System

Abstract

A system is provided.SOLUTION: A system, comprising: means for obtaining weather forecast, appointment and contact information input by a user; means for obtaining an existing clothing list of the user; means for sending the obtained information to a server; means for generating a collocation proposal based on the information received by the server using a generative AI model; means for returning the generated collocation proposal from the server to the user; means for displaying the collocation proposal to the user; and means for obtaining a feedback of the user and sending the feedback to the server; and means for fine-tuning the generative AI model based on the feedback.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] While people today desire to look stylish every day, they find it difficult to choose clothing and keep up with the latest fashion trends in their busy daily lives. They also face the challenge of not being able to make the most of the clothes they already have and instead tending to buy new clothes, which prevents them from contributing to sustainable consumption (SDG Goal 12: Responsible Consumption and Production). These issues can increase stress and waste time when it comes to fashion styling. [Means for solving the problem]

[0005] The system includes a means for acquiring information entered by the user about the weather, schedule, and people to meet, as well as a means for acquiring an existing clothing list. It also includes a means for transmitting this information to a server. The server uses the received information to generate outfit suggestions using a generative AI model and sends the suggestions back to the device. The device displays the suggestions to the user, receives feedback from the user, and sends it to the server. The server uses the feedback to fine-tune the generative AI model and improve the accuracy of the next suggestions. The generative AI model also generates suggestions taking into account the user's preferences and trend data. The server collects trend data and updates the generative AI model based on it. In this way, the system reduces the stress of fashion styling for users and promotes sustainable consumption.

[0006] "User" refers to an individual who uses this system to receive fashion advice and coordination suggestions.

[0007] "Weather" refers to the weather conditions (sunny, rainy, etc.) and temperature on a particular day.

[0008] "Plans" refers to what the user plans to do that day (for example, a meeting with friends, a business meeting, etc.).

[0009] "Meeting person" refers to a person the user plans to meet on that day.

[0010] "Existing clothing list" refers to a list of clothing items that the user already owns.

[0011] A "generative AI model" refers to an algorithm that uses machine learning and deep learning to generate optimal fashion coordination for users.

[0012] "Server" refers to a computer system that receives information sent by a user, generates coordination suggestions using a generative AI model, and returns them to the terminal.

[0013] "Terminal" refers to a device (smartphone, tablet, etc.) on which a user inputs information and displays outfit suggestions returned from the server.

[0014] "Outfit suggestions" refer to specific fashion combinations that the generative AI model generates based on information such as the weather, schedule, people you're meeting, and your existing clothing list.

[0015] "Feedback" refers to the user's evaluation and impressions of the proposed outfit.

[0016] "Fine-tuning" refers to the process of improving the performance of a generative AI model based on the feedback it receives.

[0017] "Trend data" refers to data that shows the latest fashion trends (for example, social media browsing results and purchasing data). [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8]FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0019] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0020] First, the terms used in the following description will be explained.

[0021] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0022] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0023] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0024] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0031] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0038] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0039] Overall system overview

[0040] This invention is a personal style assistant system that aims to provide personalized fashion advice based on user input of weather, schedule, and meeting information. The system utilizes the user's existing clothing list and a generative AI model to suggest outfits that take into account the user's preferences and trends. Furthermore, the AI ​​model is fine-tuned based on user feedback to improve the accuracy of future suggestions.

[0041] Explanation of program processing

[0042] 1. User Input

[0043] The user inputs information about the weather, schedule, and people they are meeting into a device (such as a smartphone or tablet). In addition, the user inputs or updates an existing clothing list.

[0044] Examples: "Today it's sunny and 18 degrees, I'm meeting a friend" and "White shirt, blue jeans, leather shoes"

[0045] 2. Data transmission

[0046] The terminal transmits the input information and the existing clothing list to the server. The transmitted data includes weather information, event information, clothing list, etc.

[0047] Example: Data format is "{'weather': 'Sunny, 18°C', 'event': 'Meeting with a friend', 'clothing_list': ['Blue jeans', 'White shirt', 'Leather shoes']}"

[0048] 3. Coordination suggestions by AI models

[0049] The server analyzes the user data received from the device, then runs a generative AI model to generate outfit suggestions based on the analyzed data, taking into account the user's preferences and trend data.

[0050] Example: A suggested outfit is "white shirt, blue jeans, and leather shoes."

[0051] 4. Consider trend data

[0052] The server references trend data (SNS browsing results, purchasing data, etc.) and adds the latest trend items to the generated coordination suggestions.

[0053] Example: "Add red scarf as a trend" to your suggestion

[0054] 5. Return of outfit suggestions

[0055] The server transmits the final generated coordination proposal to the terminal, which then displays the received proposal to the user.

[0056] For example: "White shirt, blue jeans, leather shoes, red scarf."

[0057] 6. Presentation to the User

[0058] The terminal displays the generated coordination proposal to the user.

[0059] Example: The suggested outfit for today is: white shirt, blue jeans, leather shoes, red scarf.

[0060] 7. Gathering Feedback

[0061] The user provides feedback on the proposed outfit (e.g., what they like and don't like), and the device sends this feedback to the server.

[0062] Example: "A white shirt and leather shoes go together really well."

[0063] 8. Update the AI ​​model

[0064] The server fine-tunes the generative AI model based on the received feedback, improving the accuracy of the next outfit suggestion.

[0065] Example: Improve the model based on feedback to better suit user preferences.

[0066] The advantage of this system is that it allows users to easily enjoy daily styling. Furthermore, it promotes sustainable consumption by maximizing the use of existing clothing and reducing the need to purchase new clothes. As a result, it significantly reduces stress and wastes time for users regarding fashion.

[0067] The processing flow will be explained below.

[0068] Step 1:

[0069] The user uses the device to input information about the weather, appointments, and people they are meeting. In addition, the user enters or updates an existing clothing list. At this stage, the user provides information about the specific weather conditions, events, and people they are meeting for the day.

[0070] Step 2:

[0071] The terminal sends the information entered by the user (weather, schedule, meeting person information, and existing clothing list) to the server. The data sent includes weather information, event information, clothing list, etc., and is sent in a standardized format.

[0072] Step 3:

[0073] The server analyzes the user data received from the device, including weather, schedule, meeting information, and existing clothing lists. The server uses this data to run a generative AI model.

[0074] Step 4:

[0075] The server generates outfit suggestions using a generative AI model, which takes into account the user's preferences and past feedback to generate optimal clothing combinations.

[0076] Step 5:

[0077] The server references trend data (social media browsing results, purchasing data, etc.) and adds trend items to the generated coordination suggestions. At this stage, the latest fashion trends are reflected in the generated basic suggestions.

[0078] Step 6:

[0079] The server then transmits the final coordinated outfit suggestions to the terminal, including specific clothing combinations and trend items.

[0080] Step 7:

[0081] The terminal displays the received outfit suggestions to the user, who can visually check the suggested outfits and use them as a reference for deciding on their style for the day.

[0082] Step 8:

[0083] Users provide feedback on the suggested outfits, including their preferences and whether the outfits look good or not.

[0084] Step 9:

[0085] The device sends user feedback to a server, where the feedback data is stored and analyzed to improve the accuracy of the generative AI model.

[0086] Step 10:

[0087] The server then fine-tunes the generative AI model based on the received feedback. This process improves the accuracy of the next outfit suggestions, generating suggestions that more closely match the user's preferences.

[0088] This process reduces the stress of daily styling for users, allowing them to enjoy fashion while promoting sustainable consumption.

[0089] Example 1

[0090] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0091] In today's consumer society, it is difficult to receive personalized fashion advice on a daily basis, and many people often struggle with their own style and choices. Furthermore, there are few systems that automatically suggest outfits that reflect the latest trends while optimizing existing clothing. Therefore, an effective method is needed to promote sustainable consumption while reducing stress related to fashion.

[0092] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0093] In this invention, the server includes means for acquiring information entered by the user about the weather, schedule, and people to meet, means for acquiring the user's existing clothing list, and means for transmitting the acquired information to the server, thereby making it possible to provide personalized fashion advice based on detailed user data.

[0094] The server also includes a means for generating outfit suggestions using a generative AI model based on the received information, a means for configuring input prompts for the generative AI model, and a means for referencing trend data and adding the latest trend items to the suggestions, thereby making it possible to provide outfit suggestions that reflect the user's preferences and the latest trends.

[0095] Furthermore, the server includes means for returning the generated outfit suggestions from the server to the terminal, means for the terminal to display the outfit suggestions to the user, means for acquiring user feedback and sending it to the server, and means for fine-tuning the generating AI model based on the feedback, thereby making it possible to provide more accurate outfit suggestions that reflect the user feedback from the next time onwards.

[0096] "User" refers to an individual using the system who inputs weather, schedule, meeting information, and existing clothing lists.

[0097] A "terminal" refers to an electronic device used by a user to input information, such as a smartphone or tablet.

[0098] "Weather information" is data that indicates the weather conditions for that day, and includes, for example, the temperature and the probability of precipitation.

[0099] "Schedule information" is data describing the actions and activities that the user plans to take that day.

[0100] "Information about people to meet" is information about people the user plans to meet that day, such as friends, family, or business partners.

[0101] The "existing clothing list" refers to a list of clothing owned by the user, specifically including items such as shirts, pants, and shoes.

[0102] "Server" refers to a computer system for receiving and processing data sent by users.

[0103] A "generative AI model" is a model for generating coordination suggestions using artificial intelligence technology, and specifically, for example, a generative language model.

[0104] A "prompt" is a way to create specific questions or instructions to input into a generative AI model.

[0105] "Trend data" refers to information about current fashion trends, and is data collected from social media, purchasing history, etc.

[0106] "Coordination suggestions" are suggestions for fashion combinations generated using information entered by the user and a generative AI model.

[0107] "Feedback" refers to the evaluation or opinion that the user inputs regarding the presented outfit.

[0108] "Fine-tuning" is a method of retraining the generative AI model based on user feedback, so that the next suggestions will be closer to the user's preferences.

[0109] This invention relates to a personal style assistant system that allows users to easily enjoy daily styling. The system's purpose is to provide personalized fashion advice by having users input information about the weather, their schedule, and the people they're meeting. The system utilizes the user's existing clothing list and uses a generative AI model to suggest outfits that take into account the user's preferences and trends. Furthermore, the AI ​​model is fine-tuned based on user feedback to improve the accuracy of future suggestions.

[0110] Hardware and Software Configuration

[0111] The system consists of two main pieces of hardware: a terminal and a server. The terminal is a device operated by the user, such as a smartphone or tablet, that runs a user interface application. The server is a cloud-based computer system that processes user data, runs generative AI models, and analyzes trend data.

[0112] The software running on the device is a user interface application. It sends information entered by the user to the server and displays outfit suggestions received from the server. The software on the server analyzes data, runs generative AI models (e.g., GPT-4), references trend data, and processes feedback.

[0113] Data Processing and Data Arithmetic

[0114] 1. User input:

[0115] The user inputs information about the weather, appointments, and people they are meeting through the device, and also inputs or updates an existing clothing list.

[0116] Example: A user enters "Today is sunny and 18 degrees. I plan to meet a friend," and registers "white shirt, blue jeans, leather shoes" in the clothing list.

[0117] 2. Data transmission:

[0118] The device sends the entered information and the existing clothing list to the server. The data is sent in JSON format using the HTTP protocol.

[0119] 3. Data analysis and model input:

[0120] The server receives the data, analyzes the weather information, event information, and clothing list, and then composes input prompts for the generative AI model.

[0121] Example prompt:

[0122] User info: {'weather': 'Sunny, 18°C', 'event': 'Meeting friends', 'clothing_list': ['White shirt', 'Blue jeans', 'Leather shoes']}

[0123] Generate outfit recommendations, taking into account user preferences and trends.

[0124] 4. Coordination proposal generation:

[0125] The server runs the generative AI model and generates outfit suggestions based on the analyzed data, taking into account the user's preferences and trend data.

[0126] 5. View trend data:

[0127] The server refers to trend data and adds the latest trend items to the coordination suggestions.

[0128] 6. Return and view outfit suggestions:

[0129] The server transmits the generated coordination proposal to the terminal, which displays the proposal to the user.

[0130] Example: The suggestion would be "Today's recommended outfit: white shirt, blue jeans, leather shoes, red scarf."

[0131] 7. Gathering Feedback:

[0132] The user provides feedback on the proposed coordination, which the terminal sends to the server.

[0133] Example: A user rates the combination of a white shirt and leather shoes as "a great look."

[0134] 8. Fine-tuning AI models:

[0135] The server fine-tunes the generative AI model based on user feedback to improve the accuracy of the next outfit suggestion.

[0136] In this way, the system provides users with personalized and accurate fashion advice, promotes sustainable consumption by making the most of existing clothing, and reduces stress and time wasted when it comes to fashion.

[0137] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0138] Step 1:

[0139] Enter user information

[0140] The user uses the device to input information about the weather, schedules, and people they are meeting, and also to input or update an existing clothing list. This information is collected through the user interface.

[0141] Input: Weather information, schedule information, meeting information, existing clothing list

[0142] Data processing: The user interface application converts this information into JSON format.

[0143] Output: Weather information, schedule information, meeting information, and clothing list in JSON format

[0144] Specific behavior:

[0145] The user opens the app, enters the weather as "Sunny, 18 degrees," the appointment as "Meeting a friend," and the person information as "Friend."

[0146] Register "white shirt, blue jeans, leather shoes" as a clothing list on the device.

[0147] Step 2:

[0148] Sending data

[0149] The device sends the entered information and the existing clothing list to the server. The data is transmitted using the HTTP protocol.

[0150] Input: Weather information, schedule information, meeting information, and clothing list entered by the user

[0151] Data processing: The device compiles this information into a single JSON object and sends it to the server.

[0152] Output: Input data sent to the server in JSON format

[0153] Specific behavior:

[0154] The device sends data to the server in the format "{'weather': 'Sunny 18 degrees', 'event': 'Meeting a friend', 'meet_person': 'Friend', 'clothing_list': ['White shirt', 'Blue jeans', 'Leather shoes']}".

[0155] Step 3:

[0156] Data analysis and model input

[0157] The server receives the data and analyzes the weather, events, people to meet, and clothing list, then composes input prompts for the generative AI model.

[0158] Input: Input data sent to the server in JSON format

[0159] Data processing: The server analyzes the received data and generates prompts in a format suitable for the generative AI model.

[0160] Output: Input prompts to the generative AI model

[0161] Specific behavior:

[0162] The server parses the data it receives and generates a prompt of the following form:

[0163] User info: {'weather': 'Sunny, 18°C', 'event': 'Meeting a friend', 'meet_person': 'Friend', 'clothing_list': ['White shirt', 'Blue jeans', 'Leather shoes']}

[0164] Generate outfit recommendations, taking into account user preferences and trends.

[0165] Step 4:

[0166] Generating outfit suggestions

[0167] The server runs the generative AI model and generates outfit suggestions based on the analyzed data, taking into account the user's preferences and trend data.

[0168] Input: Input prompts for the generative AI model

[0169] Data processing: A generative AI model generates outfit suggestions based on prompts.

[0170] Output: Coordination suggestions

[0171] Specific behavior:

[0172] The server runs the generative AI model and generates suggestions like: "Pair a white shirt with blue jeans and leather shoes."

[0173] Step 5:

[0174] Applying trend data

[0175] The server refers to trend data and adds the latest trend items to the coordination suggestions.

[0176] Input: Coordination suggestions, trend data

[0177] Data processing: Add items from trend data to the generated outfit suggestions.

[0178] Output: Updated outfit suggestions

[0179] Specific behavior:

[0180] The server retrieves the latest trend data from social media and purchasing data and adds "Red Scarf" to the suggestions.

[0181] Step 6:

[0182] Return and display of outfit suggestions

[0183] The server finally sends the updated coordination proposal to the terminal, which displays the proposal to the user.

[0184] Input: Updated outfit suggestions

[0185] Data processing: The server sends the proposal to the terminal, which then displays it on the user interface.

[0186] Output: Coordination suggestions presented to the user

[0187] Specific behavior:

[0188] The server sends "{'suggested_outfit': 'White shirt, blue jeans, leather shoes, red scarf'}" to the device.

[0189] The device displays on the user screen, "Today's recommended outfit: white shirt, blue jeans, leather shoes, red scarf."

[0190] Step 7:

[0191] Collecting feedback

[0192] The user provides feedback on the proposed coordination, and the terminal transmits the feedback to the server.

[0193] Input: User feedback

[0194] Data processing: The feedback information is converted back to JSON format and sent to the server.

[0195] Output: Feedback data sent to the server

[0196] Specific behavior:

[0197] A user reviews the outfit on the app, saying, "The combination of the white shirt and leather shoes is very good."

[0198] The device sends "{'feed_back': 'The combination of a white shirt and leather shoes is very good'}" to the server.

[0199] Step 8:

[0200] Fine-tuning AI models

[0201] The server fine-tunes the generative AI model based on user feedback to improve the accuracy of the next outfit suggestion.

[0202] Input: Feedback data from users

[0203] Data processing: The generative AI model retrains based on feedback and improves the model.

[0204] Output: A fine-tuned generative AI model

[0205] Specific behavior:

[0206] The server uses the feedback data to retrain the generative AI model and reflect it in future coordination suggestions.

[0207] (Application example 1)

[0208] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0209] Existing personal style assistant systems suggest outfits based on information entered by the user, such as the weather, schedule, and people they are meeting, but they have the problem of not being able to provide a real-time user experience like in a physical store. Furthermore, they are unable to instantly display outfit suggestions based on the products the user actually picks up, and there is a lack of means to further improve the user experience.

[0210] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0211] In this invention, the server includes means for acquiring information input by the user regarding the weather, schedule, and people to meet, means for acquiring the user's existing clothing list, means for transmitting the acquired information to the server, means for the server to generate outfit suggestions using a generative AI model based on the information received, means for the server to return the generated outfit suggestions to the terminal, means for the terminal to display the outfit suggestions to the user, means for acquiring user feedback and transmitting it to the server, means for the server to fine-tune the generative AI model based on the feedback, means for displaying outfit suggestions in real time when the user picks up a product in a physical store using smart glasses or a head-mounted display, and means for the terminal to generate a prompt sentence based on the user's input information and the picked up product and transmit the prompt sentence to the server. This enables users to receive appropriate outfit suggestions in real time even in physical stores.

[0212] "Means for obtaining information entered by the user about the weather, plans, and people to meet" refers to a function that allows the user to use a device such as a smartphone or tablet to enter information about the day's weather, plans, and people to meet, and the system collects this information.

[0213] The "means for acquiring the user's existing clothing list" is a function that allows the user to input or update a list of clothing that the user owns into the terminal and acquire that information from the system.

[0214] The "means for transmitting acquired information to the server" is a communication means for transmitting the weather, schedule, information on people to meet, and clothing list input by the user from the terminal to the server.

[0215] "Means for generating coordination suggestions using a generative AI model based on information received by the server" refers to a function for analyzing user data received by the server and using a generative AI model to create optimal coordination suggestions for the user.

[0216] The "means for returning the generated coordination proposal from the server to the terminal" is a communication means for transmitting the coordination proposal generated by the server to the terminal and providing it to the user.

[0217] The "means for the terminal to display a coordination suggestion to the user" is a function for visually presenting the generated coordination suggestion to the user using the display screen of the terminal.

[0218] The "means for acquiring user feedback and transmitting it to the server" is a function that allows the user to input their evaluation and opinion on the proposed outfit and transmit it from the terminal to the server.

[0219] "Means for the server to fine-tune the generative AI model based on feedback" is a function that receives feedback from users, improves the generative AI model based on that feedback, and increases the accuracy of the next outfit suggestion.

[0220] "A means for displaying coordination suggestions in real time when a user picks up a product in a physical store using smart glasses or a head-mounted display" is a function that displays coordination suggestions based on a product in real time when a user picks up the product in a physical store using smart glasses or a head-mounted display.

[0221] "Means for the terminal to generate a prompt sentence based on the information input by the user and the product picked up, and to send the prompt sentence to the server" refers to a function that generates a prompt sentence based on the weather, schedule, and person to meet information input by the user, and information on the product picked up in a physical store, and sends the prompt sentence from the terminal to the server.

[0222] System Overview

[0223] This invention is a style assistant system that provides personalized fashion suggestions based on the user's weather, schedule, and meeting information. In particular, it aims to provide optimal coordination suggestions in real time using smart glasses or head-mounted displays in brick-and-mortar stores.

[0224] Hardware and software used

[0225] Hardware: Smart glasses (e.g., Google Glass) or head-mounted displays (e.g., Microsoft HoloLens)

[0226] Software: Django (server-side framework), React (front-end framework), TensorFlow (generative AI model), OpenCV (visual data processing)

[0227] Specific explanation of the system's operation

[0228] Obtaining user input information

[0229] This function allows users to input information about the day's weather, schedule, and people they're meeting through smart glasses or a head-mounted display. Users can also upload their existing clothing lists.

[0230] Sending data

[0231] The entered information and existing clothing list are sent from the device to a server, which uses this information to create a user profile and prepares the data for the generative AI model.

[0232] Coordination suggestions using generative AI models

[0233] The server analyzes the received information and uses a generative AI model to generate optimal outfit suggestions for the user. It also references trend data to include the latest fashion items in the suggestions.

[0234] Real-time display

[0235] When a user picks up a product in a physical store, outfit suggestions based on that product are displayed in real time through smart glasses or a head-mounted display. At this time, prompts are generated based on the user's input information and the product they picked up.

[0236] Displaying suggested outfits

[0237] The generated coordination proposal is sent back to the terminal and visually presented to the user, who can see the entire coordination on the screen.

[0238] Getting feedback and tuning the AI ​​model

[0239] Users provide feedback on the proposed outfits, which is sent to the server, and the generative AI model is fine-tuned based on that feedback, improving the accuracy of the next suggestion.

[0240] Specific examples

[0241] Suppose a user uses smart glasses to input information such as "Today is sunny, 18 degrees, and I'm meeting a friend," and then picks up a black T-shirt. An example prompt sent to the server is:

[0242] "The weather is sunny, I'm meeting a friend, and I've picked up a black T-shirt. Can you suggest the best outfit for this situation?"

[0243] This allows the server to generate a coordination suggestion based on the user's preferences and the latest trends, such as "a black T-shirt, white sneakers, and dark denim pants," and display it in real time on the user's smart glasses.

[0244] As described above, the present invention can provide users with personalized and real-time fashion suggestions even in brick-and-mortar stores.

[0245] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0246] Step 1:

[0247] The user inputs information about the weather, schedule, and people they are meeting through smart glasses or a head-mounted display. The user inputs this information in text format using a device. The input of this step is the user's input data, and the output is the data stored on the device.

[0248] Step 2:

[0249] The terminal obtains the user's existing clothing list. The clothing list previously entered or updated by the user is read from the database. The input of this step is the user's clothing list data, and the output is the list data stored in the terminal.

[0250] Step 3:

[0251] The device sends the acquired information (weather, schedule, meeting person information, and clothing list) to the server. The input of this step is the user data stored on the device, and the output is the data sent to the server.

[0252] Step 4:

[0253] The server generates outfit suggestions using a generative AI model based on the information it receives. The server first analyzes the received data and passes it to the generative AI model, taking into account trend data and user preferences. The input to this step is the user data sent to the server, and the output is the generated outfit suggestions.

[0254] Step 5:

[0255] The server returns the generated coordination proposal to the terminal. The input of this step is the generated coordination proposal, and the output is the proposal data sent to the terminal.

[0256] Step 6:

[0257] The terminal displays outfit suggestions to the user. The terminal visually presents the outfit suggestions to the user. The input to this step is the suggestion data sent to the terminal, and the output is the outfit suggestions displayed on the display screen.

[0258] Step 7:

[0259] A user picks up a product in a physical store. The smart glasses or head-mounted display recognizes the product and reports it to the server. The input of this step is the product information picked up by the user, and the output is the product data sent to the server.

[0260] Step 8:

[0261] The terminal generates a prompt sentence based on the user's input information and the product picked up, and sends the prompt sentence to the server. The input for this step is the user's input information and product data, and the output is the generated prompt sentence.

[0262] Step 9:

[0263] The server receives the prompt sentence and generates outfit suggestions in real time using a generative AI model. The input of this step is the generated prompt sentence, and the output is real-time outfit suggestions.

[0264] Step 10:

[0265] The server sends the coordinated proposals generated in real time to the terminal and displays them to the user. The input of this step is the real-time coordinated proposals, and the output is the proposals displayed on the terminal.

[0266] Step 11:

[0267] The user provides feedback on the proposed coordination, and the terminal sends it to the server. The input of this step is the user's feedback, and the output is the feedback data sent to the server.

[0268] Step 12:

[0269] The server fine-tunes the generative AI model based on the feedback, which improves the accuracy of the next proposal. The input of this step is the feedback data, and the output is an improved generative AI model.

[0270] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0271] Overall system overview

[0272] This invention is a system that realizes a personal style assistant that provides users with personalized fashion advice and encourages sustainable consumption. In particular, by adding an emotion engine that recognizes the user's emotions, it is possible to propose outfits that are more tailored to the user's individual needs.

[0273] Explanation of program processing

[0274] 1. User Input

[0275] The user uses the terminal to input information about the weather, plans, and people to meet for the day, and also registers or updates an existing clothing list on the terminal.

[0276] Examples: "Today it's sunny and 18 degrees, I'm meeting a friend" and "White shirt, blue jeans, leather shoes"

[0277] 2. Emotional Recognition

[0278] The emotion engine recognizes emotions from the user's facial expressions and voice. The recognized emotional information (e.g., joy, sadness, stress, etc.) is input into the generative AI model.

[0279] Example: Your current emotion is judged to be "stress."

[0280] 3. Data transmission

[0281] The terminal sends the information input by the user (weather, schedule, information about people to meet, existing clothing list, and emotional information) to the server.

[0282] Data format: {'weather': 'Sunny, 18°C', 'event': 'Meeting with a friend', 'clothing_list': ['Blue jeans', 'White shirt', 'Leather shoes'], 'emotion': 'Stress'}

[0283] 4. Coordination suggestions by AI models

[0284] The server then activates a generative AI model based on the received data to generate outfit suggestions, taking into account the user's preferences, trend data, and emotional information.

[0285] For example, suggest outfits such as, "Choose a relaxed style to reduce stress."

[0286] 5. Consider trend data

[0287] The server references trend data (SNS browsing results, purchasing data, etc.) and adds the latest trend items to the generated coordination suggestions.

[0288] Example: "Add red scarf as a trend" to your suggestion

[0289] 6. Return of coordination proposal

[0290] The server then transmits the final coordinated outfit suggestions to the terminal, including specific clothing combinations and trend items.

[0291] For example: "White shirt, blue jeans, leather shoes, red scarf."

[0292] 7. Presentation to the User

[0293] The terminal displays the generated outfit suggestions to the user, who can visually check the suggested outfits and use them as reference for deciding on their style for the day.

[0294] Example: "Today's recommended outfit: white shirt, blue jeans, leather shoes, red scarf."

[0295] 8. Gathering Feedback

[0296] The user provides feedback on the suggested outfits, including whether they like the outfits or don't like them.

[0297] Example: "A white shirt and leather shoes go together really well."

[0298] 9. Update the AI ​​model

[0299] The server fine-tunes the generative AI model based on the received feedback, improving the accuracy of the next outfit suggestion.

[0300] Example: Improve the model based on feedback to make suggestions that better match the user's preferences.

[0301] This system allows users to receive more appropriate outfit suggestions based on their emotions, making it easier to choose the outfit that will make them feel good throughout the day. It also has the advantage of promoting sustainable consumption by utilizing existing clothing lists.

[0302] The processing flow will be explained below.

[0303] Step 1:

[0304] A user uses a device to input information about the weather, appointments, and people they are meeting. For example, the user inputs "Today it's sunny and 18 degrees, and I'm meeting a friend," updating an existing clothing list of "white shirt, blue jeans, leather shoes."

[0305] Step 2:

[0306] The device activates an emotion engine and recognizes emotions from the user's facial expressions and voice. For example, if the user has an expression that indicates stress, the emotion engine will recognize this as "stress."

[0307] Step 3:

[0308] The device sends data including the input information and emotion information to the server. The sent data includes "weather information, event information, clothing list, emotion information," etc. An example of data is "{'weather': 'Sunny, 18°C', 'event': 'Meeting with a friend', 'clothing_list': ['Blue jeans', 'White shirt', 'Leather shoes'], 'emotion': 'Stress'}."

[0309] Step 4:

[0310] The server analyzes the user data received from the device, including weather, schedules, people to meet, existing clothing lists, and emotional information, and activates a generative AI model based on this data.

[0311] Step 5:

[0312] The server uses a generative AI model to generate outfit suggestions. The generative AI model considers the user's preferences, past feedback, and current emotional information to generate appropriate clothing combinations. For example, it may suggest, "If you're feeling stressed, we recommend a relaxed style."

[0313] Step 6:

[0314] The server references trend data (such as social media browsing results and purchasing data) and adds the latest trend items to the generated coordination suggestions. For example, "Add a red scarf to a white shirt and blue jeans as a trend."

[0315] Step 7:

[0316] The server then sends the final outfit recommendation to the device. The data includes specific clothing combinations and trend items. An example of the data is "{'recommendation': ['White shirt', 'Blue jeans', 'Leather shoes', 'Red scarf']}".

[0317] Step 8:

[0318] The terminal displays the received outfit suggestions to the user. The user can visually check the suggested outfits and use them as a reference for deciding on their style for the day. An example display might be "Today's recommended outfit: white shirt, blue jeans, leather shoes, red scarf."

[0319] Step 9:

[0320] The user provides feedback on the proposed outfit, including specific preferences and areas for improvement. For example, the user may provide feedback such as, "The combination of a white shirt and leather shoes is very good."

[0321] Step 10:

[0322] The device sends user feedback to a server, where the feedback data is stored and analyzed to improve the accuracy of the generative AI model.

[0323] Step 11:

[0324] The server fine-tunes the generative AI model based on the received feedback. This improves the accuracy of the next outfit suggestion and generates suggestions that are closer to the user's preferences. For example, reflecting the user's feedback, the server will continue to recommend a combination of a white shirt and leather shoes.

[0325] Example 2

[0326] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0327] Conventional fashion assistant systems have the problem of not being able to fully meet the user's needs because they do not take into account the user's emotions or real-time trend information. In addition, because they are unable to propose outfits that take the user's emotional state into account, the suggested styles may not match the user's mood or the situation. As a result, users tend to be dissatisfied with the outfits provided and have fewer opportunities to actually wear them.

[0328] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0329] In this invention, the server includes means for acquiring information on the weather, schedule, and people to meet input by the user, means for acquiring the user's existing clothing list, means for acquiring the user's facial expressions and voice and recognizing emotions, means for generating outfit suggestions using a generative AI model based on the acquired information and the recognized emotion information, means for adding trend items to the generated outfit suggestions by referring to trend data, and means for fine-tuning the generative AI model based on user feedback. This enables personalized outfit suggestions that take into account the user's emotions and real-time trend information.

[0330] "Weather information" refers to data entered by the user regarding the weather conditions for that day.

[0331] "Schedule" refers to information entered by the user about activities and events to be held that day.

[0332] "Information about people to meet" refers to information about people the user plans to meet on that day.

[0333] "Existing Clothing List" refers to a list of clothing owned by the user, including data registered with a particular application or device.

[0334] "Emotion information" refers to data that indicates the emotional state of the user as recognized from their facial expressions and voice.

[0335] "Server" refers to the computer system that receives and processes data, runs the generative AI model, obtains feedback, and fine-tunes the model.

[0336] A "generative AI model" refers to an artificial intelligence model that generates fashion coordination suggestions based on user input and emotional information.

[0337] "Outfit suggestions" refer to clothing combinations recommended based on the user's input information and emotions.

[0338] "Trend data" refers to information about the latest fashion trends and includes data collected from social media and purchasing data.

[0339] "Feedback" refers to user-provided ratings and comments on the proposed outfits.

[0340] "Fine-tuning" refers to the process of adjusting the parameters of a generative AI model based on received feedback to improve the accuracy of its suggestions.

[0341] Overall system configuration

[0342] This invention is a personal style assistant system that provides users with personalized fashion advice and encourages sustainable consumption. In particular, by adding an emotion engine that recognizes the user's emotions, it is possible to propose outfits that are more tailored to the user's individual needs.

[0343] Hardware and Software Configuration

[0344] Terminal

[0345] Users use devices such as smartphones and tablets. The devices are equipped with cameras and microphones that capture the user's facial expressions and voice. They also install applications and input information about the weather, their schedule, people they are meeting, and their existing clothing list.

[0346] server

[0347] The server is a high-performance computer system that receives and processes data and runs the generative AI model. The server can use Microsoft Azure's emotion analysis API as an emotion engine, which analyzes the user's emotional information and generates optimal outfit suggestions.

[0348] Generative AI Models

[0349] The generative AI model uses an advanced language model such as GPT-4, and the server uses this generative AI model to generate fashion coordination suggestions based on the user's input and emotional information.

[0350] Program processing

[0351] The device first acquires the user's input information (weather, schedule, information about people to meet, existing clothing list), as well as facial expressions and voice. The data acquired using the camera and microphone is analyzed by the emotion engine and sent to the server as emotion information.

[0352] Next, the server launches a generative AI model based on the received information. The generative AI model receives the following text data as a prompt:

[0353] "Today's weather is sunny and 18 degrees, plans include meeting a friend, and current emotion is stress. The user has the following clothing list: white shirt, blue jeans, leather shoes."

[0354] Based on this, the generative AI model generates coordination suggestions that take into account the user's preferences and trend data. As a specific example, the generative AI model might suggest "adding a red scarf to a white shirt, blue jeans, and leather shoes as a trend."

[0355] The generated outfit suggestions are sent back from the server to the device, which then displays them to the user through the application. The user can review the suggested outfits and decide on their style for the day. In addition, the user can provide feedback on the suggested outfits. For example, the user can leave a specific comment such as, "The combination of a white shirt and leather shoes is very good."

[0356] Finally, the server fine-tunes the generative AI model based on the received feedback, improving the accuracy of the next outfit suggestions and providing results that better match the user's preferences.

[0357] The system allows users to receive personalized outfit suggestions that take into account emotions and real-time trend information, and also promotes sustainable consumption.

[0358] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0359] Step 1:

[0360] The device receives input from the user about today's weather, plans, and people to meet. The user enters this data using text boxes and selection boxes in the application. For example, the user enters information like "Today it's sunny and 18 degrees, and I'm planning to meet a friend." The device then temporarily stores this information.

[0361] Step 2:

[0362] The device retrieves the user's existing clothing list. The user provides data by manually entering text or uploading photos of the clothing. For example, if information such as "white shirt, blue jeans, leather shoes" is entered, the device will store this data.

[0363] Step 3:

[0364] The device's camera and microphone are used to capture the user's facial and voice data. This data is captured in real time and processed by facial recognition software and voice analysis software. The emotion engine analyzes the user's emotional state (e.g., joy, stress) and extracts emotional information.

[0365] Step 4:

[0366] The device sends the weather, schedule, meeting information, existing clothing list, and emotion information acquired as JSON format data to the server. The input information is formatted as follows and sent to the server:

[0367] json

[0368] {

[0369] "weather": "Sunny, 18°C",

[0370] "event": "Meeting with a friend",

[0371] "clothing_list": ["Blue jeans", "White shirt", "Leather shoes"],

[0372] "emotion": "Stress"

[0373] }

[0374] Step 5:

[0375] The server processes the received information and launches a generative AI model, which receives the following prompt text and generates outfit suggestions based on it:

[0376] "Today's weather is sunny and 18 degrees, plans include meeting a friend, and current emotion is stress. The user has the following clothing list: white shirt, blue jeans, leather shoes."

[0377] Step 6:

[0378] The server uses a generative AI model to generate personalized outfit suggestions for each user. The generative AI model takes into account the user's preferences, emotional information, and trend data, and generates outfit suggestions as output. For example, a suggestion might be generated such as "Add a red scarf to a white shirt, blue jeans, and leather shoes, as a trend."

[0379] Step 7:

[0380] The server finally sends the generated coordination proposal to the device. The generated data is sent to the device in the following format:

[0381] json

[0382] {

[0383] "recommendation": ["White shirt", "Blue jeans", "Leather shoes", "Red scarf"]

[0384] }

[0385] Step 8:

[0386] The terminal displays the received outfit suggestions to the user. The user can visually check the suggested outfits on the application screen. For example, "Today's recommended outfit: white shirt, blue jeans, leather shoes, red scarf" is displayed.

[0387] Step 9:

[0388] Users provide feedback on the suggested outfits. Feedback is entered using an in-app evaluation form, and includes pros and cons of the suggested outfits and areas for improvement. For example, a specific comment such as "The combination of a white shirt and leather shoes is very good" can be entered.

[0389] Step 10:

[0390] The device sends the user's feedback to the server, which then formats the feedback as follows and sends it to the server:

[0391] json

[0392] {

[0393] "feedback": "The combination of a white shirt and leather shoes is very good"

[0394] }

[0395] Step 11:

[0396] The server fine-tunes the generative AI model based on the received feedback. The server analyzes the feedback and adjusts the parameters of the generative AI model to improve the accuracy of future outfit suggestions, thereby providing results that better match the user's preferences.

[0397] (Application example 2)

[0398] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0399] Conventional personal style assistants have been unable to provide coordination suggestions that take the user's emotions into account. As a result, they are unable to provide fashion suggestions based on the user's mood or emotions of the day, making it difficult to increase user satisfaction. In addition, there is a demand for more personalized suggestions that match the user's mood by providing fashion suggestions that take into account not only information such as the weather and schedule, but also the user's emotions.

[0400] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for recognizing the user's emotion using an emotion engine, means for transmitting the recognized emotion information to the server, and means for generating coordination suggestions using a generative AI model based on the information received by the server. This makes it possible to make fashion suggestions that take the user's emotions into consideration.

[0401] "Means for acquiring information entered by the user about the weather, schedule, and people to meet" refers to a function that allows the user to input information about the weather for the day, schedule, and people to meet into an electronic terminal, and the system acquires that information.

[0402] The "means for acquiring a list of the user's existing clothing" is a function that allows the user to register the clothing he or she owns in a list, and for the system to acquire that list.

[0403] The "means for transmitting acquired information to a server" is a function for transmitting information entered by the user and recognized emotion information to a server via the Internet.

[0404] The "means for recognizing the user's emotions using an emotion engine" is a function that detects the user's current emotional state by analyzing the user's facial expressions and voice.

[0405] The "means for transmitting the recognized emotion information to the server" is a function for transmitting the emotion information recognized by the emotion engine to the server.

[0406] "Means for generating coordination suggestions using a generative AI model based on information received by the server" refers to a function that activates a generative AI model based on information and emotional information received by the server from the user, and suggests optimal fashion coordination.

[0407] The "means for returning the generated coordination proposal from the server to the terminal" is a function for transmitting the fashion coordination proposal generated by the server to the user's terminal.

[0408] The "means for the terminal to display coordination suggestions to the user" is a function for visually displaying to the user fashion coordination suggestions received by the terminal from the server.

[0409] The "means for acquiring user feedback and transmitting it to the server" is a function that allows the user to input opinions and evaluations of the provided coordination proposals and transmit the feedback to the server.

[0410] "Means for the server to fine-tune the generative AI model based on feedback" refers to a function that makes adjustments to improve the accuracy of the generative AI model based on feedback information from users.

[0411] "The generative AI model generates outfit suggestions by taking into account the user's preferences, trend data, and emotional information" refers to the process in which the generative AI model combines the user's personal preferences, the latest fashion trend data, and the user's current emotional state to suggest optimal fashion outfits.

[0412] "Means for collecting trend data and updating the generative AI model based on that data" refers to a function in which the server collects fashion trend data from the internet and various databases, and uses that data to keep the algorithm of the generative AI model up to date.

[0413] The present invention provides a personal style assistant system that uses an emotion engine to suggest optimal outfits to users by utilizing information on the user's weather, schedule, people they are meeting, existing clothing list, and emotion information. By taking the user's emotions into consideration, the system can provide more personalized fashion suggestions and improve user satisfaction.

[0414] Hardware and software used

[0415] Hardware: Smartphone (iOS or Android)

[0416] software:

[0417] EmotionEngine (emotion recognition engine)

[0418] AICoordinator (AI model for suggesting outfits)

[0419] REST API (a server that supports HTTP requests)

[0420] The server uses the EmotionEngine to recognize emotions from the user's facial expressions and voice. It captures the user's face and voice using the smartphone camera and microphone, and analyzes the data. The analyzed emotional data is sent to the server along with the weather, schedule, meeting information, and existing clothing list entered by the user.

[0421] The server launches a generative AI model based on all the received data, and generates outfit suggestions based on the information obtained. The generative AI model comprehensively considers the user's preferences, trend data, and emotional information. For example, based on the information "Today is sunny and 18 degrees, and I plan to meet a friend," "A white shirt, blue jeans, and leather shoes," and "I'm feeling stressed," the model suggests a "relaxed style" of a white shirt, blue jeans, leather shoes, and a trendy red scarf.

[0422] The generated outfit suggestions are sent back from the server to the smartphone and visually displayed to the user on the smartphone screen. The user can use the suggested outfits as a reference to decide on their fashion for the day. Furthermore, the user can input feedback about the suggested outfits and send it to the server, which can then use that feedback to fine-tune the generative AI model and improve the accuracy of the next suggestions.

[0423] Examples of concrete examples and prompts

[0424] As an example, a user enters the following information:

[0425] Weather: Sunny and 18 degrees

[0426] Plans: Meeting with friends

[0427] Existing clothing list: White shirt, blue jeans, leather shoes

[0428] Emotional information: I'm feeling stressed

[0429] Example prompt sentence:

[0430] "Today is sunny and 18 degrees, and I'm meeting a friend. My existing clothing list includes a white shirt, blue jeans, and leather shoes. My current emotion is determined to be stress."

[0431] As described above, the present invention can improve user satisfaction by providing fashion suggestions that take the user's emotions into consideration. It also has the advantage of promoting sustainable consumption by utilizing existing clothing.

[0432] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0433] Step 1:

[0434] A user inputs information about the weather, plans, people to meet, and an existing clothing list into a smartphone. The smartphone has an interface that accepts user input, and this collects the necessary information. Examples of input data include "Today is sunny and 18 degrees. I plan to meet a friend," "White shirt, blue jeans, leather shoes."

[0435] Step 2:

[0436] Using the emotion engine, the smartphone device analyzes the user's facial expressions and voice to recognize emotions. Using data captured through the smartphone's camera and microphone, the emotion engine identifies emotions such as "stress." This recognized emotion information is used for further processing.

[0437] Step 3:

[0438] The device sends the collected weather, schedule, meeting information, existing clothing list, and recognized emotion information to the server in a JSON format, such as "{'weather': 'Sunny, 18°C', 'event': 'Meeting with a friend', 'clothing_list': ['Blue jeans', 'White shirt', 'Leather shoes'], 'emotion': 'Stress'}".

[0439] Step 4:

[0440] The server then activates a generative AI model based on the received data to generate outfit suggestions. The generative AI model uses an algorithm that takes into account the user's preferences, trend data, and emotional information. For example, suggestions might be generated in the form of "pick a relaxed style to reduce stress."

[0441] Step 5:

[0442] The server references the latest trend data collected (such as social media posts and purchasing data) and reflects it in the coordination suggestions. For example, "add a red scarf as a trend item" to the generated coordination.

[0443] Step 6:

[0444] The generated outfit suggestions are sent from the server to the smartphone device. The suggestions include specific clothing combinations and trendy items. For example, a "white shirt, blue jeans, leather shoes, and red scarf" combination might be suggested.

[0445] Step 7:

[0446] The device displays the generated outfit suggestions to the user, who can then check the suggested fashions on their smartphone screen and use them as a reference for deciding what to wear that day.

[0447] Step 8:

[0448] The user provides feedback on the proposed outfits, including their preferences and points that do not suit them, and inputs this feedback into the terminal.

[0449] Step 9:

[0450] The device sends user feedback to the server, which then fine-tunes the generative AI model based on the received feedback. This improves the accuracy of the next outfit suggestions, for example, by providing outfits that better match the user's preferences.

[0451] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0452] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0453] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0454] [Second embodiment]

[0455] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0456] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0457] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0458] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0459] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0460] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0461] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0462] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0463] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0464] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0465] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0466] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0467] Overall system overview

[0468] This invention is a personal style assistant system that aims to provide personalized fashion advice based on user input of weather, schedule, and meeting information. The system utilizes the user's existing clothing list and a generative AI model to suggest outfits that take into account the user's preferences and trends. Furthermore, the AI ​​model is fine-tuned based on user feedback to improve the accuracy of future suggestions.

[0469] Explanation of program processing

[0470] 1. User Input

[0471] The user inputs information about the weather, schedule, and people they are meeting into a device (such as a smartphone or tablet). In addition, the user inputs or updates an existing clothing list.

[0472] Examples: "Today it's sunny and 18 degrees, I'm meeting a friend" and "White shirt, blue jeans, leather shoes"

[0473] 2. Data transmission

[0474] The terminal transmits the input information and the existing clothing list to the server. The transmitted data includes weather information, event information, clothing list, etc.

[0475] Example: Data format is "{'weather': 'Sunny, 18°C', 'event': 'Meeting with a friend', 'clothing_list': ['Blue jeans', 'White shirt', 'Leather shoes']}"

[0476] 3. Coordination suggestions by AI models

[0477] The server analyzes the user data received from the device, then runs a generative AI model to generate outfit suggestions based on the analyzed data, taking into account the user's preferences and trend data.

[0478] Example: A suggested outfit is "white shirt, blue jeans, and leather shoes."

[0479] 4. Consider trend data

[0480] The server references trend data (SNS browsing results, purchasing data, etc.) and adds the latest trend items to the generated coordination suggestions.

[0481] Example: "Add red scarf as a trend" to your suggestion

[0482] 5. Return of outfit suggestions

[0483] The server transmits the final generated coordination proposal to the terminal, which then displays the received proposal to the user.

[0484] For example: "White shirt, blue jeans, leather shoes, red scarf."

[0485] 6. Presentation to the User

[0486] The terminal displays the generated coordination proposal to the user.

[0487] Example: The suggested outfit for today is: white shirt, blue jeans, leather shoes, red scarf.

[0488] 7. Gathering Feedback

[0489] The user provides feedback on the proposed outfit (e.g., what they like and don't like), and the device sends this feedback to the server.

[0490] Example: "A white shirt and leather shoes go together really well."

[0491] 8. Update the AI ​​model

[0492] The server fine-tunes the generative AI model based on the received feedback, improving the accuracy of the next outfit suggestion.

[0493] Example: Improve the model based on feedback to better suit user preferences.

[0494] The advantage of this system is that it allows users to easily enjoy daily styling. Furthermore, it promotes sustainable consumption by maximizing the use of existing clothing and reducing the need to purchase new clothes. As a result, it significantly reduces stress and wastes time for users regarding fashion.

[0495] The processing flow will be explained below.

[0496] Step 1:

[0497] The user uses the device to input information about the weather, appointments, and people they are meeting. In addition, the user enters or updates an existing clothing list. At this stage, the user provides information about the specific weather conditions, events, and people they are meeting for the day.

[0498] Step 2:

[0499] The terminal sends the information entered by the user (weather, schedule, meeting person information, and existing clothing list) to the server. The data sent includes weather information, event information, clothing list, etc., and is sent in a standardized format.

[0500] Step 3:

[0501] The server analyzes the user data received from the device, including weather, schedule, meeting information, and existing clothing lists. The server uses this data to run a generative AI model.

[0502] Step 4:

[0503] The server generates outfit suggestions using a generative AI model, which takes into account the user's preferences and past feedback to generate optimal clothing combinations.

[0504] Step 5:

[0505] The server references trend data (social media browsing results, purchasing data, etc.) and adds trend items to the generated coordination suggestions. At this stage, the latest fashion trends are reflected in the generated basic suggestions.

[0506] Step 6:

[0507] The server then transmits the final coordinated outfit suggestions to the terminal, including specific clothing combinations and trend items.

[0508] Step 7:

[0509] The terminal displays the received outfit suggestions to the user, who can visually check the suggested outfits and use them as a reference for deciding on their style for the day.

[0510] Step 8:

[0511] Users provide feedback on the suggested outfits, including their preferences and whether the outfits look good or not.

[0512] Step 9:

[0513] The device sends user feedback to a server, where the feedback data is stored and analyzed to improve the accuracy of the generative AI model.

[0514] Step 10:

[0515] The server then fine-tunes the generative AI model based on the received feedback. This process improves the accuracy of the next outfit suggestions, generating suggestions that more closely match the user's preferences.

[0516] This process reduces the stress of daily styling for users, allowing them to enjoy fashion while promoting sustainable consumption.

[0517] Example 1

[0518] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0519] In today's consumer society, it is difficult to receive personalized fashion advice on a daily basis, and many people often struggle with their own style and choices. Furthermore, there are few systems that automatically suggest outfits that reflect the latest trends while optimizing existing clothing. Therefore, an effective method is needed to promote sustainable consumption while reducing stress related to fashion.

[0520] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0521] In this invention, the server includes means for acquiring information entered by the user about the weather, schedule, and people to meet, means for acquiring the user's existing clothing list, and means for transmitting the acquired information to the server, thereby making it possible to provide personalized fashion advice based on detailed user data.

[0522] The server also includes a means for generating outfit suggestions using a generative AI model based on the received information, a means for configuring input prompts for the generative AI model, and a means for referencing trend data and adding the latest trend items to the suggestions, thereby making it possible to provide outfit suggestions that reflect the user's preferences and the latest trends.

[0523] Furthermore, the server includes means for returning the generated outfit suggestions from the server to the terminal, means for the terminal to display the outfit suggestions to the user, means for acquiring user feedback and sending it to the server, and means for fine-tuning the generating AI model based on the feedback, thereby making it possible to provide more accurate outfit suggestions that reflect the user feedback from the next time onwards.

[0524] "User" refers to an individual using the system who inputs weather, schedule, meeting information, and existing clothing lists.

[0525] A "terminal" refers to an electronic device used by a user to input information, such as a smartphone or tablet.

[0526] "Weather information" is data that indicates the weather conditions for that day, and includes, for example, the temperature and the probability of precipitation.

[0527] "Schedule information" is data describing the actions and activities that the user plans to take that day.

[0528] "Information about people to meet" is information about people the user plans to meet that day, such as friends, family, or business partners.

[0529] The "existing clothing list" refers to a list of clothing owned by the user, specifically including items such as shirts, pants, and shoes.

[0530] "Server" refers to a computer system for receiving and processing data sent by users.

[0531] A "generative AI model" is a model for generating coordination suggestions using artificial intelligence technology, and specifically, for example, a generative language model.

[0532] A "prompt" is a way to create specific questions or instructions to input into a generative AI model.

[0533] "Trend data" refers to information about current fashion trends, and is data collected from social media, purchasing history, etc.

[0534] "Coordination suggestions" are suggestions for fashion combinations generated using information entered by the user and a generative AI model.

[0535] "Feedback" refers to the evaluation or opinion that the user inputs regarding the presented outfit.

[0536] "Fine-tuning" is a method of retraining the generative AI model based on user feedback, so that the next suggestions will be closer to the user's preferences.

[0537] This invention relates to a personal style assistant system that allows users to easily enjoy daily styling. The system's purpose is to provide personalized fashion advice by having users input information about the weather, their schedule, and the people they're meeting. The system utilizes the user's existing clothing list and uses a generative AI model to suggest outfits that take into account the user's preferences and trends. Furthermore, the AI ​​model is fine-tuned based on user feedback to improve the accuracy of future suggestions.

[0538] Hardware and Software Configuration

[0539] The system consists of two main pieces of hardware: a terminal and a server. The terminal is a device operated by the user, such as a smartphone or tablet, that runs a user interface application. The server is a cloud-based computer system that processes user data, runs generative AI models, and analyzes trend data.

[0540] The software running on the device is a user interface application. It sends information entered by the user to the server and displays outfit suggestions received from the server. The software on the server analyzes data, runs generative AI models (e.g., GPT-4), references trend data, and processes feedback.

[0541] Data Processing and Data Arithmetic

[0542] 1. User input:

[0543] The user inputs information about the weather, appointments, and people they are meeting through the device, and also inputs or updates an existing clothing list.

[0544] Example: A user enters "Today is sunny and 18 degrees. I plan to meet a friend," and registers "white shirt, blue jeans, leather shoes" in the clothing list.

[0545] 2. Data transmission:

[0546] The device sends the entered information and the existing clothing list to the server. The data is sent in JSON format using the HTTP protocol.

[0547] 3. Data analysis and model input:

[0548] The server receives the data, analyzes the weather information, event information, and clothing list, and then composes input prompts for the generative AI model.

[0549] Example prompt:

[0550] User info: {'weather': 'Sunny, 18°C', 'event': 'Meeting friends', 'clothing_list': ['White shirt', 'Blue jeans', 'Leather shoes']}

[0551] Generate outfit recommendations, taking into account user preferences and trends.

[0552] 4. Coordination proposal generation:

[0553] The server runs the generative AI model and generates outfit suggestions based on the analyzed data, taking into account the user's preferences and trend data.

[0554] 5. View trend data:

[0555] The server refers to trend data and adds the latest trend items to the coordination suggestions.

[0556] 6. Return and view outfit suggestions:

[0557] The server transmits the generated coordination proposal to the terminal, which displays the proposal to the user.

[0558] Example: The suggestion would be "Today's recommended outfit: white shirt, blue jeans, leather shoes, red scarf."

[0559] 7. Gathering Feedback:

[0560] The user provides feedback on the proposed coordination, which the terminal sends to the server.

[0561] Example: A user rates the combination of a white shirt and leather shoes as "a great look."

[0562] 8. Fine-tuning AI models:

[0563] The server fine-tunes the generative AI model based on user feedback to improve the accuracy of the next outfit suggestion.

[0564] In this way, the system provides users with personalized and accurate fashion advice, promotes sustainable consumption by making the most of existing clothing, and reduces stress and time wasted when it comes to fashion.

[0565] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0566] Step 1:

[0567] Enter user information

[0568] The user uses the device to input information about the weather, schedules, and people they are meeting, and also to input or update an existing clothing list. This information is collected through the user interface.

[0569] Input: Weather information, schedule information, meeting information, existing clothing list

[0570] Data processing: The user interface application converts this information into JSON format.

[0571] Output: Weather information, schedule information, meeting information, and clothing list in JSON format

[0572] Specific behavior:

[0573] The user opens the app, enters the weather as "Sunny, 18 degrees," the appointment as "Meeting a friend," and the person information as "Friend."

[0574] Register "white shirt, blue jeans, leather shoes" as a clothing list on the device.

[0575] Step 2:

[0576] Sending data

[0577] The device sends the entered information and the existing clothing list to the server. The data is transmitted using the HTTP protocol.

[0578] Input: Weather information, schedule information, meeting information, and clothing list entered by the user

[0579] Data processing: The device compiles this information into a single JSON object and sends it to the server.

[0580] Output: Input data sent to the server in JSON format

[0581] Specific behavior:

[0582] The device sends data to the server in the format "{'weather': 'Sunny 18 degrees', 'event': 'Meeting a friend', 'meet_person': 'Friend', 'clothing_list': ['White shirt', 'Blue jeans', 'Leather shoes']}".

[0583] Step 3:

[0584] Data analysis and model input

[0585] The server receives the data and analyzes the weather, events, people to meet, and clothing list, then composes input prompts for the generative AI model.

[0586] Input: Input data sent to the server in JSON format

[0587] Data processing: The server analyzes the received data and generates prompts in a format suitable for the generative AI model.

[0588] Output: Input prompts to the generative AI model

[0589] Specific behavior:

[0590] The server parses the data it receives and generates a prompt of the following form:

[0591] User info: {'weather': 'Sunny, 18°C', 'event': 'Meeting a friend', 'meet_person': 'Friend', 'clothing_list': ['White shirt', 'Blue jeans', 'Leather shoes']}

[0592] Generate outfit recommendations, taking into account user preferences and trends.

[0593] Step 4:

[0594] Generating outfit suggestions

[0595] The server runs the generative AI model and generates outfit suggestions based on the analyzed data, taking into account the user's preferences and trend data.

[0596] Input: Input prompts for the generative AI model

[0597] Data processing: A generative AI model generates outfit suggestions based on prompts.

[0598] Output: Coordination suggestions

[0599] Specific behavior:

[0600] The server runs the generative AI model and generates suggestions like: "Pair a white shirt with blue jeans and leather shoes."

[0601] Step 5:

[0602] Applying trend data

[0603] The server refers to trend data and adds the latest trend items to the coordination suggestions.

[0604] Input: Coordination suggestions, trend data

[0605] Data processing: Add items from trend data to the generated outfit suggestions.

[0606] Output: Updated outfit suggestions

[0607] Specific behavior:

[0608] The server retrieves the latest trend data from social media and purchasing data and adds "Red Scarf" to the suggestions.

[0609] Step 6:

[0610] Return and display of outfit suggestions

[0611] The server finally sends the updated coordination proposal to the terminal, which displays the proposal to the user.

[0612] Input: Updated outfit suggestions

[0613] Data processing: The server sends the proposal to the terminal, which then displays it on the user interface.

[0614] Output: Coordination suggestions presented to the user

[0615] Specific behavior:

[0616] The server sends "{'suggested_outfit': 'White shirt, blue jeans, leather shoes, red scarf'}" to the device.

[0617] The device displays on the user screen, "Today's recommended outfit: white shirt, blue jeans, leather shoes, red scarf."

[0618] Step 7:

[0619] Collecting feedback

[0620] The user provides feedback on the proposed coordination, and the terminal transmits the feedback to the server.

[0621] Input: User feedback

[0622] Data processing: The feedback information is converted back to JSON format and sent to the server.

[0623] Output: Feedback data sent to the server

[0624] Specific behavior:

[0625] A user reviews the outfit on the app, saying, "The combination of the white shirt and leather shoes is very good."

[0626] The device sends "{'feed_back': 'The combination of a white shirt and leather shoes is very good'}" to the server.

[0627] Step 8:

[0628] Fine-tuning AI models

[0629] The server fine-tunes the generative AI model based on user feedback to improve the accuracy of the next outfit suggestion.

[0630] Input: Feedback data from users

[0631] Data processing: The generative AI model retrains based on feedback and improves the model.

[0632] Output: A fine-tuned generative AI model

[0633] Specific behavior:

[0634] The server uses the feedback data to retrain the generative AI model and reflect it in future coordination suggestions.

[0635] (Application example 1)

[0636] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0637] Existing personal style assistant systems suggest outfits based on information entered by the user, such as the weather, schedule, and people they are meeting, but they have the problem of not being able to provide a real-time user experience like in a physical store. Furthermore, they are unable to instantly display outfit suggestions based on the products the user actually picks up, and there is a lack of means to further improve the user experience.

[0638] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0639] In this invention, the server includes means for acquiring information input by the user regarding the weather, schedule, and people to meet, means for acquiring the user's existing clothing list, means for transmitting the acquired information to the server, means for the server to generate outfit suggestions using a generative AI model based on the information received, means for the server to return the generated outfit suggestions to the terminal, means for the terminal to display the outfit suggestions to the user, means for acquiring user feedback and transmitting it to the server, means for the server to fine-tune the generative AI model based on the feedback, means for displaying outfit suggestions in real time when the user picks up a product in a physical store using smart glasses or a head-mounted display, and means for the terminal to generate a prompt sentence based on the user's input information and the picked up product and transmit the prompt sentence to the server. This enables users to receive appropriate outfit suggestions in real time even in physical stores.

[0640] "Means for obtaining information entered by the user about the weather, plans, and people to meet" refers to a function that allows the user to use a device such as a smartphone or tablet to enter information about the day's weather, plans, and people to meet, and the system collects this information.

[0641] The "means for acquiring the user's existing clothing list" is a function that allows the user to input or update a list of clothing that the user owns into the terminal and acquire that information from the system.

[0642] The "means for transmitting acquired information to the server" is a communication means for transmitting the weather, schedule, information on people to meet, and clothing list input by the user from the terminal to the server.

[0643] "Means for generating coordination suggestions using a generative AI model based on information received by the server" refers to a function for analyzing user data received by the server and using a generative AI model to create optimal coordination suggestions for the user.

[0644] The "means for returning the generated coordination proposal from the server to the terminal" is a communication means for transmitting the coordination proposal generated by the server to the terminal and providing it to the user.

[0645] The "means for the terminal to display a coordination suggestion to the user" is a function for visually presenting the generated coordination suggestion to the user using the display screen of the terminal.

[0646] The "means for acquiring user feedback and transmitting it to the server" is a function that allows the user to input their evaluation and opinion on the proposed outfit and transmit it from the terminal to the server.

[0647] "Means for the server to fine-tune the generative AI model based on feedback" is a function that receives feedback from users, improves the generative AI model based on that feedback, and increases the accuracy of the next outfit suggestion.

[0648] "A means for displaying coordination suggestions in real time when a user picks up a product in a physical store using smart glasses or a head-mounted display" is a function that displays coordination suggestions based on a product in real time when a user picks up the product in a physical store using smart glasses or a head-mounted display.

[0649] "Means for the terminal to generate a prompt sentence based on the information input by the user and the product picked up, and to send the prompt sentence to the server" refers to a function that generates a prompt sentence based on the weather, schedule, and person to meet information input by the user, and information on the product picked up in a physical store, and sends the prompt sentence from the terminal to the server.

[0650] System Overview

[0651] This invention is a style assistant system that provides personalized fashion suggestions based on the user's weather, schedule, and meeting information. In particular, it aims to provide optimal coordination suggestions in real time using smart glasses or head-mounted displays in brick-and-mortar stores.

[0652] Hardware and software used

[0653] Hardware: Smart glasses (e.g., Google Glass) or head-mounted displays (e.g., Microsoft HoloLens)

[0654] Software: Django (server-side framework), React (front-end framework), TensorFlow (generative AI model), OpenCV (visual data processing)

[0655] Specific explanation of the system's operation

[0656] Obtaining user input information

[0657] This function allows users to input information about the day's weather, schedule, and people they're meeting through smart glasses or a head-mounted display. Users can also upload their existing clothing lists.

[0658] Sending data

[0659] The entered information and existing clothing list are sent from the device to a server, which uses this information to create a user profile and prepares the data for the generative AI model.

[0660] Coordination suggestions using generative AI models

[0661] The server analyzes the received information and uses a generative AI model to generate optimal outfit suggestions for the user. It also references trend data to include the latest fashion items in the suggestions.

[0662] Real-time display

[0663] When a user picks up a product in a physical store, outfit suggestions based on that product are displayed in real time through smart glasses or a head-mounted display. At this time, prompts are generated based on the user's input information and the product they picked up.

[0664] Displaying suggested outfits

[0665] The generated coordination proposal is sent back to the terminal and visually presented to the user, who can see the entire coordination on the screen.

[0666] Getting feedback and tuning the AI ​​model

[0667] Users provide feedback on the proposed outfits, which is sent to the server, and the generative AI model is fine-tuned based on that feedback, improving the accuracy of the next suggestion.

[0668] Specific examples

[0669] Suppose a user uses smart glasses to input information such as "Today is sunny, 18 degrees, and I'm meeting a friend," and then picks up a black T-shirt. An example prompt sent to the server is:

[0670] "The weather is sunny, I'm meeting a friend, and I've picked up a black T-shirt. Can you suggest the best outfit for this situation?"

[0671] This allows the server to generate a coordination suggestion based on the user's preferences and the latest trends, such as "a black T-shirt, white sneakers, and dark denim pants," and display it in real time on the user's smart glasses.

[0672] As described above, the present invention can provide users with personalized and real-time fashion suggestions even in brick-and-mortar stores.

[0673] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0674] Step 1:

[0675] The user inputs information about the weather, schedule, and people they are meeting through smart glasses or a head-mounted display. The user inputs this information in text format using a device. The input of this step is the user's input data, and the output is the data stored on the device.

[0676] Step 2:

[0677] The terminal obtains the user's existing clothing list. The clothing list previously entered or updated by the user is read from the database. The input of this step is the user's clothing list data, and the output is the list data stored in the terminal.

[0678] Step 3:

[0679] The device sends the acquired information (weather, schedule, meeting person information, and clothing list) to the server. The input of this step is the user data stored on the device, and the output is the data sent to the server.

[0680] Step 4:

[0681] The server generates outfit suggestions using a generative AI model based on the information it receives. The server first analyzes the received data and passes it to the generative AI model, taking into account trend data and user preferences. The input to this step is the user data sent to the server, and the output is the generated outfit suggestions.

[0682] Step 5:

[0683] The server returns the generated coordination proposal to the terminal. The input of this step is the generated coordination proposal, and the output is the proposal data sent to the terminal.

[0684] Step 6:

[0685] The terminal displays outfit suggestions to the user. The terminal visually presents the outfit suggestions to the user. The input to this step is the suggestion data sent to the terminal, and the output is the outfit suggestions displayed on the display screen.

[0686] Step 7:

[0687] A user picks up a product in a physical store. The smart glasses or head-mounted display recognizes the product and reports it to the server. The input of this step is the product information picked up by the user, and the output is the product data sent to the server.

[0688] Step 8:

[0689] The terminal generates a prompt sentence based on the user's input information and the product picked up, and sends the prompt sentence to the server. The input for this step is the user's input information and product data, and the output is the generated prompt sentence.

[0690] Step 9:

[0691] The server receives the prompt sentence and generates outfit suggestions in real time using a generative AI model. The input of this step is the generated prompt sentence, and the output is real-time outfit suggestions.

[0692] Step 10:

[0693] The server sends the coordinated proposals generated in real time to the terminal and displays them to the user. The input of this step is the real-time coordinated proposals, and the output is the proposals displayed on the terminal.

[0694] Step 11:

[0695] The user provides feedback on the proposed coordination, and the terminal sends it to the server. The input of this step is the user's feedback, and the output is the feedback data sent to the server.

[0696] Step 12:

[0697] The server fine-tunes the generative AI model based on the feedback, which improves the accuracy of the next proposal. The input of this step is the feedback data, and the output is an improved generative AI model.

[0698] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0699] Overall system overview

[0700] This invention is a system that realizes a personal style assistant that provides users with personalized fashion advice and encourages sustainable consumption. In particular, by adding an emotion engine that recognizes the user's emotions, it is possible to propose outfits that are more tailored to the user's individual needs.

[0701] Explanation of program processing

[0702] 1. User Input

[0703] The user uses the terminal to input information about the weather, plans, and people to meet for the day, and also registers or updates an existing clothing list on the terminal.

[0704] Examples: "Today it's sunny and 18 degrees, I'm meeting a friend" and "White shirt, blue jeans, leather shoes"

[0705] 2. Emotional Recognition

[0706] The emotion engine recognizes emotions from the user's facial expressions and voice. The recognized emotional information (e.g., joy, sadness, stress, etc.) is input into the generative AI model.

[0707] Example: Your current emotion is judged to be "stress."

[0708] 3. Data transmission

[0709] The terminal sends the information input by the user (weather, schedule, information about people to meet, existing clothing list, and emotional information) to the server.

[0710] Data format: {'weather': 'Sunny, 18°C', 'event': 'Meeting with a friend', 'clothing_list': ['Blue jeans', 'White shirt', 'Leather shoes'], 'emotion': 'Stress'}

[0711] 4. Coordination suggestions by AI models

[0712] The server then activates a generative AI model based on the received data to generate outfit suggestions, taking into account the user's preferences, trend data, and emotional information.

[0713] For example, suggest outfits such as, "Choose a relaxed style to reduce stress."

[0714] 5. Consider trend data

[0715] The server references trend data (SNS browsing results, purchasing data, etc.) and adds the latest trend items to the generated coordination suggestions.

[0716] Example: "Add red scarf as a trend" to your suggestion

[0717] 6. Return of coordination proposal

[0718] The server then transmits the final coordinated outfit suggestions to the terminal, including specific clothing combinations and trend items.

[0719] For example: "White shirt, blue jeans, leather shoes, red scarf."

[0720] 7. Presentation to the User

[0721] The terminal displays the generated outfit suggestions to the user, who can visually check the suggested outfits and use them as reference for deciding on their style for the day.

[0722] Example: "Today's recommended outfit: white shirt, blue jeans, leather shoes, red scarf."

[0723] 8. Gathering Feedback

[0724] The user provides feedback on the suggested outfits, including whether they like the outfits or don't like them.

[0725] Example: "A white shirt and leather shoes go together really well."

[0726] 9. Update the AI ​​model

[0727] The server fine-tunes the generative AI model based on the received feedback, improving the accuracy of the next outfit suggestion.

[0728] Example: Improve the model based on feedback to make suggestions that better match the user's preferences.

[0729] This system allows users to receive more appropriate outfit suggestions based on their emotions, making it easier to choose the outfit that will make them feel good throughout the day. It also has the advantage of promoting sustainable consumption by utilizing existing clothing lists.

[0730] The processing flow will be explained below.

[0731] Step 1:

[0732] A user uses a device to input information about the weather, appointments, and people they are meeting. For example, the user inputs "Today it's sunny and 18 degrees, and I'm meeting a friend," updating an existing clothing list of "white shirt, blue jeans, leather shoes."

[0733] Step 2:

[0734] The device activates an emotion engine and recognizes emotions from the user's facial expressions and voice. For example, if the user has an expression that indicates stress, the emotion engine will recognize this as "stress."

[0735] Step 3:

[0736] The device sends data including the input information and emotion information to the server. The sent data includes "weather information, event information, clothing list, emotion information," etc. An example of data is "{'weather': 'Sunny, 18°C', 'event': 'Meeting with a friend', 'clothing_list': ['Blue jeans', 'White shirt', 'Leather shoes'], 'emotion': 'Stress'}."

[0737] Step 4:

[0738] The server analyzes the user data received from the device, including weather, schedules, people to meet, existing clothing lists, and emotional information, and activates a generative AI model based on this data.

[0739] Step 5:

[0740] The server uses a generative AI model to generate outfit suggestions. The generative AI model considers the user's preferences, past feedback, and current emotional information to generate appropriate clothing combinations. For example, it may suggest, "If you're feeling stressed, we recommend a relaxed style."

[0741] Step 6:

[0742] The server references trend data (such as social media browsing results and purchasing data) and adds the latest trend items to the generated coordination suggestions. For example, "Add a red scarf to a white shirt and blue jeans as a trend."

[0743] Step 7:

[0744] The server then sends the final outfit recommendation to the device. The data includes specific clothing combinations and trend items. An example of the data is "{'recommendation': ['White shirt', 'Blue jeans', 'Leather shoes', 'Red scarf']}".

[0745] Step 8:

[0746] The terminal displays the received outfit suggestions to the user. The user can visually check the suggested outfits and use them as a reference for deciding on their style for the day. An example display might be "Today's recommended outfit: white shirt, blue jeans, leather shoes, red scarf."

[0747] Step 9:

[0748] The user provides feedback on the proposed outfit, including specific preferences and areas for improvement. For example, the user may provide feedback such as, "The combination of a white shirt and leather shoes is very good."

[0749] Step 10:

[0750] The device sends user feedback to a server, where the feedback data is stored and analyzed to improve the accuracy of the generative AI model.

[0751] Step 11:

[0752] The server fine-tunes the generative AI model based on the received feedback. This improves the accuracy of the next outfit suggestion and generates suggestions that are closer to the user's preferences. For example, reflecting the user's feedback, the server will continue to recommend a combination of a white shirt and leather shoes.

[0753] Example 2

[0754] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0755] Conventional fashion assistant systems have the problem of not being able to fully meet the user's needs because they do not take into account the user's emotions or real-time trend information. In addition, because they are unable to propose outfits that take the user's emotional state into account, the suggested styles may not match the user's mood or the situation. As a result, users tend to be dissatisfied with the outfits provided and have fewer opportunities to actually wear them.

[0756] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0757] In this invention, the server includes means for acquiring information on the weather, schedule, and people to meet input by the user, means for acquiring the user's existing clothing list, means for acquiring the user's facial expressions and voice and recognizing emotions, means for generating outfit suggestions using a generative AI model based on the acquired information and the recognized emotion information, means for adding trend items to the generated outfit suggestions by referring to trend data, and means for fine-tuning the generative AI model based on user feedback. This enables personalized outfit suggestions that take into account the user's emotions and real-time trend information.

[0758] "Weather information" refers to data entered by the user regarding the weather conditions for that day.

[0759] "Schedule" refers to information entered by the user about activities and events to be held that day.

[0760] "Information about people to meet" refers to information about people the user plans to meet on that day.

[0761] "Existing Clothing List" refers to a list of clothing owned by the user, including data registered with a particular application or device.

[0762] "Emotion information" refers to data that indicates the emotional state of the user as recognized from their facial expressions and voice.

[0763] "Server" refers to the computer system that receives and processes data, runs the generative AI model, obtains feedback, and fine-tunes the model.

[0764] A "generative AI model" refers to an artificial intelligence model that generates fashion coordination suggestions based on user input and emotional information.

[0765] "Outfit suggestions" refer to clothing combinations recommended based on the user's input information and emotions.

[0766] "Trend data" refers to information about the latest fashion trends and includes data collected from social media and purchasing data.

[0767] "Feedback" refers to user-provided ratings and comments on the proposed outfits.

[0768] "Fine-tuning" refers to the process of adjusting the parameters of a generative AI model based on received feedback to improve the accuracy of its suggestions.

[0769] Overall system configuration

[0770] This invention is a personal style assistant system that provides users with personalized fashion advice and encourages sustainable consumption. In particular, by adding an emotion engine that recognizes the user's emotions, it is possible to propose outfits that are more tailored to the user's individual needs.

[0771] Hardware and Software Configuration

[0772] Terminal

[0773] Users use devices such as smartphones and tablets. The devices are equipped with cameras and microphones that capture the user's facial expressions and voice. They also install applications and input information about the weather, their schedule, people they are meeting, and their existing clothing list.

[0774] server

[0775] The server is a high-performance computer system that receives and processes data and runs the generative AI model. The server can use Microsoft Azure's emotion analysis API as an emotion engine, which analyzes the user's emotional information and generates optimal outfit suggestions.

[0776] Generative AI Models

[0777] The generative AI model uses an advanced language model such as GPT-4, and the server uses this generative AI model to generate fashion coordination suggestions based on the user's input and emotional information.

[0778] Program processing

[0779] The device first acquires the user's input information (weather, schedule, information about people to meet, existing clothing list), as well as facial expressions and voice. The data acquired using the camera and microphone is analyzed by the emotion engine and sent to the server as emotion information.

[0780] Next, the server launches a generative AI model based on the received information. The generative AI model receives the following text data as a prompt:

[0781] "Today's weather is sunny and 18 degrees, plans include meeting a friend, and current emotion is stress. The user has the following clothing list: white shirt, blue jeans, leather shoes."

[0782] Based on this, the generative AI model generates coordination suggestions that take into account the user's preferences and trend data. As a specific example, the generative AI model might suggest "adding a red scarf to a white shirt, blue jeans, and leather shoes as a trend."

[0783] The generated outfit suggestions are sent back from the server to the device, which then displays them to the user through the application. The user can review the suggested outfits and decide on their style for the day. In addition, the user can provide feedback on the suggested outfits. For example, the user can leave a specific comment such as, "The combination of a white shirt and leather shoes is very good."

[0784] Finally, the server fine-tunes the generative AI model based on the received feedback, improving the accuracy of the next outfit suggestions and providing results that better match the user's preferences.

[0785] The system allows users to receive personalized outfit suggestions that take into account emotions and real-time trend information, and also promotes sustainable consumption.

[0786] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0787] Step 1:

[0788] The device receives input from the user about today's weather, plans, and people to meet. The user enters this data using text boxes and selection boxes in the application. For example, the user enters information like "Today it's sunny and 18 degrees, and I'm planning to meet a friend." The device then temporarily stores this information.

[0789] Step 2:

[0790] The device retrieves the user's existing clothing list. The user provides data by manually entering text or uploading photos of the clothing. For example, if information such as "white shirt, blue jeans, leather shoes" is entered, the device will store this data.

[0791] Step 3:

[0792] The device's camera and microphone are used to capture the user's facial and voice data. This data is captured in real time and processed by facial recognition software and voice analysis software. The emotion engine analyzes the user's emotional state (e.g., joy, stress) and extracts emotional information.

[0793] Step 4:

[0794] The device sends the weather, schedule, meeting information, existing clothing list, and emotion information acquired as JSON format data to the server. The input information is formatted as follows and sent to the server:

[0795] json

[0796] {

[0797] "weather": "Sunny, 18°C",

[0798] "event": "Meeting with a friend",

[0799] "clothing_list": ["Blue jeans", "White shirt", "Leather shoes"],

[0800] "emotion": "Stress"

[0801] }

[0802] Step 5:

[0803] The server processes the received information and launches a generative AI model, which receives the following prompt text and generates outfit suggestions based on it:

[0804] "Today's weather is sunny and 18 degrees, plans include meeting a friend, and current emotion is stress. The user has the following clothing list: white shirt, blue jeans, leather shoes."

[0805] Step 6:

[0806] The server uses a generative AI model to generate personalized outfit suggestions for each user. The generative AI model takes into account the user's preferences, emotional information, and trend data, and generates outfit suggestions as output. For example, a suggestion might be generated such as "Add a red scarf to a white shirt, blue jeans, and leather shoes, as a trend."

[0807] Step 7:

[0808] The server finally sends the generated coordination proposal to the device. The generated data is sent to the device in the following format:

[0809] json

[0810] {

[0811] "recommendation": ["White shirt", "Blue jeans", "Leather shoes", "Red scarf"]

[0812] }

[0813] Step 8:

[0814] The terminal displays the received outfit suggestions to the user. The user can visually check the suggested outfits on the application screen. For example, "Today's recommended outfit: white shirt, blue jeans, leather shoes, red scarf" is displayed.

[0815] Step 9:

[0816] Users provide feedback on the suggested outfits. Feedback is entered using an in-app evaluation form, and includes pros and cons of the suggested outfits and areas for improvement. For example, a specific comment such as "The combination of a white shirt and leather shoes is very good" can be entered.

[0817] Step 10:

[0818] The device sends the user's feedback to the server, which then formats the feedback as follows and sends it to the server:

[0819] json

[0820] {

[0821] "feedback": "The combination of a white shirt and leather shoes is very good"

[0822] }

[0823] Step 11:

[0824] The server fine-tunes the generative AI model based on the received feedback. The server analyzes the feedback and adjusts the parameters of the generative AI model to improve the accuracy of future outfit suggestions, thereby providing results that better match the user's preferences.

[0825] (Application example 2)

[0826] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0827] Conventional personal style assistants have been unable to provide coordination suggestions that take the user's emotions into account. As a result, they are unable to provide fashion suggestions based on the user's mood or emotions of the day, making it difficult to increase user satisfaction. In addition, there is a demand for more personalized suggestions that match the user's mood by providing fashion suggestions that take into account not only information such as the weather and schedule, but also the user's emotions.

[0828] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for recognizing the user's emotion using an emotion engine, means for transmitting the recognized emotion information to the server, and means for generating coordination suggestions using a generative AI model based on the information received by the server. This makes it possible to make fashion suggestions that take the user's emotions into consideration.

[0829] "Means for acquiring information entered by the user about the weather, schedule, and people to meet" refers to a function that allows the user to input information about the weather for the day, schedule, and people to meet into an electronic terminal, and the system acquires that information.

[0830] The "means for acquiring a list of the user's existing clothing" is a function that allows the user to register the clothing he or she owns in a list, and for the system to acquire that list.

[0831] The "means for transmitting acquired information to a server" is a function for transmitting information entered by the user and recognized emotion information to a server via the Internet.

[0832] The "means for recognizing the user's emotions using an emotion engine" is a function that detects the user's current emotional state by analyzing the user's facial expressions and voice.

[0833] The "means for transmitting the recognized emotion information to the server" is a function for transmitting the emotion information recognized by the emotion engine to the server.

[0834] "Means for generating coordination suggestions using a generative AI model based on information received by the server" refers to a function that activates a generative AI model based on information and emotional information received by the server from the user, and suggests optimal fashion coordination.

[0835] The "means for returning the generated coordination proposal from the server to the terminal" is a function for transmitting the fashion coordination proposal generated by the server to the user's terminal.

[0836] The "means for the terminal to display coordination suggestions to the user" is a function for visually displaying to the user fashion coordination suggestions received by the terminal from the server.

[0837] The "means for acquiring user feedback and transmitting it to the server" is a function that allows the user to input opinions and evaluations of the provided coordination proposals and transmit the feedback to the server.

[0838] "Means for the server to fine-tune the generative AI model based on feedback" refers to a function that makes adjustments to improve the accuracy of the generative AI model based on feedback information from users.

[0839] "The generative AI model generates outfit suggestions by taking into account the user's preferences, trend data, and emotional information" refers to the process in which the generative AI model combines the user's personal preferences, the latest fashion trend data, and the user's current emotional state to suggest optimal fashion outfits.

[0840] "Means for collecting trend data and updating the generative AI model based on that data" refers to a function in which the server collects fashion trend data from the internet and various databases, and uses that data to keep the algorithm of the generative AI model up to date.

[0841] The present invention provides a personal style assistant system that uses an emotion engine to suggest optimal outfits to users by utilizing information on the user's weather, schedule, people they are meeting, existing clothing list, and emotion information. By taking the user's emotions into consideration, the system can provide more personalized fashion suggestions and improve user satisfaction.

[0842] Hardware and software used

[0843] Hardware: Smartphone (iOS or Android)

[0844] software:

[0845] EmotionEngine (emotion recognition engine)

[0846] AICoordinator (AI model for suggesting outfits)

[0847] REST API (a server that supports HTTP requests)

[0848] The server uses the EmotionEngine to recognize emotions from the user's facial expressions and voice. It captures the user's face and voice using the smartphone camera and microphone, and analyzes the data. The analyzed emotional data is sent to the server along with the weather, schedule, meeting information, and existing clothing list entered by the user.

[0849] The server launches a generative AI model based on all the received data, and generates outfit suggestions based on the information obtained. The generative AI model comprehensively considers the user's preferences, trend data, and emotional information. For example, based on the information "Today is sunny and 18 degrees, and I plan to meet a friend," "A white shirt, blue jeans, and leather shoes," and "I'm feeling stressed," the model suggests a "relaxed style" of a white shirt, blue jeans, leather shoes, and a trendy red scarf.

[0850] The generated outfit suggestions are sent back from the server to the smartphone and visually displayed to the user on the smartphone screen. The user can use the suggested outfits as a reference to decide on their fashion for the day. Furthermore, the user can input feedback about the suggested outfits and send it to the server, which can then use that feedback to fine-tune the generative AI model and improve the accuracy of the next suggestions.

[0851] Examples of concrete examples and prompts

[0852] As an example, a user enters the following information:

[0853] Weather: Sunny and 18 degrees

[0854] Plans: Meeting with friends

[0855] Existing clothing list: White shirt, blue jeans, leather shoes

[0856] Emotional information: I'm feeling stressed

[0857] Example prompt sentence:

[0858] "Today is sunny and 18 degrees, and I'm meeting a friend. My existing clothing list includes a white shirt, blue jeans, and leather shoes. My current emotion is determined to be stress."

[0859] As described above, the present invention can improve user satisfaction by providing fashion suggestions that take the user's emotions into consideration. It also has the advantage of promoting sustainable consumption by utilizing existing clothing.

[0860] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0861] Step 1:

[0862] A user inputs information about the weather, plans, people to meet, and an existing clothing list into a smartphone. The smartphone has an interface that accepts user input, and this collects the necessary information. Examples of input data include "Today is sunny and 18 degrees. I plan to meet a friend," "White shirt, blue jeans, leather shoes."

[0863] Step 2:

[0864] Using the emotion engine, the smartphone device analyzes the user's facial expressions and voice to recognize emotions. Using data captured through the smartphone's camera and microphone, the emotion engine identifies emotions such as "stress." This recognized emotion information is used for further processing.

[0865] Step 3:

[0866] The device sends the collected weather, schedule, meeting information, existing clothing list, and recognized emotion information to the server in a JSON format, such as "{'weather': 'Sunny, 18°C', 'event': 'Meeting with a friend', 'clothing_list': ['Blue jeans', 'White shirt', 'Leather shoes'], 'emotion': 'Stress'}".

[0867] Step 4:

[0868] The server then activates a generative AI model based on the received data to generate outfit suggestions. The generative AI model uses an algorithm that takes into account the user's preferences, trend data, and emotional information. For example, suggestions might be generated in the form of "pick a relaxed style to reduce stress."

[0869] Step 5:

[0870] The server references the latest trend data collected (such as social media posts and purchasing data) and reflects it in the coordination suggestions. For example, "add a red scarf as a trend item" to the generated coordination.

[0871] Step 6:

[0872] The generated outfit suggestions are sent from the server to the smartphone device. The suggestions include specific clothing combinations and trendy items. For example, a "white shirt, blue jeans, leather shoes, and red scarf" combination might be suggested.

[0873] Step 7:

[0874] The device displays the generated outfit suggestions to the user, who can then check the suggested fashions on their smartphone screen and use them as a reference for deciding what to wear that day.

[0875] Step 8:

[0876] The user provides feedback on the proposed outfits, including their preferences and points that do not suit them, and inputs this feedback into the terminal.

[0877] Step 9:

[0878] The device sends user feedback to the server, which then fine-tunes the generative AI model based on the received feedback. This improves the accuracy of the next outfit suggestions, for example, by providing outfits that better match the user's preferences.

[0879] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0880] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0881] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0882] [Third embodiment]

[0883] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0884] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0885] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0886] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0887] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0888] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0889] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0890] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0891] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0892] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0893] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0894] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0895] Overall system overview

[0896] This invention is a personal style assistant system that aims to provide personalized fashion advice based on user input of weather, schedule, and meeting information. The system utilizes the user's existing clothing list and a generative AI model to suggest outfits that take into account the user's preferences and trends. Furthermore, the AI ​​model is fine-tuned based on user feedback to improve the accuracy of future suggestions.

[0897] Explanation of program processing

[0898] 1. User Input

[0899] The user inputs information about the weather, schedule, and people they are meeting into a device (such as a smartphone or tablet). In addition, the user inputs or updates an existing clothing list.

[0900] Examples: "Today it's sunny and 18 degrees, I'm meeting a friend" and "White shirt, blue jeans, leather shoes"

[0901] 2. Data transmission

[0902] The terminal transmits the input information and the existing clothing list to the server. The transmitted data includes weather information, event information, clothing list, etc.

[0903] Example: Data format is "{'weather': 'Sunny, 18°C', 'event': 'Meeting with a friend', 'clothing_list': ['Blue jeans', 'White shirt', 'Leather shoes']}"

[0904] 3. Coordination suggestions by AI models

[0905] The server analyzes the user data received from the device, then runs a generative AI model to generate outfit suggestions based on the analyzed data, taking into account the user's preferences and trend data.

[0906] Example: A suggested outfit is "white shirt, blue jeans, and leather shoes."

[0907] 4. Consider trend data

[0908] The server references trend data (SNS browsing results, purchasing data, etc.) and adds the latest trend items to the generated coordination suggestions.

[0909] Example: "Add red scarf as a trend" to your suggestion

[0910] 5. Return of outfit suggestions

[0911] The server transmits the final generated coordination proposal to the terminal, which then displays the received proposal to the user.

[0912] For example: "White shirt, blue jeans, leather shoes, red scarf."

[0913] 6. Presentation to the User

[0914] The terminal displays the generated coordination proposal to the user.

[0915] Example: The suggested outfit for today is: white shirt, blue jeans, leather shoes, red scarf.

[0916] 7. Gathering Feedback

[0917] The user provides feedback on the proposed outfit (e.g., what they like and don't like), and the device sends this feedback to the server.

[0918] Example: "A white shirt and leather shoes go together really well."

[0919] 8. Update the AI ​​model

[0920] The server fine-tunes the generative AI model based on the received feedback, improving the accuracy of the next outfit suggestion.

[0921] Example: Improve the model based on feedback to better suit user preferences.

[0922] The advantage of this system is that it allows users to easily enjoy daily styling. Furthermore, it promotes sustainable consumption by maximizing the use of existing clothing and reducing the need to purchase new clothes. As a result, it significantly reduces stress and wastes time for users regarding fashion.

[0923] The processing flow will be explained below.

[0924] Step 1:

[0925] The user uses the device to input information about the weather, appointments, and people they are meeting. In addition, the user enters or updates an existing clothing list. At this stage, the user provides information about the specific weather conditions, events, and people they are meeting for the day.

[0926] Step 2:

[0927] The terminal sends the information entered by the user (weather, schedule, meeting person information, and existing clothing list) to the server. The data sent includes weather information, event information, clothing list, etc., and is sent in a standardized format.

[0928] Step 3:

[0929] The server analyzes the user data received from the device, including weather, schedule, meeting information, and existing clothing lists. The server uses this data to run a generative AI model.

[0930] Step 4:

[0931] The server generates outfit suggestions using a generative AI model, which takes into account the user's preferences and past feedback to generate optimal clothing combinations.

[0932] Step 5:

[0933] The server references trend data (social media browsing results, purchasing data, etc.) and adds trend items to the generated coordination suggestions. At this stage, the latest fashion trends are reflected in the generated basic suggestions.

[0934] Step 6:

[0935] The server then transmits the final coordinated outfit suggestions to the terminal, including specific clothing combinations and trend items.

[0936] Step 7:

[0937] The terminal displays the received outfit suggestions to the user, who can visually check the suggested outfits and use them as a reference for deciding on their style for the day.

[0938] Step 8:

[0939] Users provide feedback on the suggested outfits, including their preferences and whether the outfits look good or not.

[0940] Step 9:

[0941] The device sends user feedback to a server, where the feedback data is stored and analyzed to improve the accuracy of the generative AI model.

[0942] Step 10:

[0943] The server then fine-tunes the generative AI model based on the received feedback. This process improves the accuracy of the next outfit suggestions, generating suggestions that more closely match the user's preferences.

[0944] This process reduces the stress of daily styling for users, allowing them to enjoy fashion while promoting sustainable consumption.

[0945] Example 1

[0946] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0947] In today's consumer society, it is difficult to receive personalized fashion advice on a daily basis, and many people often struggle with their own style and choices. Furthermore, there are few systems that automatically suggest outfits that reflect the latest trends while optimizing existing clothing. Therefore, an effective method is needed to promote sustainable consumption while reducing stress related to fashion.

[0948] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0949] In this invention, the server includes means for acquiring information entered by the user about the weather, schedule, and people to meet, means for acquiring the user's existing clothing list, and means for transmitting the acquired information to the server, thereby making it possible to provide personalized fashion advice based on detailed user data.

[0950] The server also includes a means for generating outfit suggestions using a generative AI model based on the received information, a means for configuring input prompts for the generative AI model, and a means for referencing trend data and adding the latest trend items to the suggestions, thereby making it possible to provide outfit suggestions that reflect the user's preferences and the latest trends.

[0951] Furthermore, the server includes means for returning the generated outfit suggestions from the server to the terminal, means for the terminal to display the outfit suggestions to the user, means for acquiring user feedback and sending it to the server, and means for fine-tuning the generating AI model based on the feedback, thereby making it possible to provide more accurate outfit suggestions that reflect the user feedback from the next time onwards.

[0952] "User" refers to an individual using the system who inputs weather, schedule, meeting information, and existing clothing lists.

[0953] A "terminal" refers to an electronic device used by a user to input information, such as a smartphone or tablet.

[0954] "Weather information" is data that indicates the weather conditions for that day, and includes, for example, the temperature and the probability of precipitation.

[0955] "Schedule information" is data describing the actions and activities that the user plans to take that day.

[0956] "Information about people to meet" is information about people the user plans to meet that day, such as friends, family, or business partners.

[0957] The "existing clothing list" refers to a list of clothing owned by the user, specifically including items such as shirts, pants, and shoes.

[0958] "Server" refers to a computer system for receiving and processing data sent by users.

[0959] A "generative AI model" is a model for generating coordination suggestions using artificial intelligence technology, and specifically, for example, a generative language model.

[0960] A "prompt" is a way to create specific questions or instructions to input into a generative AI model.

[0961] "Trend data" refers to information about current fashion trends, and is data collected from social media, purchasing history, etc.

[0962] "Coordination suggestions" are suggestions for fashion combinations generated using information entered by the user and a generative AI model.

[0963] "Feedback" refers to the evaluation or opinion that the user inputs regarding the presented outfit.

[0964] "Fine-tuning" is a method of retraining the generative AI model based on user feedback, so that the next suggestions will be closer to the user's preferences.

[0965] This invention relates to a personal style assistant system that allows users to easily enjoy daily styling. The system's purpose is to provide personalized fashion advice by having users input information about the weather, their schedule, and the people they're meeting. The system utilizes the user's existing clothing list and uses a generative AI model to suggest outfits that take into account the user's preferences and trends. Furthermore, the AI ​​model is fine-tuned based on user feedback to improve the accuracy of future suggestions.

[0966] Hardware and Software Configuration

[0967] The system consists of two main pieces of hardware: a terminal and a server. The terminal is a device operated by the user, such as a smartphone or tablet, that runs a user interface application. The server is a cloud-based computer system that processes user data, runs generative AI models, and analyzes trend data.

[0968] The software running on the device is a user interface application. It sends information entered by the user to the server and displays outfit suggestions received from the server. The software on the server analyzes data, runs generative AI models (e.g., GPT-4), references trend data, and processes feedback.

[0969] Data Processing and Data Arithmetic

[0970] 1. User input:

[0971] The user inputs information about the weather, appointments, and people they are meeting through the device, and also inputs or updates an existing clothing list.

[0972] Example: A user enters "Today is sunny and 18 degrees. I plan to meet a friend," and registers "white shirt, blue jeans, leather shoes" in the clothing list.

[0973] 2. Data transmission:

[0974] The device sends the entered information and the existing clothing list to the server. The data is sent in JSON format using the HTTP protocol.

[0975] 3. Data analysis and model input:

[0976] The server receives the data, analyzes the weather information, event information, and clothing list, and then composes input prompts for the generative AI model.

[0977] Example prompt:

[0978] User info: {'weather': 'Sunny, 18°C', 'event': 'Meeting friends', 'clothing_list': ['White shirt', 'Blue jeans', 'Leather shoes']}

[0979] Generate outfit recommendations, taking into account user preferences and trends.

[0980] 4. Coordination proposal generation:

[0981] The server runs the generative AI model and generates outfit suggestions based on the analyzed data, taking into account the user's preferences and trend data.

[0982] 5. View trend data:

[0983] The server refers to trend data and adds the latest trend items to the coordination suggestions.

[0984] 6. Return and view outfit suggestions:

[0985] The server transmits the generated coordination proposal to the terminal, which displays the proposal to the user.

[0986] Example: The suggestion would be "Today's recommended outfit: white shirt, blue jeans, leather shoes, red scarf."

[0987] 7. Gathering Feedback:

[0988] The user provides feedback on the proposed coordination, which the terminal sends to the server.

[0989] Example: A user rates the combination of a white shirt and leather shoes as "a great look."

[0990] 8. Fine-tuning AI models:

[0991] The server fine-tunes the generative AI model based on user feedback to improve the accuracy of the next outfit suggestion.

[0992] In this way, the system provides users with personalized and accurate fashion advice, promotes sustainable consumption by making the most of existing clothing, and reduces stress and time wasted when it comes to fashion.

[0993] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0994] Step 1:

[0995] Enter user information

[0996] The user uses the device to input information about the weather, schedules, and people they are meeting, and also to input or update an existing clothing list. This information is collected through the user interface.

[0997] Input: Weather information, schedule information, meeting information, existing clothing list

[0998] Data processing: The user interface application converts this information into JSON format.

[0999] Output: Weather information, schedule information, meeting information, and clothing list in JSON format

[1000] Specific behavior:

[1001] The user opens the app, enters the weather as "Sunny, 18 degrees," the appointment as "Meeting a friend," and the person information as "Friend."

[1002] Register "white shirt, blue jeans, leather shoes" as a clothing list on the device.

[1003] Step 2:

[1004] Sending data

[1005] The device sends the entered information and the existing clothing list to the server. The data is transmitted using the HTTP protocol.

[1006] Input: Weather information, schedule information, meeting information, and clothing list entered by the user

[1007] Data processing: The device compiles this information into a single JSON object and sends it to the server.

[1008] Output: Input data sent to the server in JSON format

[1009] Specific behavior:

[1010] The device sends data to the server in the format "{'weather': 'Sunny 18 degrees', 'event': 'Meeting a friend', 'meet_person': 'Friend', 'clothing_list': ['White shirt', 'Blue jeans', 'Leather shoes']}".

[1011] Step 3:

[1012] Data analysis and model input

[1013] The server receives the data and analyzes the weather, events, people to meet, and clothing list, then composes input prompts for the generative AI model.

[1014] Input: Input data sent to the server in JSON format

[1015] Data processing: The server analyzes the received data and generates prompts in a format suitable for the generative AI model.

[1016] Output: Input prompts to the generative AI model

[1017] Specific behavior:

[1018] The server parses the data it receives and generates a prompt of the following form:

[1019] User info: {'weather': 'Sunny, 18°C', 'event': 'Meeting a friend', 'meet_person': 'Friend', 'clothing_list': ['White shirt', 'Blue jeans', 'Leather shoes']}

[1020] Generate outfit recommendations, taking into account user preferences and trends.

[1021] Step 4:

[1022] Generating outfit suggestions

[1023] The server runs the generative AI model and generates outfit suggestions based on the analyzed data, taking into account the user's preferences and trend data.

[1024] Input: Input prompts for the generative AI model

[1025] Data processing: A generative AI model generates outfit suggestions based on prompts.

[1026] Output: Coordination suggestions

[1027] Specific behavior:

[1028] The server runs the generative AI model and generates suggestions like: "Pair a white shirt with blue jeans and leather shoes."

[1029] Step 5:

[1030] Applying trend data

[1031] The server refers to trend data and adds the latest trend items to the coordination suggestions.

[1032] Input: Coordination suggestions, trend data

[1033] Data processing: Add items from trend data to the generated outfit suggestions.

[1034] Output: Updated outfit suggestions

[1035] Specific behavior:

[1036] The server retrieves the latest trend data from social media and purchasing data and adds "Red Scarf" to the suggestions.

[1037] Step 6:

[1038] Return and display of outfit suggestions

[1039] The server finally sends the updated coordination proposal to the terminal, which displays the proposal to the user.

[1040] Input: Updated outfit suggestions

[1041] Data processing: The server sends the proposal to the terminal, which then displays it on the user interface.

[1042] Output: Coordination suggestions presented to the user

[1043] Specific behavior:

[1044] The server sends "{'suggested_outfit': 'White shirt, blue jeans, leather shoes, red scarf'}" to the device.

[1045] The device displays on the user screen, "Today's recommended outfit: white shirt, blue jeans, leather shoes, red scarf."

[1046] Step 7:

[1047] Collecting feedback

[1048] The user provides feedback on the proposed coordination, and the terminal transmits the feedback to the server.

[1049] Input: User feedback

[1050] Data processing: The feedback information is converted back to JSON format and sent to the server.

[1051] Output: Feedback data sent to the server

[1052] Specific behavior:

[1053] A user reviews the outfit on the app, saying, "The combination of the white shirt and leather shoes is very good."

[1054] The device sends "{'feed_back': 'The combination of a white shirt and leather shoes is very good'}" to the server.

[1055] Step 8:

[1056] Fine-tuning AI models

[1057] The server fine-tunes the generative AI model based on user feedback to improve the accuracy of the next outfit suggestion.

[1058] Input: Feedback data from users

[1059] Data processing: The generative AI model retrains based on feedback and improves the model.

[1060] Output: A fine-tuned generative AI model

[1061] Specific behavior:

[1062] The server uses the feedback data to retrain the generative AI model and reflect it in future coordination suggestions.

[1063] (Application example 1)

[1064] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1065] Existing personal style assistant systems suggest outfits based on information entered by the user, such as the weather, schedule, and people they are meeting, but they have the problem of not being able to provide a real-time user experience like in a physical store. Furthermore, they are unable to instantly display outfit suggestions based on the products the user actually picks up, and there is a lack of means to further improve the user experience.

[1066] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1067] In this invention, the server includes means for acquiring information input by the user regarding the weather, schedule, and people to meet, means for acquiring the user's existing clothing list, means for transmitting the acquired information to the server, means for the server to generate outfit suggestions using a generative AI model based on the information received, means for the server to return the generated outfit suggestions to the terminal, means for the terminal to display the outfit suggestions to the user, means for acquiring user feedback and transmitting it to the server, means for the server to fine-tune the generative AI model based on the feedback, means for displaying outfit suggestions in real time when the user picks up a product in a physical store using smart glasses or a head-mounted display, and means for the terminal to generate a prompt sentence based on the user's input information and the picked up product and transmit the prompt sentence to the server. This enables users to receive appropriate outfit suggestions in real time even in physical stores.

[1068] "Means for obtaining information entered by the user about the weather, plans, and people to meet" refers to a function that allows the user to use a device such as a smartphone or tablet to enter information about the day's weather, plans, and people to meet, and the system collects this information.

[1069] The "means for acquiring the user's existing clothing list" is a function that allows the user to input or update a list of clothing that the user owns into the terminal and acquire that information from the system.

[1070] The "means for transmitting acquired information to the server" is a communication means for transmitting the weather, schedule, information on people to meet, and clothing list input by the user from the terminal to the server.

[1071] "Means for generating coordination suggestions using a generative AI model based on information received by the server" refers to a function for analyzing user data received by the server and using a generative AI model to create optimal coordination suggestions for the user.

[1072] The "means for returning the generated coordination proposal from the server to the terminal" is a communication means for transmitting the coordination proposal generated by the server to the terminal and providing it to the user.

[1073] The "means for the terminal to display a coordination suggestion to the user" is a function for visually presenting the generated coordination suggestion to the user using the display screen of the terminal.

[1074] The "means for acquiring user feedback and transmitting it to the server" is a function that allows the user to input their evaluation and opinion on the proposed outfit and transmit it from the terminal to the server.

[1075] "Means for the server to fine-tune the generative AI model based on feedback" is a function that receives feedback from users, improves the generative AI model based on that feedback, and increases the accuracy of the next outfit suggestion.

[1076] "A means for displaying coordination suggestions in real time when a user picks up a product in a physical store using smart glasses or a head-mounted display" is a function that displays coordination suggestions based on a product in real time when a user picks up the product in a physical store using smart glasses or a head-mounted display.

[1077] "Means for the terminal to generate a prompt sentence based on the information input by the user and the product picked up, and to send the prompt sentence to the server" refers to a function that generates a prompt sentence based on the weather, schedule, and person to meet information input by the user, and information on the product picked up in a physical store, and sends the prompt sentence from the terminal to the server.

[1078] System Overview

[1079] This invention is a style assistant system that provides personalized fashion suggestions based on the user's weather, schedule, and meeting information. In particular, it aims to provide optimal coordination suggestions in real time using smart glasses or head-mounted displays in brick-and-mortar stores.

[1080] Hardware and software used

[1081] Hardware: Smart glasses (e.g., Google Glass) or head-mounted displays (e.g., Microsoft HoloLens)

[1082] Software: Django (server-side framework), React (front-end framework), TensorFlow (generative AI model), OpenCV (visual data processing)

[1083] Specific explanation of the system's operation

[1084] Obtaining user input information

[1085] This function allows users to input information about the day's weather, schedule, and people they're meeting through smart glasses or a head-mounted display. Users can also upload their existing clothing lists.

[1086] Sending data

[1087] The entered information and existing clothing list are sent from the device to a server, which uses this information to create a user profile and prepares the data for the generative AI model.

[1088] Coordination suggestions using generative AI models

[1089] The server analyzes the received information and uses a generative AI model to generate optimal outfit suggestions for the user. It also references trend data to include the latest fashion items in the suggestions.

[1090] Real-time display

[1091] When a user picks up a product in a physical store, outfit suggestions based on that product are displayed in real time through smart glasses or a head-mounted display. At this time, prompts are generated based on the user's input information and the product they picked up.

[1092] Displaying suggested outfits

[1093] The generated coordination proposal is sent back to the terminal and visually presented to the user, who can see the entire coordination on the screen.

[1094] Getting feedback and tuning the AI ​​model

[1095] Users provide feedback on the proposed outfits, which is sent to the server, and the generative AI model is fine-tuned based on that feedback, improving the accuracy of the next suggestion.

[1096] Specific examples

[1097] Suppose a user uses smart glasses to input information such as "Today is sunny, 18 degrees, and I'm meeting a friend," and then picks up a black T-shirt. An example prompt sent to the server is:

[1098] "The weather is sunny, I'm meeting a friend, and I've picked up a black T-shirt. Can you suggest the best outfit for this situation?"

[1099] This allows the server to generate a coordination suggestion based on the user's preferences and the latest trends, such as "a black T-shirt, white sneakers, and dark denim pants," and display it in real time on the user's smart glasses.

[1100] As described above, the present invention can provide users with personalized and real-time fashion suggestions even in brick-and-mortar stores.

[1101] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1102] Step 1:

[1103] The user inputs information about the weather, schedule, and people they are meeting through smart glasses or a head-mounted display. The user inputs this information in text format using a device. The input of this step is the user's input data, and the output is the data stored on the device.

[1104] Step 2:

[1105] The terminal obtains the user's existing clothing list. The clothing list previously entered or updated by the user is read from the database. The input of this step is the user's clothing list data, and the output is the list data stored in the terminal.

[1106] Step 3:

[1107] The device sends the acquired information (weather, schedule, meeting person information, and clothing list) to the server. The input of this step is the user data stored on the device, and the output is the data sent to the server.

[1108] Step 4:

[1109] The server generates outfit suggestions using a generative AI model based on the information it receives. The server first analyzes the received data and passes it to the generative AI model, taking into account trend data and user preferences. The input to this step is the user data sent to the server, and the output is the generated outfit suggestions.

[1110] Step 5:

[1111] The server returns the generated coordination proposal to the terminal. The input of this step is the generated coordination proposal, and the output is the proposal data sent to the terminal.

[1112] Step 6:

[1113] The terminal displays outfit suggestions to the user. The terminal visually presents the outfit suggestions to the user. The input to this step is the suggestion data sent to the terminal, and the output is the outfit suggestions displayed on the display screen.

[1114] Step 7:

[1115] A user picks up a product in a physical store. The smart glasses or head-mounted display recognizes the product and reports it to the server. The input of this step is the product information picked up by the user, and the output is the product data sent to the server.

[1116] Step 8:

[1117] The terminal generates a prompt sentence based on the user's input information and the product picked up, and sends the prompt sentence to the server. The input for this step is the user's input information and product data, and the output is the generated prompt sentence.

[1118] Step 9:

[1119] The server receives the prompt sentence and generates outfit suggestions in real time using a generative AI model. The input of this step is the generated prompt sentence, and the output is real-time outfit suggestions.

[1120] Step 10:

[1121] The server sends the coordinated proposals generated in real time to the terminal and displays them to the user. The input of this step is the real-time coordinated proposals, and the output is the proposals displayed on the terminal.

[1122] Step 11:

[1123] The user provides feedback on the proposed coordination, and the terminal sends it to the server. The input of this step is the user's feedback, and the output is the feedback data sent to the server.

[1124] Step 12:

[1125] The server fine-tunes the generative AI model based on the feedback, which improves the accuracy of the next proposal. The input of this step is the feedback data, and the output is an improved generative AI model.

[1126] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1127] Overall system overview

[1128] This invention is a system that realizes a personal style assistant that provides users with personalized fashion advice and encourages sustainable consumption. In particular, by adding an emotion engine that recognizes the user's emotions, it is possible to propose outfits that are more tailored to the user's individual needs.

[1129] Explanation of program processing

[1130] 1. User Input

[1131] The user uses the terminal to input information about the weather, plans, and people to meet for the day, and also registers or updates an existing clothing list on the terminal.

[1132] Examples: "Today it's sunny and 18 degrees, I'm meeting a friend" and "White shirt, blue jeans, leather shoes"

[1133] 2. Emotional Recognition

[1134] The emotion engine recognizes emotions from the user's facial expressions and voice. The recognized emotional information (e.g., joy, sadness, stress, etc.) is input into the generative AI model.

[1135] Example: Your current emotion is judged to be "stress."

[1136] 3. Data transmission

[1137] The terminal sends the information input by the user (weather, schedule, information about people to meet, existing clothing list, and emotional information) to the server.

[1138] Data format: {'weather': 'Sunny, 18°C', 'event': 'Meeting with a friend', 'clothing_list': ['Blue jeans', 'White shirt', 'Leather shoes'], 'emotion': 'Stress'}

[1139] 4. Coordination suggestions by AI models

[1140] The server then activates a generative AI model based on the received data to generate outfit suggestions, taking into account the user's preferences, trend data, and emotional information.

[1141] For example, suggest outfits such as, "Choose a relaxed style to reduce stress."

[1142] 5. Consider trend data

[1143] The server references trend data (SNS browsing results, purchasing data, etc.) and adds the latest trend items to the generated coordination suggestions.

[1144] Example: "Add red scarf as a trend" to your suggestion

[1145] 6. Return of coordination proposal

[1146] The server then transmits the final coordinated outfit suggestions to the terminal, including specific clothing combinations and trend items.

[1147] For example: "White shirt, blue jeans, leather shoes, red scarf."

[1148] 7. Presentation to the User

[1149] The terminal displays the generated outfit suggestions to the user, who can visually check the suggested outfits and use them as reference for deciding on their style for the day.

[1150] Example: "Today's recommended outfit: white shirt, blue jeans, leather shoes, red scarf."

[1151] 8. Gathering Feedback

[1152] The user provides feedback on the suggested outfits, including whether they like the outfits or don't like them.

[1153] Example: "A white shirt and leather shoes go together really well."

[1154] 9. Update the AI ​​model

[1155] The server fine-tunes the generative AI model based on the received feedback, improving the accuracy of the next outfit suggestion.

[1156] Example: Improve the model based on feedback to make suggestions that better match the user's preferences.

[1157] This system allows users to receive more appropriate outfit suggestions based on their emotions, making it easier to choose the outfit that will make them feel good throughout the day. It also has the advantage of promoting sustainable consumption by utilizing existing clothing lists.

[1158] The processing flow will be explained below.

[1159] Step 1:

[1160] A user uses a device to input information about the weather, appointments, and people they are meeting. For example, the user inputs "Today it's sunny and 18 degrees, and I'm meeting a friend," updating an existing clothing list of "white shirt, blue jeans, leather shoes."

[1161] Step 2:

[1162] The device activates an emotion engine and recognizes emotions from the user's facial expressions and voice. For example, if the user has an expression that indicates stress, the emotion engine will recognize this as "stress."

[1163] Step 3:

[1164] The device sends data including the input information and emotion information to the server. The sent data includes "weather information, event information, clothing list, emotion information," etc. An example of data is "{'weather': 'Sunny, 18°C', 'event': 'Meeting with a friend', 'clothing_list': ['Blue jeans', 'White shirt', 'Leather shoes'], 'emotion': 'Stress'}."

[1165] Step 4:

[1166] The server analyzes the user data received from the device, including weather, schedules, people to meet, existing clothing lists, and emotional information, and activates a generative AI model based on this data.

[1167] Step 5:

[1168] The server uses a generative AI model to generate outfit suggestions. The generative AI model considers the user's preferences, past feedback, and current emotional information to generate appropriate clothing combinations. For example, it may suggest, "If you're feeling stressed, we recommend a relaxed style."

[1169] Step 6:

[1170] The server references trend data (such as social media browsing results and purchasing data) and adds the latest trend items to the generated coordination suggestions. For example, "Add a red scarf to a white shirt and blue jeans as a trend."

[1171] Step 7:

[1172] The server then sends the final outfit recommendation to the device. The data includes specific clothing combinations and trend items. An example of the data is "{'recommendation': ['White shirt', 'Blue jeans', 'Leather shoes', 'Red scarf']}".

[1173] Step 8:

[1174] The terminal displays the received outfit suggestions to the user. The user can visually check the suggested outfits and use them as a reference for deciding on their style for the day. An example display might be "Today's recommended outfit: white shirt, blue jeans, leather shoes, red scarf."

[1175] Step 9:

[1176] The user provides feedback on the proposed outfit, including specific preferences and areas for improvement. For example, the user may provide feedback such as, "The combination of a white shirt and leather shoes is very good."

[1177] Step 10:

[1178] The device sends user feedback to a server, where the feedback data is stored and analyzed to improve the accuracy of the generative AI model.

[1179] Step 11:

[1180] The server fine-tunes the generative AI model based on the received feedback. This improves the accuracy of the next outfit suggestion and generates suggestions that are closer to the user's preferences. For example, reflecting the user's feedback, the server will continue to recommend a combination of a white shirt and leather shoes.

[1181] Example 2

[1182] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1183] Conventional fashion assistant systems have the problem of not being able to fully meet the user's needs because they do not take into account the user's emotions or real-time trend information. In addition, because they are unable to propose outfits that take the user's emotional state into account, the suggested styles may not match the user's mood or the situation. As a result, users tend to be dissatisfied with the outfits provided and have fewer opportunities to actually wear them.

[1184] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1185] In this invention, the server includes means for acquiring information on the weather, schedule, and people to meet input by the user, means for acquiring the user's existing clothing list, means for acquiring the user's facial expressions and voice and recognizing emotions, means for generating outfit suggestions using a generative AI model based on the acquired information and the recognized emotion information, means for adding trend items to the generated outfit suggestions by referring to trend data, and means for fine-tuning the generative AI model based on user feedback. This enables personalized outfit suggestions that take into account the user's emotions and real-time trend information.

[1186] "Weather information" refers to data entered by the user regarding the weather conditions for that day.

[1187] "Schedule" refers to information entered by the user about activities and events to be held that day.

[1188] "Information about people to meet" refers to information about people the user plans to meet on that day.

[1189] "Existing Clothing List" refers to a list of clothing owned by the user, including data registered with a particular application or device.

[1190] "Emotion information" refers to data that indicates the emotional state of the user as recognized from their facial expressions and voice.

[1191] "Server" refers to the computer system that receives and processes data, runs the generative AI model, obtains feedback, and fine-tunes the model.

[1192] A "generative AI model" refers to an artificial intelligence model that generates fashion coordination suggestions based on user input and emotional information.

[1193] "Outfit suggestions" refer to clothing combinations recommended based on the user's input information and emotions.

[1194] "Trend data" refers to information about the latest fashion trends and includes data collected from social media and purchasing data.

[1195] "Feedback" refers to user-provided ratings and comments on the proposed outfits.

[1196] "Fine-tuning" refers to the process of adjusting the parameters of a generative AI model based on received feedback to improve the accuracy of its suggestions.

[1197] Overall system configuration

[1198] This invention is a personal style assistant system that provides users with personalized fashion advice and encourages sustainable consumption. In particular, by adding an emotion engine that recognizes the user's emotions, it is possible to propose outfits that are more tailored to the user's individual needs.

[1199] Hardware and Software Configuration

[1200] Terminal

[1201] Users use devices such as smartphones and tablets. The devices are equipped with cameras and microphones that capture the user's facial expressions and voice. They also install applications and input information about the weather, their schedule, people they are meeting, and their existing clothing list.

[1202] server

[1203] The server is a high-performance computer system that receives and processes data and runs the generative AI model. The server can use Microsoft Azure's emotion analysis API as an emotion engine, which analyzes the user's emotional information and generates optimal outfit suggestions.

[1204] Generative AI Models

[1205] The generative AI model uses an advanced language model such as GPT-4, and the server uses this generative AI model to generate fashion coordination suggestions based on the user's input and emotional information.

[1206] Program processing

[1207] The device first acquires the user's input information (weather, schedule, information about people to meet, existing clothing list), as well as facial expressions and voice. The data acquired using the camera and microphone is analyzed by the emotion engine and sent to the server as emotion information.

[1208] Next, the server launches a generative AI model based on the received information. The generative AI model receives the following text data as a prompt:

[1209] "Today's weather is sunny and 18 degrees, plans include meeting a friend, and current emotion is stress. The user has the following clothing list: white shirt, blue jeans, leather shoes."

[1210] Based on this, the generative AI model generates coordination suggestions that take into account the user's preferences and trend data. As a specific example, the generative AI model might suggest "adding a red scarf to a white shirt, blue jeans, and leather shoes as a trend."

[1211] The generated outfit suggestions are sent back from the server to the device, which then displays them to the user through the application. The user can review the suggested outfits and decide on their style for the day. In addition, the user can provide feedback on the suggested outfits. For example, the user can leave a specific comment such as, "The combination of a white shirt and leather shoes is very good."

[1212] Finally, the server fine-tunes the generative AI model based on the received feedback, improving the accuracy of the next outfit suggestions and providing results that better match the user's preferences.

[1213] The system allows users to receive personalized outfit suggestions that take into account emotions and real-time trend information, and also promotes sustainable consumption.

[1214] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1215] Step 1:

[1216] The device receives input from the user about today's weather, plans, and people to meet. The user enters this data using text boxes and selection boxes in the application. For example, the user enters information like "Today it's sunny and 18 degrees, and I'm planning to meet a friend." The device then temporarily stores this information.

[1217] Step 2:

[1218] The device retrieves the user's existing clothing list. The user provides data by manually entering text or uploading photos of the clothing. For example, if information such as "white shirt, blue jeans, leather shoes" is entered, the device will store this data.

[1219] Step 3:

[1220] The device's camera and microphone are used to capture the user's facial and voice data. This data is captured in real time and processed by facial recognition software and voice analysis software. The emotion engine analyzes the user's emotional state (e.g., joy, stress) and extracts emotional information.

[1221] Step 4:

[1222] The device sends the weather, schedule, meeting information, existing clothing list, and emotion information acquired as JSON format data to the server. The input information is formatted as follows and sent to the server:

[1223] json

[1224] {

[1225] "weather": "Sunny, 18°C",

[1226] "event": "Meeting with a friend",

[1227] "clothing_list": ["Blue jeans", "White shirt", "Leather shoes"],

[1228] "emotion": "Stress"

[1229] }

[1230] Step 5:

[1231] The server processes the received information and launches a generative AI model, which receives the following prompt text and generates outfit suggestions based on it:

[1232] "Today's weather is sunny and 18 degrees, plans include meeting a friend, and current emotion is stress. The user has the following clothing list: white shirt, blue jeans, leather shoes."

[1233] Step 6:

[1234] The server uses a generative AI model to generate personalized outfit suggestions for each user. The generative AI model takes into account the user's preferences, emotional information, and trend data, and generates outfit suggestions as output. For example, a suggestion might be generated such as "Add a red scarf to a white shirt, blue jeans, and leather shoes, as a trend."

[1235] Step 7:

[1236] The server finally sends the generated coordination proposal to the device. The generated data is sent to the device in the following format:

[1237] json

[1238] {

[1239] "recommendation": ["White shirt", "Blue jeans", "Leather shoes", "Red scarf"]

[1240] }

[1241] Step 8:

[1242] The terminal displays the received outfit suggestions to the user. The user can visually check the suggested outfits on the application screen. For example, "Today's recommended outfit: white shirt, blue jeans, leather shoes, red scarf" is displayed.

[1243] Step 9:

[1244] Users provide feedback on the suggested outfits. Feedback is entered using an in-app evaluation form, and includes pros and cons of the suggested outfits and areas for improvement. For example, a specific comment such as "The combination of a white shirt and leather shoes is very good" can be entered.

[1245] Step 10:

[1246] The device sends the user's feedback to the server, which then formats the feedback as follows and sends it to the server:

[1247] json

[1248] {

[1249] "feedback": "The combination of a white shirt and leather shoes is very good"

[1250] }

[1251] Step 11:

[1252] The server fine-tunes the generative AI model based on the received feedback. The server analyzes the feedback and adjusts the parameters of the generative AI model to improve the accuracy of future outfit suggestions, thereby providing results that better match the user's preferences.

[1253] (Application example 2)

[1254] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1255] Conventional personal style assistants have been unable to provide coordination suggestions that take the user's emotions into account. As a result, they are unable to provide fashion suggestions based on the user's mood or emotions of the day, making it difficult to increase user satisfaction. In addition, there is a demand for more personalized suggestions that match the user's mood by providing fashion suggestions that take into account not only information such as the weather and schedule, but also the user's emotions.

[1256] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for recognizing the user's emotion using an emotion engine, means for transmitting the recognized emotion information to the server, and means for generating coordination suggestions using a generative AI model based on the information received by the server. This makes it possible to make fashion suggestions that take the user's emotions into consideration.

[1257] "Means for acquiring information entered by the user about the weather, schedule, and people to meet" refers to a function that allows the user to input information about the weather for the day, schedule, and people to meet into an electronic terminal, and the system acquires that information.

[1258] The "means for acquiring a list of the user's existing clothing" is a function that allows the user to register the clothing he or she owns in a list, and for the system to acquire that list.

[1259] The "means for transmitting acquired information to a server" is a function for transmitting information entered by the user and recognized emotion information to a server via the Internet.

[1260] The "means for recognizing the user's emotions using an emotion engine" is a function that detects the user's current emotional state by analyzing the user's facial expressions and voice.

[1261] The "means for transmitting the recognized emotion information to the server" is a function for transmitting the emotion information recognized by the emotion engine to the server.

[1262] "Means for generating coordination suggestions using a generative AI model based on information received by the server" refers to a function that activates a generative AI model based on information and emotional information received by the server from the user, and suggests optimal fashion coordination.

[1263] The "means for returning the generated coordination proposal from the server to the terminal" is a function for transmitting the fashion coordination proposal generated by the server to the user's terminal.

[1264] The "means for the terminal to display coordination suggestions to the user" is a function for visually displaying to the user fashion coordination suggestions received by the terminal from the server.

[1265] The "means for acquiring user feedback and transmitting it to the server" is a function that allows the user to input opinions and evaluations of the provided coordination proposals and transmit the feedback to the server.

[1266] "Means for the server to fine-tune the generative AI model based on feedback" refers to a function that makes adjustments to improve the accuracy of the generative AI model based on feedback information from users.

[1267] "The generative AI model generates outfit suggestions by taking into account the user's preferences, trend data, and emotional information" refers to the process in which the generative AI model combines the user's personal preferences, the latest fashion trend data, and the user's current emotional state to suggest optimal fashion outfits.

[1268] "Means for collecting trend data and updating the generative AI model based on that data" refers to a function in which the server collects fashion trend data from the internet and various databases, and uses that data to keep the algorithm of the generative AI model up to date.

[1269] The present invention provides a personal style assistant system that uses an emotion engine to suggest optimal outfits to users by utilizing information on the user's weather, schedule, people they are meeting, existing clothing list, and emotion information. By taking the user's emotions into consideration, the system can provide more personalized fashion suggestions and improve user satisfaction.

[1270] Hardware and software used

[1271] Hardware: Smartphone (iOS or Android)

[1272] software:

[1273] EmotionEngine (emotion recognition engine)

[1274] AICoordinator (AI model for suggesting outfits)

[1275] REST API (a server that supports HTTP requests)

[1276] The server uses the EmotionEngine to recognize emotions from the user's facial expressions and voice. It captures the user's face and voice using the smartphone camera and microphone, and analyzes the data. The analyzed emotional data is sent to the server along with the weather, schedule, meeting information, and existing clothing list entered by the user.

[1277] The server launches a generative AI model based on all the received data, and generates outfit suggestions based on the information obtained. The generative AI model comprehensively considers the user's preferences, trend data, and emotional information. For example, based on the information "Today is sunny and 18 degrees, and I plan to meet a friend," "A white shirt, blue jeans, and leather shoes," and "I'm feeling stressed," the model suggests a "relaxed style" of a white shirt, blue jeans, leather shoes, and a trendy red scarf.

[1278] The generated outfit suggestions are sent back from the server to the smartphone and visually displayed to the user on the smartphone screen. The user can use the suggested outfits as a reference to decide on their fashion for the day. Furthermore, the user can input feedback about the suggested outfits and send it to the server, which can then use that feedback to fine-tune the generative AI model and improve the accuracy of the next suggestions.

[1279] Examples of concrete examples and prompts

[1280] As an example, a user enters the following information:

[1281] Weather: Sunny and 18 degrees

[1282] Plans: Meeting with friends

[1283] Existing clothing list: White shirt, blue jeans, leather shoes

[1284] Emotional information: I'm feeling stressed

[1285] Example prompt sentence:

[1286] "Today is sunny and 18 degrees, and I'm meeting a friend. My existing clothing list includes a white shirt, blue jeans, and leather shoes. My current emotion is determined to be stress."

[1287] As described above, the present invention can improve user satisfaction by providing fashion suggestions that take the user's emotions into consideration. It also has the advantage of promoting sustainable consumption by utilizing existing clothing.

[1288] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1289] Step 1:

[1290] A user inputs information about the weather, plans, people to meet, and an existing clothing list into a smartphone. The smartphone has an interface that accepts user input, and this collects the necessary information. Examples of input data include "Today is sunny and 18 degrees. I plan to meet a friend," "White shirt, blue jeans, leather shoes."

[1291] Step 2:

[1292] Using the emotion engine, the smartphone device analyzes the user's facial expressions and voice to recognize emotions. Using data captured through the smartphone's camera and microphone, the emotion engine identifies emotions such as "stress." This recognized emotion information is used for further processing.

[1293] Step 3:

[1294] The device sends the collected weather, schedule, meeting information, existing clothing list, and recognized emotion information to the server in a JSON format, such as "{'weather': 'Sunny, 18°C', 'event': 'Meeting with a friend', 'clothing_list': ['Blue jeans', 'White shirt', 'Leather shoes'], 'emotion': 'Stress'}".

[1295] Step 4:

[1296] The server then activates a generative AI model based on the received data to generate outfit suggestions. The generative AI model uses an algorithm that takes into account the user's preferences, trend data, and emotional information. For example, suggestions might be generated in the form of "pick a relaxed style to reduce stress."

[1297] Step 5:

[1298] The server references the latest trend data collected (such as social media posts and purchasing data) and reflects it in the coordination suggestions. For example, "add a red scarf as a trend item" to the generated coordination.

[1299] Step 6:

[1300] The generated outfit suggestions are sent from the server to the smartphone device. The suggestions include specific clothing combinations and trendy items. For example, a "white shirt, blue jeans, leather shoes, and red scarf" combination might be suggested.

[1301] Step 7:

[1302] The device displays the generated outfit suggestions to the user, who can then check the suggested fashions on their smartphone screen and use them as a reference for deciding what to wear that day.

[1303] Step 8:

[1304] The user provides feedback on the proposed outfits, including their preferences and points that do not suit them, and inputs this feedback into the terminal.

[1305] Step 9:

[1306] The device sends user feedback to the server, which then fine-tunes the generative AI model based on the received feedback. This improves the accuracy of the next outfit suggestions, for example, by providing outfits that better match the user's preferences.

[1307] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1308] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1309] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1310] [Fourth embodiment]

[1311] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1312] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1313] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1314] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1315] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1316] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1317] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1318] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1319] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1320] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1321] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1322] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1323] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1324] Overall system overview

[1325] This invention is a personal style assistant system that aims to provide personalized fashion advice based on user input of weather, schedule, and meeting information. The system utilizes the user's existing clothing list and a generative AI model to suggest outfits that take into account the user's preferences and trends. Furthermore, the AI ​​model is fine-tuned based on user feedback to improve the accuracy of future suggestions.

[1326] Explanation of program processing

[1327] 1. User Input

[1328] The user inputs information about the weather, schedule, and people they are meeting into a device (such as a smartphone or tablet). In addition, the user inputs or updates an existing clothing list.

[1329] Examples: "Today it's sunny and 18 degrees, I'm meeting a friend" and "White shirt, blue jeans, leather shoes"

[1330] 2. Data transmission

[1331] The terminal transmits the input information and the existing clothing list to the server. The transmitted data includes weather information, event information, clothing list, etc.

[1332] Example: Data format is "{'weather': 'Sunny, 18°C', 'event': 'Meeting with a friend', 'clothing_list': ['Blue jeans', 'White shirt', 'Leather shoes']}"

[1333] 3. Coordination suggestions by AI models

[1334] The server analyzes the user data received from the device, then runs a generative AI model to generate outfit suggestions based on the analyzed data, taking into account the user's preferences and trend data.

[1335] Example: A suggested outfit is "white shirt, blue jeans, and leather shoes."

[1336] 4. Consider trend data

[1337] The server references trend data (SNS browsing results, purchasing data, etc.) and adds the latest trend items to the generated coordination suggestions.

[1338] Example: "Add red scarf as a trend" to your suggestion

[1339] 5. Return of outfit suggestions

[1340] The server transmits the final generated coordination proposal to the terminal, which then displays the received proposal to the user.

[1341] For example: "White shirt, blue jeans, leather shoes, red scarf."

[1342] 6. Presentation to the User

[1343] The terminal displays the generated coordination proposal to the user.

[1344] Example: The suggested outfit for today is: white shirt, blue jeans, leather shoes, red scarf.

[1345] 7. Gathering Feedback

[1346] The user provides feedback on the proposed outfit (e.g., what they like and don't like), and the device sends this feedback to the server.

[1347] Example: "A white shirt and leather shoes go together really well."

[1348] 8. Update the AI ​​model

[1349] The server fine-tunes the generative AI model based on the received feedback, improving the accuracy of the next outfit suggestion.

[1350] Example: Improve the model based on feedback to better suit user preferences.

[1351] The advantage of this system is that it allows users to easily enjoy daily styling. Furthermore, it promotes sustainable consumption by maximizing the use of existing clothing and reducing the need to purchase new clothes. As a result, it significantly reduces stress and wastes time for users regarding fashion.

[1352] The processing flow will be explained below.

[1353] Step 1:

[1354] The user uses the device to input information about the weather, appointments, and people they are meeting. In addition, the user enters or updates an existing clothing list. At this stage, the user provides information about the specific weather conditions, events, and people they are meeting for the day.

[1355] Step 2:

[1356] The terminal sends the information entered by the user (weather, schedule, meeting person information, and existing clothing list) to the server. The data sent includes weather information, event information, clothing list, etc., and is sent in a standardized format.

[1357] Step 3:

[1358] The server analyzes the user data received from the device, including weather, schedule, meeting information, and existing clothing lists. The server uses this data to run a generative AI model.

[1359] Step 4:

[1360] The server generates outfit suggestions using a generative AI model, which takes into account the user's preferences and past feedback to generate optimal clothing combinations.

[1361] Step 5:

[1362] The server references trend data (social media browsing results, purchasing data, etc.) and adds trend items to the generated coordination suggestions. At this stage, the latest fashion trends are reflected in the generated basic suggestions.

[1363] Step 6:

[1364] The server then transmits the final coordinated outfit suggestions to the terminal, including specific clothing combinations and trend items.

[1365] Step 7:

[1366] The terminal displays the received outfit suggestions to the user, who can visually check the suggested outfits and use them as a reference for deciding on their style for the day.

[1367] Step 8:

[1368] Users provide feedback on the suggested outfits, including their preferences and whether the outfits look good or not.

[1369] Step 9:

[1370] The device sends user feedback to a server, where the feedback data is stored and analyzed to improve the accuracy of the generative AI model.

[1371] Step 10:

[1372] The server then fine-tunes the generative AI model based on the received feedback. This process improves the accuracy of the next outfit suggestions, generating suggestions that more closely match the user's preferences.

[1373] This process reduces the stress of daily styling for users, allowing them to enjoy fashion while promoting sustainable consumption.

[1374] Example 1

[1375] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1376] In today's consumer society, it is difficult to receive personalized fashion advice on a daily basis, and many people often struggle with their own style and choices. Furthermore, there are few systems that automatically suggest outfits that reflect the latest trends while optimizing existing clothing. Therefore, an effective method is needed to promote sustainable consumption while reducing stress related to fashion.

[1377] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1378] In this invention, the server includes means for acquiring information entered by the user about the weather, schedule, and people to meet, means for acquiring the user's existing clothing list, and means for transmitting the acquired information to the server, thereby making it possible to provide personalized fashion advice based on detailed user data.

[1379] The server also includes a means for generating outfit suggestions using a generative AI model based on the received information, a means for configuring input prompts for the generative AI model, and a means for referencing trend data and adding the latest trend items to the suggestions, thereby making it possible to provide outfit suggestions that reflect the user's preferences and the latest trends.

[1380] Furthermore, the server includes means for returning the generated outfit suggestions from the server to the terminal, means for the terminal to display the outfit suggestions to the user, means for acquiring user feedback and sending it to the server, and means for fine-tuning the generating AI model based on the feedback, thereby making it possible to provide more accurate outfit suggestions that reflect the user feedback from the next time onwards.

[1381] "User" refers to an individual using the system who inputs weather, schedule, meeting information, and existing clothing lists.

[1382] A "terminal" refers to an electronic device used by a user to input information, such as a smartphone or tablet.

[1383] "Weather information" is data that indicates the weather conditions for that day, and includes, for example, the temperature and the probability of precipitation.

[1384] "Schedule information" is data describing the actions and activities that the user plans to take that day.

[1385] "Information about people to meet" is information about people the user plans to meet that day, such as friends, family, or business partners.

[1386] The "existing clothing list" refers to a list of clothing owned by the user, specifically including items such as shirts, pants, and shoes.

[1387] "Server" refers to a computer system for receiving and processing data sent by users.

[1388] A "generative AI model" is a model for generating coordination suggestions using artificial intelligence technology, and specifically, for example, a generative language model.

[1389] A "prompt" is a way to create specific questions or instructions to input into a generative AI model.

[1390] "Trend data" refers to information about current fashion trends, and is data collected from social media, purchasing history, etc.

[1391] "Coordination suggestions" are suggestions for fashion combinations generated using information entered by the user and a generative AI model.

[1392] "Feedback" refers to the evaluation or opinion that the user inputs regarding the presented outfit.

[1393] "Fine-tuning" is a method of retraining the generative AI model based on user feedback, so that the next suggestions will be closer to the user's preferences.

[1394] This invention relates to a personal style assistant system that allows users to easily enjoy daily styling. The system's purpose is to provide personalized fashion advice by having users input information about the weather, their schedule, and the people they're meeting. The system utilizes the user's existing clothing list and uses a generative AI model to suggest outfits that take into account the user's preferences and trends. Furthermore, the AI ​​model is fine-tuned based on user feedback to improve the accuracy of future suggestions.

[1395] Hardware and Software Configuration

[1396] The system consists of two main pieces of hardware: a terminal and a server. The terminal is a device operated by the user, such as a smartphone or tablet, that runs a user interface application. The server is a cloud-based computer system that processes user data, runs generative AI models, and analyzes trend data.

[1397] The software running on the device is a user interface application. It sends information entered by the user to the server and displays outfit suggestions received from the server. The software on the server analyzes data, runs generative AI models (e.g., GPT-4), references trend data, and processes feedback.

[1398] Data Processing and Data Arithmetic

[1399] 1. User input:

[1400] The user inputs information about the weather, appointments, and people they are meeting through the device, and also inputs or updates an existing clothing list.

[1401] Example: A user enters "Today is sunny and 18 degrees. I plan to meet a friend," and registers "white shirt, blue jeans, leather shoes" in the clothing list.

[1402] 2. Data transmission:

[1403] The device sends the entered information and the existing clothing list to the server. The data is sent in JSON format using the HTTP protocol.

[1404] 3. Data analysis and model input:

[1405] The server receives the data, analyzes the weather information, event information, and clothing list, and then composes input prompts for the generative AI model.

[1406] Example prompt:

[1407] User info: {'weather': 'Sunny, 18°C', 'event': 'Meeting friends', 'clothing_list': ['White shirt', 'Blue jeans', 'Leather shoes']}

[1408] Generate outfit recommendations, taking into account user preferences and trends.

[1409] 4. Coordination proposal generation:

[1410] The server runs the generative AI model and generates outfit suggestions based on the analyzed data, taking into account the user's preferences and trend data.

[1411] 5. View trend data:

[1412] The server refers to trend data and adds the latest trend items to the coordination suggestions.

[1413] 6. Return and view outfit suggestions:

[1414] The server transmits the generated coordination proposal to the terminal, which displays the proposal to the user.

[1415] Example: The suggestion would be "Today's recommended outfit: white shirt, blue jeans, leather shoes, red scarf."

[1416] 7. Gathering Feedback:

[1417] The user provides feedback on the proposed coordination, which the terminal sends to the server.

[1418] Example: A user rates the combination of a white shirt and leather shoes as "a great look."

[1419] 8. Fine-tuning AI models:

[1420] The server fine-tunes the generative AI model based on user feedback to improve the accuracy of the next outfit suggestion.

[1421] In this way, the system provides users with personalized and accurate fashion advice, promotes sustainable consumption by making the most of existing clothing, and reduces stress and time wasted when it comes to fashion.

[1422] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1423] Step 1:

[1424] Enter user information

[1425] The user uses the device to input information about the weather, schedules, and people they are meeting, and also to input or update an existing clothing list. This information is collected through the user interface.

[1426] Input: Weather information, schedule information, meeting information, existing clothing list

[1427] Data processing: The user interface application converts this information into JSON format.

[1428] Output: Weather information, schedule information, meeting information, and clothing list in JSON format

[1429] Specific behavior:

[1430] The user opens the app, enters the weather as "Sunny, 18 degrees," the appointment as "Meeting a friend," and the person information as "Friend."

[1431] Register "white shirt, blue jeans, leather shoes" as a clothing list on the device.

[1432] Step 2:

[1433] Sending data

[1434] The device sends the entered information and the existing clothing list to the server. The data is transmitted using the HTTP protocol.

[1435] Input: Weather information, schedule information, meeting information, and clothing list entered by the user

[1436] Data processing: The device compiles this information into a single JSON object and sends it to the server.

[1437] Output: Input data sent to the server in JSON format

[1438] Specific behavior:

[1439] The device sends data to the server in the format "{'weather': 'Sunny 18 degrees', 'event': 'Meeting a friend', 'meet_person': 'Friend', 'clothing_list': ['White shirt', 'Blue jeans', 'Leather shoes']}".

[1440] Step 3:

[1441] Data analysis and model input

[1442] The server receives the data and analyzes the weather, events, people to meet, and clothing list, then composes input prompts for the generative AI model.

[1443] Input: Input data sent to the server in JSON format

[1444] Data processing: The server analyzes the received data and generates prompts in a format suitable for the generative AI model.

[1445] Output: Input prompts to the generative AI model

[1446] Specific behavior:

[1447] The server parses the data it receives and generates a prompt of the following form:

[1448] User info: {'weather': 'Sunny, 18°C', 'event': 'Meeting a friend', 'meet_person': 'Friend', 'clothing_list': ['White shirt', 'Blue jeans', 'Leather shoes']}

[1449] Generate outfit recommendations, taking into account user preferences and trends.

[1450] Step 4:

[1451] Generating outfit suggestions

[1452] The server runs the generative AI model and generates outfit suggestions based on the analyzed data, taking into account the user's preferences and trend data.

[1453] Input: Input prompts for the generative AI model

[1454] Data processing: A generative AI model generates outfit suggestions based on prompts.

[1455] Output: Coordination suggestions

[1456] Specific behavior:

[1457] The server runs the generative AI model and generates suggestions like: "Pair a white shirt with blue jeans and leather shoes."

[1458] Step 5:

[1459] Applying trend data

[1460] The server refers to trend data and adds the latest trend items to the coordination suggestions.

[1461] Input: Coordination suggestions, trend data

[1462] Data processing: Add items from trend data to the generated outfit suggestions.

[1463] Output: Updated outfit suggestions

[1464] Specific behavior:

[1465] The server retrieves the latest trend data from social media and purchasing data and adds "Red Scarf" to the suggestions.

[1466] Step 6:

[1467] Return and display of outfit suggestions

[1468] The server finally sends the updated coordination proposal to the terminal, which displays the proposal to the user.

[1469] Input: Updated outfit suggestions

[1470] Data processing: The server sends the proposal to the terminal, which then displays it on the user interface.

[1471] Output: Coordination suggestions presented to the user

[1472] Specific behavior:

[1473] The server sends "{'suggested_outfit': 'White shirt, blue jeans, leather shoes, red scarf'}" to the device.

[1474] The device displays on the user screen, "Today's recommended outfit: white shirt, blue jeans, leather shoes, red scarf."

[1475] Step 7:

[1476] Collecting feedback

[1477] The user provides feedback on the proposed coordination, and the terminal transmits the feedback to the server.

[1478] Input: User feedback

[1479] Data processing: The feedback information is converted back to JSON format and sent to the server.

[1480] Output: Feedback data sent to the server

[1481] Specific behavior:

[1482] A user reviews the outfit on the app, saying, "The combination of the white shirt and leather shoes is very good."

[1483] The device sends "{'feed_back': 'The combination of a white shirt and leather shoes is very good'}" to the server.

[1484] Step 8:

[1485] Fine-tuning AI models

[1486] The server fine-tunes the generative AI model based on user feedback to improve the accuracy of the next outfit suggestion.

[1487] Input: Feedback data from users

[1488] Data processing: The generative AI model retrains based on feedback and improves the model.

[1489] Output: A fine-tuned generative AI model

[1490] Specific behavior:

[1491] The server uses the feedback data to retrain the generative AI model and reflect it in future coordination suggestions.

[1492] (Application example 1)

[1493] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1494] Existing personal style assistant systems suggest outfits based on information entered by the user, such as the weather, schedule, and people they are meeting, but they have the problem of not being able to provide a real-time user experience like in a physical store. Furthermore, they are unable to instantly display outfit suggestions based on the products the user actually picks up, and there is a lack of means to further improve the user experience.

[1495] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1496] In this invention, the server includes means for acquiring information input by the user regarding the weather, schedule, and people to meet, means for acquiring the user's existing clothing list, means for transmitting the acquired information to the server, means for the server to generate outfit suggestions using a generative AI model based on the information received, means for the server to return the generated outfit suggestions to the terminal, means for the terminal to display the outfit suggestions to the user, means for acquiring user feedback and transmitting it to the server, means for the server to fine-tune the generative AI model based on the feedback, means for displaying outfit suggestions in real time when the user picks up a product in a physical store using smart glasses or a head-mounted display, and means for the terminal to generate a prompt sentence based on the user's input information and the picked up product and transmit the prompt sentence to the server. This enables users to receive appropriate outfit suggestions in real time even in physical stores.

[1497] "Means for obtaining information entered by the user about the weather, plans, and people to meet" refers to a function that allows the user to use a device such as a smartphone or tablet to enter information about the day's weather, plans, and people to meet, and the system collects this information.

[1498] The "means for acquiring the user's existing clothing list" is a function that allows the user to input or update a list of clothing that the user owns into the terminal and acquire that information from the system.

[1499] The "means for transmitting acquired information to the server" is a communication means for transmitting the weather, schedule, information on people to meet, and clothing list input by the user from the terminal to the server.

[1500] "Means for generating coordination suggestions using a generative AI model based on information received by the server" refers to a function for analyzing user data received by the server and using a generative AI model to create optimal coordination suggestions for the user.

[1501] The "means for returning the generated coordination proposal from the server to the terminal" is a communication means for transmitting the coordination proposal generated by the server to the terminal and providing it to the user.

[1502] The "means for the terminal to display a coordination suggestion to the user" is a function for visually presenting the generated coordination suggestion to the user using the display screen of the terminal.

[1503] The "means for acquiring user feedback and transmitting it to the server" is a function that allows the user to input their evaluation and opinion on the proposed outfit and transmit it from the terminal to the server.

[1504] "Means for the server to fine-tune the generative AI model based on feedback" is a function that receives feedback from users, improves the generative AI model based on that feedback, and increases the accuracy of the next outfit suggestion.

[1505] "A means for displaying coordination suggestions in real time when a user picks up a product in a physical store using smart glasses or a head-mounted display" is a function that displays coordination suggestions based on a product in real time when a user picks up the product in a physical store using smart glasses or a head-mounted display.

[1506] "Means for the terminal to generate a prompt sentence based on the information input by the user and the product picked up, and to send the prompt sentence to the server" refers to a function that generates a prompt sentence based on the weather, schedule, and person to meet information input by the user, and information on the product picked up in a physical store, and sends the prompt sentence from the terminal to the server.

[1507] System Overview

[1508] This invention is a style assistant system that provides personalized fashion suggestions based on the user's weather, schedule, and meeting information. In particular, it aims to provide optimal coordination suggestions in real time using smart glasses or head-mounted displays in brick-and-mortar stores.

[1509] Hardware and software used

[1510] Hardware: Smart glasses (e.g., Google Glass) or head-mounted displays (e.g., Microsoft HoloLens)

[1511] Software: Django (server-side framework), React (front-end framework), TensorFlow (generative AI model), OpenCV (visual data processing)

[1512] Specific explanation of the system's operation

[1513] Obtaining user input information

[1514] This function allows users to input information about the day's weather, schedule, and people they're meeting through smart glasses or a head-mounted display. Users can also upload their existing clothing lists.

[1515] Sending data

[1516] The entered information and existing clothing list are sent from the device to a server, which uses this information to create a user profile and prepares the data for the generative AI model.

[1517] Coordination suggestions using generative AI models

[1518] The server analyzes the received information and uses a generative AI model to generate optimal outfit suggestions for the user. It also references trend data to include the latest fashion items in the suggestions.

[1519] Real-time display

[1520] When a user picks up a product in a physical store, outfit suggestions based on that product are displayed in real time through smart glasses or a head-mounted display. At this time, prompts are generated based on the user's input information and the product they picked up.

[1521] Displaying suggested outfits

[1522] The generated coordination proposal is sent back to the terminal and visually presented to the user, who can see the entire coordination on the screen.

[1523] Getting feedback and tuning the AI ​​model

[1524] Users provide feedback on the proposed outfits, which is sent to the server, and the generative AI model is fine-tuned based on that feedback, improving the accuracy of the next suggestion.

[1525] Specific examples

[1526] Suppose a user uses smart glasses to input information such as "Today is sunny, 18 degrees, and I'm meeting a friend," and then picks up a black T-shirt. An example prompt sent to the server is:

[1527] "The weather is sunny, I'm meeting a friend, and I've picked up a black T-shirt. Can you suggest the best outfit for this situation?"

[1528] This allows the server to generate a coordination suggestion based on the user's preferences and the latest trends, such as "a black T-shirt, white sneakers, and dark denim pants," and display it in real time on the user's smart glasses.

[1529] As described above, the present invention can provide users with personalized and real-time fashion suggestions even in brick-and-mortar stores.

[1530] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1531] Step 1:

[1532] The user inputs information about the weather, schedule, and people they are meeting through smart glasses or a head-mounted display. The user inputs this information in text format using a device. The input of this step is the user's input data, and the output is the data stored on the device.

[1533] Step 2:

[1534] The terminal obtains the user's existing clothing list. The clothing list previously entered or updated by the user is read from the database. The input of this step is the user's clothing list data, and the output is the list data stored in the terminal.

[1535] Step 3:

[1536] The device sends the acquired information (weather, schedule, meeting person information, and clothing list) to the server. The input of this step is the user data stored on the device, and the output is the data sent to the server.

[1537] Step 4:

[1538] The server generates outfit suggestions using a generative AI model based on the information it receives. The server first analyzes the received data and passes it to the generative AI model, taking into account trend data and user preferences. The input to this step is the user data sent to the server, and the output is the generated outfit suggestions.

[1539] Step 5:

[1540] The server returns the generated coordination proposal to the terminal. The input of this step is the generated coordination proposal, and the output is the proposal data sent to the terminal.

[1541] Step 6:

[1542] The terminal displays outfit suggestions to the user. The terminal visually presents the outfit suggestions to the user. The input to this step is the suggestion data sent to the terminal, and the output is the outfit suggestions displayed on the display screen.

[1543] Step 7:

[1544] A user picks up a product in a physical store. The smart glasses or head-mounted display recognizes the product and reports it to the server. The input of this step is the product information picked up by the user, and the output is the product data sent to the server.

[1545] Step 8:

[1546] The terminal generates a prompt sentence based on the user's input information and the product picked up, and sends the prompt sentence to the server. The input for this step is the user's input information and product data, and the output is the generated prompt sentence.

[1547] Step 9:

[1548] The server receives the prompt sentence and generates outfit suggestions in real time using a generative AI model. The input of this step is the generated prompt sentence, and the output is real-time outfit suggestions.

[1549] Step 10:

[1550] The server sends the coordinated proposals generated in real time to the terminal and displays them to the user. The input of this step is the real-time coordinated proposals, and the output is the proposals displayed on the terminal.

[1551] Step 11:

[1552] The user provides feedback on the proposed coordination, and the terminal sends it to the server. The input of this step is the user's feedback, and the output is the feedback data sent to the server.

[1553] Step 12:

[1554] The server fine-tunes the generative AI model based on the feedback, which improves the accuracy of the next proposal. The input of this step is the feedback data, and the output is an improved generative AI model.

[1555] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1556] Overall system overview

[1557] This invention is a system that realizes a personal style assistant that provides users with personalized fashion advice and encourages sustainable consumption. In particular, by adding an emotion engine that recognizes the user's emotions, it is possible to propose outfits that are more tailored to the user's individual needs.

[1558] Explanation of program processing

[1559] 1. User Input

[1560] The user uses the terminal to input information about the weather, plans, and people to meet for the day, and also registers or updates an existing clothing list on the terminal.

[1561] Examples: "Today it's sunny and 18 degrees, I'm meeting a friend" and "White shirt, blue jeans, leather shoes"

[1562] 2. Emotional Recognition

[1563] The emotion engine recognizes emotions from the user's facial expressions and voice. The recognized emotional information (e.g., joy, sadness, stress, etc.) is input into the generative AI model.

[1564] Example: Your current emotion is judged to be "stress."

[1565] 3. Data transmission

[1566] The terminal sends the information input by the user (weather, schedule, information about people to meet, existing clothing list, and emotional information) to the server.

[1567] Data format: {'weather': 'Sunny, 18°C', 'event': 'Meeting with a friend', 'clothing_list': ['Blue jeans', 'White shirt', 'Leather shoes'], 'emotion': 'Stress'}

[1568] 4. Coordination suggestions by AI models

[1569] The server then activates a generative AI model based on the received data to generate outfit suggestions, taking into account the user's preferences, trend data, and emotional information.

[1570] For example, suggest outfits such as, "Choose a relaxed style to reduce stress."

[1571] 5. Consider trend data

[1572] The server references trend data (SNS browsing results, purchasing data, etc.) and adds the latest trend items to the generated coordination suggestions.

[1573] Example: "Add red scarf as a trend" to your suggestion

[1574] 6. Return of coordination proposal

[1575] The server then transmits the final coordinated outfit suggestions to the terminal, including specific clothing combinations and trend items.

[1576] For example: "White shirt, blue jeans, leather shoes, red scarf."

[1577] 7. Presentation to the User

[1578] The terminal displays the generated outfit suggestions to the user, who can visually check the suggested outfits and use them as reference for deciding on their style for the day.

[1579] Example: "Today's recommended outfit: white shirt, blue jeans, leather shoes, red scarf."

[1580] 8. Gathering Feedback

[1581] The user provides feedback on the suggested outfits, including whether they like the outfits or don't like them.

[1582] Example: "A white shirt and leather shoes go together really well."

[1583] 9. Update the AI ​​model

[1584] The server fine-tunes the generative AI model based on the received feedback, improving the accuracy of the next outfit suggestion.

[1585] Example: Improve the model based on feedback to make suggestions that better match the user's preferences.

[1586] This system allows users to receive more appropriate outfit suggestions based on their emotions, making it easier to choose the outfit that will make them feel good throughout the day. It also has the advantage of promoting sustainable consumption by utilizing existing clothing lists.

[1587] The processing flow will be explained below.

[1588] Step 1:

[1589] A user uses a device to input information about the weather, appointments, and people they are meeting. For example, the user inputs "Today it's sunny and 18 degrees, and I'm meeting a friend," updating an existing clothing list of "white shirt, blue jeans, leather shoes."

[1590] Step 2:

[1591] The device activates an emotion engine and recognizes emotions from the user's facial expressions and voice. For example, if the user has an expression that indicates stress, the emotion engine will recognize this as "stress."

[1592] Step 3:

[1593] The device sends data including the input information and emotion information to the server. The sent data includes "weather information, event information, clothing list, emotion information," etc. An example of data is "{'weather': 'Sunny, 18°C', 'event': 'Meeting with a friend', 'clothing_list': ['Blue jeans', 'White shirt', 'Leather shoes'], 'emotion': 'Stress'}."

[1594] Step 4:

[1595] The server analyzes the user data received from the device, including weather, schedules, people to meet, existing clothing lists, and emotional information, and activates a generative AI model based on this data.

[1596] Step 5:

[1597] The server uses a generative AI model to generate outfit suggestions. The generative AI model considers the user's preferences, past feedback, and current emotional information to generate appropriate clothing combinations. For example, it may suggest, "If you're feeling stressed, we recommend a relaxed style."

[1598] Step 6:

[1599] The server references trend data (such as social media browsing results and purchasing data) and adds the latest trend items to the generated coordination suggestions. For example, "Add a red scarf to a white shirt and blue jeans as a trend."

[1600] Step 7:

[1601] The server then sends the final outfit recommendation to the device. The data includes specific clothing combinations and trend items. An example of the data is "{'recommendation': ['White shirt', 'Blue jeans', 'Leather shoes', 'Red scarf']}".

[1602] Step 8:

[1603] The terminal displays the received outfit suggestions to the user. The user can visually check the suggested outfits and use them as a reference for deciding on their style for the day. An example display might be "Today's recommended outfit: white shirt, blue jeans, leather shoes, red scarf."

[1604] Step 9:

[1605] The user provides feedback on the proposed outfit, including specific preferences and areas for improvement. For example, the user may provide feedback such as, "The combination of a white shirt and leather shoes is very good."

[1606] Step 10:

[1607] The device sends user feedback to a server, where the feedback data is stored and analyzed to improve the accuracy of the generative AI model.

[1608] Step 11:

[1609] The server fine-tunes the generative AI model based on the received feedback. This improves the accuracy of the next outfit suggestion and generates suggestions that are closer to the user's preferences. For example, reflecting the user's feedback, the server will continue to recommend a combination of a white shirt and leather shoes.

[1610] Example 2

[1611] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1612] Conventional fashion assistant systems have the problem of not being able to fully meet the user's needs because they do not take into account the user's emotions or real-time trend information. In addition, because they are unable to propose outfits that take the user's emotional state into account, the suggested styles may not match the user's mood or the situation. As a result, users tend to be dissatisfied with the outfits provided and have fewer opportunities to actually wear them.

[1613] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1614] In this invention, the server includes means for acquiring information on the weather, schedule, and people to meet input by the user, means for acquiring the user's existing clothing list, means for acquiring the user's facial expressions and voice and recognizing emotions, means for generating outfit suggestions using a generative AI model based on the acquired information and the recognized emotion information, means for adding trend items to the generated outfit suggestions by referring to trend data, and means for fine-tuning the generative AI model based on user feedback. This enables personalized outfit suggestions that take into account the user's emotions and real-time trend information.

[1615] "Weather information" refers to data entered by the user regarding the weather conditions for that day.

[1616] "Schedule" refers to information entered by the user about activities and events to be held that day.

[1617] "Information about people to meet" refers to information about people the user plans to meet on that day.

[1618] "Existing Clothing List" refers to a list of clothing owned by the user, including data registered with a particular application or device.

[1619] "Emotion information" refers to data that indicates the emotional state of the user as recognized from their facial expressions and voice.

[1620] "Server" refers to the computer system that receives and processes data, runs the generative AI model, obtains feedback, and fine-tunes the model.

[1621] A "generative AI model" refers to an artificial intelligence model that generates fashion coordination suggestions based on user input and emotional information.

[1622] "Outfit suggestions" refer to clothing combinations recommended based on the user's input information and emotions.

[1623] "Trend data" refers to information about the latest fashion trends and includes data collected from social media and purchasing data.

[1624] "Feedback" refers to user-provided ratings and comments on the proposed outfits.

[1625] "Fine-tuning" refers to the process of adjusting the parameters of a generative AI model based on received feedback to improve the accuracy of its suggestions.

[1626] Overall system configuration

[1627] This invention is a personal style assistant system that provides users with personalized fashion advice and encourages sustainable consumption. In particular, by adding an emotion engine that recognizes the user's emotions, it is possible to propose outfits that are more tailored to the user's individual needs.

[1628] Hardware and Software Configuration

[1629] Terminal

[1630] Users use devices such as smartphones and tablets. The devices are equipped with cameras and microphones that capture the user's facial expressions and voice. They also install applications and input information about the weather, their schedule, people they are meeting, and their existing clothing list.

[1631] server

[1632] The server is a high-performance computer system that receives and processes data and runs the generative AI model. The server can use Microsoft Azure's emotion analysis API as an emotion engine, which analyzes the user's emotional information and generates optimal outfit suggestions.

[1633] Generative AI Models

[1634] The generative AI model uses an advanced language model such as GPT-4, and the server uses this generative AI model to generate fashion coordination suggestions based on the user's input and emotional information.

[1635] Program processing

[1636] The device first acquires the user's input information (weather, schedule, information about people to meet, existing clothing list), as well as facial expressions and voice. The data acquired using the camera and microphone is analyzed by the emotion engine and sent to the server as emotion information.

[1637] Next, the server launches a generative AI model based on the received information. The generative AI model receives the following text data as a prompt:

[1638] "Today's weather is sunny and 18 degrees, plans include meeting a friend, and current emotion is stress. The user has the following clothing list: white shirt, blue jeans, leather shoes."

[1639] Based on this, the generative AI model generates coordination suggestions that take into account the user's preferences and trend data. As a specific example, the generative AI model might suggest "adding a red scarf to a white shirt, blue jeans, and leather shoes as a trend."

[1640] The generated outfit suggestions are sent back from the server to the device, which then displays them to the user through the application. The user can review the suggested outfits and decide on their style for the day. In addition, the user can provide feedback on the suggested outfits. For example, the user can leave a specific comment such as, "The combination of a white shirt and leather shoes is very good."

[1641] Finally, the server fine-tunes the generative AI model based on the received feedback, improving the accuracy of the next outfit suggestions and providing results that better match the user's preferences.

[1642] The system allows users to receive personalized outfit suggestions that take into account emotions and real-time trend information, and also promotes sustainable consumption.

[1643] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1644] Step 1:

[1645] The device receives input from the user about today's weather, plans, and people to meet. The user enters this data using text boxes and selection boxes in the application. For example, the user enters information like "Today it's sunny and 18 degrees, and I'm planning to meet a friend." The device then temporarily stores this information.

[1646] Step 2:

[1647] The device retrieves the user's existing clothing list. The user provides data by manually entering text or uploading photos of the clothing. For example, if information such as "white shirt, blue jeans, leather shoes" is entered, the device will store this data.

[1648] Step 3:

[1649] The device's camera and microphone are used to capture the user's facial and voice data. This data is captured in real time and processed by facial recognition software and voice analysis software. The emotion engine analyzes the user's emotional state (e.g., joy, stress) and extracts emotional information.

[1650] Step 4:

[1651] The device sends the weather, schedule, meeting information, existing clothing list, and emotion information acquired as JSON format data to the server. The input information is formatted as follows and sent to the server:

[1652] json

[1653] {

[1654] "weather": "Sunny, 18°C",

[1655] "event": "Meeting with a friend",

[1656] "clothing_list": ["Blue jeans", "White shirt", "Leather shoes"],

[1657] "emotion": "Stress"

[1658] }

[1659] Step 5:

[1660] The server processes the received information and launches a generative AI model, which receives the following prompt text and generates outfit suggestions based on it:

[1661] "Today's weather is sunny and 18 degrees, plans include meeting a friend, and current emotion is stress. The user has the following clothing list: white shirt, blue jeans, leather shoes."

[1662] Step 6:

[1663] The server uses a generative AI model to generate personalized outfit suggestions for each user. The generative AI model takes into account the user's preferences, emotional information, and trend data, and generates outfit suggestions as output. For example, a suggestion might be generated such as "Add a red scarf to a white shirt, blue jeans, and leather shoes, as a trend."

[1664] Step 7:

[1665] The server finally sends the generated coordination proposal to the device. The generated data is sent to the device in the following format:

[1666] json

[1667] {

[1668] "recommendation": ["White shirt", "Blue jeans", "Leather shoes", "Red scarf"]

[1669] }

[1670] Step 8:

[1671] The terminal displays the received outfit suggestions to the user. The user can visually check the suggested outfits on the application screen. For example, "Today's recommended outfit: white shirt, blue jeans, leather shoes, red scarf" is displayed.

[1672] Step 9:

[1673] Users provide feedback on the suggested outfits. Feedback is entered using an in-app evaluation form, and includes pros and cons of the suggested outfits and areas for improvement. For example, a specific comment such as "The combination of a white shirt and leather shoes is very good" can be entered.

[1674] Step 10:

[1675] The device sends the user's feedback to the server, which then formats the feedback as follows and sends it to the server:

[1676] json

[1677] {

[1678] "feedback": "The combination of a white shirt and leather shoes is very good"

[1679] }

[1680] Step 11:

[1681] The server fine-tunes the generative AI model based on the received feedback. The server analyzes the feedback and adjusts the parameters of the generative AI model to improve the accuracy of future outfit suggestions, thereby providing results that better match the user's preferences.

[1682] (Application example 2)

[1683] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1684] Conventional personal style assistants have been unable to provide coordination suggestions that take the user's emotions into account. As a result, they are unable to provide fashion suggestions based on the user's mood or emotions of the day, making it difficult to increase user satisfaction. In addition, there is a demand for more personalized suggestions that match the user's mood by providing fashion suggestions that take into account not only information such as the weather and schedule, but also the user's emotions.

[1685] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for recognizing the user's emotion using an emotion engine, means for transmitting the recognized emotion information to the server, and means for generating coordination suggestions using a generative AI model based on the information received by the server. This makes it possible to make fashion suggestions that take the user's emotions into consideration.

[1686] "Means for acquiring information entered by the user about the weather, schedule, and people to meet" refers to a function that allows the user to input information about the weather for the day, schedule, and people to meet into an electronic terminal, and the system acquires that information.

[1687] The "means for acquiring a list of the user's existing clothing" is a function that allows the user to register the clothing he or she owns in a list, and for the system to acquire that list.

[1688] The "means for transmitting acquired information to a server" is a function for transmitting information entered by the user and recognized emotion information to a server via the Internet.

[1689] The "means for recognizing the user's emotions using an emotion engine" is a function that detects the user's current emotional state by analyzing the user's facial expressions and voice.

[1690] The "means for transmitting the recognized emotion information to the server" is a function for transmitting the emotion information recognized by the emotion engine to the server.

[1691] "Means for generating coordination suggestions using a generative AI model based on information received by the server" refers to a function that activates a generative AI model based on information and emotional information received by the server from the user, and suggests optimal fashion coordination.

[1692] The "means for returning the generated coordination proposal from the server to the terminal" is a function for transmitting the fashion coordination proposal generated by the server to the user's terminal.

[1693] The "means for the terminal to display coordination suggestions to the user" is a function for visually displaying to the user fashion coordination suggestions received by the terminal from the server.

[1694] The "means for acquiring user feedback and transmitting it to the server" is a function that allows the user to input opinions and evaluations of the provided coordination proposals and transmit the feedback to the server.

[1695] "Means for the server to fine-tune the generative AI model based on feedback" refers to a function that makes adjustments to improve the accuracy of the generative AI model based on feedback information from users.

[1696] "The generative AI model generates outfit suggestions by taking into account the user's preferences, trend data, and emotional information" refers to the process in which the generative AI model combines the user's personal preferences, the latest fashion trend data, and the user's current emotional state to suggest optimal fashion outfits.

[1697] "Means for collecting trend data and updating the generative AI model based on that data" refers to a function in which the server collects fashion trend data from the internet and various databases, and uses that data to keep the algorithm of the generative AI model up to date.

[1698] The present invention provides a personal style assistant system that uses an emotion engine to suggest optimal outfits to users by utilizing information on the user's weather, schedule, people they are meeting, existing clothing list, and emotion information. By taking the user's emotions into consideration, the system can provide more personalized fashion suggestions and improve user satisfaction.

[1699] Hardware and software used

[1700] Hardware: Smartphone (iOS or Android)

[1701] software:

[1702] EmotionEngine (emotion recognition engine)

[1703] AICoordinator (AI model for suggesting outfits)

[1704] REST API (a server that supports HTTP requests)

[1705] The server uses the EmotionEngine to recognize emotions from the user's facial expressions and voice. It captures the user's face and voice using the smartphone camera and microphone, and analyzes the data. The analyzed emotional data is sent to the server along with the weather, schedule, meeting information, and existing clothing list entered by the user.

[1706] The server launches a generative AI model based on all the received data, and generates outfit suggestions based on the information obtained. The generative AI model comprehensively considers the user's preferences, trend data, and emotional information. For example, based on the information "Today is sunny and 18 degrees, and I plan to meet a friend," "A white shirt, blue jeans, and leather shoes," and "I'm feeling stressed," the model suggests a "relaxed style" of a white shirt, blue jeans, leather shoes, and a trendy red scarf.

[1707] The generated outfit suggestions are sent back from the server to the smartphone and visually displayed to the user on the smartphone screen. The user can use the suggested outfits as a reference to decide on their fashion for the day. Furthermore, the user can input feedback about the suggested outfits and send it to the server, which can then use that feedback to fine-tune the generative AI model and improve the accuracy of the next suggestions.

[1708] Examples of concrete examples and prompts

[1709] As an example, a user enters the following information:

[1710] Weather: Sunny and 18 degrees

[1711] Plans: Meeting with friends

[1712] Existing clothing list: White shirt, blue jeans, leather shoes

[1713] Emotional information: I'm feeling stressed

[1714] Example prompt sentence:

[1715] "Today is sunny and 18 degrees, and I'm meeting a friend. My existing clothing list includes a white shirt, blue jeans, and leather shoes. My current emotion is determined to be stress."

[1716] As described above, the present invention can improve user satisfaction by providing fashion suggestions that take the user's emotions into consideration. It also has the advantage of promoting sustainable consumption by utilizing existing clothing.

[1717] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1718] Step 1:

[1719] A user inputs information about the weather, plans, people to meet, and an existing clothing list into a smartphone. The smartphone has an interface that accepts user input, and this collects the necessary information. Examples of input data include "Today is sunny and 18 degrees. I plan to meet a friend," "White shirt, blue jeans, leather shoes."

[1720] Step 2:

[1721] Using the emotion engine, the smartphone device analyzes the user's facial expressions and voice to recognize emotions. Using data captured through the smartphone's camera and microphone, the emotion engine identifies emotions such as "stress." This recognized emotion information is used for further processing.

[1722] Step 3:

[1723] The device sends the collected weather, schedule, meeting information, existing clothing list, and recognized emotion information to the server in a JSON format, such as "{'weather': 'Sunny, 18°C', 'event': 'Meeting with a friend', 'clothing_list': ['Blue jeans', 'White shirt', 'Leather shoes'], 'emotion': 'Stress'}".

[1724] Step 4:

[1725] The server then activates a generative AI model based on the received data to generate outfit suggestions. The generative AI model uses an algorithm that takes into account the user's preferences, trend data, and emotional information. For example, suggestions might be generated in the form of "pick a relaxed style to reduce stress."

[1726] Step 5:

[1727] The server references the latest trend data collected (such as social media posts and purchasing data) and reflects it in the coordination suggestions. For example, "add a red scarf as a trend item" to the generated coordination.

[1728] Step 6:

[1729] The generated outfit suggestions are sent from the server to the smartphone device. The suggestions include specific clothing combinations and trendy items. For example, a "white shirt, blue jeans, leather shoes, and red scarf" combination might be suggested.

[1730] Step 7:

[1731] The device displays the generated outfit suggestions to the user, who can then check the suggested fashions on their smartphone screen and use them as a reference for deciding what to wear that day.

[1732] Step 8:

[1733] The user provides feedback on the proposed outfits, including their preferences and points that do not suit them, and inputs this feedback into the terminal.

[1734] Step 9:

[1735] The device sends user feedback to the server, which then fine-tunes the generative AI model based on the received feedback. This improves the accuracy of the next outfit suggestions, for example, by providing outfits that better match the user's preferences.

[1736] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1737] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1738] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1739] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1740] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1741] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1742] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1743] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1744] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1745] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1746] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1747] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1748] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1749] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1750] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1751] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1752] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1753] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1754] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1755] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1756] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1757] The following is further disclosed regarding the above embodiment.

[1758] (Claim 1)

[1759] A means for acquiring information input by a user about the weather, schedule, and people to meet;

[1760] means for obtaining a user's existing clothing list;

[1761] means for transmitting the acquired information to a server;

[1762] A means for generating coordination suggestions using a generative AI model based on the information received by the server;

[1763] means for returning the generated coordination proposal from the server to the terminal;

[1764] a means for displaying coordination suggestions to a user by the terminal;

[1765] a means for obtaining and transmitting user feedback to a server;

[1766] A system that includes a means for the server to fine-tune the generative AI model based on feedback.

[1767] (Claim 2)

[1768] The system of claim 1 , wherein the generative AI model generates outfit suggestions taking into account user preferences and trend data.

[1769] (Claim 3)

[1770] 10. The system of claim 1, wherein the server includes means for collecting trend data and updating the generative AI model based thereon.

[1771] "Example 1"

[1772] (Claim 1)

[1773] A means for acquiring information input by a user about the weather, schedule, and people to meet;

[1774] means for obtaining a user's existing clothing list;

[1775] means for transmitting the acquired information to a server;

[1776] A means for generating coordination suggestions using a generative AI model based on the information received by the server;

[1777] a means for configuring input prompts to the generative AI model;

[1778] A means for the server to generate coordination suggestions taking into consideration the user's preferences and trend data;

[1779] means for returning the generated coordination proposal from the server to the terminal;

[1780] a means for displaying coordination suggestions to a user by the terminal;

[1781] a means for obtaining and transmitting user feedback to a server;

[1782] A means for the server to fine-tune the generative AI model based on the feedback; and

[1783] The system includes a means for referring to trend data and adding the latest trend items to coordination suggestions.

[1784] (Claim 2)

[1785] 10. The system of claim 1, wherein the generative AI model generates outfit suggestions taking into account user preferences and trend data.

[1786] (Claim 3)

[1787] 10. The system of claim 1, wherein the server includes means for collecting trend data and updating the generative AI model based thereon.

[1788] "Application Example 1"

[1789] (Claim 1)

[1790] A means for acquiring information input by a user about the weather, schedule, and people to meet;

[1791] means for obtaining a user's existing clothing list;

[1792] means for transmitting the acquired information to a server;

[1793] A means for generating coordination suggestions using a generative AI model based on the information received by the server;

[1794] means for returning the generated coordination proposal from the server to the terminal;

[1795] a means for displaying coordination suggestions to a user by the terminal;

[1796] a means for obtaining and transmitting user feedback to a server;

[1797] A means for the server to fine-tune the generative AI model based on the feedback; and

[1798] A means for displaying coordination suggestions in real time when a user picks up a product in a physical store using smart glasses or a head-mounted display;

[1799] a means for generating a prompt sentence based on the user's input information and the product picked up by the terminal and transmitting the prompt sentence to the server;

[1800] A system including:

[1801] (Claim 2)

[1802] The system of claim 1 , wherein the generative AI model generates outfit suggestions taking into account user preferences and trend data.

[1803] (Claim 3)

[1804] 10. The system of claim 1, wherein the server includes means for collecting trend data and updating the generative AI model based thereon.

[1805] "Example 2: Combining Emotion Engines"

[1806] (Claim 1)

[1807] A means for acquiring information input by a user about the weather, schedule, and people to meet;

[1808] means for obtaining a user's existing clothing list;

[1809] A means for acquiring facial expressions and voice of a user and recognizing emotions;

[1810] means for transmitting the acquired information and the recognized emotion information to a server;

[1811] A means for generating coordination suggestions using a generative AI model based on the information and emotion information received by the server;

[1812] means for returning the generated coordination proposal from the server to the terminal;

[1813] a means for displaying coordination suggestions to a user by the terminal;

[1814] a means for obtaining and transmitting user feedback to a server;

[1815] A system that includes a means for the server to fine-tune the generative AI model based on feedback.

[1816] (Claim 2)

[1817] The system of claim 1 , wherein the generative AI model generates outfit suggestions by taking into account user preferences, emotional information, and trend data.

[1818] (Claim 3)

[1819] The system according to claim 1, further comprising means for adding trend items to the coordination suggestions generated by the server with reference to trend data.

[1820] "Application example 2 when combining emotion engines"

[1821] (Claim 1)

[1822] A means for acquiring information input by a user about the weather, schedule, and people to meet;

[1823] means for obtaining a user's existing clothing list;

[1824] means for transmitting the acquired information to a server;

[1825] means for recognizing a user's emotion by an emotion engine;

[1826] means for transmitting the recognized emotion information to a server;

[1827] A means for generating coordination suggestions using a generative AI model based on the information received by the server;

[1828] means for returning the generated coordination proposal from the server to the terminal;

[1829] a means for displaying coordination suggestions to a user by the terminal;

[1830] a means for obtaining and transmitting user feedback to a server;

[1831] A system that includes a means for the server to fine-tune the generative AI model based on feedback.

[1832] (Claim 2)

[1833] The system of claim 1 , wherein the generative AI model generates outfit suggestions by taking into account user preferences, trend data, and emotional information.

[1834] (Claim 3)

[1835] 10. The system of claim 1, wherein the server includes means for collecting trend data and updating the generative AI model based thereon. [Explanation of symbols]

[1836] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for acquiring information input by a user about the weather, schedule, and people to meet; means for obtaining a user's existing clothing list; means for transmitting the acquired information to a server; A means for generating coordination suggestions using a generative AI model based on the information received by the server; means for returning the generated coordination proposal from the server to the terminal; a means for displaying coordination suggestions to a user by the terminal; a means for obtaining and transmitting user feedback to a server; A system that includes a means for the server to fine-tune the generative AI model based on feedback.

2. The system of claim 1 , wherein the generative AI model generates outfit suggestions taking into account user preferences and trend data.

3. The system of claim 1 , wherein the server includes means for collecting trend data and updating the generative AI model based thereon.

Images