application and enters personal information such as name, age, gender, fashion preferences, and budget.

[0156] Input: Name, age, gender, fashion preferences, budget

[0157] Specific action: The user logs into the app from their smartphone or PC and enters the required information into the form.

[0158] 1-2. The terminal collects the entered information and sends it to the server.

[0159] Output: Entered user information

[0160] Specific operation: The device sends the input information to the server in real time, and a confirmation message is displayed to confirm successful transmission.

[0161] 1-3. The server saves the received information to the database.

[0162] Output: User information stored in the database

[0163] Specific operation: The server stores the received information in the database, and the saving of user information is confirmed.

[0164] Step 2: Collect your fashion preferences

[0165] 2-1. Users use the chat interface to specify their preferred style, color, and items.

[0166] Input: Preferred style, color, item

[0167] Specific action: The user enters "I like casual clothes and blue, and I usually wear jeans and t-shirts."

[0168] 2-2. The terminal sends the user's input to the server as text data.

[0169] Output: Sent preference data

[0170] Specific action: The terminal formats this as text data and sends it to the server.

[0171] 2-3. The server analyzes the input data using a natural language processing engine.

[0172] Input: Submitted preference data

[0173] Output: Analyzed preference data

[0174] Specific operation: The server uses a natural language processing engine to extract keywords such as "casual," "blue," "jeans," and "T-shirt."

[0175] 2-4. The server saves the analysis results to the database.

[0176] Output: Preference data stored in the database

[0177] Specific operation: The server saves the preferred data to the database, and a confirmation message is displayed.

[0178] Step 3: Fashion Coordination Suggestions

[0179] 3-1. The server matches user information, preference data, and trend information.

[0180] Input: User information, preference data, trend information

[0181] Output: Matched data

[0182] Specific operation: The server retrieves user information and trend information from the database and executes database queries to match them.

[0183] 3-2. The server generates the optimal fashion coordinate using an AI model for coordinate generation.

[0184] Input: Matched data

[0185] Output: Generated coordinate

[0186] Specific operation: The server generates outfits based on the user's preferences, such as "white blouse, black skinny jeans, and red pumps."

[0187] 3-3. The server sends the generated coordinate to the terminal.

[0188] Output: Coordinate sent to the terminal

[0189] Specific operation: The server sends the generated coordination information to the terminal, and a message indicating successful transmission is displayed.

[0190] 3-4. The device displays the outfit to the user.

[0191] Output: Coordinates displayed to the user

[0192] Specific action: The device displays an outfit to the user, such as "white blouse, black skinny jeans, red pumps," and a notification is issued asking for confirmation.

[0193] Step 4: Perform a virtual try-on.

[0194] 4-1. The user requests to virtually try on the item.

[0195] Input: Request for virtual try-on

[0196] Specific action: The user clicks a button that says, "I want to virtually try on this outfit."

[0197] 4-2. The terminal sends 3D model data for virtual try-on to the server.

[0198] Input: User body shape data, outfit data

[0199] Output: Sent 3D model data

[0200] Specific operation: The device sends the user's body shape data and outfit information to the server.

[0201] 4-3. The server uses a 3D rendering engine to generate a 3D model for virtual try-on.

[0202] Input: Submitted 3D model data

[0203] Output: Generated 3D model

[0204] Specific operation: The server uses a 3D rendering engine to generate a 3D model for virtual try-on.

[0205] 4-4. The server sends the generated 3D model to the terminal.

[0206] Output: 3D model sent to the terminal

[0207] Specific operation: The server sends the generated 3D model to the terminal, and a confirmation message is displayed.

[0208] 4-5. The terminal displays the results of the virtual try-on to the user.

[0209] Output: Virtual fitting results displayed to the user

[0210] Specific operation: The device displays a 3D model, and the user can see the results of a virtual try-on.

[0211] Step 5: Provide the purchase link

[0212] 5-1. The server generates a purchase link for the suggested fashion item.

[0213] Input: Suggested fashion item information

[0214] Output: Generated purchase link

[0215] Specific operation: The server generates a purchase URL for each item and creates a link.

[0216] 5-2. The server sends the generated purchase link to the device.

[0217] Output: Purchase link sent to the device

[0218] Specific operation: The server sends the generated purchase link to the device, and the link is displayed on the user's screen.

[0219] 5-3. The terminal displays this to the user.

[0220] Output: Purchase link displayed to the user

[0221] Specific action: The device displays a link saying "You can purchase it here," allowing the user to click it.

[0222] Step 6: Gathering Feedback

[0223] 6-1. The user fills out a form to provide feedback after purchase or after trying on the item.

[0224] Input: Feedback after purchase or try-on

[0225] Specific action: The user enters their opinions and feedback through a feedback form.

[0226] 6-2. The device sends feedback data to the server.

[0227] Output: Sent feedback data

[0228] Specific action: The terminal sends the input feedback to the server.

[0229] 6-3. The server saves the feedback information to the database.

[0230] Output: Feedback information stored in the database

[0231] Specific operation: The server stores the received data in the database, and a confirmation message for saving is displayed.

[0232] 6-4. The server incorporates the feedback into the next proposal.

[0233] Input: Saved feedback information

[0234] Output: Feedback reflected in the next proposal

[0235] Specific operation: The server optimizes the next coordination suggestion based on the feedback information.

[0236] The above outlines the specific processing steps of the program for this system.

[0237] (Application Example 1)

[0238] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0239] Traditional fashion advice systems had limitations in providing personalized fashion suggestions to users, particularly in effectively linking trend information with user preferences. Furthermore, virtual try-on features failed to adequately replicate the feeling of actually trying on clothes, resulting in insufficient user satisfaction. Additionally, mechanisms for collecting post-purchase feedback and incorporating it into future suggestions were incomplete.

[0240] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0241] In this invention, the server includes means for inputting user information, means for collecting fashion preferences, means for suggesting optimal fashion items based on trend information and user preference data using a generative AI model, means for providing a virtual fitting room, means for providing a purchase link, means for collecting post-purchase feedback, and means for sending post-purchase follow-up messages. This makes it possible to provide users with a more personalized and realistic fashion experience and improve user satisfaction.

[0242] "Means of inputting user information" refers to methods of collecting personal information such as the user's name, age, gender, fashion preferences, and budget through a terminal or application, and transmitting it to a server.

[0243] "Means of collecting fashion preferences" refers to a method by which users specify their preferred styles, colors, items, etc., using a chat interface or other input method, and send that data to a server.

[0244] A "generative AI model" is an artificial intelligence model that uses user information and preference data to match with trend information and suggest the most suitable fashion items.

[0245] A "virtual fitting room" is a system that allows users to virtually try on suggested fashion items. It uses 3D rendering technology to generate 3D models of the items to be virtually tried on and displays them to the user.

[0246] "Means of providing purchase links" refers to a means of generating and displaying to the user a link that allows them to purchase the proposed fashion item.

[0247] "Means of collecting post-purchase feedback" refers to providing a form for users to enter their opinions and impressions after purchasing or trying on an item, and then sending that feedback data to a server and storing it in a database.

[0248] "Method for sending follow-up messages after purchase" refers to a method for sending messages from a server to a user after they have purchased an item, in order to check on their experience and satisfaction with the item.

[0249] "Means of acquiring trend information" refers to methods of obtaining the latest trend information from external fashion-related databases or APIs and storing it on a server.

[0250] This invention is a system that provides personalized fashion advice to users. Specifically, it proposes the optimal outfit using user information, fashion preferences, and trend information. The aim of this system is to comprehensively support users in choosing their fashion through features such as virtual fitting rooms, assistance with product purchases, and feedback collection.

[0251] Key components of the system

[0252] 1. User information input means

[0253] Users use their devices to enter personal information such as their name, age, gender, fashion preferences, and budget. This information is sent from the device to the server, which stores the received information in a database.

[0254] 2. Methods for collecting fashion preferences

[0255] Users specify their preferred style, color, and items through a chat interface. The terminal sends this conversational data to a server, which uses a natural language processing engine to analyze the input data and store the user's preferences in a database.

[0256] 3. Proposed method using a generative AI model

[0257] The server generates optimal fashion coordinates based on user information and preference data, matching them with trend information. This is where a generation AI model is utilized. The generated fashion item recommendations are displayed to the user via their device.

[0258] 4. Virtual fitting room means

[0259] When a user requests to virtually try on a suggested outfit, the device sends 3D model data of the outfit to the server. The server uses a 3D rendering engine to generate a 3D model of the outfit and sends it to the device. The device then displays the results of the virtual try-on to the user.

[0260] 5. Means of providing purchase links

[0261] The server generates a purchase link (e.g., an affiliate link to a partner online shop) for the suggested fashion item. This allows the user to easily purchase the item. The terminal displays this to the user.

[0262] 6. Methods for collecting feedback

[0263] When a user fills out a form to provide feedback after a purchase or try-on, the data is sent from the device to the server and stored in a database. The server then uses the feedback information to improve future suggestions.

[0264] 7. Means of sending follow-up messages

[0265] The server sends a follow-up message after a user purchases an item to inquire about their experience and satisfaction with it. This allows for further collection of user feedback, which can then be used to improve future offerings.

[0266] Specific examples of actions

[0267] In a scenario where a user is using the application for the first time, the following prompt will be displayed:

[0268] Prompt: New user registration

[0269] name

[0270] age

[0271] sex

[0272] budget

[0273] style

[0274] Prompt: Collect your preferences details

[0275] Favorite color: Blue

[0276] Everyday clothing items: Jeans, T-shirts

[0277] Prompt: Generate recommended items

[0278] Prompt: Conduct virtual try-on

[0279] Prompt: Display purchase link

[0280] Prompt: Collect feedback

[0281] With this system, users can receive personalized fashion suggestions and further utilize the virtual try-on function to experience a real try-on. This improves user satisfaction and enables optimization of next-time suggestions through the collection of feedback.

[0282] The flow of specific processing in Application Example 1 will be described using FIG. 12.

[0283] Step 1:

[0284] The user opens the application and enters initial registration information (name, age, gender, fashion preference, budget). The terminal sends this input data to the server. The server saves the received user information in the database. Through this procedure, the basic user information is recorded in the database.

[0285] Input: User registration information (name, age, gender, fashion preference, budget)

[0286] Output: User information saved in the database

[0287] Step 2:

[0288] The user uses the chat interface to specify preferred styles, colors, items, etc. The terminal sends this dialogue data to the server. The server analyzes the input data using a natural language processing engine and saves the user's preference data in the database. Thus, the user's detailed preference information is accumulated.

[0289] Input: User dialogue data (preferred styles, colors, items)

[0290] Output: User preference data stored in the database

[0291] Step 3:

[0292] The server generates optimal fashion coordinates by matching user information and preference data with trend information. This is where a generation AI model is utilized. The generated fashion item recommendations are sent to the device and displayed to the user. This provides personalized fashion suggestions for each individual user.

[0293] Input: User information, preference data, trend information

[0294] Output: Fashion coordination suggestions sent to the terminal

[0295] Step 4:

[0296] The user sends a request to virtually try on suggested fashion items. The device sends this request to the server. The server generates a 3D model of the virtual try-on using a 3D rendering engine and sends it to the device. The device displays the virtual try-on results to the user. This allows the user to virtually try on the suggested items.

[0297] Input: User's virtual try-on request

[0298] Output: 3D model and virtual try-on results sent to the terminal

[0299] Step 5:

[0300] The server generates purchase links for items the user likes after a virtual try-on. These purchase links are structured as affiliate links to partner online shops. The terminal displays these links to the user, providing them with an environment where they can actually purchase the items.

[0301] Input: Information of an item that the user likes

[0302] Output: Purchase link displayed on the terminal

[0303] Step 6:

[0304] After the user purchases an item, the server sends a follow-up message after the purchase and prompts the user to provide feedback. When the user enters the feedback form, the terminal sends the feedback data to the server. The server saves this feedback information in the database and reflects it in the next recommendation. This enables further improvement of the service based on the user's opinions.

[0305] Input: User's feedback data

[0306] Output: Feedback information saved in the database

[0307] Step 7:

[0308] The server performs data analysis to optimize the next recommendation based on the user's feedback. By feeding this analysis data back to the generative AI model, it becomes possible to make more accurate fashion item recommendations.

[0309] Input: Feedback information

[0310] Output: Analysis data fed back to the generative AI model

[0311] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform specific processing using the user's emotion.

[0312] Overall system overview

[0313] This invention is a system that provides personalized fashion advice to users, suggesting optimal outfits using user information, fashion preferences, trend information, and the user's emotional state. Its aim is to comprehensively support users' fashion choices through features such as virtual fitting rooms, product purchase assistance, and feedback collection.

[0314] Key components of the system

[0315] 1. User information input means

[0316] Users enter personal information such as their name, age, gender, fashion preferences, and budget using the application.

[0317] The device collects this information and sends it to the server.

[0318] The server stores the received information in a database.

[0319] 2. Methods for collecting fashion preferences

[0320] Users specify their preferred style, color, and items through a chat interface.

[0321] The terminal sends this conversation data to the server.

[0322] The server uses a natural language processing engine to analyze the input data and saves the user's preferences to a database.

[0323] 3. Means of proposing fashion items

[0324] The server analyzes user information and preference data, along with trend information, to generate the optimal fashion coordinate. For example, the coordinate might consist of a white blouse, black skinny jeans, and red pumps.

[0325] The terminal displays this to the user.

[0326] 4. Virtual fitting room means

[0327] The user requests to virtually try on the suggested outfit.

[0328] The terminal sends 3D model data for virtual try-on to the server.

[0329] The server uses a 3D rendering engine to generate a 3D model for virtual try-on and sends it to the terminal.

[0330] The device displays the results of the virtual try-on to the user.

[0331] 5. Means of providing purchase links

[0332] The server generates purchase links (e.g., affiliate links to partner online shops) for the suggested fashion items.

[0333] The terminal displays this to the user.

[0334] 6. Methods for collecting feedback

[0335] Users fill out a form to provide feedback after purchasing or trying on an item.

[0336] The device sends feedback data to the server.

[0337] The server saves the feedback information to a database and incorporates it into future proposals.

[0338] 7. Emotional Engine

[0339] When a user uses the conversational interface, the emotion engine analyzes the user's emotional state from their input text and voice.

[0340] The device sends user emotion data to the server.

[0341] The server adjusts suggested fashion items and outfits based on emotional data.

[0342] Specific example

[0343] Coordination suggestions that take emotions into consideration

[0344] 1. The user opens the application for the first time and enters their name, age, gender, fashion preference (e.g., casual, elegant), and budget (e.g., less than 30,000 yen per month).

[0345] 2. The terminal sends the entered information to the server, and the server stores it in the database.

[0346] 3. The user uses the chat interface to enter their favorite color (e.g., blue) and the type of clothing they usually wear (e.g., jeans or a T-shirt).

[0347] 4. The terminal sends conversation data to the server, which uses a natural language processing engine to analyze the user's information and record it in a database.

[0348] 5. The emotion engine identifies the user's emotional state from their dialogue data and voice data, and analyzes emotional data such as happy, calm, and excited.

[0349] 6. The server generates fashion coordinates appropriate to the user's emotional state based on their emotional data, preference data, and trend data. For example, if the user is relaxed, it will suggest a casual and comfortable style (e.g., relaxed-fit jeans, a soft cardigan).

[0350] 7. The server sends the generated coordinate to the terminal, and the terminal displays it to the user.

[0351] 8. If the user requests a virtual try-on, the device sends a virtual try-on request to the server.

[0352] 9. The server generates a virtual model using a 3D rendering engine and sends it to the terminal.

[0353] 10. The device displays the results of the virtual try-on to the user, and the user clicks the purchase link for the items they like.

[0354] 11. The device proceeds with the purchase process, the server saves the purchase data, and the affiliate commission is earned.

[0355] 12. One week after purchase, the server sends a follow-up message to the user, who then provides feedback.

[0356] 13. The server saves the feedback to a database and incorporates it into future suggestions.

[0357] By combining these emotion engines, it becomes possible to provide a more personalized fashion experience that responds to the user's emotional state.

[0358] The following describes the processing flow.

[0359] Step 1:

[0360] The user opens the application and enters their name, age, gender, fashion preference (e.g., casual, elegant), and budget (e.g., under 30,000 yen per month).

[0361] Step 2:

[0362] The terminal sends the entered user information to the server. A method using an API to send data is employed.

[0363] Step 3:

[0364] The server saves the received user information to the database. The information is stored in the user profile table.

[0365] Step 4:

[0366] Users specify their preferred styles, colors, and the types of clothes they usually wear through a chat interface. For example, a user might input that they like blue, jeans, and t-shirts.

[0367] Step 5:

[0368] The device sends the collected conversation data to the server. The conversation data is sent in text format via the API.

[0369] Step 6:

[0370] The server uses a natural language processing engine to analyze user dialogue data. The analysis results are recorded in a database as user preferences and needs.

[0371] Step 7:

[0372] The emotion engine analyzes the user's input text and voice data to identify their emotional state. For example, it can analyze whether the user is happy, calm, or excited.

[0373] Step 8:

[0374] The device sends user emotion data to the server. This emotion data is retrieved in conjunction with a natural language processing engine.

[0375] Step 9:

[0376] The server comprehensively analyzes user preference data, emotional data, and trend information to generate fashion coordinates that suit the user's emotional state. For example, if the user is relaxed, it will suggest relaxed-fit jeans or a soft cardigan.

[0377] Step 10:

[0378] The server sends the generated outfit suggestions to the user's device. The outfit data is sent to the user's device via the API.

[0379] Step 11:

[0380] The device displays outfit suggestions to the user. The user can review the suggestions and choose whether or not they wish to virtually try them on.

[0381] Step 12:

[0382] If a user wishes to virtually try on clothes, the device sends a virtual try-on request to the server. The request includes information about the selected outfit.

[0383] Step 13:

[0384] The server uses a 3D rendering engine to generate a 3D model for virtual try-on. The data for the virtual model is prepared.

[0385] Step 14:

[0386] The server sends the generated 3D model data to the terminal. The terminal receives the model data upon request.

[0387] Step 15:

[0388] The device displays the results of the virtual try-on to the user. The user reviews the results and clicks the purchase link for the items they like.

[0389] Step 16:

[0390] The user clicks the purchase link and proceeds with the purchase of the item they like. The device sends the purchase data to the server.

[0391] Step 17:

[0392] The server receives the purchase data and saves it to the database. At the same time, affiliate marketing commissions are recorded.

[0393] Step 18:

[0394] One week after purchase, the server will send a follow-up message to the user. The message will include a link to a feedback form.

[0395] Step 19:

[0396] The user submits their opinions and feedback by filling out a feedback form. The device then sends the entered feedback data to the server.

[0397] Step 20:

[0398] The server receives the feedback and stores it in the database. The feedback will be incorporated into the next proposal.

[0399] Step 21:

[0400] The server optimizes the next outfit suggestion based on the collected feedback and user profile. A new outfit is generated and sent to the device.

[0401] This series of processes makes it possible to provide a personalized fashion experience that takes into account the user's emotional state.

[0402] (Example 2)

[0403] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0404] In modern society, the diversification of individual preferences and trends in fashion makes it difficult for users to choose the most suitable fashion items for themselves. Furthermore, there is a lack of systems that can appropriately reflect the influence of a user's emotional state on their fashion choices, making it difficult to realize personalized suggestions. Moreover, there is a lack of mechanisms to achieve a higher level of personalization through virtual try-on and feedback. To solve these problems, the system proposed in this invention makes it possible to suggest fashion items that take into account user information, preferences, and emotional state.

[0405] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0406] In this invention, the server includes means for inputting information about the user, means for collecting the user's fashion preferences, and means for analyzing the user's emotional state. This makes it possible to suggest optimal fashion items based on the user's detailed information and preferences, as well as their emotional state.

[0407] "User information" refers to personal data entered by the user, such as name, age, gender, fashion preferences, and budget.

[0408] A "fashion preference collection method" is an interface and mechanism for processing information that allows users to provide the system with their preferred styles, colors, and clothing items.

[0409] "Fashion item suggestion means" refers to a function for generating optimal fashion coordinates based on user information and fashion preferences.

[0410] A "virtual fitting room" is a function that allows users to virtually try on suggested fashion items using the system.

[0411] The "purchase link provision method" is a function that generates and provides links to facilitate the purchase of proposed fashion items.

[0412] A "feedback collection method" is a function for collecting opinions and impressions from users regarding the results of their purchases or try-ons.

[0413] A "database" is a collection of information that stores user input and feedback information and is accessible as needed.

[0414] A "natural language processing engine" is a software system that analyzes text and audio data input by users and extracts meaning from them.

[0415] A "sentiment analysis engine" is a software system that analyzes a user's emotional state from their input text or voice and provides the results.

[0416] Modes for carrying out the invention

[0417] This invention is a system that provides personalized fashion advice to users. The system proposes the optimal outfit using user information, fashion preferences, trend information, and the user's emotional state. It aims to comprehensively support users in choosing their fashion through features such as virtual fitting rooms, product purchase assistance, and feedback collection.

[0418] The system includes the following main components:

[0419] User information input means

[0420] Users enter personal information such as their name, age, gender, fashion preferences, and budget using the application.

[0421] The device collects this information and sends it to the server.

[0422] The server saves the received information to the database.

[0423] Fashion preferences and collecting methods

[0424] Users specify their preferred style, color, and items through a chat interface.

[0425] The terminal sends this conversation data to the server.

[0426] The server analyzes the input data using a natural language processing engine (for example, OpenAI's GPT-3®) and stores the user's preferences in a database.

[0427] sentiment analysis tool

[0428] When a user uses the conversational interface, the emotion engine analyzes the user's emotional state from their input text and voice.

[0429] The device sends user emotion data to the server.

[0430] The server adjusts suggested fashion items and outfits based on emotional data.

[0431] Fashion Item Proposal Method

[0432] The server generates optimal fashion coordinates based on user information and preference data, combined with trend information. Specifically, it suggests items such as a white blouse, black skinny jeans, and red pumps.

[0433] The device displays this to the user.

[0434] Virtual fitting room method

[0435] The user sends a request to virtually try on the suggested outfit.

[0436] The device sends 3D model data for virtual try-on to the server.

[0437] The server generates a 3D model for virtual try-on using a 3D rendering engine (such as Unity 3D) and sends it to the terminal.

[0438] The device displays the results of the virtual try-on to the user.

[0439] Purchase link provision method

[0440] The server generates purchase links (such as affiliate links to partner online shops) for the suggested fashion items.

[0441] The device displays this to the user.

[0442] Feedback collection methods

[0443] Users fill out a form to provide feedback after purchasing or trying on an item.

[0444] The device sends feedback data to the server.

[0445] The server saves the feedback information to a database and incorporates it into future proposals.

[0446] Specific example

[0447] A process for suggesting outfits that take emotions into consideration

[0448] 1. The user opens the application for the first time and enters their name (e.g., Taro Tanaka), age (30 years old), gender (male), fashion preference (casual), and budget (under 30,000 yen per month).

[0449] 2. The terminal sends the entered information to the server, and the server saves it to the database.

[0450] 3. The user types "I like blue, and I usually wear jeans and a T-shirt" in the chat interface.

[0451] 4. The terminal sends conversation data to the server, and the server uses a natural language processing engine to analyze and store the data.

[0452] 5. The emotion engine identifies the emotional state of "relaxed" from the user's dialogue data and voice data, and stores the data in a database.

[0453] 6. Generate the optimal outfit (e.g., relaxed-fit jeans, soft cardigan) when the server is "relaxed".

[0454] 7. The server sends the generated coordinate to the terminal, and the terminal displays it to the user.

[0455] 8. The user requests a virtual try-on and sends a request from their device to the server.

[0456] 9. The server uses a 3D rendering engine to generate a model for virtual try-on and sends it to the terminal.

[0457] 10. The device displays the results of the virtual try-on to the user, and the user clicks the purchase link for the items they like.

[0458] 11. The device proceeds with the purchase process, the server saves the purchase data, and the affiliate receives the commission.

[0459] 12. One week after purchase, the server sends a follow-up message to the user, who then provides feedback.

[0460] Example of a prompt

[0461] "Please suggest casual fashion outfits that are suitable for when the user is relaxing."

[0462] "Please tell us what items would be good for users to wear when they seem to be having fun."

[0463] As a result, the system takes into account the user's detailed information and emotional state to provide highly personalized fashion suggestions.

[0464] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0465] Step 1:

[0466] The user launches the application and enters information such as their name, age, gender, fashion preferences, and budget.

[0467] Input: Name, age, gender, fashion preferences, budget

[0468] Output: User Information

[0469] Specific action: The user enters personal information such as "Taro Tanaka, 30 years old, male, casual attire, monthly income under 30,000 yen."

[0470] Step 2:

[0471] The terminal sends the entered user information to the server.

[0472] Input: User information

[0473] Output: User information sent to the server

[0474] Specific action: The device sends the information "Taro Tanaka, 30 years old, male, casual wear, monthly income under 30,000 yen" to the server.

[0475] Step 3:

[0476] The server saves the received user information to the database.

[0477] Input: User information sent to the server

[0478] Output: User information stored in the database

[0479] Specific action: The server records the information "Taro Tanaka, 30 years old, male, casual wear, monthly salary of 30,000 yen or less" in the database.

[0480] Step 4:

[0481] Users can use the chat interface to specify their preferred style, color, and items.

[0482] Input: Favorite style, color, item

[0483] Output: Preference information

[0484] Specific action: The user enters "I like blue, and I usually wear jeans and a T-shirt."

[0485] Step 5:

[0486] The terminal sends the conversation data to the server.

[0487] Input: Preference information

[0488] Output: Preference information sent to the server

[0489] Specific action: The device sends the information "I like blue and usually wear jeans and a T-shirt" to the server.

[0490] Step 6:

[0491] The server uses a natural language processing engine to analyze the input data and saves the user's preferences to a database.

[0492] Input: Preference information sent to the server

[0493] Output: Preference information stored in the database

[0494] Specific operation: The server uses a natural language processing engine such as OpenAI GPT-3 to extract keywords such as "blue, jeans, T-shirt" and save them to a database.

[0495] Step 7:

[0496] Users input text or voice through a conversational interface.

[0497] Input: Text or audio data

[0498] Output: Sentiment data

[0499] Specific action: The user types or speaks the phrase "I want to relax today."

[0500] Step 8:

[0501] The terminal sends the entered text or voice data to the server.

[0502] Input: Text or audio data

[0503] Output: Text and audio data sent to the server

[0504] Specific action: The device sends text or audio data of "I want to relax today" to the server.

[0505] Step 9:

[0506] The server's emotion engine analyzes the user's emotional state from text and audio.

[0507] Input: Text or audio data sent to the server

[0508] Output: Analyzed sentiment data

[0509] Specific operation: The server's emotion engine analyzes text and audio data to identify emotional states such as "relaxed."

[0510] Step 10:

[0511] The server adjusts suggested fashion items and outfits based on emotional data.

[0512] Input: Analyzed sentiment data

[0513] Output: Suggestions for tailored fashion items and outfits.

[0514] Specific operation: The server generates outfits such as "relaxed-fit jeans and a soft cardigan" based on sentiment data.

[0515] Step 11:

[0516] The server sends the generated outfit to the terminal.

[0517] Input: Suggestions for coordinated fashion items and outfits

[0518] Output: Fashion coordinates displayed to the user

[0519] Specific operation: The server sends the generated outfit to the terminal and displays suggestions to the user, such as "relaxed-fit denim, soft cardigan."

[0520] Step 12:

[0521] The user sends a request for a virtual try-on.

[0522] Input: Virtual try-on request

[0523] Output: Virtual fitting request data

[0524] Specific action: The user sends a request saying, "I want to virtually try on this outfit."

[0525] Step 13:

[0526] The device sends a request to the server for a virtual try-on.

[0527] Input: Virtual fitting request data

[0528] Output: Virtual try-on request data sent to the server

[0529] Specific operation: The terminal receives the user's request and sends it to the server.

[0530] Step 14:

[0531] The server uses a 3D rendering engine to generate a 3D model for the virtual try-on.

[0532] Input: Virtual try-on request data sent to the server

[0533] Output: 3D model data

[0534] Specific operation: The server uses a 3D rendering engine such as Unity 3D to generate a 3D model for virtual try-on.

[0535] Step 15:

[0536] The server sends the generated 3D model to the terminal.

[0537] Input: 3D model data

[0538] Output: 3D model data sent to the terminal

[0539] Specific operation: The server sends the generated 3D model to the terminal.

[0540] Step 16:

[0541] The device displays the results of the virtual try-on to the user.

[0542] Input: 3D model data sent to the terminal

[0543] Output: Virtual try-on results displayed to the user

[0544] Specific action: The device displays the results of the virtual try-on to the user, allowing the user to confirm them.

[0545] Step 17:

[0546] The server generates purchase links for the suggested fashion items.

[0547] Input: Suggestions for coordinated fashion items and outfits

[0548] Output: Purchase link

[0549] Specific operation: The server generates a purchase link (such as an affiliate link) for the suggested item.

[0550] Step 18:

[0551] The server sends a purchase link to the device.

[0552] Input: Purchase link

[0553] Output: Purchase link sent to the device

[0554] Specific action: The server sends the generated purchase link to the device.

[0555] Step 19:

[0556] The device displays a purchase link to the user.

[0557] Input: Purchase link sent to your device

[0558] Output: Purchase link displayed to the user

[0559] Specific action: The device displays a purchase link to the user, allowing the user to purchase the item.

[0560] Step 20:

[0561] The user purchases the item via the purchase link.

[0562] Input: Purchase link

[0563] Output: Purchase data

[0564] Specific action: The user clicks the purchase link and buys the item.

[0565] Step 21:

[0566] The server stores the purchase data and earns affiliate commissions.

[0567] Input: Purchase data

[0568] Output: Purchase data stored in the database, retrieved affiliate commissions.

[0569] Specific operation: The server stores the purchase data and receives affiliate commissions.

[0570] Step 22:

[0571] The server sends a follow-up message to the user, who then provides feedback.

[0572] Input: Purchase data

[0573] Output: Follow-up messages, feedback data

[0574] Specific action: One week after purchase, the server sends a follow-up message and the user enters feedback.

[0575] Step 23:

[0576] The device sends feedback data to the server.

[0577] Input: Feedback data

[0578] Output: Feedback data sent to the server

[0579] Specific action: The device sends user feedback data to the server.

[0580] Step 24:

[0581] The server saves the feedback information to a database and incorporates it into future proposals.

[0582] Input: Feedback data sent to the server

[0583] Output: Feedback information stored in the database, optimized next-generation suggestions.

[0584] Specific operation: The server saves the feedback information to a database and uses it to inform future suggestions.

[0585] (Application Example 2)

[0586] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0587] Traditional fashion advice systems have a problem in that they cannot fully suggest the most suitable outfits for users because they do not take into account the user's emotional state. Furthermore, they lack sufficient integration of features that comprehensively support the user's online shopping experience, such as virtual try-on functionality and purchase links. As a result, users face the challenge of not being able to efficiently select fashion items that suit their preferences and mood.

[0588] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting information about the user, means for collecting the user's fashion preferences, means for collecting emotional data using an engine that analyzes emotional states and reflecting it in fashion item suggestions, means for providing a virtual fitting room, means for providing purchase links for the fashion items, and means for collecting user feedback and optimizing suggestions for the next time. This makes it possible to suggest more personalized fashion coordinates according to the user's emotional state.

[0589] A "user information input method" is a means for users to input personal information such as their name, age, gender, fashion preferences, and budget.

[0590] A "fashion preference collection method" is a means by which users specify their preferred styles, colors, and items using a chat interface, and the collection of that information is then performed.

[0591] A "fashion item suggestion method" is a method for generating optimal fashion coordinates by simultaneously analyzing trend information based on user information and preference data.

[0592] A "virtual fitting room means" is a method for generating 3D model data and displaying it to the user so that the user can virtually try on the suggested outfit.

[0593] A "purchase link provision method" is a means of generating purchase links for proposed fashion items and displaying them to the user.

[0594] A "feedback collection method" refers to a method of providing a form for users to provide feedback after purchase or trying on an item, and collecting that data.

[0595] An "emotion engine" is an engine that analyzes a user's emotional state from their input text or voice.

[0596] A "natural language processing engine" is an engine used to analyze user input information.

[0597] A "database" is a system for storing user input information and feedback information.

[0598] A "3D rendering engine" is an engine used to generate 3D models for virtual try-on.

[0599] System Configuration

[0600] This invention is a system that provides personalized fashion advice to users. This system proposes optimal outfits using user information, fashion preferences, trend information, and the user's emotional state. Its aim is to comprehensively support users' fashion choices through features such as virtual fitting rooms, product purchase assistance, and feedback collection.

[0601] Hardware and software used

[0602] The following hardware and software will be used.

[0603] Smartphone

[0604] server

[0605] Database (for example, Amazon RDS)

[0606] Natural language processing engine (e.g., Google NLP API)

[0607] Emotion engine (e.g., Microsoft® Azure® Emotion API)

[0608] 3D rendering engine (e.g., Unity 3D)

[0609] Collection of user information

[0610] Users enter personal information such as their name, age, gender, fashion preferences, and budget via their smartphone, and the device sends this information to a server. The server stores the received information in a database.

[0611] Fashion-loving collector

[0612] Users use a chat interface to input their preferred style, color, and items. The device sends this conversational data to a server, which uses a natural language processing engine to analyze the data and store the user's preferences in a database.

[0613] Analysis of emotional states

[0614] The emotion engine analyzes the user's emotional state from their dialogue and voice data. The device sends this emotional data to the server, which stores it in a database. The emotional state is then reflected in the suggested coordination.

[0615] Coordination suggestions

[0616] The server generates the optimal fashion coordinate based on user information, preference data, sentiment data, and trend information. The generated coordinate is then displayed to the user on their device.

[0617] Virtual fitting room

[0618] When a user requests to virtually try on a suggested outfit, the device sends 3D model data for the virtual try-on to the server. The server generates a virtual model using a 3D rendering engine and sends it to the device. The device then displays the results of the virtual try-on to the user.

[0619] Purchase link provided

[0620] The server generates a purchase link for the suggested fashion item. This link is, for example, an affiliate link to a partner online shop. The terminal displays this to the user, who then proceeds with the purchase.

[0621] Gathering feedback and optimizing future proposals

[0622] When a user provides feedback after purchasing or trying on an item, the device sends the feedback data to the server. The server stores the feedback information in a database and uses it to improve future recommendations.

[0623] Examples of specific cases and prompt statements

[0624] The user opens the application and enters their name, age, gender, fashion preferences (casual, elegant, etc.), and budget (under 30,000 yen per month, etc.). Next, they are asked, "What's your favorite color?" and the user answers, "Blue." Then they are asked, "What kind of clothes do you usually wear?" and they answer, "Jeans and T-shirts." After that, the system's emotion engine analyzes that the user is "relaxed" and suggests, "A relaxed style is recommended for today. How about relaxed-fit jeans and a soft cardigan?"

[0625] Example of a prompt

[0626] Username: User A, Preferred Style: Casual, Current Mood: Relaxed

[0627] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0628] Step 1:

[0629] Users enter personal information such as their name, age, gender, fashion preferences, and budget via their smartphone. The device sends the entered information to the server. The server, upon receiving the user's input data, stores that information in a database.

[0630] Step 2:

[0631] Users input their preferred styles, colors, and items using a chat interface. This conversational data is sent from the terminal to the server. The server analyzes the received data using a natural language processing engine and stores data about the user's fashion preferences in a database.

[0632] Step 3:

[0633] The emotion engine analyzes the user's emotional state from their input text and voice. The device sends the user's emotional data to the server, which stores it in a database. The emotion engine analyzes the text and voice data and generates emotional labels such as "relaxed," "joyful," and "excited."

[0634] Step 4:

[0635] The server uses a generative AI model to suggest the optimal fashion outfit based on user information, fashion preference data, sentiment data, and trend information. The generated outfit is output in the form of, for example, "white blouse, black skinny jeans, red pumps." The outfit result is sent from the server to the terminal.

[0636] Step 5:

[0637] The user sends a request from their device to virtually try on the suggested outfit. The device sends 3D model data for the virtual try-on to the server, which generates the virtual model using a 3D rendering engine. The generated virtual model is sent from the server to the device and displayed to the user.

[0638] Step 6:

[0639] The server generates purchase links for the suggested fashion items. These purchase links are provided as affiliate links to partner online shops. The server sends the generated links to the user's device, where they are displayed. The user can then purchase the desired items.

[0640] Step 7:

[0641] Users input feedback into a terminal after purchasing or trying on items. The terminal sends the feedback data to a server, where it is stored in a database. The server updates the generated AI model based on the collected feedback and incorporates it into future fashion coordination suggestions.

[0642] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0643] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0644] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0645] [Second Embodiment]

[0646] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0647] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0648] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0649] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0650] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0651] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0652] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0653] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0654] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0655] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0656] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0657] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0658] System Overview

[0659] This invention is a system that provides personalized fashion advice to users, suggesting optimal outfits using user information, fashion preferences, and trend information. Its aim is to comprehensively support users' fashion choices through features such as virtual fitting rooms, product purchase assistance, and feedback collection.

[0660] Key components of the system

[0661] 1. User information input means

[0662] Users enter personal information such as their name, age, gender, fashion preferences, and budget using the application.

[0663] The device collects this information and sends it to the server.

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

[0665] 2. Methods for collecting fashion preferences

[0666] Users specify their preferred style, color, and items through a chat interface.

[0667] The terminal sends this conversation data to the server.

[0668] The server uses a natural language processing engine to analyze the input data and saves the user's preferences to a database.

[0669] 3. Means of proposing fashion items

[0670] The server generates optimal fashion coordinates by matching user information and preference data with trend information.

[0671] The terminal displays this to the user.

[0672] 4. Virtual fitting room means

[0673] The user requests to virtually try on the suggested outfit.

[0674] The terminal sends 3D model data for virtual try-on to the server.

[0675] The server uses a 3D rendering engine to generate a 3D model for virtual try-on and sends it to the terminal.

[0676] The device displays the results of the virtual try-on to the user.

[0677] 5. Means of providing purchase links

[0678] The server generates purchase links (e.g., affiliate links to partner online shops) for the suggested fashion items.

[0679] The terminal displays this to the user.

[0680] 6. Methods for collecting feedback

[0681] Users fill out a form to provide feedback after purchasing or trying on an item.

[0682] The device sends feedback data to the server.

[0683] The server saves the feedback information to a database and incorporates it into future proposals.

[0684] Specific example

[0685] User registration and initial outfit suggestion

[0686] 1. The user opens the application for the first time and enters their name, age, gender, fashion preference (e.g., casual, elegant), and budget (e.g., less than 30,000 yen per month).

[0687] 2. The terminal sends the entered information to the server, and the server stores it in the database.

[0688] 3. The user uses the chat interface to enter their favorite color (e.g., blue) and the type of clothing they usually wear (e.g., jeans or a T-shirt).

[0689] 4. The terminal sends conversation data to the server, which uses a natural language processing engine to analyze the user's information and record it in a database.

[0690] 5. Based on user preference data and trend data, the server generates a casual yet elegant style outfit (e.g., white blouse, black skinny jeans, red pumps) and sends it to the terminal.

[0691] 6. The device displays recommended outfits to the user, and the user requests a virtual try-on.

[0692] 7. The device sends a virtual try-on request to the server, the server generates a virtual model using a 3D rendering engine, and sends it to the device.

[0693] 8. The device displays the results of the virtual try-on to the user, and the user clicks the purchase link for the items they like.

[0694] 9. The device proceeds with the purchase process, the server stores the purchase data, and the affiliate commission is earned.

[0695] 10. One week after purchase, the server sends a follow-up message to the user, who then provides feedback.

[0696] 11. The server saves the feedback to a database and incorporates it into future suggestions.

[0697] In this way, each component works together to provide users with a personalized fashion experience.

[0698] The following describes the processing flow.

[0699] Step 1:

[0700] The user opens the application and enters basic information such as their name, age, gender, fashion preferences, and budget.

[0701] Step 2:

[0702] The terminal sends the entered information to the server. Specifically, it sends user data to the server via an API.

[0703] Step 3:

[0704] The server saves the received information to the database. The database stores the information in the user profile table.

[0705] Step 4:

[0706] Users specify their preferred style, colors, and the types of clothes they usually wear through a chat interface.

[0707] Step 5:

[0708] The terminal sends the input dialogue data to the server. The dialogue data is sent in text format and passed to the server via an API.

[0709] Step 6:

[0710] The server uses a natural language processing engine to analyze the user's input data. The analysis results are recorded in a database as the user's preferences and needs.

[0711] Step 7:

[0712] The server analyzes user information and preference data, along with trend information, to generate the optimal fashion coordinate. For example, the coordinate might consist of a white blouse, black skinny jeans, and red pumps.

[0713] Step 8:

[0714] The server sends the generated outfit to the device. Specifically, the outfit data is passed to the device via an API.

[0715] Step 9:

[0716] The device displays outfit suggestions to the user. The user can review these and choose to virtually try them on.

[0717] Step 10:

[0718] The user selects a virtual try-on, and the device sends a virtual try-on request to the server. The request includes information about the selected outfit.

[0719] Step 11:

[0720] The server uses a 3D rendering engine to generate a 3D model of the virtual try-on garment. The model data for the virtual try-on garment is prepared.

[0721] Step 12:

[0722] The server sends the generated 3D model data to the terminal. The terminal receives the model data upon request.

[0723] Step 13:

[0724] The device displays the results of the virtual try-on to the user. The user reviews the results and decides which items they like.

[0725] Step 14:

[0726] The user clicks the purchase link and proceeds with the purchase of the item they like. The device sends the purchase data to the server.

[0727] Step 15:

[0728] The server receives purchase data and stores it in the database. Simultaneously, it records the commissions for affiliate marketing.

[0729] Step 16:

[0730] One week after purchase, the server will send a follow-up message to the user. The message will include a link to a feedback form.

[0731] Step 17:

[0732] The user submits their opinions and feedback by filling out a feedback form. The device then sends the entered feedback data to the server.

[0733] Step 18:

[0734] The server receives the feedback and stores it in the database. The feedback will be incorporated into the next proposal.

[0735] Step 19:

[0736] The server optimizes the next outfit suggestion based on collected feedback and user profiles. The server generates a new outfit and sends it to the device.

[0737] This series of processes makes it possible to provide users with a personalized fashion experience.

[0738] (Example 1)

[0739] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0740] Traditional fashion suggestion systems struggled to provide personalized recommendations that fully reflected user preferences and trend information. Furthermore, the lack of integrated features such as virtual try-on functionality, purchase links, feedback collection, and the ability to incorporate feedback into future suggestions resulted in a fragmented user experience, making it difficult to provide optimal outfits.

[0741] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0742] In this invention, the server includes means for inputting information about the user, means for collecting the user's fashion preferences, means for suggesting fashion items based on the user information and the user's fashion preferences, means for providing a virtual fitting room, means for providing purchase links for the fashion items, means for collecting user feedback, means for optimizing the next suggestion based on the feedback, means for analyzing user input using a natural language processing engine, means for using a generative AI model that suggests the optimal fashion items by matching user information, preference data, and trend information, and means for using a three-dimensional rendering engine that generates a three-dimensional model of the virtual fitting. This enables highly personalized fashion suggestions tailored to the user's preferences, resulting in an integrated user experience and a system that is efficient and easy to use.

[0743] A "user" refers to a person who uses this system and is the entity that provides personal information such as name, age, gender, fashion preferences, and budget.

[0744] A "user information input method" is a means for users to input personal information such as their name, age, gender, fashion preferences, and budget.

[0745] A "fashion preference collection method" refers to a means of collecting a user's preferred style, colors, items, etc.

[0746] "Fashion item suggestion means" refers to a means for suggesting fashion items based on the above-mentioned information about the user and the user's fashion preferences.

[0747] A "virtual fitting room system" is a means for users to virtually try on suggested fashion items.

[0748] "Method of providing purchase links" refers to a means of providing purchase links for proposed fashion items (for example, affiliate links to partner online shops).

[0749] "Feedback collection methods" refer to methods for collecting user feedback and obtaining information to optimize future proposals based on this feedback.

[0750] A "natural language processing engine" is an engine used to analyze user input information and has the function of analyzing the meaning of text.

[0751] A "generative AI model" is an artificial intelligence model used to suggest the most suitable fashion items by matching user information, preference data, and trend information.

[0752] A "three-dimensional rendering engine" is an engine used to generate three-dimensional models for virtual try-on.

[0753] This invention is a system that provides personalized fashion advice to users. It uses user information, fashion preferences, and trend information to suggest optimal outfits, and provides support for virtual fitting rooms, product purchases, and feedback collection. This invention consists of the following main components:

[0754] User information input means

[0755] The user uses the application to enter personal information such as name, age, gender, fashion preferences, and budget. The device collects this information and sends it to the server. The server stores the received information in a database.

[0756] Fashion preferences and collecting methods

[0757] Users specify their preferred style, color, and items using a chat interface. The device sends this conversational data to a server, which uses a natural language processing engine (e.g., Google Cloud Natural Language API) to analyze the input data and store the user's preferences in a database.

[0758] Fashion Item Proposal Method

[0759] The server generates the optimal fashion coordinate based on user information and preference data, matching it with trend information (e.g., the latest fashion magazine data). Specifically, a generative AI model is used to generate the fashion coordinate. The generated coordinate is sent to the terminal, which then displays it to the user.

[0760] Virtual fitting room method

[0761] The user sends a request to virtually try on the suggested outfit. The device sends 3D model data for the virtual try-on to the server, which generates a 3D model of the virtual try-on using a 3D rendering engine (e.g., Unity3D) and sends it back to the device. The device then displays the results of the virtual try-on to the user.

[0762] Purchase link provision method

[0763] The server generates a purchase link (e.g., an affiliate link to a partner online shop) for the suggested fashion item. The terminal then displays this to the user.

[0764] Feedback collection methods

[0765] The user fills out a form to provide feedback after purchase or trying on an item. The device sends the feedback data to the server, which stores the feedback information in a database. The stored feedback is then used to inform future suggestions.

[0766] Specific example

[0767] User registration and initial outfit suggestion

[0768] 1. The user opens the application for the first time and enters their name, age, gender, fashion preference (e.g., casual, elegant), and budget (e.g., less than 30,000 yen per month). The device sends the entered information to the server, which stores it in a database.

[0769] 2. The user uses the chat interface to input their favorite color (e.g., blue) and the type of clothing they usually wear (e.g., jeans or a T-shirt). The terminal sends the conversation data to the server, which uses a natural language processing engine to analyze the user's information and record it in a database.

[0770] 3. Based on user preference data and trend data, the server generates a casual yet elegant style outfit (e.g., white blouse, black skinny jeans, red pumps) and sends it to the terminal.

[0771] 4. The device displays recommended outfits to the user, and the user requests a virtual try-on. The device sends a virtual try-on request to the server, which generates a virtual model using a 3D rendering engine and sends it to the device.

[0772] 5. The terminal displays the results of the virtual try-on to the user, and the user clicks the purchase link for the items they like. The terminal proceeds with the purchase process, the server saves the purchase data, and earns affiliate commissions. One week after the purchase, the server sends a follow-up message to the user, who provides feedback. The server saves the feedback in its database and uses it to improve future recommendations.

[0773] In this way, each component works together to provide users with a personalized fashion experience.

[0774] Example of a prompt

[0775] "Please tell us your favorite fashion style, colors, and items."

[0776] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0777] Step 1: Collecting User Information

[0778] 1-1. The user launches the application and enters personal information such as name, age, gender, fashion preferences, and budget.

[0779] Input: Name, age, gender, fashion preferences, budget

[0780] Specific action: The user logs into the app from their smartphone or PC and enters the required information into the form.

[0781] 1-2. The terminal collects the entered information and sends it to the server.

[0782] Output: Entered user information

[0783] Specific operation: The device sends the input information to the server in real time, and a confirmation message is displayed to confirm successful transmission.

[0784] 1-3. The server saves the received information to the database.

[0785] Output: User information stored in the database

[0786] Specific operation: The server stores the received information in the database, and the saving of user information is confirmed.

[0787] Step 2: Collect your fashion preferences

[0788] 2-1. Users use the chat interface to specify their preferred style, color, and items.

[0789] Input: Preferred style, color, item

[0790] Specific action: The user enters "I like casual clothes and blue, and I usually wear jeans and t-shirts."

[0791] 2-2. The terminal sends the user's input to the server as text data.

[0792] Output: Sent preference data

[0793] Specific action: The terminal formats this as text data and sends it to the server.

[0794] 2-3. The server analyzes the input data using a natural language processing engine.

[0795] Input: Submitted preference data

[0796] Output: Analyzed preference data

[0797] Specific operation: The server uses a natural language processing engine to extract keywords such as "casual," "blue," "jeans," and "T-shirt."

[0798] 2-4. The server saves the analysis results to the database.

[0799] Output: Preference data stored in the database

[0800] Specific operation: The server saves the preferred data to the database, and a confirmation message is displayed.

[0801] Step 3: Fashion Coordination Suggestions

[0802] 3-1. The server matches user information, preference data, and trend information.

[0803] Input: User information, preference data, trend information

[0804] Output: Matched data

[0805] Specific operation: The server retrieves user information and trend information from the database and executes database queries to match them.

[0806] 3-2. The server generates the optimal fashion coordinate using an AI model for coordinate generation.

[0807] Input: Matched data

[0808] Output: Generated coordinate

[0809] Specific operation: The server generates outfits based on the user's preferences, such as "white blouse, black skinny jeans, and red pumps."

[0810] 3-3. The server sends the generated coordinate to the terminal.

[0811] Output: Coordinate sent to the terminal

[0812] Specific operation: The server sends the generated coordination information to the terminal, and a message indicating successful transmission is displayed.

[0813] 3-4. The device displays the outfit to the user.

[0814] Output: Coordinates displayed to the user

[0815] Specific action: The device displays an outfit to the user, such as "white blouse, black skinny jeans, red pumps," and a notification is issued asking for confirmation.

[0816] Step 4: Perform a virtual try-on.

[0817] 4-1. The user requests to virtually try on the item.

[0818] Input: Request for virtual try-on

[0819] Specific action: The user clicks a button that says, "I want to virtually try on this outfit."

[0820] 4-2. The terminal sends 3D model data for virtual try-on to the server.

[0821] Input: User body shape data, outfit data

[0822] Output: Sent 3D model data

[0823] Specific operation: The device sends the user's body shape data and outfit information to the server.

[0824] 4-3. The server uses a 3D rendering engine to generate a 3D model for virtual try-on.

[0825] Input: Submitted 3D model data

[0826] Output: Generated 3D model

[0827] Specific operation: The server uses a 3D rendering engine to generate a 3D model for virtual try-on.

[0828] 4-4. The server sends the generated 3D model to the terminal.

[0829] Output: 3D model sent to the terminal

[0830] Specific operation: The server sends the generated 3D model to the terminal, and a confirmation message is displayed.

[0831] 4-5. The terminal displays the results of the virtual try-on to the user.

[0832] Output: Virtual fitting results displayed to the user

[0833] Specific operation: The device displays a 3D model, and the user can see the results of a virtual try-on.

[0834] Step 5: Provide the purchase link

[0835] 5-1. The server generates a purchase link for the suggested fashion item.

[0836] Input: Suggested fashion item information

[0837] Output: Generated purchase link

[0838] Specific operation: The server generates a purchase URL for each item and creates a link.

[0839] 5-2. The server sends the generated purchase link to the device.

[0840] Output: Purchase link sent to the device

[0841] Specific operation: The server sends the generated purchase link to the device, and the link is displayed on the user's screen.

[0842] 5-3. The terminal displays this to the user.

[0843] Output: Purchase link displayed to the user

[0844] Specific action: The device displays a link saying "You can purchase it here," allowing the user to click it.

[0845] Step 6: Gathering Feedback

[0846] 6-1. The user fills out a form to provide feedback after purchase or after trying on the item.

[0847] Input: Feedback after purchase or try-on

[0848] Specific action: The user enters their opinions and feedback through a feedback form.

[0849] 6-2. The device sends feedback data to the server.

[0850] Output: Sent feedback data

[0851] Specific action: The terminal sends the input feedback to the server.

[0852] 6-3. The server saves the feedback information to the database.

[0853] Output: Feedback information stored in the database

[0854] Specific operation: The server stores the received data in the database, and a confirmation message for saving is displayed.

[0855] 6-4. The server incorporates the feedback into the next proposal.

[0856] Input: Saved feedback information

[0857] Output: Feedback reflected in the next proposal

[0858] Specific operation: The server optimizes the next coordination suggestion based on the feedback information.

[0859] The above outlines the specific processing steps of the program for this system.

[0860] (Application Example 1)

[0861] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0862] Traditional fashion advice systems had limitations in providing personalized fashion suggestions to users, particularly in effectively linking trend information with user preferences. Furthermore, virtual try-on features failed to adequately replicate the feeling of actually trying on clothes, resulting in insufficient user satisfaction. Additionally, mechanisms for collecting post-purchase feedback and incorporating it into future suggestions were incomplete.

[0863] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0864] In this invention, the server includes means for inputting user information, means for collecting fashion preferences, means for suggesting optimal fashion items based on trend information and user preference data using a generative AI model, means for providing a virtual fitting room, means for providing a purchase link, means for collecting post-purchase feedback, and means for sending post-purchase follow-up messages. This makes it possible to provide users with a more personalized and realistic fashion experience and improve user satisfaction.

[0865] "Means of inputting user information" refers to methods of collecting personal information such as the user's name, age, gender, fashion preferences, and budget through a terminal or application, and transmitting it to a server.

[0866] "Means of collecting fashion preferences" refers to a method by which users specify their preferred styles, colors, items, etc., using a chat interface or other input method, and send that data to a server.

[0867] A "generative AI model" is an artificial intelligence model that uses user information and preference data to match with trend information and suggest the most suitable fashion items.

[0868] A "virtual fitting room" is a system that allows users to virtually try on suggested fashion items. It uses 3D rendering technology to generate 3D models of the items to be virtually tried on and displays them to the user.

[0869] "Means of providing purchase links" refers to a means of generating and displaying to the user a link that allows them to purchase the proposed fashion item.

[0870] "Means of collecting post-purchase feedback" refers to providing a form for users to enter their opinions and impressions after purchasing or trying on an item, and then sending that feedback data to a server and storing it in a database.

[0871] "Method for sending follow-up messages after purchase" refers to a method for sending messages from a server to a user after they have purchased an item, in order to check on their experience and satisfaction with the item.

[0872] "Means of acquiring trend information" refers to methods of obtaining the latest trend information from external fashion-related databases or APIs and storing it on a server.

[0873] This invention is a system that provides personalized fashion advice to users. Specifically, it proposes the optimal outfit using user information, fashion preferences, and trend information. The aim of this system is to comprehensively support users in choosing their fashion through features such as virtual fitting rooms, assistance with product purchases, and feedback collection.

[0874] Key components of the system

[0875] 1. User information input means

[0876] Users use their devices to enter personal information such as their name, age, gender, fashion preferences, and budget. This information is sent from the device to the server, which stores the received information in a database.

[0877] 2. Methods for collecting fashion preferences

[0878] Users specify their preferred style, color, and items through a chat interface. The terminal sends this conversational data to a server, which uses a natural language processing engine to analyze the input data and store the user's preferences in a database.

[0879] 3. Proposed method using a generative AI model

[0880] The server generates optimal fashion coordinates based on user information and preference data, matching them with trend information. This is where a generation AI model is utilized. The generated fashion item recommendations are displayed to the user via their device.

[0881] 4. Virtual fitting room means

[0882] When a user requests to virtually try on a suggested outfit, the device sends 3D model data of the outfit to the server. The server uses a 3D rendering engine to generate a 3D model of the outfit and sends it to the device. The device then displays the results of the virtual try-on to the user.

[0883] 5. Means of providing purchase links

[0884] The server generates a purchase link (e.g., an affiliate link to a partner online shop) for the suggested fashion item. This allows the user to easily purchase the item. The terminal displays this to the user.

[0885] 6. Methods for collecting feedback

[0886] When a user fills out a form to provide feedback after a purchase or try-on, the data is sent from the device to the server and stored in a database. The server then uses the feedback information to improve future suggestions.

[0887] 7. Means of sending follow-up messages

[0888] The server sends a follow-up message after a user purchases an item to inquire about their experience and satisfaction with it. This allows for further collection of user feedback, which can then be used to improve future offerings.

[0889] Specific examples of actions

[0890] In a scenario where a user is using the application for the first time, the following prompt will be displayed:

[0891] Prompt: New user registration

[0892] name

[0893] age

[0894] sex

[0895] budget

[0896] style

[0897] Prompt: Collect your preferences details

[0898] Favorite color: Blue

[0899] Everyday clothing items: Jeans, T-shirts

[0900] Prompt: Generate recommended items

[0901] Prompt: Try on clothes virtually

[0902] Prompt: Purchase link displayed

[0903] Prompt: Feedback collection

[0904] This system allows users to receive personalized fashion suggestions and further enhance their experience by using a virtual try-on function. This improves user satisfaction and enables the optimization of future suggestions through the collection of feedback.

[0905] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0906] Step 1:

[0907] The user opens the application and enters their initial registration information (name, age, gender, fashion preferences, budget). The device sends this input data to the server. The server saves the received user information to its database. Through this process, basic user information is recorded in the database.

[0908] Input: User registration information (name, age, gender, fashion preferences, budget)

[0909] Output: User information stored in the database

[0910] Step 2:

[0911] Users specify their preferred style, colors, items, etc., using a chat interface. The terminal sends this conversational data to the server. The server analyzes the input data using a natural language processing engine and stores the user's preference data in a database. This allows for the accumulation of detailed user preference information.

[0912] Input: User interaction data (preferred style, color, item)

[0913] Output: User preference data stored in the database

[0914] Step 3:

[0915] The server generates optimal fashion coordinates by matching user information and preference data with trend information. This is where a generation AI model is utilized. The generated fashion item recommendations are sent to the device and displayed to the user. This provides personalized fashion suggestions for each individual user.

[0916] Input: User information, preference data, trend information

[0917] Output: Fashion coordination suggestions sent to the terminal

[0918] Step 4:

[0919] The user sends a request to virtually try on suggested fashion items. The device sends this request to the server. The server generates a 3D model of the virtual try-on using a 3D rendering engine and sends it to the device. The device displays the virtual try-on results to the user. This allows the user to virtually try on the suggested items.

[0920] Input: User's virtual try-on request

[0921] Output: 3D model and virtual try-on results sent to the terminal

[0922] Step 5:

[0923] The server generates purchase links for items the user likes after a virtual try-on. These purchase links are structured as affiliate links to partner online shops. The terminal displays these links to the user, providing them with an environment where they can actually purchase the items.

[0924] Input: Information about items the user liked

[0925] Output: Purchase link displayed on the device

[0926] Step 6:

[0927] After a user purchases an item, the server sends a follow-up message prompting the user to provide feedback. When the user fills out a feedback form, the device sends the feedback data to the server. The server stores this feedback information in a database and uses it to improve future suggestions. This allows for further service improvements based on user feedback.

[0928] Input: User feedback data

[0929] Output: Feedback information stored in the database

[0930] Step 7:

[0931] The server performs data analysis based on user feedback to optimize future recommendations. This analysis data is then fed back into the generating AI model, enabling more accurate fashion item recommendations.

[0932] Input: Feedback Information

[0933] Output: Analysis data fed back into the generated AI model

[0934] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0935] System Overview

[0936] This invention is a system that provides personalized fashion advice to users, suggesting optimal outfits using user information, fashion preferences, trend information, and the user's emotional state. Its aim is to comprehensively support users' fashion choices through features such as virtual fitting rooms, product purchase assistance, and feedback collection.

[0937] Key components of the system

[0938] 1. User information input means

[0939] Users enter personal information such as their name, age, gender, fashion preferences, and budget using the application.

[0940] The device collects this information and sends it to the server.

[0941] The server stores the received information in a database.

[0942] 2. Methods for collecting fashion preferences

[0943] Users specify their preferred style, color, and items through a chat interface.

[0944] The terminal sends this conversation data to the server.

[0945] The server uses a natural language processing engine to analyze the input data and saves the user's preferences to a database.

[0946] 3. Means of proposing fashion items

[0947] The server analyzes user information and preference data, along with trend information, to generate the optimal fashion coordinate. For example, the coordinate might consist of a white blouse, black skinny jeans, and red pumps.

[0948] The terminal displays this to the user.

[0949] 4. Virtual fitting room means

[0950] The user requests to virtually try on the suggested outfit.

[0951] The terminal sends 3D model data for virtual try-on to the server.

[0952] The server uses a 3D rendering engine to generate a 3D model for virtual try-on and sends it to the terminal.

[0953] The device displays the results of the virtual try-on to the user.

[0954] 5. Means of providing purchase links

[0955] The server generates purchase links (e.g., affiliate links to partner online shops) for the suggested fashion items.

[0956] The terminal displays this to the user.

[0957] 6. Methods for collecting feedback

[0958] Users fill out a form to provide feedback after purchasing or trying on an item.

[0959] The device sends feedback data to the server.

[0960] The server saves the feedback information to a database and incorporates it into future proposals.

[0961] 7. Emotional Engine

[0962] When a user uses the conversational interface, the emotion engine analyzes the user's emotional state from their input text and voice.

[0963] The device sends user emotion data to the server.

[0964] The server adjusts suggested fashion items and outfits based on emotional data.

[0965] Specific example

[0966] Coordination suggestions that take emotions into consideration

[0967] 1. The user opens the application for the first time and enters their name, age, gender, fashion preference (e.g., casual, elegant), and budget (e.g., less than 30,000 yen per month).

[0968] 2. The terminal sends the entered information to the server, and the server stores it in the database.

[0969] 3. The user uses the chat interface to enter their favorite color (e.g., blue) and the type of clothing they usually wear (e.g., jeans or a T-shirt).

[0970] 4. The terminal sends conversation data to the server, which uses a natural language processing engine to analyze the user's information and record it in a database.

[0971] 5. The emotion engine identifies the user's emotional state from their dialogue data and voice data, and analyzes emotional data such as happy, calm, and excited.

[0972] 6. The server generates fashion coordinates appropriate to the user's emotional state based on their emotional data, preference data, and trend data. For example, if the user is relaxed, it will suggest a casual and comfortable style (e.g., relaxed-fit jeans, a soft cardigan).

[0973] 7. The server sends the generated coordinate to the terminal, and the terminal displays it to the user.

[0974] 8. If the user requests a virtual try-on, the device sends a virtual try-on request to the server.

[0975] 9. The server generates a virtual model using a 3D rendering engine and sends it to the terminal.

[0976] 10. The device displays the results of the virtual try-on to the user, and the user clicks the purchase link for the items they like.

[0977] 11. The device proceeds with the purchase process, the server saves the purchase data, and the affiliate commission is earned.

[0978] 12. One week after purchase, the server sends a follow-up message to the user, who then provides feedback.

[0979] 13. The server saves the feedback to a database and incorporates it into future suggestions.

[0980] By combining these emotion engines, it becomes possible to provide a more personalized fashion experience that responds to the user's emotional state.

[0981] The following describes the processing flow.

[0982] Step 1:

[0983] The user opens the application and enters their name, age, gender, fashion preference (e.g., casual, elegant), and budget (e.g., under 30,000 yen per month).

[0984] Step 2:

[0985] The terminal sends the entered user information to the server. A method using an API to send data is employed.

[0986] Step 3:

[0987] The server saves the received user information to the database. The information is stored in the user profile table.

[0988] Step 4:

[0989] Users specify their preferred styles, colors, and the types of clothes they usually wear through a chat interface. For example, a user might input that they like blue, jeans, and t-shirts.

[0990] Step 5:

[0991] The device sends the collected conversation data to the server. The conversation data is sent in text format via the API.

[0992] Step 6:

[0993] The server uses a natural language processing engine to analyze user dialogue data. The analysis results are recorded in a database as user preferences and needs.

[0994] Step 7:

[0995] The emotion engine analyzes the user's input text and voice data to identify their emotional state. For example, it can analyze whether the user is happy, calm, or excited.

[0996] Step 8:

[0997] The device sends user emotion data to the server. This emotion data is retrieved in conjunction with a natural language processing engine.

[0998] Step 9:

[0999] The server comprehensively analyzes user preference data, emotional data, and trend information to generate fashion coordinates that suit the user's emotional state. For example, if the user is relaxed, it will suggest relaxed-fit jeans or a soft cardigan.

[1000] Step 10:

[1001] The server sends the generated outfit suggestions to the user's device. The outfit data is sent to the user's device via the API.

[1002] Step 11:

[1003] The device displays outfit suggestions to the user. The user can review the suggestions and choose whether or not they wish to virtually try them on.

[1004] Step 12:

[1005] If a user wishes to virtually try on clothes, the device sends a virtual try-on request to the server. The request includes information about the selected outfit.

[1006] Step 13:

[1007] The server uses a 3D rendering engine to generate a 3D model for virtual try-on. The data for the virtual model is prepared.

[1008] Step 14:

[1009] The server sends the generated 3D model data to the terminal. The terminal receives the model data upon request.

[1010] Step 15:

[1011] The device displays the results of the virtual try-on to the user. The user reviews the results and clicks the purchase link for the items they like.

[1012] Step 16:

[1013] The user clicks the purchase link and proceeds with the purchase of the item they like. The device sends the purchase data to the server.

[1014] Step 17:

[1015] The server receives the purchase data and saves it to the database. At the same time, affiliate marketing commissions are recorded.

[1016] Step 18:

[1017] One week after purchase, the server will send a follow-up message to the user. The message will include a link to a feedback form.

[1018] Step 19:

[1019] The user submits their opinions and feedback by filling out a feedback form. The device then sends the entered feedback data to the server.

[1020] Step 20:

[1021] The server receives the feedback and stores it in the database. The feedback will be incorporated into the next proposal.

[1022] Step 21:

[1023] The server optimizes the next outfit suggestion based on the collected feedback and user profile. A new outfit is generated and sent to the device.

[1024] This series of processes makes it possible to provide a personalized fashion experience that takes into account the user's emotional state.

[1025] (Example 2)

[1026] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[1027] In modern society, the diversification of individual preferences and trends in fashion makes it difficult for users to choose the most suitable fashion items for themselves. Furthermore, there is a lack of systems that can appropriately reflect the influence of a user's emotional state on their fashion choices, making it difficult to realize personalized suggestions. Moreover, there is a lack of mechanisms to achieve a higher level of personalization through virtual try-on and feedback. To solve these problems, the system proposed in this invention makes it possible to suggest fashion items that take into account user information, preferences, and emotional state.

[1028] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1029] In this invention, the server includes means for inputting information about the user, means for collecting the user's fashion preferences, and means for analyzing the user's emotional state. This makes it possible to suggest optimal fashion items based on the user's detailed information and preferences, as well as their emotional state.

[1030] "User information" refers to personal data entered by the user, such as name, age, gender, fashion preferences, and budget.

[1031] A "fashion preference collection method" is an interface and mechanism for processing information that allows users to provide the system with their preferred styles, colors, and clothing items.

[1032] "Fashion item suggestion means" refers to a function for generating optimal fashion coordinates based on user information and fashion preferences.

[1033] A "virtual fitting room" is a function that allows users to virtually try on suggested fashion items using the system.

[1034] The "purchase link provision method" is a function that generates and provides links to facilitate the purchase of proposed fashion items.

[1035] A "feedback collection method" is a function for collecting opinions and impressions from users regarding the results of their purchases or try-ons.

[1036] A "database" is a collection of information that stores user input and feedback information and is accessible as needed.

[1037] A "natural language processing engine" is a software system that analyzes text and audio data input by users and extracts meaning from them.

[1038] A "sentiment analysis engine" is a software system that analyzes a user's emotional state from their input text or voice and provides the results.

[1039] Modes for carrying out the invention

[1040] This invention is a system that provides personalized fashion advice to users. The system proposes the optimal outfit using user information, fashion preferences, trend information, and the user's emotional state. It aims to comprehensively support users in choosing their fashion through features such as virtual fitting rooms, product purchase assistance, and feedback collection.

[1041] The system includes the following main components:

[1042] User information input means

[1043] Users enter personal information such as their name, age, gender, fashion preferences, and budget using the application.

[1044] The device collects this information and sends it to the server.

[1045] The server saves the received information to the database.

[1046] Fashion preferences and collecting methods

[1047] Users specify their preferred style, color, and items through a chat interface.

[1048] The terminal sends this conversation data to the server.

[1049] The server analyzes the input data using a natural language processing engine (such as OpenAI's GPT-3) and stores the user's preferences in a database.

[1050] sentiment analysis tool

[1051] When a user uses the conversational interface, the emotion engine analyzes the user's emotional state from their input text and voice.

[1052] The device sends user emotion data to the server.

[1053] The server adjusts suggested fashion items and outfits based on emotional data.

[1054] Fashion Item Proposal Method

[1055] The server generates optimal fashion coordinates based on user information and preference data, combined with trend information. Specifically, it suggests items such as a white blouse, black skinny jeans, and red pumps.

[1056] The device displays this to the user.

[1057] Virtual fitting room method

[1058] The user sends a request to virtually try on the suggested outfit.

[1059] The device sends 3D model data for virtual try-on to the server.

[1060] The server generates a 3D model for virtual try-on using a 3D rendering engine (such as Unity 3D) and sends it to the terminal.

[1061] The device displays the results of the virtual try-on to the user.

[1062] Purchase link provision method

[1063] The server generates purchase links (such as affiliate links to partner online shops) for the suggested fashion items.

[1064] The device displays this to the user.

[1065] Feedback collection methods

[1066] Users fill out a form to provide feedback after purchasing or trying on an item.

[1067] The device sends feedback data to the server.

[1068] The server saves the feedback information to a database and incorporates it into future proposals.

[1069] Specific example

[1070] A process for suggesting outfits that take emotions into consideration

[1071] 1. The user opens the application for the first time and enters their name (e.g., Taro Tanaka), age (30 years old), gender (male), fashion preference (casual), and budget (under 30,000 yen per month).

[1072] 2. The terminal sends the entered information to the server, and the server saves it to the database.

[1073] 3. The user types "I like blue, and I usually wear jeans and a T-shirt" in the chat interface.

[1074] 4. The terminal sends conversation data to the server, and the server uses a natural language processing engine to analyze and store the data.

[1075] 5. The emotion engine identifies the emotional state of "relaxed" from the user's dialogue data and voice data, and stores the data in a database.

[1076] 6. Generate the optimal outfit (e.g., relaxed-fit jeans, soft cardigan) when the server is "relaxed".

[1077] 7. The server sends the generated coordinate to the terminal, and the terminal displays it to the user.

[1078] 8. The user requests a virtual try-on and sends a request from their device to the server.

[1079] 9. The server uses a 3D rendering engine to generate a model for virtual try-on and sends it to the terminal.

[1080] 10. The device displays the results of the virtual try-on to the user, and the user clicks the purchase link for the items they like.

[1081] 11. The device proceeds with the purchase process, the server saves the purchase data, and the affiliate receives the commission.

[1082] 12. One week after purchase, the server sends a follow-up message to the user, who then provides feedback.

[1083] Example of a prompt

[1084] "Please suggest casual fashion outfits that are suitable for when the user is relaxing."

[1085] "Please tell us what items would be good for users to wear when they seem to be having fun."

[1086] As a result, the system takes into account the user's detailed information and emotional state to provide highly personalized fashion suggestions.

[1087] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1088] Step 1:

[1089] The user launches the application and enters information such as their name, age, gender, fashion preferences, and budget.

[1090] Input: Name, age, gender, fashion preferences, budget

[1091] Output: User Information

[1092] Specific action: The user enters personal information such as "Taro Tanaka, 30 years old, male, casual attire, monthly income under 30,000 yen."

[1093] Step 2:

[1094] The terminal sends the entered user information to the server.

[1095] Input: User information

[1096] Output: User information sent to the server

[1097] Specific action: The device sends the information "Taro Tanaka, 30 years old, male, casual wear, monthly income under 30,000 yen" to the server.

[1098] Step 3:

[1099] The server saves the received user information to the database.

[1100] Input: User information sent to the server

[1101] Output: User information stored in the database

[1102] Specific action: The server records the information "Taro Tanaka, 30 years old, male, casual wear, monthly salary of 30,000 yen or less" in the database.

[1103] Step 4:

[1104] Users can use the chat interface to specify their preferred style, color, and items.

[1105] Input: Favorite style, color, item

[1106] Output: Preference information

[1107] Specific action: The user enters "I like blue, and I usually wear jeans and a T-shirt."

[1108] Step 5:

[1109] The terminal sends the conversation data to the server.

[1110] Input: Preference information

[1111] Output: Preference information sent to the server

[1112] Specific action: The device sends the information "I like blue and usually wear jeans and a T-shirt" to the server.

[1113] Step 6:

[1114] The server uses a natural language processing engine to analyze the input data and saves the user's preferences to a database.

[1115] Input: Preference information sent to the server

[1116] Output: Preference information stored in the database

[1117] Specific operation: The server uses a natural language processing engine such as OpenAI GPT-3 to extract keywords such as "blue, jeans, T-shirt" and save them to a database.

[1118] Step 7:

[1119] Users input text or voice through a conversational interface.

[1120] Input: Text or audio data

[1121] Output: Sentiment data

[1122] Specific action: The user types or speaks the phrase "I want to relax today."

[1123] Step 8:

[1124] The terminal sends the entered text or voice data to the server.

[1125] Input: Text or audio data

[1126] Output: Text and audio data sent to the server

[1127] Specific action: The device sends text or audio data of "I want to relax today" to the server.

[1128] Step 9:

[1129] The server's emotion engine analyzes the user's emotional state from text and audio.

[1130] Input: Text or audio data sent to the server

[1131] Output: Analyzed sentiment data

[1132] Specific operation: The server's emotion engine analyzes text and audio data to identify emotional states such as "relaxed."

[1133] Step 10:

[1134] The server adjusts suggested fashion items and outfits based on emotional data.

[1135] Input: Analyzed sentiment data

[1136] Output: Suggestions for tailored fashion items and outfits.

[1137] Specific operation: The server generates outfits such as "relaxed-fit jeans and a soft cardigan" based on sentiment data.

[1138] Step 11:

[1139] The server sends the generated outfit to the terminal.

[1140] Input: Suggestions for coordinated fashion items and outfits

[1141] Output: Fashion coordinates displayed to the user

[1142] Specific operation: The server sends the generated outfit to the terminal and displays suggestions to the user, such as "relaxed-fit denim, soft cardigan."

[1143] Step 12:

[1144] The user sends a request for a virtual try-on.

[1145] Input: Virtual try-on request

[1146] Output: Virtual fitting request data

[1147] Specific action: The user sends a request saying, "I want to virtually try on this outfit."

[1148] Step 13:

[1149] The device sends a request to the server for a virtual try-on.

[1150] Input: Virtual fitting request data

[1151] Output: Virtual try-on request data sent to the server

[1152] Specific operation: The terminal receives the user's request and sends it to the server.

[1153] Step 14:

[1154] The server uses a 3D rendering engine to generate a 3D model for the virtual try-on.

[1155] Input: Virtual try-on request data sent to the server

[1156] Output: 3D model data

[1157] Specific operation: The server uses a 3D rendering engine such as Unity 3D to generate a 3D model for virtual try-on.

[1158] Step 15:

[1159] The server sends the generated 3D model to the terminal.

[1160] Input: 3D model data

[1161] Output: 3D model data sent to the terminal

[1162] Specific operation: The server sends the generated 3D model to the terminal.

[1163] Step 16:

[1164] The device displays the results of the virtual try-on to the user.

[1165] Input: 3D model data sent to the terminal

[1166] Output: Virtual try-on results displayed to the user

[1167] Specific action: The device displays the results of the virtual try-on to the user, allowing the user to confirm them.

[1168] Step 17:

[1169] The server generates purchase links for the suggested fashion items.

[1170] Input: Suggestions for coordinated fashion items and outfits

[1171] Output: Purchase link

[1172] Specific operation: The server generates a purchase link (such as an affiliate link) for the suggested item.

[1173] Step 18:

[1174] The server sends a purchase link to the device.

[1175] Input: Purchase link

[1176] Output: Purchase link sent to the device

[1177] Specific action: The server sends the generated purchase link to the device.

[1178] Step 19:

[1179] The device displays a purchase link to the user.

[1180] Input: Purchase link sent to your device

[1181] Output: Purchase link displayed to the user

[1182] Specific action: The device displays a purchase link to the user, allowing the user to purchase the item.

[1183] Step 20:

[1184] The user purchases the item via the purchase link.

[1185] Input: Purchase link

[1186] Output: Purchase data

[1187] Specific action: The user clicks the purchase link and buys the item.

[1188] Step 21:

[1189] The server stores the purchase data and earns affiliate commissions.

[1190] Input: Purchase data

[1191] Output: Purchase data stored in the database, retrieved affiliate commissions.

[1192] Specific operation: The server stores the purchase data and receives affiliate commissions.

[1193] Step 22:

[1194] The server sends a follow-up message to the user, who then provides feedback.

[1195] Input: Purchase data

[1196] Output: Follow-up messages, feedback data

[1197] Specific action: One week after purchase, the server sends a follow-up message and the user enters feedback.

[1198] Step 23:

[1199] The device sends feedback data to the server.

[1200] Input: Feedback data

[1201] Output: Feedback data sent to the server

[1202] Specific action: The device sends user feedback data to the server.

[1203] Step 24:

[1204] The server saves the feedback information to a database and incorporates it into future proposals.

[1205] Input: Feedback data sent to the server

[1206] Output: Feedback information stored in the database, optimized next-generation suggestions.

[1207] Specific operation: The server saves the feedback information to a database and uses it to inform future suggestions.

[1208] (Application Example 2)

[1209] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[1210] Traditional fashion advice systems have a problem in that they cannot fully suggest the most suitable outfits for users because they do not take into account the user's emotional state. Furthermore, they lack sufficient integration of features that comprehensively support the user's online shopping experience, such as virtual try-on functionality and purchase links. As a result, users face the challenge of not being able to efficiently select fashion items that suit their preferences and mood.

[1211] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting information about the user, means for collecting the user's fashion preferences, means for collecting emotional data using an engine that analyzes emotional states and reflecting it in fashion item suggestions, means for providing a virtual fitting room, means for providing purchase links for the fashion items, and means for collecting user feedback and optimizing suggestions for the next time. This makes it possible to suggest more personalized fashion coordinates according to the user's emotional state.

[1212] A "user information input method" is a means for users to input personal information such as their name, age, gender, fashion preferences, and budget.

[1213] A "fashion preference collection method" is a means by which users specify their preferred styles, colors, and items using a chat interface, and the collection of that information is then performed.

[1214] A "fashion item suggestion method" is a method for generating optimal fashion coordinates by simultaneously analyzing trend information based on user information and preference data.

[1215] A "virtual fitting room means" is a method for generating 3D model data and displaying it to the user so that the user can virtually try on the suggested outfit.

[1216] A "purchase link provision method" is a means of generating purchase links for proposed fashion items and displaying them to the user.

[1217] A "feedback collection method" refers to a method of providing a form for users to provide feedback after purchase or trying on an item, and collecting that data.

[1218] An "emotion engine" is an engine that analyzes a user's emotional state from their input text or voice.

[1219] A "natural language processing engine" is an engine used to analyze user input information.

[1220] A "database" is a system for storing user input information and feedback information.

[1221] A "3D rendering engine" is an engine used to generate 3D models for virtual try-on.

[1222] System Configuration

[1223] This invention is a system that provides personalized fashion advice to users. This system proposes optimal outfits using user information, fashion preferences, trend information, and the user's emotional state. Its aim is to comprehensively support users' fashion choices through features such as virtual fitting rooms, product purchase assistance, and feedback collection.

[1224] Hardware and software used

[1225] The following hardware and software will be used.

[1226] Smartphone

[1227] server

[1228] Database (for example, Amazon RDS)

[1229] Natural language processing engine (e.g., Google NLP API)

[1230] Emotion engine (e.g., Microsoft Azure Emotion API)

[1231] 3D rendering engine (e.g., Unity 3D)

[1232] Collection of user information

[1233] Users enter personal information such as their name, age, gender, fashion preferences, and budget via their smartphone, and the device sends this information to a server. The server stores the received information in a database.

[1234] Fashion-loving collector

[1235] Users use a chat interface to input their preferred style, color, and items. The device sends this conversational data to a server, which uses a natural language processing engine to analyze the data and store the user's preferences in a database.

[1236] Analysis of emotional states

[1237] The emotion engine analyzes the user's emotional state from their dialogue and voice data. The device sends this emotional data to the server, which stores it in a database. The emotional state is then reflected in the suggested coordination.

[1238] Coordination suggestions

[1239] The server generates the optimal fashion coordinate based on user information, preference data, sentiment data, and trend information. The generated coordinate is then displayed to the user on their device.

[1240] Virtual fitting room

[1241] When a user requests to virtually try on a suggested outfit, the device sends 3D model data for the virtual try-on to the server. The server generates a virtual model using a 3D rendering engine and sends it to the device. The device then displays the results of the virtual try-on to the user.

[1242] Purchase link provided

[1243] The server generates a purchase link for the suggested fashion item. This link is, for example, an affiliate link to a partner online shop. The terminal displays this to the user, who then proceeds with the purchase.

[1244] Gathering feedback and optimizing future proposals

[1245] When a user provides feedback after purchasing or trying on an item, the device sends the feedback data to the server. The server stores the feedback information in a database and uses it to improve future recommendations.

[1246] Examples of specific cases and prompt statements

[1247] The user opens the application and enters their name, age, gender, fashion preferences (casual, elegant, etc.), and budget (under 30,000 yen per month, etc.). Next, they are asked, "What's your favorite color?" and the user answers, "Blue." Then they are asked, "What kind of clothes do you usually wear?" and they answer, "Jeans and T-shirts." After that, the system's emotion engine analyzes that the user is "relaxed" and suggests, "A relaxed style is recommended for today. How about relaxed-fit jeans and a soft cardigan?"

[1248] Example of a prompt

[1249] Username: User A, Preferred Style: Casual, Current Mood: Relaxed

[1250] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1251] Step 1:

[1252] Users enter personal information such as their name, age, gender, fashion preferences, and budget via their smartphone. The device sends the entered information to the server. The server, upon receiving the user's input data, stores that information in a database.

[1253] Step 2:

[1254] Users input their preferred styles, colors, and items using a chat interface. This conversational data is sent from the terminal to the server. The server analyzes the received data using a natural language processing engine and stores data about the user's fashion preferences in a database.

[1255] Step 3:

[1256] The emotion engine analyzes the user's emotional state from their input text and voice. The device sends the user's emotional data to the server, which stores it in a database. The emotion engine analyzes the text and voice data and generates emotional labels such as "relaxed," "joyful," and "excited."

[1257] Step 4:

[1258] The server uses a generative AI model to suggest the optimal fashion outfit based on user information, fashion preference data, sentiment data, and trend information. The generated outfit is output in the form of, for example, "white blouse, black skinny jeans, red pumps." The outfit result is sent from the server to the terminal.

[1259] Step 5:

[1260] The user sends a request from their device to virtually try on the suggested outfit. The device sends 3D model data for the virtual try-on to the server, which generates the virtual model using a 3D rendering engine. The generated virtual model is sent from the server to the device and displayed to the user.

[1261] Step 6:

[1262] The server generates purchase links for the suggested fashion items. These purchase links are provided as affiliate links to partner online shops. The server sends the generated links to the user's device, where they are displayed. The user can then purchase the desired items.

[1263] Step 7:

[1264] Users input feedback into a terminal after purchasing or trying on items. The terminal sends the feedback data to a server, where it is stored in a database. The server updates the generated AI model based on the collected feedback and incorporates it into future fashion coordination suggestions.

[1265] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1266] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1267] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[1268] [Third Embodiment]

[1269] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[1270] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1271] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1272] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[1273] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1274] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1275] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1276] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1277] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1278] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1279] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1280] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[1281] System Overview

[1282] This invention is a system that provides personalized fashion advice to users, suggesting optimal outfits using user information, fashion preferences, and trend information. Its aim is to comprehensively support users' fashion choices through features such as virtual fitting rooms, product purchase assistance, and feedback collection.

[1283] Key components of the system

[1284] 1. User information input means

[1285] Users enter personal information such as their name, age, gender, fashion preferences, and budget using the application.

[1286] The device collects this information and sends it to the server.

[1287] The server stores the received information in a database.

[1288] 2. Methods for collecting fashion preferences

[1289] Users specify their preferred style, color, and items through a chat interface.

[1290] The terminal sends this conversation data to the server.

[1291] The server uses a natural language processing engine to analyze the input data and saves the user's preferences to a database.

[1292] 3. Means of proposing fashion items

[1293] The server generates optimal fashion coordinates by matching user information and preference data with trend information.

[1294] The terminal displays this to the user.

[1295] 4. Virtual fitting room means

[1296] The user requests to virtually try on the suggested outfit.

[1297] The terminal sends 3D model data for virtual try-on to the server.

[1298] The server uses a 3D rendering engine to generate a 3D model for virtual try-on and sends it to the terminal.

[1299] The device displays the results of the virtual try-on to the user.

[1300] 5. Means of providing purchase links

[1301] The server generates purchase links (e.g., affiliate links to partner online shops) for the suggested fashion items.

[1302] The terminal displays this to the user.

[1303] 6. Methods for collecting feedback

[1304] Users fill out a form to provide feedback after purchasing or trying on an item.

[1305] The device sends feedback data to the server.

[1306] The server saves the feedback information to a database and incorporates it into future proposals.

[1307] Specific example

[1308] User registration and initial outfit suggestion

[1309] 1. The user opens the application for the first time and enters their name, age, gender, fashion preference (e.g., casual, elegant), and budget (e.g., less than 30,000 yen per month).

[1310] 2. The terminal sends the entered information to the server, and the server stores it in the database.

[1311] 3. The user uses the chat interface to enter their favorite color (e.g., blue) and the type of clothing they usually wear (e.g., jeans or a T-shirt).

[1312] 4. The terminal sends conversation data to the server, which uses a natural language processing engine to analyze the user's information and record it in a database.

[1313] 5. Based on user preference data and trend data, the server generates a casual yet elegant style outfit (e.g., white blouse, black skinny jeans, red pumps) and sends it to the terminal.

[1314] 6. The device displays recommended outfits to the user, and the user requests a virtual try-on.

[1315] 7. The device sends a virtual try-on request to the server, the server generates a virtual model using a 3D rendering engine, and sends it to the device.

[1316] 8. The device displays the results of the virtual try-on to the user, and the user clicks the purchase link for the items they like.

[1317] 9. The device proceeds with the purchase process, the server stores the purchase data, and the affiliate commission is earned.

[1318] 10. One week after purchase, the server sends a follow-up message to the user, who then provides feedback.

[1319] 11. The server saves the feedback to a database and incorporates it into future suggestions.

[1320] In this way, each component works together to provide users with a personalized fashion experience.

[1321] The following describes the processing flow.

[1322] Step 1:

[1323] The user opens the application and enters basic information such as their name, age, gender, fashion preferences, and budget.

[1324] Step 2:

[1325] The terminal sends the entered information to the server. Specifically, it sends user data to the server via an API.

[1326] Step 3:

[1327] The server saves the received information to the database. The database stores the information in the user profile table.

[1328] Step 4:

[1329] Users specify their preferred style, colors, and the types of clothes they usually wear through a chat interface.

[1330] Step 5:

[1331] The terminal sends the input dialogue data to the server. The dialogue data is sent in text format and passed to the server via an API.

[1332] Step 6:

[1333] The server uses a natural language processing engine to analyze the user's input data. The analysis results are recorded in a database as the user's preferences and needs.

[1334] Step 7:

[1335] The server analyzes user information and preference data, along with trend information, to generate the optimal fashion coordinate. For example, the coordinate might consist of a white blouse, black skinny jeans, and red pumps.

[1336] Step 8:

[1337] The server sends the generated outfit to the device. Specifically, the outfit data is passed to the device via an API.

[1338] Step 9:

[1339] The device displays outfit suggestions to the user. The user can review these and choose to virtually try them on.

[1340] Step 10:

[1341] The user selects a virtual try-on, and the device sends a virtual try-on request to the server. The request includes information about the selected outfit.

[1342] Step 11:

[1343] The server uses a 3D rendering engine to generate a 3D model of the virtual try-on garment. The model data for the virtual try-on garment is prepared.

[1344] Step 12:

[1345] The server sends the generated 3D model data to the terminal. The terminal receives the model data upon request.

[1346] Step 13:

[1347] The device displays the results of the virtual try-on to the user. The user reviews the results and decides which items they like.

[1348] Step 14:

[1349] The user clicks the purchase link and proceeds with the purchase of the item they like. The device sends the purchase data to the server.

[1350] Step 15:

[1351] The server receives purchase data and stores it in the database. Simultaneously, it records the commissions for affiliate marketing.

[1352] Step 16:

[1353] One week after purchase, the server will send a follow-up message to the user. The message will include a link to a feedback form.

[1354] Step 17:

[1355] The user submits their opinions and feedback by filling out a feedback form. The device then sends the entered feedback data to the server.

[1356] Step 18:

[1357] The server receives the feedback and stores it in the database. The feedback will be incorporated into the next proposal.

[1358] Step 19:

[1359] The server optimizes the next outfit suggestion based on collected feedback and user profiles. The server generates a new outfit and sends it to the device.

[1360] This series of processes makes it possible to provide users with a personalized fashion experience.

[1361] (Example 1)

[1362] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1363] Traditional fashion suggestion systems struggled to provide personalized recommendations that fully reflected user preferences and trend information. Furthermore, the lack of integrated features such as virtual try-on functionality, purchase links, feedback collection, and the ability to incorporate feedback into future suggestions resulted in a fragmented user experience, making it difficult to provide optimal outfits.

[1364] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1365] In this invention, the server includes means for inputting information about the user, means for collecting the user's fashion preferences, means for suggesting fashion items based on the user information and the user's fashion preferences, means for providing a virtual fitting room, means for providing purchase links for the fashion items, means for collecting user feedback, means for optimizing the next suggestion based on the feedback, means for analyzing user input using a natural language processing engine, means for using a generative AI model that suggests the optimal fashion items by matching user information, preference data, and trend information, and means for using a three-dimensional rendering engine that generates a three-dimensional model of the virtual fitting. This enables highly personalized fashion suggestions tailored to the user's preferences, resulting in an integrated user experience and a system that is efficient and easy to use.

[1366] A "user" refers to a person who uses this system and is the entity that provides personal information such as name, age, gender, fashion preferences, and budget.

[1367] A "user information input method" is a means for users to input personal information such as their name, age, gender, fashion preferences, and budget.

[1368] A "fashion preference collection method" refers to a means of collecting a user's preferred style, colors, items, etc.

[1369] "Fashion item suggestion means" refers to a means for suggesting fashion items based on the above-mentioned information about the user and the user's fashion preferences.

[1370] A "virtual fitting room system" is a means for users to virtually try on suggested fashion items.

[1371] "Method of providing purchase links" refers to a means of providing purchase links for proposed fashion items (for example, affiliate links to partner online shops).

[1372] "Feedback collection methods" refer to methods for collecting user feedback and obtaining information to optimize future proposals based on this feedback.

[1373] A "natural language processing engine" is an engine used to analyze user input information and has the function of analyzing the meaning of text.

[1374] A "generative AI model" is an artificial intelligence model used to suggest the most suitable fashion items by matching user information, preference data, and trend information.

[1375] A "three-dimensional rendering engine" is an engine used to generate three-dimensional models for virtual try-on.

[1376] This invention is a system that provides personalized fashion advice to users. It uses user information, fashion preferences, and trend information to suggest optimal outfits, and provides support for virtual fitting rooms, product purchases, and feedback collection. This invention consists of the following main components:

[1377] User information input means

[1378] The user uses the application to enter personal information such as name, age, gender, fashion preferences, and budget. The device collects this information and sends it to the server. The server stores the received information in a database.

[1379] Fashion preferences and collecting methods

[1380] Users specify their preferred style, color, and items using a chat interface. The device sends this conversational data to a server, which uses a natural language processing engine (e.g., Google Cloud Natural Language API) to analyze the input data and store the user's preferences in a database.

[1381] Fashion Item Proposal Method

[1382] The server generates the optimal fashion coordinate based on user information and preference data, matching it with trend information (e.g., the latest fashion magazine data). Specifically, a generative AI model is used to generate the fashion coordinate. The generated coordinate is sent to the terminal, which then displays it to the user.

[1383] Virtual fitting room method

[1384] The user sends a request to virtually try on the suggested outfit. The device sends 3D model data for the virtual try-on to the server, which generates a 3D model of the virtual try-on using a 3D rendering engine (e.g., Unity3D) and sends it back to the device. The device then displays the results of the virtual try-on to the user.

[1385] Purchase link provision method

[1386] The server generates a purchase link (e.g., an affiliate link to a partner online shop) for the suggested fashion item. The terminal then displays this to the user.

[1387] Feedback collection methods

[1388] The user fills out a form to provide feedback after purchase or trying on an item. The device sends the feedback data to the server, which stores the feedback information in a database. The stored feedback is then used to inform future suggestions.

[1389] Specific example

[1390] User registration and initial outfit suggestion

[1391] 1. The user opens the application for the first time and enters their name, age, gender, fashion preference (e.g., casual, elegant), and budget (e.g., less than 30,000 yen per month). The device sends the entered information to the server, which stores it in a database.

[1392] 2. The user uses the chat interface to input their favorite color (e.g., blue) and the type of clothing they usually wear (e.g., jeans or a T-shirt). The terminal sends the conversation data to the server, which uses a natural language processing engine to analyze the user's information and record it in a database.

[1393] 3. Based on user preference data and trend data, the server generates a casual yet elegant style outfit (e.g., white blouse, black skinny jeans, red pumps) and sends it to the terminal.

[1394] 4. The device displays recommended outfits to the user, and the user requests a virtual try-on. The device sends a virtual try-on request to the server, which generates a virtual model using a 3D rendering engine and sends it to the device.

[1395] 5. The terminal displays the results of the virtual try-on to the user, and the user clicks the purchase link for the items they like. The terminal proceeds with the purchase process, the server saves the purchase data, and earns affiliate commissions. One week after the purchase, the server sends a follow-up message to the user, who provides feedback. The server saves the feedback in its database and uses it to improve future recommendations.

[1396] In this way, each component works together to provide users with a personalized fashion experience.

[1397] Example of a prompt

[1398] "Please tell us your favorite fashion style, colors, and items."

[1399] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1400] Step 1: Collecting User Information

[1401] 1-1. The user launches the application and enters personal information such as name, age, gender, fashion preferences, and budget.

[1402] Input: Name, age, gender, fashion preferences, budget

[1403] Specific action: The user logs into the app from their smartphone or PC and enters the required information into the form.

[1404] 1-2. The terminal collects the entered information and sends it to the server.

[1405] Output: Entered user information

[1406] Specific operation: The device sends the input information to the server in real time, and a confirmation message is displayed to confirm successful transmission.

[1407] 1-3. The server saves the received information to the database.

[1408] Output: User information stored in the database

[1409] Specific operation: The server stores the received information in the database, and the saving of user information is confirmed.

[1410] Step 2: Collect your fashion preferences

[1411] 2-1. Users use the chat interface to specify their preferred style, color, and items.

[1412] Input: Preferred style, color, item

[1413] Specific action: The user enters "I like casual clothes and blue, and I usually wear jeans and t-shirts."

[1414] 2-2. The terminal sends the user's input to the server as text data.

[1415] Output: Sent preference data

[1416] Specific action: The terminal formats this as text data and sends it to the server.

[1417] 2-3. The server analyzes the input data using a natural language processing engine.

[1418] Input: Submitted preference data

[1419] Output: Analyzed preference data

[1420] Specific operation: The server uses a natural language processing engine to extract keywords such as "casual," "blue," "jeans," and "T-shirt."

[1421] 2-4. The server saves the analysis results to the database.

[1422] Output: Preference data stored in the database

[1423] Specific operation: The server saves the preferred data to the database, and a confirmation message is displayed.

[1424] Step 3: Fashion Coordination Suggestions

[1425] 3-1. The server matches user information, preference data, and trend information.

[1426] Input: User information, preference data, trend information

[1427] Output: Matched data

[1428] Specific operation: The server retrieves user information and trend information from the database and executes database queries to match them.

[1429] 3-2. The server generates the optimal fashion coordinate using an AI model for coordinate generation.

[1430] Input: Matched data

[1431] Output: Generated coordinate

[1432] Specific operation: The server generates outfits based on the user's preferences, such as "white blouse, black skinny jeans, and red pumps."

[1433] 3-3. The server sends the generated coordinate to the terminal.

[1434] Output: Coordinate sent to the terminal

[1435] Specific operation: The server sends the generated coordination information to the terminal, and a message indicating successful transmission is displayed.

[1436] 3-4. The device displays the outfit to the user.

[1437] Output: Coordinates displayed to the user

[1438] Specific action: The device displays an outfit to the user, such as "white blouse, black skinny jeans, red pumps," and a notification is issued asking for confirmation.

[1439] Step 4: Perform a virtual try-on.

[1440] 4-1. The user requests to virtually try on the item.

[1441] Input: Request for virtual try-on

[1442] Specific action: The user clicks a button that says, "I want to virtually try on this outfit."

[1443] 4-2. The terminal sends 3D model data for virtual try-on to the server.

[1444] Input: User body shape data, outfit data

[1445] Output: Sent 3D model data

[1446] Specific operation: The device sends the user's body shape data and outfit information to the server.

[1447] 4-3. The server uses a 3D rendering engine to generate a 3D model for virtual try-on.

[1448] Input: Submitted 3D model data

[1449] Output: Generated 3D model

[1450] Specific operation: The server uses a 3D rendering engine to generate a 3D model for virtual try-on.

[1451] 4-4. The server sends the generated 3D model to the terminal.

[1452] Output: 3D model sent to the terminal

[1453] Specific operation: The server sends the generated 3D model to the terminal, and a confirmation message is displayed.

[1454] 4-5. The terminal displays the results of the virtual try-on to the user.

[1455] Output: Virtual fitting results displayed to the user

[1456] Specific operation: The device displays a 3D model, and the user can see the results of a virtual try-on.

[1457] Step 5: Provide the purchase link

[1458] 5-1. The server generates a purchase link for the suggested fashion item.

[1459] Input: Suggested fashion item information

[1460] Output: Generated purchase link

[1461] Specific operation: The server generates a purchase URL for each item and creates a link.

[1462] 5-2. The server sends the generated purchase link to the device.

[1463] Output: Purchase link sent to the device

[1464] Specific operation: The server sends the generated purchase link to the device, and the link is displayed on the user's screen.

[1465] 5-3. The terminal displays this to the user.

[1466] Output: Purchase link displayed to the user

[1467] Specific action: The device displays a link saying "You can purchase it here," allowing the user to click it.

[1468] Step 6: Gathering Feedback

[1469] 6-1. The user fills out a form to provide feedback after purchase or after trying on the item.

[1470] Input: Feedback after purchase or try-on

[1471] Specific action: The user enters their opinions and feedback through a feedback form.

[1472] 6-2. The device sends feedback data to the server.

[1473] Output: Sent feedback data

[1474] Specific action: The terminal sends the input feedback to the server.

[1475] 6-3. The server saves the feedback information to the database.

[1476] Output: Feedback information stored in the database

[1477] Specific operation: The server stores the received data in the database, and a confirmation message for saving is displayed.

[1478] 6-4. The server incorporates the feedback into the next proposal.

[1479] Input: Saved feedback information

[1480] Output: Feedback reflected in the next proposal

[1481] Specific operation: The server optimizes the next coordination suggestion based on the feedback information.

[1482] The above outlines the specific processing steps of the program for this system.

[1483] (Application Example 1)

[1484] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1485] Traditional fashion advice systems had limitations in providing personalized fashion suggestions to users, particularly in effectively linking trend information with user preferences. Furthermore, virtual try-on features failed to adequately replicate the feeling of actually trying on clothes, resulting in insufficient user satisfaction. Additionally, mechanisms for collecting post-purchase feedback and incorporating it into future suggestions were incomplete.

[1486] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1487] In this invention, the server includes means for inputting user information, means for collecting fashion preferences, means for suggesting optimal fashion items based on trend information and user preference data using a generative AI model, means for providing a virtual fitting room, means for providing a purchase link, means for collecting post-purchase feedback, and means for sending post-purchase follow-up messages. This makes it possible to provide users with a more personalized and realistic fashion experience and improve user satisfaction.

[1488] "Means of inputting user information" refers to methods of collecting personal information such as the user's name, age, gender, fashion preferences, and budget through a terminal or application, and transmitting it to a server.

[1489] "Means of collecting fashion preferences" refers to a method by which users specify their preferred styles, colors, items, etc., using a chat interface or other input method, and send that data to a server.

[1490] A "generative AI model" is an artificial intelligence model that uses user information and preference data to match with trend information and suggest the most suitable fashion items.

[1491] A "virtual fitting room" is a system that allows users to virtually try on suggested fashion items. It uses 3D rendering technology to generate 3D models of the items to be virtually tried on and displays them to the user.

[1492] "Means of providing purchase links" refers to a means of generating and displaying to the user a link that allows them to purchase the proposed fashion item.

[1493] "Means of collecting post-purchase feedback" refers to providing a form for users to enter their opinions and impressions after purchasing or trying on an item, and then sending that feedback data to a server and storing it in a database.

[1494] "Method for sending follow-up messages after purchase" refers to a method for sending messages from a server to a user after they have purchased an item, in order to check on their experience and satisfaction with the item.

[1495] "Means of acquiring trend information" refers to methods of obtaining the latest trend information from external fashion-related databases or APIs and storing it on a server.

[1496] This invention is a system that provides personalized fashion advice to users. Specifically, it proposes the optimal outfit using user information, fashion preferences, and trend information. The aim of this system is to comprehensively support users in choosing their fashion through features such as virtual fitting rooms, assistance with product purchases, and feedback collection.

[1497] Key components of the system

[1498] 1. User information input means

[1499] Users use their devices to enter personal information such as their name, age, gender, fashion preferences, and budget. This information is sent from the device to the server, which stores the received information in a database.

[1500] 2. Methods for collecting fashion preferences

[1501] Users specify their preferred style, color, and items through a chat interface. The terminal sends this conversational data to a server, which uses a natural language processing engine to analyze the input data and store the user's preferences in a database.

[1502] 3. Proposed method using a generative AI model

[1503] The server generates optimal fashion coordinates based on user information and preference data, matching them with trend information. This is where a generation AI model is utilized. The generated fashion item recommendations are displayed to the user via their device.

[1504] 4. Virtual fitting room means

[1505] When a user requests to virtually try on a suggested outfit, the device sends 3D model data of the outfit to the server. The server uses a 3D rendering engine to generate a 3D model of the outfit and sends it to the device. The device then displays the results of the virtual try-on to the user.

[1506] 5. Means of providing purchase links

[1507] The server generates a purchase link (e.g., an affiliate link to a partner online shop) for the suggested fashion item. This allows the user to easily purchase the item. The terminal displays this to the user.

[1508] 6. Methods for collecting feedback

[1509] When a user fills out a form to provide feedback after a purchase or try-on, the data is sent from the device to the server and stored in a database. The server then uses the feedback information to improve future suggestions.

[1510] 7. Means of sending follow-up messages

[1511] The server sends a follow-up message after a user purchases an item to inquire about their experience and satisfaction with it. This allows for further collection of user feedback, which can then be used to improve future offerings.

[1512] Specific examples of actions

[1513] In a scenario where a user is using the application for the first time, the following prompt will be displayed:

[1514] Prompt: New user registration

[1515] name

[1516] age

[1517] sex

[1518] budget

[1519] style

[1520] Prompt: Collect your preferences details

[1521] Favorite color: Blue

[1522] Everyday clothing items: Jeans, T-shirts

[1523] Prompt: Generate recommended items

[1524] Prompt: Try on clothes virtually

[1525] Prompt: Purchase link displayed

[1526] Prompt: Feedback collection

[1527] This system allows users to receive personalized fashion suggestions and further enhance their experience by using a virtual try-on function. This improves user satisfaction and enables the optimization of future suggestions through the collection of feedback.

[1528] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1529] Step 1:

[1530] The user opens the application and enters their initial registration information (name, age, gender, fashion preferences, budget). The device sends this input data to the server. The server saves the received user information to its database. Through this process, basic user information is recorded in the database.

[1531] Input: User registration information (name, age, gender, fashion preferences, budget)

[1532] Output: User information stored in the database

[1533] Step 2:

[1534] Users specify their preferred style, colors, items, etc., using a chat interface. The terminal sends this conversational data to the server. The server analyzes the input data using a natural language processing engine and stores the user's preference data in a database. This allows for the accumulation of detailed user preference information.

[1535] Input: User interaction data (preferred style, color, item)

[1536] Output: User preference data stored in the database

[1537] Step 3:

[1538] The server generates optimal fashion coordinates by matching user information and preference data with trend information. This is where a generation AI model is utilized. The generated fashion item recommendations are sent to the device and displayed to the user. This provides personalized fashion suggestions for each individual user.

[1539] Input: User information, preference data, trend information

[1540] Output: Fashion coordination suggestions sent to the terminal

[1541] Step 4:

[1542] The user sends a request to virtually try on suggested fashion items. The device sends this request to the server. The server generates a 3D model of the virtual try-on using a 3D rendering engine and sends it to the device. The device displays the virtual try-on results to the user. This allows the user to virtually try on the suggested items.

[1543] Input: User's virtual try-on request

[1544] Output: 3D model and virtual try-on results sent to the terminal

[1545] Step 5:

[1546] The server generates purchase links for items the user likes after a virtual try-on. These purchase links are structured as affiliate links to partner online shops. The terminal displays these links to the user, providing them with an environment where they can actually purchase the items.

[1547] Input: Information about items the user liked

[1548] Output: Purchase link displayed on the device

[1549] Step 6:

[1550] After a user purchases an item, the server sends a follow-up message prompting the user to provide feedback. When the user fills out a feedback form, the device sends the feedback data to the server. The server stores this feedback information in a database and uses it to improve future suggestions. This allows for further service improvements based on user feedback.

[1551] Input: User feedback data

[1552] Output: Feedback information stored in the database

[1553] Step 7:

[1554] The server performs data analysis based on user feedback to optimize future recommendations. This analysis data is then fed back into the generating AI model, enabling more accurate fashion item recommendations.

[1555] Input: Feedback Information

[1556] Output: Analysis data fed back into the generated AI model

[1557] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1558] System Overview

[1559] This invention is a system that provides personalized fashion advice to users, suggesting optimal outfits using user information, fashion preferences, trend information, and the user's emotional state. Its aim is to comprehensively support users' fashion choices through features such as virtual fitting rooms, product purchase assistance, and feedback collection.

[1560] Key components of the system

[1561] 1. User information input means

[1562] Users enter personal information such as their name, age, gender, fashion preferences, and budget using the application.

[1563] The device collects this information and sends it to the server.

[1564] The server stores the received information in a database.

[1565] 2. Methods for collecting fashion preferences

[1566] Users specify their preferred style, color, and items through a chat interface.

[1567] The terminal sends this conversation data to the server.

[1568] The server uses a natural language processing engine to analyze the input data and saves the user's preferences to a database.

[1569] 3. Means of proposing fashion items

[1570] The server analyzes user information and preference data, along with trend information, to generate the optimal fashion coordinate. For example, the coordinate might consist of a white blouse, black skinny jeans, and red pumps.

[1571] The terminal displays this to the user.

[1572] 4. Virtual fitting room means

[1573] The user requests to virtually try on the suggested outfit.

[1574] The terminal sends 3D model data for virtual try-on to the server.

[1575] The server uses a 3D rendering engine to generate a 3D model for virtual try-on and sends it to the terminal.

[1576] The device displays the results of the virtual try-on to the user.

[1577] 5. Means of providing purchase links

[1578] The server generates purchase links (e.g., affiliate links to partner online shops) for the suggested fashion items.

[1579] The terminal displays this to the user.

[1580] 6. Methods for collecting feedback

[1581] Users fill out a form to provide feedback after purchasing or trying on an item.

[1582] The device sends feedback data to the server.

[1583] The server saves the feedback information to a database and incorporates it into future proposals.

[1584] 7. Emotional Engine

[1585] When a user uses the conversational interface, the emotion engine analyzes the user's emotional state from their input text and voice.

[1586] The device sends user emotion data to the server.

[1587] The server adjusts suggested fashion items and outfits based on emotional data.

[1588] Specific example

[1589] Coordination suggestions that take emotions into consideration

[1590] 1. The user opens the application for the first time and enters their name, age, gender, fashion preference (e.g., casual, elegant), and budget (e.g., less than 30,000 yen per month).

[1591] 2. The terminal sends the entered information to the server, and the server stores it in the database.

[1592] 3. The user uses the chat interface to enter their favorite color (e.g., blue) and the type of clothing they usually wear (e.g., jeans or a T-shirt).

[1593] 4. The terminal sends conversation data to the server, which uses a natural language processing engine to analyze the user's information and record it in a database.

[1594] 5. The emotion engine identifies the user's emotional state from their dialogue data and voice data, and analyzes emotional data such as happy, calm, and excited.

[1595] 6. The server generates fashion coordinates appropriate to the user's emotional state based on their emotional data, preference data, and trend data. For example, if the user is relaxed, it will suggest a casual and comfortable style (e.g., relaxed-fit jeans, a soft cardigan).

[1596] 7. The server sends the generated coordinate to the terminal, and the terminal displays it to the user.

[1597] 8. If the user requests a virtual try-on, the device sends a virtual try-on request to the server.

[1598] 9. The server generates a virtual model using a 3D rendering engine and sends it to the terminal.

[1599] 10. The device displays the results of the virtual try-on to the user, and the user clicks the purchase link for the items they like.

[1600] 11. The device proceeds with the purchase process, the server saves the purchase data, and the affiliate commission is earned.

[1601] 12. One week after purchase, the server sends a follow-up message to the user, who then provides feedback.

[1602] 13. The server saves the feedback to a database and incorporates it into future suggestions.

[1603] By combining these emotion engines, it becomes possible to provide a more personalized fashion experience that responds to the user's emotional state.

[1604] The following describes the processing flow.

[1605] Step 1:

[1606] The user opens the application and enters their name, age, gender, fashion preference (e.g., casual, elegant), and budget (e.g., under 30,000 yen per month).

[1607] Step 2:

[1608] The terminal sends the entered user information to the server. A method using an API to send data is employed.

[1609] Step 3:

[1610] The server saves the received user information to the database. The information is stored in the user profile table.

[1611] Step 4:

[1612] Users specify their preferred styles, colors, and the types of clothes they usually wear through a chat interface. For example, a user might input that they like blue, jeans, and t-shirts.

[1613] Step 5:

[1614] The device sends the collected conversation data to the server. The conversation data is sent in text format via the API.

[1615] Step 6:

[1616] The server uses a natural language processing engine to analyze user dialogue data. The analysis results are recorded in a database as user preferences and needs.

[1617] Step 7:

[1618] The emotion engine analyzes the user's input text and voice data to identify their emotional state. For example, it can analyze whether the user is happy, calm, or excited.

[1619] Step 8:

[1620] The device sends user emotion data to the server. This emotion data is retrieved in conjunction with a natural language processing engine.

[1621] Step 9:

[1622] The server comprehensively analyzes user preference data, emotional data, and trend information to generate fashion coordinates that suit the user's emotional state. For example, if the user is relaxed, it will suggest relaxed-fit jeans or a soft cardigan.

[1623] Step 10:

[1624] The server sends the generated outfit suggestions to the user's device. The outfit data is sent to the user's device via the API.

[1625] Step 11:

[1626] The device displays outfit suggestions to the user. The user can review the suggestions and choose whether or not they wish to virtually try them on.

[1627] Step 12:

[1628] If a user wishes to virtually try on clothes, the device sends a virtual try-on request to the server. The request includes information about the selected outfit.

[1629] Step 13:

[1630] The server uses a 3D rendering engine to generate a 3D model for virtual try-on. The data for the virtual model is prepared.

[1631] Step 14:

[1632] The server sends the generated 3D model data to the terminal. The terminal receives the model data upon request.

[1633] Step 15:

[1634] The device displays the results of the virtual try-on to the user. The user reviews the results and clicks the purchase link for the items they like.

[1635] Step 16:

[1636] The user clicks the purchase link and proceeds with the purchase of the item they like. The device sends the purchase data to the server.

[1637] Step 17:

[1638] The server receives the purchase data and saves it to the database. At the same time, affiliate marketing commissions are recorded.

[1639] Step 18:

[1640] One week after purchase, the server will send a follow-up message to the user. The message will include a link to a feedback form.

[1641] Step 19:

[1642] The user submits their opinions and feedback by filling out a feedback form. The device then sends the entered feedback data to the server.

[1643] Step 20:

[1644] The server receives the feedback and stores it in the database. The feedback will be incorporated into the next proposal.

[1645] Step 21:

[1646] The server optimizes the next outfit suggestion based on the collected feedback and user profile. A new outfit is generated and sent to the device.

[1647] This series of processes makes it possible to provide a personalized fashion experience that takes into account the user's emotional state.

[1648] (Example 2)

[1649] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1650] In modern society, the diversification of individual preferences and trends in fashion makes it difficult for users to choose the most suitable fashion items for themselves. Furthermore, there is a lack of systems that can appropriately reflect the influence of a user's emotional state on their fashion choices, making it difficult to realize personalized suggestions. Moreover, there is a lack of mechanisms to achieve a higher level of personalization through virtual try-on and feedback. To solve these problems, the system proposed in this invention makes it possible to suggest fashion items that take into account user information, preferences, and emotional state.

[1651] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1652] In this invention, the server includes means for inputting information about the user, means for collecting the user's fashion preferences, and means for analyzing the user's emotional state. This makes it possible to suggest optimal fashion items based on the user's detailed information and preferences, as well as their emotional state.

[1653] "User information" refers to personal data entered by the user, such as name, age, gender, fashion preferences, and budget.

[1654] A "fashion preference collection method" is an interface and mechanism for processing information that allows users to provide the system with their preferred styles, colors, and clothing items.

[1655] "Fashion item suggestion means" refers to a function for generating optimal fashion coordinates based on user information and fashion preferences.

[1656] A "virtual fitting room" is a function that allows users to virtually try on suggested fashion items using the system.

[1657] The "purchase link provision method" is a function that generates and provides links to facilitate the purchase of proposed fashion items.

[1658] A "feedback collection method" is a function for collecting opinions and impressions from users regarding the results of their purchases or try-ons.

[1659] A "database" is a collection of information that stores user input and feedback information and is accessible as needed.

[1660] A "natural language processing engine" is a software system that analyzes text and audio data input by users and extracts meaning from them.

[1661] A "sentiment analysis engine" is a software system that analyzes a user's emotional state from their input text or voice and provides the results.

[1662] Modes for carrying out the invention

[1663] This invention is a system that provides personalized fashion advice to users. The system proposes the optimal outfit using user information, fashion preferences, trend information, and the user's emotional state. It aims to comprehensively support users in choosing their fashion through features such as virtual fitting rooms, product purchase assistance, and feedback collection.

[1664] The system includes the following main components:

[1665] User information input means

[1666] Users enter personal information such as their name, age, gender, fashion preferences, and budget using the application.

[1667] The device collects this information and sends it to the server.

[1668] The server saves the received information to the database.

[1669] Fashion preferences and collecting methods

[1670] Users specify their preferred style, color, and items through a chat interface.

[1671] The terminal sends this conversation data to the server.

[1672] The server analyzes the input data using a natural language processing engine (such as OpenAI's GPT-3) and stores the user's preferences in a database.

[1673] sentiment analysis tool

[1674] When a user uses the conversational interface, the emotion engine analyzes the user's emotional state from their input text and voice.

[1675] The device sends user emotion data to the server.

[1676] The server adjusts suggested fashion items and outfits based on emotional data.

[1677] Fashion Item Proposal Method

[1678] The server generates optimal fashion coordinates based on user information and preference data, combined with trend information. Specifically, it suggests items such as a white blouse, black skinny jeans, and red pumps.

[1679] The device displays this to the user.

[1680] Virtual fitting room method

[1681] The user sends a request to virtually try on the suggested outfit.

[1682] The device sends 3D model data for virtual try-on to the server.

[1683] The server generates a 3D model for virtual try-on using a 3D rendering engine (such as Unity 3D) and sends it to the terminal.

[1684] The device displays the results of the virtual try-on to the user.

[1685] Purchase link provision method

[1686] The server generates purchase links (such as affiliate links to partner online shops) for the suggested fashion items.

[1687] The device displays this to the user.

[1688] Feedback collection methods

[1689] Users fill out a form to provide feedback after purchasing or trying on an item.

[1690] The device sends feedback data to the server.

[1691] The server saves the feedback information to a database and incorporates it into future proposals.

[1692] Specific example

[1693] A process for suggesting outfits that take emotions into consideration

[1694] 1. The user opens the application for the first time and enters their name (e.g., Taro Tanaka), age (30 years old), gender (male), fashion preference (casual), and budget (under 30,000 yen per month).

[1695] 2. The terminal sends the entered information to the server, and the server saves it to the database.

[1696] 3. The user types "I like blue, and I usually wear jeans and a T-shirt" in the chat interface.

[1697] 4. The terminal sends conversation data to the server, and the server uses a natural language processing engine to analyze and store the data.

[1698] 5. The emotion engine identifies the emotional state of "relaxed" from the user's dialogue data and voice data, and stores the data in a database.

[1699] 6. Generate the optimal outfit (e.g., relaxed-fit jeans, soft cardigan) when the server is "relaxed".

[1700] 7. The server sends the generated coordinate to the terminal, and the terminal displays it to the user.

[1701] 8. The user requests a virtual try-on and sends a request from their device to the server.

[1702] 9. The server uses a 3D rendering engine to generate a model for virtual try-on and sends it to the terminal.

[1703] 10. The device displays the results of the virtual try-on to the user, and the user clicks the purchase link for the items they like.

[1704] 11. The device proceeds with the purchase process, the server saves the purchase data, and the affiliate receives the commission.

[1705] 12. One week after purchase, the server sends a follow-up message to the user, who then provides feedback.

[1706] Example of a prompt

[1707] "Please suggest casual fashion outfits that are suitable for when the user is relaxing."

[1708] "Please tell us what items would be good for users to wear when they seem to be having fun."

[1709] As a result, the system takes into account the user's detailed information and emotional state to provide highly personalized fashion suggestions.

[1710] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1711] Step 1:

[1712] The user launches the application and enters information such as their name, age, gender, fashion preferences, and budget.

[1713] Input: Name, age, gender, fashion preferences, budget

[1714] Output: User Information

[1715] Specific action: The user enters personal information such as "Taro Tanaka, 30 years old, male, casual attire, monthly income under 30,000 yen."

[1716] Step 2:

[1717] The terminal sends the entered user information to the server.

[1718] Input: User information

[1719] Output: User information sent to the server

[1720] Specific action: The device sends the information "Taro Tanaka, 30 years old, male, casual wear, monthly income under 30,000 yen" to the server.

[1721] Step 3:

[1722] The server saves the received user information to the database.

[1723] Input: User information sent to the server

[1724] Output: User information stored in the database

[1725] Specific action: The server records the information "Taro Tanaka, 30 years old, male, casual wear, monthly salary of 30,000 yen or less" in the database.

[1726] Step 4:

[1727] Users can use the chat interface to specify their preferred style, color, and items.

[1728] Input: Favorite style, color, item

[1729] Output: Preference information

[1730] Specific action: The user enters "I like blue, and I usually wear jeans and a T-shirt."

[1731] Step 5:

[1732] The terminal sends the conversation data to the server.

[1733] Input: Preference information

[1734] Output: Preference information sent to the server

[1735] Specific action: The device sends the information "I like blue and usually wear jeans and a T-shirt" to the server.

[1736] Step 6:

[1737] The server uses a natural language processing engine to analyze the input data and saves the user's preferences to a database.

[1738] Input: Preference information sent to the server

[1739] Output: Preference information stored in the database

[1740] Specific operation: The server uses a natural language processing engine such as OpenAI GPT-3 to extract keywords such as "blue, jeans, T-shirt" and save them to a database.

[1741] Step 7:

[1742] Users input text or voice through a conversational interface.

[1743] Input: Text or audio data

[1744] Output: Sentiment data

[1745] Specific action: The user types or speaks the phrase "I want to relax today."

[1746] Step 8:

[1747] The terminal sends the entered text or voice data to the server.

[1748] Input: Text or audio data

[1749] Output: Text and audio data sent to the server

[1750] Specific action: The device sends text or audio data of "I want to relax today" to the server.

[1751] Step 9:

[1752] The server's emotion engine analyzes the user's emotional state from text and audio.

[1753] Input: Text or audio data sent to the server

[1754] Output: Analyzed sentiment data

[1755] Specific operation: The server's emotion engine analyzes text and audio data to identify emotional states such as "relaxed."

[1756] Step 10:

[1757] The server adjusts suggested fashion items and outfits based on emotional data.

[1758] Input: Analyzed sentiment data

[1759] Output: Suggestions for tailored fashion items and outfits.

[1760] Specific operation: The server generates outfits such as "relaxed-fit jeans and a soft cardigan" based on sentiment data.

[1761] Step 11:

[1762] The server sends the generated outfit to the terminal.

[1763] Input: Suggestions for coordinated fashion items and outfits

[1764] Output: Fashion coordinates displayed to the user

[1765] Specific operation: The server sends the generated outfit to the terminal and displays suggestions to the user, such as "relaxed-fit denim, soft cardigan."

[1766] Step 12:

[1767] The user sends a request for a virtual try-on.

[1768] Input: Virtual try-on request

[1769] Output: Virtual fitting request data

[1770] Specific action: The user sends a request saying, "I want to virtually try on this outfit."

[1771] Step 13:

[1772] The device sends a request to the server for a virtual try-on.

[1773] Input: Virtual fitting request data

[1774] Output: Virtual try-on request data sent to the server

[1775] Specific operation: The terminal receives the user's request and sends it to the server.

[1776] Step 14:

[1777] The server uses a 3D rendering engine to generate a 3D model for the virtual try-on.

[1778] Input: Virtual try-on request data sent to the server

[1779] Output: 3D model data

[1780] Specific operation: The server uses a 3D rendering engine such as Unity 3D to generate a 3D model for virtual try-on.

[1781] Step 15:

[1782] The server sends the generated 3D model to the terminal.

[1783] Input: 3D model data

[1784] Output: 3D model data sent to the terminal

[1785] Specific operation: The server sends the generated 3D model to the terminal.

[1786] Step 16:

[1787] The device displays the results of the virtual try-on to the user.

[1788] Input: 3D model data sent to the terminal

[1789] Output: Virtual try-on results displayed to the user

[1790] Specific action: The device displays the results of the virtual try-on to the user, allowing the user to confirm them.

[1791] Step 17:

[1792] The server generates purchase links for the suggested fashion items.

[1793] Input: Suggestions for coordinated fashion items and outfits

[1794] Output: Purchase link

[1795] Specific operation: The server generates a purchase link (such as an affiliate link) for the suggested item.

[1796] Step 18:

[1797] The server sends a purchase link to the device.

[1798] Input: Purchase link

[1799] Output: Purchase link sent to the device

[1800] Specific action: The server sends the generated purchase link to the device.

[1801] Step 19:

[1802] The device displays a purchase link to the user.

[1803] Input: Purchase link sent to your device

[1804] Output: Purchase link displayed to the user

[1805] Specific action: The device displays a purchase link to the user, allowing the user to purchase the item.

[1806] Step 20:

[1807] The user purchases the item via the purchase link.

[1808] Input: Purchase link

[1809] Output: Purchase data

[1810] Specific action: The user clicks the purchase link and buys the item.

[1811] Step 21:

[1812] The server stores the purchase data and earns affiliate commissions.

[1813] Input: Purchase data

[1814] Output: Purchase data stored in the database, retrieved affiliate commissions.

[1815] Specific operation: The server stores the purchase data and receives affiliate commissions.

[1816] Step 22:

[1817] The server sends a follow-up message to the user, who then provides feedback.

[1818] Input: Purchase data

[1819] Output: Follow-up messages, feedback data

[1820] Specific action: One week after purchase, the server sends a follow-up message and the user enters feedback.

[1821] Step 23:

[1822] The device sends feedback data to the server.

[1823] Input: Feedback data

[1824] Output: Feedback data sent to the server

[1825] Specific action: The device sends user feedback data to the server.

[1826] Step 24:

[1827] The server saves the feedback information to a database and incorporates it into future proposals.

[1828] Input: Feedback data sent to the server

[1829] Output: Feedback information stored in the database, optimized next-generation suggestions.

[1830] Specific operation: The server saves the feedback information to a database and uses it to inform future suggestions.

[1831] (Application Example 2)

[1832] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1833] Traditional fashion advice systems have a problem in that they cannot fully suggest the most suitable outfits for users because they do not take into account the user's emotional state. Furthermore, they lack sufficient integration of features that comprehensively support the user's online shopping experience, such as virtual try-on functionality and purchase links. As a result, users face the challenge of not being able to efficiently select fashion items that suit their preferences and mood.

[1834] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting information about the user, means for collecting the user's fashion preferences, means for collecting emotional data using an engine that analyzes emotional states and reflecting it in fashion item suggestions, means for providing a virtual fitting room, means for providing purchase links for the fashion items, and means for collecting user feedback and optimizing suggestions for the next time. This makes it possible to suggest more personalized fashion coordinates according to the user's emotional state.

[1835] A "user information input method" is a means for users to input personal information such as their name, age, gender, fashion preferences, and budget.

[1836] A "fashion preference collection method" is a means by which users specify their preferred styles, colors, and items using a chat interface, and the collection of that information is then performed.

[1837] A "fashion item suggestion method" is a method for generating optimal fashion coordinates by simultaneously analyzing trend information based on user information and preference data.

[1838] A "virtual fitting room means" is a method for generating 3D model data and displaying it to the user so that the user can virtually try on the suggested outfit.

[1839] A "purchase link provision method" is a means of generating purchase links for proposed fashion items and displaying them to the user.

[1840] A "feedback collection method" refers to a method of providing a form for users to provide feedback after purchase or trying on an item, and collecting that data.

[1841] An "emotion engine" is an engine that analyzes a user's emotional state from their input text or voice.

[1842] A "natural language processing engine" is an engine used to analyze user input information.

[1843] A "database" is a system for storing user input information and feedback information.

[1844] A "3D rendering engine" is an engine used to generate 3D models for virtual try-on.

[1845] System Configuration

[1846] This invention is a system that provides personalized fashion advice to users. This system proposes optimal outfits using user information, fashion preferences, trend information, and the user's emotional state. Its aim is to comprehensively support users' fashion choices through features such as virtual fitting rooms, product purchase assistance, and feedback collection.

[1847] Hardware and software used

[1848] The following hardware and software will be used.

[1849] Smartphone

[1850] server

[1851] Database (for example, Amazon RDS)

[1852] Natural language processing engine (e.g., Google NLP API)

[1853] Emotion engine (e.g., Microsoft Azure Emotion API)

[1854] 3D rendering engine (e.g., Unity 3D)

[1855] Collection of user information

[1856] Users enter personal information such as their name, age, gender, fashion preferences, and budget via their smartphone, and the device sends this information to a server. The server stores the received information in a database.

[1857] Fashion-loving collector

[1858] Users use a chat interface to input their preferred style, color, and items. The device sends this conversational data to a server, which uses a natural language processing engine to analyze the data and store the user's preferences in a database.

[1859] Analysis of emotional states

[1860] The emotion engine analyzes the user's emotional state from their dialogue and voice data. The device sends this emotional data to the server, which stores it in a database. The emotional state is then reflected in the suggested coordination.

[1861] Coordination suggestions

[1862] The server generates the optimal fashion coordinate based on user information, preference data, sentiment data, and trend information. The generated coordinate is then displayed to the user on their device.

[1863] Virtual fitting room

[1864] When a user requests to virtually try on a suggested outfit, the device sends 3D model data for the virtual try-on to the server. The server generates a virtual model using a 3D rendering engine and sends it to the device. The device then displays the results of the virtual try-on to the user.

[1865] Purchase link provided

[1866] The server generates a purchase link for the suggested fashion item. This link is, for example, an affiliate link to a partner online shop. The terminal displays this to the user, who then proceeds with the purchase.

[1867] Gathering feedback and optimizing future proposals

[1868] When a user provides feedback after purchasing or trying on an item, the device sends the feedback data to the server. The server stores the feedback information in a database and uses it to improve future recommendations.

[1869] Examples of specific cases and prompt statements

[1870] The user opens the application and enters their name, age, gender, fashion preferences (casual, elegant, etc.), and budget (under 30,000 yen per month, etc.). Next, they are asked, "What's your favorite color?" and the user answers, "Blue." Then they are asked, "What kind of clothes do you usually wear?" and they answer, "Jeans and T-shirts." After that, the system's emotion engine analyzes that the user is "relaxed" and suggests, "A relaxed style is recommended for today. How about relaxed-fit jeans and a soft cardigan?"

[1871] Example of a prompt

[1872] Username: User A, Preferred Style: Casual, Current Mood: Relaxed

[1873] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1874] Step 1:

[1875] Users enter personal information such as their name, age, gender, fashion preferences, and budget via their smartphone. The device sends the entered information to the server. The server, upon receiving the user's input data, stores that information in a database.

[1876] Step 2:

[1877] Users input their preferred styles, colors, and items using a chat interface. This conversational data is sent from the terminal to the server. The server analyzes the received data using a natural language processing engine and stores data about the user's fashion preferences in a database.

[1878] Step 3:

[1879] The emotion engine analyzes the user's emotional state from their input text and voice. The device sends the user's emotional data to the server, which stores it in a database. The emotion engine analyzes the text and voice data and generates emotional labels such as "relaxed," "joyful," and "excited."

[1880] Step 4:

[1881] The server uses a generative AI model to suggest the optimal fashion outfit based on user information, fashion preference data, sentiment data, and trend information. The generated outfit is output in the form of, for example, "white blouse, black skinny jeans, red pumps." The outfit result is sent from the server to the terminal.

[1882] Step 5:

[1883] The user sends a request from their device to virtually try on the suggested outfit. The device sends 3D model data for the virtual try-on to the server, which generates the virtual model using a 3D rendering engine. The generated virtual model is sent from the server to the device and displayed to the user.

[1884] Step 6:

[1885] The server generates purchase links for the suggested fashion items. These purchase links are provided as affiliate links to partner online shops. The server sends the generated links to the user's device, where they are displayed. The user can then purchase the desired items.

[1886] Step 7:

[1887] Users input feedback into a terminal after purchasing or trying on items. The terminal sends the feedback data to a server, where it is stored in a database. The server updates the generated AI model based on the collected feedback and incorporates it into future fashion coordination suggestions.

[1888] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1889] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1890] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1891] [Fourth Embodiment]

[1892] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1893] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1894] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1895] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1896] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1897] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1898] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1899] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1900] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1901] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1902] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1903] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1904] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1905] System Overview

[1906] This invention is a system that provides personalized fashion advice to users, suggesting optimal outfits using user information, fashion preferences, and trend information. Its aim is to comprehensively support users' fashion choices through features such as virtual fitting rooms, product purchase assistance, and feedback collection.

[1907] Key components of the system

[1908] 1. User information input means

[1909] Users enter personal information such as their name, age, gender, fashion preferences, and budget using the application.

[1910] The device collects this information and sends it to the server.

[1911] The server stores the received information in a database.

[1912] 2. Methods for collecting fashion preferences

[1913] Users specify their preferred style, color, and items through a chat interface.

[1914] The terminal sends this conversation data to the server.

[1915] The server uses a natural language processing engine to analyze the input data and saves the user's preferences to a database.

[1916] 3. Means of proposing fashion items

[1917] The server generates optimal fashion coordinates by matching user information and preference data with trend information.

[1918] The terminal displays this to the user.

[1919] 4. Virtual fitting room means

[1920] The user requests to virtually try on the suggested outfit.

[1921] The terminal sends 3D model data for virtual try-on to the server.

[1922] The server uses a 3D rendering engine to generate a 3D model for virtual try-on and sends it to the terminal.

[1923] The device displays the results of the virtual try-on to the user.

[1924] 5. Means of providing purchase links

[1925] The server generates purchase links (e.g., affiliate links to partner online shops) for the suggested fashion items.

[1926] The terminal displays this to the user.

[1927] 6. Methods for collecting feedback

[1928] Users fill out a form to provide feedback after purchasing or trying on an item.

[1929] The device sends feedback data to the server.

[1930] The server saves the feedback information to a database and incorporates it into future proposals.

[1931] Specific example

[1932] User registration and initial outfit suggestion

[1933] 1. The user opens the application for the first time and enters their name, age, gender, fashion preference (e.g., casual, elegant), and budget (e.g., less than 30,000 yen per month).

[1934] 2. The terminal sends the entered information to the server, and the server stores it in the database.

[1935] 3. The user uses the chat interface to enter their favorite color (e.g., blue) and the type of clothing they usually wear (e.g., jeans or a T-shirt).

[1936] 4. The terminal sends conversation data to the server, which uses a natural language processing engine to analyze the user's information and record it in a database.

[1937] 5. Based on user preference data and trend data, the server generates a casual yet elegant style outfit (e.g., white blouse, black skinny jeans, red pumps) and sends it to the terminal.

[1938] 6. The device displays recommended outfits to the user, and the user requests a virtual try-on.

[1939] 7. The device sends a virtual try-on request to the server, the server generates a virtual model using a 3D rendering engine, and sends it to the device.

[1940] 8. The device displays the results of the virtual try-on to the user, and the user clicks the purchase link for the items they like.

[1941] 9. The device proceeds with the purchase process, the server stores the purchase data, and the affiliate commission is earned.

[1942] 10. One week after purchase, the server sends a follow-up message to the user, who then provides feedback.

[1943] 11. The server saves the feedback to a database and incorporates it into future suggestions.

[1944] In this way, each component works together to provide users with a personalized fashion experience.

[1945] The following describes the processing flow.

[1946] Step 1:

[1947] The user opens the application and enters basic information such as their name, age, gender, fashion preferences, and budget.

[1948] Step 2:

[1949] The terminal sends the entered information to the server. Specifically, it sends user data to the server via an API.

[1950] Step 3:

[1951] The server saves the received information to the database. The database stores the information in the user profile table.

[1952] Step 4:

[1953] Users specify their preferred style, colors, and the types of clothes they usually wear through a chat interface.

[1954] Step 5:

[1955] The terminal sends the input dialogue data to the server. The dialogue data is sent in text format and passed to the server via an API.

[1956] Step 6:

[1957] The server uses a natural language processing engine to analyze the user's input data. The analysis results are recorded in a database as the user's preferences and needs.

[1958] Step 7:

[1959] The server analyzes user information and preference data, along with trend information, to generate the optimal fashion coordinate. For example, the coordinate might consist of a white blouse, black skinny jeans, and red pumps.

[1960] Step 8:

[1961] The server sends the generated outfit to the device. Specifically, the outfit data is passed to the device via an API.

[1962] Step 9:

[1963] The device displays outfit suggestions to the user. The user can review these and choose to virtually try them on.

[1964] Step 10:

[1965] The user selects a virtual try-on, and the device sends a virtual try-on request to the server. The request includes information about the selected outfit.

[1966] Step 11:

[1967] The server uses a 3D rendering engine to generate a 3D model of the virtual try-on garment. The model data for the virtual try-on garment is prepared.

[1968] Step 12:

[1969] The server sends the generated 3D model data to the terminal. The terminal receives the model data upon request.

[1970] Step 13:

[1971] The device displays the results of the virtual try-on to the user. The user reviews the results and decides which items they like.

[1972] Step 14:

[1973] The user clicks the purchase link and proceeds with the purchase of the item they like. The device sends the purchase data to the server.

[1974] Step 15:

[1975] The server receives purchase data and stores it in the database. Simultaneously, it records the commissions for affiliate marketing.

[1976] Step 16:

[1977] One week after purchase, the server will send a follow-up message to the user. The message will include a link to a feedback form.

[1978] Step 17:

[1979] The user submits their opinions and feedback by filling out a feedback form. The device then sends the entered feedback data to the server.

[1980] Step 18:

[1981] The server receives the feedback and stores it in the database. The feedback will be incorporated into the next proposal.

[1982] Step 19:

[1983] The server optimizes the next outfit suggestion based on collected feedback and user profiles. The server generates a new outfit and sends it to the device.

[1984] This series of processes makes it possible to provide users with a personalized fashion experience.

[1985] (Example 1)

[1986] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1987] Traditional fashion suggestion systems struggled to provide personalized recommendations that fully reflected user preferences and trend information. Furthermore, the lack of integrated features such as virtual try-on functionality, purchase links, feedback collection, and the ability to incorporate feedback into future suggestions resulted in a fragmented user experience, making it difficult to provide optimal outfits.

[1988] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1989] In this invention, the server includes means for inputting information about the user, means for collecting the user's fashion preferences, means for suggesting fashion items based on the user information and the user's fashion preferences, means for providing a virtual fitting room, means for providing purchase links for the fashion items, means for collecting user feedback, means for optimizing the next suggestion based on the feedback, means for analyzing user input using a natural language processing engine, means for using a generative AI model that suggests the optimal fashion items by matching user information, preference data, and trend information, and means for using a three-dimensional rendering engine that generates a three-dimensional model of the virtual fitting. This enables highly personalized fashion suggestions tailored to the user's preferences, resulting in an integrated user experience and a system that is efficient and easy to use.

[1990] A "user" refers to a person who uses this system and is the entity that provides personal information such as name, age, gender, fashion preferences, and budget.

[1991] A "user information input method" is a means for users to input personal information such as their name, age, gender, fashion preferences, and budget.

[1992] A "fashion preference collection method" refers to a means of collecting a user's preferred style, colors, items, etc.

[1993] "Fashion item suggestion means" refers to a means for suggesting fashion items based on the above-mentioned information about the user and the user's fashion preferences.

[1994] A "virtual fitting room system" is a means for users to virtually try on suggested fashion items.

[1995] "Method of providing purchase links" refers to a means of providing purchase links for proposed fashion items (for example, affiliate links to partner online shops).

[1996] "Feedback collection methods" refer to methods for collecting user feedback and obtaining information to optimize future proposals based on this feedback.

[1997] A "natural language processing engine" is an engine used to analyze user input information and has the function of analyzing the meaning of text.

[1998] A "generative AI model" is an artificial intelligence model used to suggest the most suitable fashion items by matching user information, preference data, and trend information.

[1999] A "three-dimensional rendering engine" is an engine used to generate three-dimensional models for virtual try-on.

[2000] This invention is a system that provides personalized fashion advice to users. It uses user information, fashion preferences, and trend information to suggest optimal outfits, and provides support for virtual fitting rooms, product purchases, and feedback collection. This invention consists of the following main components:

[2001] User information input means

[2002] The user uses the application to enter personal information such as name, age, gender, fashion preferences, and budget. The device collects this information and sends it to the server. The server stores the received information in a database.

[2003] Fashion preferences and collecting methods

[2004] Users specify their preferred style, color, and items using a chat interface. The device sends this conversational data to a server, which uses a natural language processing engine (e.g., Google Cloud Natural Language API) to analyze the input data and store the user's preferences in a database.

[2005] Fashion Item Proposal Method

[2006] The server generates the optimal fashion coordinate based on user information and preference data, matching it with trend information (e.g., the latest fashion magazine data). Specifically, a generative AI model is used to generate the fashion coordinate. The generated coordinate is sent to the terminal, which then displays it to the user.

[2007] Virtual fitting room method

[2008] The user sends a request to virtually try on the suggested outfit. The device sends 3D model data for the virtual try-on to the server, which generates a 3D model of the virtual try-on using a 3D rendering engine (e.g., Unity3D) and sends it back to the device. The device then displays the results of the virtual try-on to the user.

[2009] Purchase link provision method

[2010] The server generates a purchase link (e.g., an affiliate link to a partner online shop) for the suggested fashion item. The terminal then displays this to the user.

[2011] Feedback collection methods

[2012] The user fills out a form to provide feedback after purchase or trying on an item. The device sends the feedback data to the server, which stores the feedback information in a database. The stored feedback is then used to inform future suggestions.

[2013] Specific example

[2014] User registration and initial outfit suggestion

[2015] 1. The user opens the application for the first time and enters their name, age, gender, fashion preference (e.g., casual, elegant), and budget (e.g., less than 30,000 yen per month). The device sends the entered information to the server, which stores it in a database.

[2016] 2. The user uses the chat interface to input their favorite color (e.g., blue) and the type of clothing they usually wear (e.g., jeans or a T-shirt). The terminal sends the conversation data to the server, which uses a natural language processing engine to analyze the user's information and record it in a database.

[2017] 3. Based on user preference data and trend data, the server generates a casual yet elegant style outfit (e.g., white blouse, black skinny jeans, red pumps) and sends it to the terminal.

[2018] 4. The device displays recommended outfits to the user, and the user requests a virtual try-on. The device sends a virtual try-on request to the server, which generates a virtual model using a 3D rendering engine and sends it to the device.

[2019] 5. The terminal displays the results of the virtual try-on to the user, and the user clicks the purchase link for the items they like. The terminal proceeds with the purchase process, the server saves the purchase data, and earns affiliate commissions. One week after the purchase, the server sends a follow-up message to the user, who provides feedback. The server saves the feedback in its database and uses it to improve future recommendations.

[2020] In this way, each component works together to provide users with a personalized fashion experience.

[2021] Example of a prompt

[2022] "Please tell us your favorite fashion style, colors, and items."

[2023] The flow of the specific processing in Example 1 will be explained using Figure 11.

[2024] Step 1: Collecting User Information

[2025] 1-1. The user launches the application and enters personal information such as name, age, gender, fashion preferences, and budget.

[2026] Input: Name, age, gender, fashion preferences, budget

[2027] Specific action: The user logs into the app from their smartphone or PC and enters the required information into the form.

[2028] 1-2. The terminal collects the entered information and sends it to the server.

[2029] Output: Entered user information

[2030] Specific operation: The device sends the input information to the server in real time, and a confirmation message is displayed to confirm successful transmission.

[2031] 1-3. The server saves the received information to the database.

[2032] Output: User information stored in the database

[2033] Specific operation: The server stores the received information in the database, and the saving of user information is confirmed.

[2034] Step 2: Collect your fashion preferences

[2035] 2-1. Users use the chat interface to specify their preferred style, color, and items.

[2036] Input: Preferred style, color, item

[2037] Specific action: The user enters "I like casual clothes and blue, and I usually wear jeans and t-shirts."

[2038] 2-2. The terminal sends the user's input to the server as text data.

[2039] Output: Sent preference data

[2040] Specific action: The terminal formats this as text data and sends it to the server.

[2041] 2-3. The server analyzes the input data using a natural language processing engine.

[2042] Input: Submitted preference data

[2043] Output: Analyzed preference data

[2044] Specific operation: The server uses a natural language processing engine to extract keywords such as "casual," "blue," "jeans," and "T-shirt."

[2045] 2-4. The server saves the analysis results to the database.

[2046] Output: Preference data stored in the database

[2047] Specific operation: The server saves the preferred data to the database, and a confirmation message is displayed.

[2048] Step 3: Fashion Coordination Suggestions

[2049] 3-1. The server matches user information, preference data, and trend information.

[2050] Input: User information, preference data, trend information

[2051] Output: Matched data

[2052] Specific operation: The server retrieves user information and trend information from the database and executes database queries to match them.

[2053] 3-2. The server generates the optimal fashion coordinate using an AI model for coordinate generation.

[2054] Input: Matched data

[2055] Output: Generated coordinate

[2056] Specific operation: The server generates outfits based on the user's preferences, such as "white blouse, black skinny jeans, and red pumps."

[2057] 3-3. The server sends the generated coordinate to the terminal.

[2058] Output: Coordinate sent to the terminal

[2059] Specific operation: The server sends the generated coordination information to the terminal, and a message indicating successful transmission is displayed.

[2060] 3-4. The device displays the outfit to the user.

[2061] Output: Coordinates displayed to the user

[2062] Specific action: The device displays an outfit to the user, such as "white blouse, black skinny jeans, red pumps," and a notification is issued asking for confirmation.

[2063] Step 4: Perform a virtual try-on.

[2064] 4-1. The user requests to virtually try on the item.

[2065] Input: Request for virtual try-on

[2066] Specific action: The user clicks a button that says, "I want to virtually try on this outfit."

[2067] 4-2. The terminal sends 3D model data for virtual try-on to the server.

[2068] Input: User body shape data, outfit data

[2069] Output: Sent 3D model data

[2070] Specific operation: The device sends the user's body shape data and outfit information to the server.

[2071] 4-3. The server uses a 3D rendering engine to generate a 3D model for virtual try-on.

[2072] Input: Submitted 3D model data

[2073] Output: Generated 3D model

[2074] Specific operation: The server uses a 3D rendering engine to generate a 3D model for virtual try-on.

[2075] 4-4. The server sends the generated 3D model to the terminal.

[2076] Output: 3D model sent to the terminal

[2077] Specific operation: The server sends the generated 3D model to the terminal, and a confirmation message is displayed.

[2078] 4-5. The terminal displays the results of the virtual try-on to the user.

[2079] Output: Virtual fitting results displayed to the user

[2080] Specific operation: The device displays a 3D model, and the user can see the results of a virtual try-on.

[2081] Step 5: Provide the purchase link

[2082] 5-1. The server generates a purchase link for the suggested fashion item.

[2083] Input: Suggested fashion item information

[2084] Output: Generated purchase link

[2085] Specific operation: The server generates a purchase URL for each item and creates a link.

[2086] 5-2. The server sends the generated purchase link to the device.

[2087] Output: Purchase link sent to the device

[2088] Specific operation: The server sends the generated purchase link to the device, and the link is displayed on the user's screen.

[2089] 5-3. The terminal displays this to the user.

[2090] Output: Purchase link displayed to the user

[2091] Specific action: The device displays a link saying "You can purchase it here," allowing the user to click it.

[2092] Step 6: Gathering Feedback

[2093] 6-1. The user fills out a form to provide feedback after purchase or after trying on the item.

[2094] Input: Feedback after purchase or try-on

[2095] Specific action: The user enters their opinions and feedback through a feedback form.

[2096] 6-2. The device sends feedback data to the server.

[2097] Output: Sent feedback data

[2098] Specific action: The terminal sends the input feedback to the server.

[2099] 6-3. The server saves the feedback information to the database.

[2100] Output: Feedback information stored in the database

[2101] Specific operation: The server stores the received data in the database, and a confirmation message for saving is displayed.

[2102] 6-4. The server incorporates the feedback into the next proposal.

[2103] Input: Saved feedback information

[2104] Output: Feedback reflected in the next proposal

[2105] Specific operation: The server optimizes the next coordination suggestion based on the feedback information.

[2106] The above outlines the specific processing steps of the program for this system.

[2107] (Application Example 1)

[2108] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[2109] Traditional fashion advice systems had limitations in providing personalized fashion suggestions to users, particularly in effectively linking trend information with user preferences. Furthermore, virtual try-on features failed to adequately replicate the feeling of actually trying on clothes, resulting in insufficient user satisfaction. Additionally, mechanisms for collecting post-purchase feedback and incorporating it into future suggestions were incomplete.

[2110] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[2111] In this invention, the server includes means for inputting user information, means for collecting fashion preferences, means for suggesting optimal fashion items based on trend information and user preference data using a generative AI model, means for providing a virtual fitting room, means for providing a purchase link, means for collecting post-purchase feedback, and means for sending post-purchase follow-up messages. This makes it possible to provide users with a more personalized and realistic fashion experience and improve user satisfaction.

[2112] "Means of inputting user information" refers to methods of collecting personal information such as the user's name, age, gender, fashion preferences, and budget through a terminal or application, and transmitting it to a server.

[2113] "Means of collecting fashion preferences" refers to a method by which users specify their preferred styles, colors, items, etc., using a chat interface or other input method, and send that data to a server.

[2114] A "generative AI model" is an artificial intelligence model that uses user information and preference data to match with trend information and suggest the most suitable fashion items.

[2115] A "virtual fitting room" is a system that allows users to virtually try on suggested fashion items. It uses 3D rendering technology to generate 3D models of the items to be virtually tried on and displays them to the user.

[2116] "Means of providing purchase links" refers to a means of generating and displaying to the user a link that allows them to purchase the proposed fashion item.

[2117] "Means of collecting post-purchase feedback" refers to providing a form for users to enter their opinions and impressions after purchasing or trying on an item, and then sending that feedback data to a server and storing it in a database.

[2118] "Method for sending follow-up messages after purchase" refers to a method for sending messages from a server to a user after they have purchased an item, in order to check on their experience and satisfaction with the item.

[2119] "Means of acquiring trend information" refers to methods of obtaining the latest trend information from external fashion-related databases or APIs and storing it on a server.

[2120] This invention is a system that provides personalized fashion advice to users. Specifically, it proposes the optimal outfit using user information, fashion preferences, and trend information. The aim of this system is to comprehensively support users in choosing their fashion through features such as virtual fitting rooms, assistance with product purchases, and feedback collection.

[2121] Key components of the system

[2122] 1. User information input means

[2123] Users use their devices to enter personal information such as their name, age, gender, fashion preferences, and budget. This information is sent from the device to the server, which stores the received information in a database.

[2124] 2. Methods for collecting fashion preferences

[2125] Users specify their preferred style, color, and items through a chat interface. The terminal sends this conversational data to a server, which uses a natural language processing engine to analyze the input data and store the user's preferences in a database.

[2126] 3. Proposed method using a generative AI model

[2127] The server generates optimal fashion coordinates based on user information and preference data, matching them with trend information. This is where a generation AI model is utilized. The generated fashion item recommendations are displayed to the user via their device.

[2128] 4. Virtual fitting room means

[2129] When a user requests to virtually try on a suggested outfit, the device sends 3D model data of the outfit to the server. The server uses a 3D rendering engine to generate a 3D model of the outfit and sends it to the device. The device then displays the results of the virtual try-on to the user.

[2130] 5. Means of providing purchase links

[2131] The server generates a purchase link (e.g., an affiliate link to a partner online shop) for the suggested fashion item. This allows the user to easily purchase the item. The terminal displays this to the user.

[2132] 6. Methods for collecting feedback

[2133] When a user fills out a form to provide feedback after a purchase or try-on, the data is sent from the device to the server and stored in a database. The server then uses the feedback information to improve future suggestions.

[2134] 7. Means of sending follow-up messages

[2135] The server sends a follow-up message after a user purchases an item to inquire about their experience and satisfaction with it. This allows for further collection of user feedback, which can then be used to improve future offerings.

[2136] Specific examples of actions

[2137] In a scenario where a user is using the application for the first time, the following prompt will be displayed:

[2138] Prompt: New user registration

[2139] name

[2140] age

[2141] sex

[2142] budget

[2143] style

[2144] Prompt: Collect your preferences details

[2145] Favorite color: Blue

[2146] Everyday clothing items: Jeans, T-shirts

[2147] Prompt: Generate recommended items

[2148] Prompt: Try on clothes virtually

[2149] Prompt: Purchase link displayed

[2150] Prompt: Feedback collection

[2151] This system allows users to receive personalized fashion suggestions and further enhance their experience by using a virtual try-on function. This improves user satisfaction and enables the optimization of future suggestions through the collection of feedback.

[2152] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[2153] Step 1:

[2154] The user opens the application and enters their initial registration information (name, age, gender, fashion preferences, budget). The device sends this input data to the server. The server saves the received user information to its database. Through this process, basic user information is recorded in the database.

[2155] Input: User registration information (name, age, gender, fashion preferences, budget)

[2156] Output: User information stored in the database

[2157] Step 2:

[2158] Users specify their preferred style, colors, items, etc., using a chat interface. The terminal sends this conversational data to the server. The server analyzes the input data using a natural language processing engine and stores the user's preference data in a database. This allows for the accumulation of detailed user preference information.

[2159] Input: User interaction data (preferred style, color, item)

[2160] Output: User preference data stored in the database

[2161] Step 3:

[2162] The server generates optimal fashion coordinates by matching user information and preference data with trend information. This is where a generation AI model is utilized. The generated fashion item recommendations are sent to the device and displayed to the user. This provides personalized fashion suggestions for each individual user.

[2163] Input: User information, preference data, trend information

[2164] Output: Fashion coordination suggestions sent to the terminal

[2165] Step 4:

[2166] The user sends a request to virtually try on suggested fashion items. The device sends this request to the server. The server generates a 3D model of the virtual try-on using a 3D rendering engine and sends it to the device. The device displays the virtual try-on results to the user. This allows the user to virtually try on the suggested items.

[2167] Input: User's virtual try-on request

[2168] Output: 3D model and virtual try-on results sent to the terminal

[2169] Step 5:

[2170] The server generates purchase links for items the user likes after a virtual try-on. These purchase links are structured as affiliate links to partner online shops. The terminal displays these links to the user, providing them with an environment where they can actually purchase the items.

[2171] Input: Information about items the user liked

[2172] Output: Purchase link displayed on the device

[2173] Step 6:

[2174] After a user purchases an item, the server sends a follow-up message prompting the user to provide feedback. When the user fills out a feedback form, the device sends the feedback data to the server. The server stores this feedback information in a database and uses it to improve future suggestions. This allows for further service improvements based on user feedback.

[2175] Input: User feedback data

[2176] Output: Feedback information stored in the database

[2177] Step 7:

[2178] The server performs data analysis based on user feedback to optimize future recommendations. This analysis data is then fed back into the generating AI model, enabling more accurate fashion item recommendations.

[2179] Input: Feedback Information

[2180] Output: Analysis data fed back into the generated AI model

[2181] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[2182] System Overview

[2183] This invention is a system that provides personalized fashion advice to users, suggesting optimal outfits using user information, fashion preferences, trend information, and the user's emotional state. Its aim is to comprehensively support users' fashion choices through features such as virtual fitting rooms, product purchase assistance, and feedback collection.

[2184] Key components of the system

[2185] 1. User information input means

[2186] Users enter personal information such as their name, age, gender, fashion preferences, and budget using the application.

[2187] The device collects this information and sends it to the server.

[2188] The server stores the received information in a database.

[2189] 2. Methods for collecting fashion preferences

[2190] Users specify their preferred style, color, and items through a chat interface.

[2191] The terminal sends this conversation data to the server.

[2192] The server uses a natural language processing engine to analyze the input data and saves the user's preferences to a database.

[2193] 3. Means of proposing fashion items

[2194] The server analyzes user information and preference data, along with trend information, to generate the optimal fashion coordinate. For example, the coordinate might consist of a white blouse, black skinny jeans, and red pumps.

[2195] The terminal displays this to the user.

[2196] 4. Virtual fitting room means

[2197] The user requests to virtually try on the suggested outfit.

[2198] The terminal sends 3D model data for virtual try-on to the server.

[2199] The server uses a 3D rendering engine to generate a 3D model for virtual try-on and sends it to the terminal.

[2200] The device displays the results of the virtual try-on to the user.

[2201] 5. Means of providing purchase links

[2202] The server generates purchase links (e.g., affiliate links to partner online shops) for the suggested fashion items.

[2203] The terminal displays this to the user.

[2204] 6. Methods for collecting feedback

[2205] Users fill out a form to provide feedback after purchasing or trying on an item.

[2206] The device sends feedback data to the server.

[2207] The server saves the feedback information to a database and incorporates it into future proposals.

[2208] 7. Emotional Engine

[2209] When a user uses the conversational interface, the emotion engine analyzes the user's emotional state from their input text and voice.

[2210] The device sends user emotion data to the server.

[2211] The server adjusts suggested fashion items and outfits based on emotional data.

[2212] Specific example

[2213] Coordination suggestions that take emotions into consideration

[2214] 1. The user opens the application for the first time and enters their name, age, gender, fashion preference (e.g., casual, elegant), and budget (e.g., less than 30,000 yen per month).

[2215] 2. The terminal sends the entered information to the server, and the server stores it in the database.

[2216] 3. The user uses the chat interface to enter their favorite color (e.g., blue) and the type of clothing they usually wear (e.g., jeans or a T-shirt).

[2217] 4. The terminal sends conversation data to the server, which uses a natural language processing engine to analyze the user's information and record it in a database.

[2218] 5. The emotion engine identifies the user's emotional state from their dialogue data and voice data, and analyzes emotional data such as happy, calm, and excited.

[2219] 6. The server generates fashion coordinates appropriate to the user's emotional state based on their emotional data, preference data, and trend data. For example, if the user is relaxed, it will suggest a casual and comfortable style (e.g., relaxed-fit jeans, a soft cardigan).

[2220] 7. The server sends the generated coordinate to the terminal, and the terminal displays it to the user.

[2221] 8. If the user requests a virtual try-on, the device sends a virtual try-on request to the server.

[2222] 9. The server generates a virtual model using a 3D rendering engine and sends it to the terminal.

[2223] 10. The device displays the results of the virtual try-on to the user, and the user clicks the purchase link for the items they like.

[2224] 11. The device proceeds with the purchase process, the server saves the purchase data, and the affiliate commission is earned.

[2225] 12. One week after purchase, the server sends a follow-up message to the user, who then provides feedback.

[2226] 13. The server saves the feedback to a database and incorporates it into future suggestions.

[2227] By combining these emotion engines, it becomes possible to provide a more personalized fashion experience that responds to the user's emotional state.

[2228] The following describes the processing flow.

[2229] Step 1:

[2230] The user opens the application and enters their name, age, gender, fashion preference (e.g., casual, elegant), and budget (e.g., under 30,000 yen per month).

[2231] Step 2:

[2232] The terminal sends the entered user information to the server. A method using an API to send data is employed.

[2233] Step 3:

[2234] The server saves the received user information to the database. The information is stored in the user profile table.

[2235] Step 4:

[2236] Users specify their preferred styles, colors, and the types of clothes they usually wear through a chat interface. For example, a user might input that they like blue, jeans, and t-shirts.

[2237] Step 5:

[2238] The device sends the collected conversation data to the server. The conversation data is sent in text format via the API.

[2239] Step 6:

[2240] The server uses a natural language processing engine to analyze user dialogue data. The analysis results are recorded in a database as user preferences and needs.

[2241] Step 7:

[2242] The emotion engine analyzes the user's input text and voice data to identify their emotional state. For example, it can analyze whether the user is happy, calm, or excited.

[2243] Step 8:

[2244] The device sends user emotion data to the server. This emotion data is retrieved in conjunction with a natural language processing engine.

[2245] Step 9:

[2246] The server comprehensively analyzes user preference data, emotional data, and trend information to generate fashion coordinates that suit the user's emotional state. For example, if the user is relaxed, it will suggest relaxed-fit jeans or a soft cardigan.

[2247] Step 10:

[2248] The server sends the generated outfit suggestions to the user's device. The outfit data is sent to the user's device via the API.

[2249] Step 11:

[2250] The device displays outfit suggestions to the user. The user can review the suggestions and choose whether or not they wish to virtually try them on.

[2251] Step 12:

[2252] If a user wishes to virtually try on clothes, the device sends a virtual try-on request to the server. The request includes information about the selected outfit.

[2253] Step 13:

[2254] The server uses a 3D rendering engine to generate a 3D model for virtual try-on. The data for the virtual model is prepared.

[2255] Step 14:

[2256] The server sends the generated 3D model data to the terminal. The terminal receives the model data upon request.

[2257] Step 15:

[2258] The device displays the results of the virtual try-on to the user. The user reviews the results and clicks the purchase link for the items they like.

[2259] Step 16:

[2260] The user clicks the purchase link and proceeds with the purchase of the item they like. The device sends the purchase data to the server.

[2261] Step 17:

[2262] The server receives the purchase data and saves it to the database. At the same time, affiliate marketing commissions are recorded.

[2263] Step 18:

[2264] One week after purchase, the server will send a follow-up message to the user. The message will include a link to a feedback form.

[2265] Step 19:

[2266] The user submits their opinions and feedback by filling out a feedback form. The device then sends the entered feedback data to the server.

[2267] Step 20:

[2268] The server receives the feedback and stores it in the database. The feedback will be incorporated into the next proposal.

[2269] Step 21:

[2270] The server optimizes the next outfit suggestion based on the collected feedback and user profile. A new outfit is generated and sent to the device.

[2271] This series of processes makes it possible to provide a personalized fashion experience that takes into account the user's emotional state.

[2272] (Example 2)

[2273] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[2274] In modern society, the diversification of individual preferences and trends in fashion makes it difficult for users to choose the most suitable fashion items for themselves. Furthermore, there is a lack of systems that can appropriately reflect the influence of a user's emotional state on their fashion choices, making it difficult to realize personalized suggestions. Moreover, there is a lack of mechanisms to achieve a higher level of personalization through virtual try-on and feedback. To solve these problems, the system proposed in this invention makes it possible to suggest fashion items that take into account user information, preferences, and emotional state.

[2275] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[2276] In this invention, the server includes means for inputting information about the user, means for collecting the user's fashion preferences, and means for analyzing the user's emotional state. This makes it possible to suggest optimal fashion items based on the user's detailed information and preferences, as well as their emotional state.

[2277] "User information" refers to personal data entered by the user, such as name, age, gender, fashion preferences, and budget.

[2278] A "fashion preference collection method" is an interface and mechanism for processing information that allows users to provide the system with their preferred styles, colors, and clothing items.

[2279] "Fashion item suggestion means" refers to a function for generating optimal fashion coordinates based on user information and fashion preferences.

[2280] A "virtual fitting room" is a function that allows users to virtually try on suggested fashion items using the system.

[2281] The "purchase link provision method" is a function that generates and provides links to facilitate the purchase of proposed fashion items.

[2282] A "feedback collection method" is a function for collecting opinions and impressions from users regarding the results of their purchases or try-ons.

[2283] A "database" is a collection of information that stores user input and feedback information and is accessible as needed.

[2284] A "natural language processing engine" is a software system that analyzes text and audio data input by users and extracts meaning from them.

[2285] A "sentiment analysis engine" is a software system that analyzes a user's emotional state from their input text or voice and provides the results.

[2286] Modes for carrying out the invention

[2287] This invention is a system that provides personalized fashion advice to users. The system proposes the optimal outfit using user information, fashion preferences, trend information, and the user's emotional state. It aims to comprehensively support users in choosing their fashion through features such as virtual fitting rooms, product purchase assistance, and feedback collection.

[2288] The system includes the following main components:

[2289] User information input means

[2290] Users enter personal information such as their name, age, gender, fashion preferences, and budget using the application.

[2291] The device collects this information and sends it to the server.

[2292] The server saves the received information to the database.

[2293] Fashion preferences and collecting methods

[2294] Users specify their preferred style, color, and items through a chat interface.

[2295] The terminal sends this conversation data to the server.

[2296] The server analyzes the input data using a natural language processing engine (such as OpenAI's GPT-3) and stores the user's preferences in a database.

[2297] sentiment analysis tool

[2298] When a user uses the conversational interface, the emotion engine analyzes the user's emotional state from their input text and voice.

[2299] The device sends user emotion data to the server.

[2300] The server adjusts suggested fashion items and outfits based on emotional data.

[2301] Fashion Item Proposal Method

[2302] The server generates optimal fashion coordinates based on user information and preference data, combined with trend information. Specifically, it suggests items such as a white blouse, black skinny jeans, and red pumps.

[2303] The device displays this to the user.

[2304] Virtual fitting room method

[2305] The user sends a request to virtually try on the suggested outfit.

[2306] The device sends 3D model data for virtual try-on to the server.

[2307] The server generates a 3D model for virtual try-on using a 3D rendering engine (such as Unity 3D) and sends it to the terminal.

[2308] The device displays the results of the virtual try-on to the user.

[2309] Purchase link provision method

[2310] The server generates purchase links (such as affiliate links to partner online shops) for the suggested fashion items.

[2311] The device displays this to the user.

[2312] Feedback collection methods

[2313] Users fill out a form to provide feedback after purchasing or trying on an item.

[2314] The device sends feedback data to the server.

[2315] The server saves the feedback information to a database and incorporates it into future proposals.

[2316] Specific example

[2317] A process for suggesting outfits that take emotions into consideration

[2318] 1. The user opens the application for the first time and enters their name (e.g., Taro Tanaka), age (30 years old), gender (male), fashion preference (casual), and budget (under 30,000 yen per month).

[2319] 2. The terminal sends the entered information to the server, and the server saves it to the database.

[2320] 3. The user types "I like blue, and I usually wear jeans and a T-shirt" in the chat interface.

[2321] 4. The terminal sends conversation data to the server, and the server uses a natural language processing engine to analyze and store the data.

[2322] 5. The emotion engine identifies the emotional state of "relaxed" from the user's dialogue data and voice data, and stores the data in a database.

[2323] 6. Generate the optimal outfit (e.g., relaxed-fit jeans, soft cardigan) when the server is "relaxed".

[2324] 7. The server sends the generated coordinate to the terminal, and the terminal displays it to the user.

[2325] 8. The user requests a virtual try-on and sends a request from their device to the server.

[2326] 9. The server uses a 3D rendering engine to generate a model for virtual try-on and sends it to the terminal.

[2327] 10. The device displays the results of the virtual try-on to the user, and the user clicks the purchase link for the items they like.

[2328] 11. The device proceeds with the purchase process, the server saves the purchase data, and the affiliate receives the commission.

[2329] 12. One week after purchase, the server sends a follow-up message to the user, who then provides feedback.

[2330] Example of a prompt

[2331] "Please suggest casual fashion outfits that are suitable for when the user is relaxing."

[2332] "Please tell us what items would be good for users to wear when they seem to be having fun."

[2333] As a result, the system takes into account the user's detailed information and emotional state to provide highly personalized fashion suggestions.

[2334] The flow of the specific processing in Example 2 will be explained using Figure 13.

[2335] Step 1:

[2336] The user launches the application and enters information such as their name, age, gender, fashion preferences, and budget.

[2337] Input: Name, age, gender, fashion preferences, budget

[2338] Output: User Information

[2339] Specific action: The user enters personal information such as "Taro Tanaka, 30 years old, male, casual attire, monthly income under 30,000 yen."

[2340] Step 2:

[2341] The terminal sends the entered user information to the server.

[2342] Input: User information

[2343] Output: User information sent to the server

[2344] Specific action: The device sends the information "Taro Tanaka, 30 years old, male, casual wear, monthly income under 30,000 yen" to the server.

[2345] Step 3:

[2346] The server saves the received user information to the database.

[2347] Input: User information sent to the server

[2348] Output: User information stored in the database

[2349] Specific action: The server records the information "Taro Tanaka, 30 years old, male, casual wear, monthly salary of 30,000 yen or less" in the database.

[2350] Step 4:

[2351] Users can use the chat interface to specify their preferred style, color, and items.

[2352] Input: Favorite style, color, item

[2353] Output: Preference information

[2354] Specific action: The user enters "I like blue, and I usually wear jeans and a T-shirt."

[2355] Step 5:

[2356] The terminal sends the conversation data to the server.

[2357] Input: Preference information

[2358] Output: Preference information sent to the server

[2359] Specific action: The device sends the information "I like blue and usually wear jeans and a T-shirt" to the server.

[2360] Step 6:

[2361] The server uses a natural language processing engine to analyze the input data and saves the user's preferences to a database.

[2362] Input: Preference information sent to the server

[2363] Output: Preference information stored in the database

[2364] Specific operation: The server uses a natural language processing engine such as OpenAI GPT-3 to extract keywords such as "blue, jeans, T-shirt" and save them to a database.

[2365] Step 7:

[2366] Users input text or voice through a conversational interface.

[2367] Input: Text or audio data

[2368] Output: Sentiment data

[2369] Specific action: The user types or speaks the phrase "I want to relax today."

[2370] Step 8:

[2371] The terminal sends the entered text or voice data to the server.

[2372] Input: Text or audio data

[2373] Output: Text and audio data sent to the server

[2374] Specific action: The device sends text or audio data of "I want to relax today" to the server.

[2375] Step 9:

[2376] The server's emotion engine analyzes the user's emotional state from text and audio.

[2377] Input: Text or audio data sent to the server

[2378] Output: Analyzed sentiment data

[2379] Specific operation: The server's emotion engine analyzes text and audio data to identify emotional states such as "relaxed."

[2380] Step 10:

[2381] The server adjusts suggested fashion items and outfits based on emotional data.

[2382] Input: Analyzed sentiment data

[2383] Output: Suggestions for tailored fashion items and outfits.

[2384] Specific operation: The server generates outfits such as "relaxed-fit jeans and a soft cardigan" based on sentiment data.

[2385] Step 11:

[2386] The server sends the generated outfit to the terminal.

[2387] Input: Suggestions for coordinated fashion items and outfits

[2388] Output: Fashion coordinates displayed to the user

[2389] Specific operation: The server sends the generated outfit to the terminal and displays suggestions to the user, such as "relaxed-fit denim, soft cardigan."

[2390] Step 12:

[2391] The user sends a request for a virtual try-on.

[2392] Input: Virtual try-on request

[2393] Output: Virtual fitting request data

[2394] Specific action: The user sends a request saying, "I want to virtually try on this outfit."

[2395] Step 13:

[2396] The device sends a request to the server for a virtual try-on.

[2397] Input: Virtual fitting request data

[2398] Output: Virtual try-on request data sent to the server

[2399] Specific operation: The terminal receives the user's request and sends it to the server.

[2400] Step 14:

[2401] The server uses a 3D rendering engine to generate a 3D model for the virtual try-on.

[2402] Input: Virtual try-on request data sent to the server

[2403] Output: 3D model data

[2404] Specific operation: The server uses a 3D rendering engine such as Unity 3D to generate a 3D model for virtual try-on.

[2405] Step 15:

[2406] The server sends the generated 3D model to the terminal.

[2407] Input: 3D model data

[2408] Output: 3D model data sent to the terminal

[2409] Specific operation: The server sends the generated 3D model to the terminal.

[2410] Step 16:

[2411] The device displays the results of the virtual try-on to the user.

[2412] Input: 3D model data sent to the terminal

[2413] Output: Virtual try-on results displayed to the user

[2414] Specific action: The device displays the results of the virtual try-on to the user, allowing the user to confirm them.

[2415] Step 17:

[2416] The server generates purchase links for the suggested fashion items.

[2417] Input: Suggestions for coordinated fashion items and outfits

[2418] Output: Purchase link

[2419] Specific operation: The server generates a purchase link (such as an affiliate link) for the suggested item.

[2420] Step 18:

[2421] The server sends a purchase link to the device.

[2422] Input: Purchase link

[2423] Output: Purchase link sent to the device

[2424] Specific action: The server sends the generated purchase link to the device.

[2425] Step 19:

[2426] The device displays a purchase link to the user.

[2427] Input: Purchase link sent to your device

[2428] Output: Purchase link displayed to the user

[2429] Specific action: The device displays a purchase link to the user, allowing the user to purchase the item.

[2430] Step 20:

[2431] The user purchases the item via the purchase link.

[2432] Input: Purchase link

[2433] Output: Purchase data

[2434] Specific action: The user clicks the purchase link and buys the item.

[2435] Step 21:

[2436] The server stores the purchase data and earns affiliate commissions.

[2437] Input: Purchase data

[2438] Output: Purchase data stored in the database, retrieved affiliate commissions.

[2439] Specific operation: The server stores the purchase data and receives affiliate commissions.

[2440] Step 22:

[2441] The server sends a follow-up message to the user, who then provides feedback.

[2442] Input: Purchase data

[2443] Output: Follow-up messages, feedback data

[2444] Specific action: One week after purchase, the server sends a follow-up message and the user enters feedback.

[2445] Step 23:

[2446] The device sends feedback data to the server.

[2447] Input: Feedback data

[2448] Output: Feedback data sent to the server

[2449] Specific action: The device sends user feedback data to the server.

[2450] Step 24:

[2451] The server saves the feedback information to a database and incorporates it into future proposals.

[2452] Input: Feedback data sent to the server

[2453] Output: Feedback information stored in the database, optimized next-generation suggestions.

[2454] Specific operation: The server saves the feedback information to a database and uses it to inform future suggestions.

[2455] (Application Example 2)

[2456] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[2457] Traditional fashion advice systems have a problem in that they cannot fully suggest the most suitable outfits for users because they do not take into account the user's emotional state. Furthermore, they lack sufficient integration of features that comprehensively support the user's online shopping experience, such as virtual try-on functionality and purchase links. As a result, users face the challenge of not being able to efficiently select fashion items that suit their preferences and mood.

[2458] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting information about the user, means for collecting the user's fashion preferences, means for collecting emotional data using an engine that analyzes emotional states and reflecting it in fashion item suggestions, means for providing a virtual fitting room, means for providing purchase links for the fashion items, and means for collecting user feedback and optimizing suggestions for the next time. This makes it possible to suggest more personalized fashion coordinates according to the user's emotional state.

[2459] A "user information input method" is a means for users to input personal information such as their name, age, gender, fashion preferences, and budget.

[2460] A "fashion preference collection method" is a means by which users specify their preferred styles, colors, and items using a chat interface, and the collection of that information is then performed.

[2461] A "fashion item suggestion method" is a method for generating optimal fashion coordinates by simultaneously analyzing trend information based on user information and preference data.

[2462] A "virtual fitting room means" is a method for generating 3D model data and displaying it to the user so that the user can virtually try on the suggested outfit.

[2463] A "purchase link provision method" is a means of generating purchase links for proposed fashion items and displaying them to the user.

[2464] A "feedback collection method" refers to a method of providing a form for users to provide feedback after purchase or trying on an item, and collecting that data.

[2465] An "emotion engine" is an engine that analyzes a user's emotional state from their input text or voice.

[2466] A "natural language processing engine" is an engine used to analyze user input information.

[2467] A "database" is a system for storing user input information and feedback information.

[2468] A "3D rendering engine" is an engine used to generate 3D models for virtual try-on.

[2469] System Configuration

[2470] This invention is a system that provides personalized fashion advice to users. This system proposes optimal outfits using user information, fashion preferences, trend information, and the user's emotional state. Its aim is to comprehensively support users' fashion choices through features such as virtual fitting rooms, product purchase assistance, and feedback collection.

[2471] Hardware and software used

[2472] The following hardware and software will be used.

[2473] Smartphone

[2474] server

[2475] Database (for example, Amazon RDS)

[2476] Natural language processing engine (e.g., Google NLP API)

[2477] Emotion engine (e.g., Microsoft Azure Emotion API)

[2478] 3D rendering engine (e.g., Unity 3D)

[2479] Collection of user information

[2480] Users enter personal information such as their name, age, gender, fashion preferences, and budget via their smartphone, and the device sends this information to a server. The server stores the received information in a database.

[2481] Fashion-loving collector

[2482] Users use a chat interface to input their preferred style, color, and items. The device sends this conversational data to a server, which uses a natural language processing engine to analyze the data and store the user's preferences in a database.

[2483] Analysis of emotional states

[2484] The emotion engine analyzes the user's emotional state from their dialogue and voice data. The device sends this emotional data to the server, which stores it in a database. The emotional state is then reflected in the suggested coordination.

[2485] Coordination suggestions

[2486] The server generates the optimal fashion coordinate based on user information, preference data, sentiment data, and trend information. The generated coordinate is then displayed to the user on their device.

[2487] Virtual fitting room

[2488] When a user requests to virtually try on a suggested outfit, the device sends 3D model data for the virtual try-on to the server. The server generates a virtual model using a 3D rendering engine and sends it to the device. The device then displays the results of the virtual try-on to the user.

[2489] Purchase link provided

[2490] The server generates a purchase link for the suggested fashion item. This link is, for example, an affiliate link to a partner online shop. The terminal displays this to the user, who then proceeds with the purchase.

[2491] Gathering feedback and optimizing future proposals

[2492] When a user provides feedback after purchasing or trying on an item, the device sends the feedback data to the server. The server stores the feedback information in a database and uses it to improve future recommendations.

[2493] Examples of specific cases and prompt statements

[2494] The user opens the application and enters their name, age, gender, fashion preferences (casual, elegant, etc.), and budget (under 30,000 yen per month, etc.). Next, they are asked, "What's your favorite color?" and the user answers, "Blue." Then they are asked, "What kind of clothes do you usually wear?" and they answer, "Jeans and T-shirts." After that, the system's emotion engine analyzes that the user is "relaxed" and suggests, "A relaxed style is recommended for today. How about relaxed-fit jeans and a soft cardigan?"

[2495] Example of a prompt

[2496] Username: User A, Preferred Style: Casual, Current Mood: Relaxed

[2497] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[2498] Step 1:

[2499] Users enter personal information such as their name, age, gender, fashion preferences, and budget via their smartphone. The device sends the entered information to the server. The server, upon receiving the user's input data, stores that information in a database.

[2500] Step 2:

[2501] Users input their preferred styles, colors, and items using a chat interface. This conversational data is sent from the terminal to the server. The server analyzes the received data using a natural language processing engine and stores data about the user's fashion preferences in a database.

[2502] Step 3:

[2503] The emotion engine analyzes the user's emotional state from their input text and voice. The device sends the user's emotional data to the server, which stores it in a database. The emotion engine analyzes the text and voice data and generates emotional labels such as "relaxed," "joyful," and "excited."

[2504] Step 4:

[2505] The server uses a generative AI model to suggest the optimal fashion outfit based on user information, fashion preference data, sentiment data, and trend information. The generated outfit is output in the form of, for example, "white blouse, black skinny jeans, red pumps." The outfit result is sent from the server to the terminal.

[2506] Step 5:

[2507] The user sends a request from their device to virtually try on the suggested outfit. The device sends 3D model data for the virtual try-on to the server, which generates the virtual model using a 3D rendering engine. The generated virtual model is sent from the server to the device and displayed to the user.

[2508] Step 6:

[2509] The server generates purchase links for the suggested fashion items. These purchase links are provided as affiliate links to partner online shops. The server sends the generated links to the user's device, where they are displayed. The user can then purchase the desired items.

[2510] Step 7:

[2511] Users input feedback into a terminal after purchasing or trying on items. The terminal sends the feedback data to a server, where it is stored in a database. The server updates the generated AI model based on the collected feedback and incorporates it into future fashion coordination suggestions.

[2512] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to out...

Claims

1. A means of entering user information, A means of collecting users' fashion preferences, A means of suggesting fashion items based on the above-mentioned information about the user and the above-mentioned user's fashion preferences, Means for providing a virtual fitting room, A means of providing purchase links for the above fashion items, Means for collecting user feedback, Based on the above feedback, we will develop a means to optimize the next proposal, A system that includes this.

2. The system according to claim 1, further comprising a natural language processing engine for analyzing user input information.

3. The system according to claim 1, further comprising a database for storing user input information and feedback information.

Images