System

Abstract

A system is provided.SOLUTION: A system, comprising: means for obtaining weather information; means for obtaining user clothing data; means for generating using an artificial intelligence model to suggest combinations of clothing based on the obtained weather information and the user clothing data; means for notifying a user device of the suggestions; means for receiving feedback from a user; means for adjusting the artificial intelligence model based on the feedback; means for identifying unused clothing data and notifying the user of listing suggestions; and means for suggesting new clothing.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] Choosing what to wear every day is a time-consuming and laborious task for many people. Finding the right outfit for the weather is particularly difficult. Furthermore, many of the clothes in a closet are rarely worn, making their management cumbersome. Furthermore, when it comes to purchasing new clothes, appropriate suggestions are often not given. There is a need for a system that can comprehensively solve these problems and allow users to comfortably choose their outfits. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems with a system including a means for acquiring weather information, a means for acquiring user clothing data, a means for generating clothing combination suggestions using an artificial intelligence model based on the acquired weather information and the user clothing data, a means for notifying a user device of the suggestions, a means for receiving user feedback, a means for adjusting the artificial intelligence model based on the feedback, a means for identifying unused clothing data and notifying the user of suggestions for selling, and a means for suggesting new clothing. Specifically, the system uses weather information automatically acquired every morning to automatically acquire weather information, and the artificial intelligence proposes optimal outfits based on the user's closet data and transmits the suggestions to the user device. The system also utilizes user feedback to improve the accuracy of the suggestions. The system also identifies unused clothing in the closet and suggests items for sale, thereby streamlining closet management and meeting user needs through new clothing suggestions.

[0006] "Weather information" refers to information that indicates the weather conditions in a specific area, such as temperature, humidity, probability of precipitation, and wind speed.

[0007] "User clothing data" refers to detailed information such as the type, color, size, material, and image data of clothing owned by the user.

[0008] An "artificial intelligence model" is a computational model that uses machine learning algorithms to analyze a user's clothing data and weather information and suggest optimal clothing combinations.

[0009] The "generation means" is a means for executing a process for generating clothing combinations based on the weather information and the user's clothing data using an artificial intelligence model.

[0010] The "notification means" is a means having a communication function for transmitting the generated clothing combination to the user's device.

[0011] "Feedback" refers to information that indicates the user's evaluation or comments on the proposed clothing combinations.

[0012] The "adjustment means" is a means for updating the parameters of the artificial intelligence model based on feedback from users and executing a process to improve the accuracy of suggestions.

[0013] "Unused clothing data" refers to information about clothing that has not been used for a long period of time in the user's closet.

[0014] A "selling suggestion" is a suggestion that refers to a proposed process or method for selling unused clothing to other users.

[0015] "User Device" refers to an electronic device, such as a smartphone, tablet, or PC, that allows a user to receive notifications from the system and provide feedback. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0024] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0037] To implement this invention, a system using weather information, user clothing data, an AI model, a generation means, a notification means, feedback, an adjustment means, unused clothing data, listing suggestions, and a user device is required. This system aims to improve user convenience by suggesting appropriate outfits to users, streamlining closet management, and even suggesting new clothing.

[0038] Program processing explanation

[0039] The system's program mainly consists of the following steps: obtaining weather information, obtaining the user's clothing data, generating outfits, notifications, processing feedback, adjusting the AI ​​model, identifying unused clothing, suggesting items for sale, and suggesting new clothing.

[0040] Obtaining weather information

[0041] Server: Calls the weather API every morning at 6am to obtain the day's weather information (e.g. temperature, humidity, chance of precipitation). This information is stored in a database and used to generate outfits.

[0042] Obtaining user clothing data

[0043] Users: When registering for the first time and when purchasing new clothes, they register their clothing through the application, taking a photo of the clothing and entering details such as type, color, and size.

[0044] Terminal: Sends the entered information to the server, which stores it in a database.

[0045] Coordinate generation

[0046] Server: Based on the user's clothing data and weather information, an artificial intelligence model is used to generate the optimal outfit. At this stage, the machine learning algorithm takes into account the user's preferences and previous feedback.

[0047] notification

[0048] Server: Generates an image and description of the coordinated outfit, and sends it to the user's LINE account using the LINE API.

[0049] User: Receive suggested outfits via LINE to help with daily outfit selection.

[0050] Processing Feedback

[0051] User: Sends feedback on the proposed outfit, either "OK" or "NG," via LINE message.

[0052] Terminal: Sends a feedback message to the server.

[0053] Server: Stores the received feedback in a database and adjusts the parameters of the AI ​​model to improve the accuracy of the next suggestion.

[0054] Identifying unused clothing

[0055] Server: Analyzes the user's usage history and identifies clothes that have not been used for a long time. Based on this information, a list of unused clothes is created.

[0056] Listing proposal

[0057] Server: Proposes to users via LINE that they should sell unused clothing.

[0058] Users: If they accept the listing proposal, the listing process is completed with one click.

[0059] Server: Sends listing information to the Yahoo! Flea Market API and automatically processes the listing.

[0060] New clothing proposals

[0061] Server: Selects new clothing items based on weather information, fashion trends, and the contents of the user's closet.

[0062] Server: Providing information about selected new clothing items to users via LINE.

[0063] Specific examples

[0064] Here's a specific example. For example, when a user wakes up in the morning and checks LINE, they receive a message saying, "Today's weather is 15 degrees Celsius and 70% humidity. We recommend the following outfit," along with an image of an outfit suggestion: "Blue jacket, white shirt, black jeans." The user checks the suggestion and sends feedback saying "OK." This feedback information is sent to the server and reflected in the next suggestion.

[0065] Furthermore, the system identifies a red dress that the user has hardly worn, and sends a message on LINE saying, "It looks like you haven't worn this dress much. Would you like to list it for sale?" If the user agrees to the listing, it will be listed on Yahoo! Flea Market with one click.

[0066] Additionally, based on the user's style and recent trends, a new "yellow cardigan" will be suggested via LINE, and a message will be sent asking, "What do you think of this item?"

[0067] In this way, the system saves users the trouble of choosing their daily clothes and also efficiently supports closet management.

[0068] The processing flow will be explained below.

[0069] Step 1:

[0070] User: When registering for the first time, users enter their basic information (e.g., name, gender, height, weight, preferred style) into the application. At the same time, they also enter information about the clothing they own (e.g., type, color, size, material) along with a photo.

[0071] Step 2:

[0072] Terminal: The basic information and clothing data entered by the user is sent to the server via the Internet.

[0073] Step 3:

[0074] Server: The received user's basic information and clothing data are stored in a database, and the characteristics of each piece of clothing are analyzed and classified using an AI-based image recognition algorithm.

[0075] Step 4:

[0076] Server: Calls the weather API every morning at 6am to get the weather information for that day (e.g. temperature, humidity, chance of precipitation) for a specific region. Stores this information in a database.

[0077] Step 5:

[0078] Server: At a specified time (e.g., 7:00 a.m. every morning), weather data for the day is extracted based on each user's registered location information, and input into the AI ​​model along with the user's basic information and clothing data.

[0079] Step 6:

[0080] Server: The AI ​​model generates optimal outfits based on input weather data and the user's clothing data. During this process, machine learning algorithms take into account the user's past feedback and preferences.

[0081] Step 7:

[0082] Server: Creates an image and description of the generated outfit, and sends it to the user's LINE account using the LINE API.

[0083] Step 8:

[0084] User: Check the suggested outfits on LINE and send feedback by pressing the "OK" button if satisfied with the selection, or the "NG" button if not.

[0085] Step 9:

[0086] Terminal: Forwards the feedback messages sent by the user to the server.

[0087] Step 10:

[0088] Server: Stores the received feedback in a database and adjusts the parameters of the AI ​​model to improve the accuracy of the next outfit suggestion.

[0089] Step 11:

[0090] Server: Periodically analyzes the user's closet data and usage history to identify clothes that have not been worn for a long time. Based on this information, it creates a list of unused clothes.

[0091] Step 12:

[0092] Server: Sends suggestions to users via LINE about clothes that have not been used for a long time. The message explains why the item should be listed and provides instructions on how to list the item.

[0093] Step 13:

[0094] User: After reviewing the listing proposal, if they agree to the listing, they click the listing button on LINE, which automatically starts the listing process on Yahoo! Flea Market.

[0095] Step 14:

[0096] Terminal: Sends user clicks to the server.

[0097] Step 15:

[0098] Server: Based on the received listing request, the Yahoo! Flea Market API is called and the listing process is automatically carried out. A listing page is created based on the registered information.

[0099] Step 16:

[0100] Server: Analyzes weather information, fashion trends, and the contents of the user's closet to select appropriate new clothing items. Creates messages to suggest this information to the user.

[0101] Step 17:

[0102] Server: Sends new clothing suggestion messages to users via LINE. The messages include images, descriptions, and purchase links for the suggested new clothing. This allows users to easily purchase new clothes.

[0103] This allows the system to support users in choosing their daily outfits and provide efficient closet management, improving the accuracy of suggestions based on feedback and encouraging users to purchase new clothes or organize unused clothing.

[0104] Example 1

[0105] 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."

[0106] Conventional closet management systems have issues with insufficient clothing suggestions and closet management for users, and have low efficiency in suggesting daily outfits, identifying unused clothing, and suggesting items for sale. In particular, there is a need for systems that can generate appropriate outfits that reflect weather information and user preferences, improve the accuracy of AI models using user feedback, and suggest new clothing.

[0107] 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.

[0108] In this invention, the server includes means for acquiring weather information, means for acquiring user clothing data, means for generating clothing combination suggestions using an AI model based on the acquired weather information and the user clothing data, means for notifying the user device of the suggestions, means for receiving feedback from the user, means for adjusting the AI ​​model based on the feedback, means for identifying unused clothing data and notifying the user of suggestions for selling, means for suggesting new clothing, schedule management means for determining when to acquire weather information, means for controlling notifications based on the weather information and the state of the user device, and means for supporting the new registration of clothing purchased by the user based on the above means. This allows for efficient and accurate clothing suggestions to be made to the user, streamlining closet management, and enabling suggestions for selling unused clothing and new clothing to be made.

[0109] "Means of obtaining weather information" refers to the function of obtaining weather data such as temperature, humidity, and probability of precipitation at specified times using a weather API, etc.

[0110] "Means for obtaining user clothing data" refers to the function that allows the user to input photos and detailed information about clothing through the application, and then send it to the server and store it in a database.

[0111] "Generation method using artificial intelligence model" refers to a function that uses machine learning algorithms to suggest optimal clothing combinations based on the user's clothing data and weather information.

[0112] The "means for notifying the user device of the proposal" refers to a function for generating an image and description of the clothing combination and transmitting them to the user device using a communication means.

[0113] "Means for receiving feedback from users" refers to a function that allows users to send feedback such as "OK" or "NG" on proposed costumes.

[0114] "Means for adjusting the AI ​​model" refers to a function that adjusts the parameters of the AI ​​model based on feedback from users to improve the accuracy of future suggestions.

[0115] "Means for identifying unused clothing data and notifying users of listing suggestions" refers to a function that identifies clothing that has not been used for a long period of time from a database and makes suggestions to users based on that information.

[0116] "Means for suggesting new clothing" refers to a function that selects and suggests new clothing suitable for the user based on weather information, trend information, and the contents of the user's closet.

[0117] "Schedule management means for determining the timing of obtaining weather information" refers to a function that sets a regular schedule and manages the timing of obtaining weather information from the API at that time.

[0118] "Means for controlling notifications based on weather information and the status of the user device" refers to a function that determines weather information and the usage status of the user device, and notifies coordination suggestions at the optimal time.

[0119] "Means to support users in registering new clothing purchases" refers to a function that allows users to easily input and register information about newly purchased clothing through the application.

[0120] To implement this invention, a system using weather information, user clothing data, an AI model, a generation means, a notification means, a feedback means, an adjustment means, unused clothing data, listing suggestions, new clothing suggestions, and a user device is required. This system aims to improve user convenience by suggesting appropriate outfits to users, streamlining closet management, and suggesting new clothing.

[0121] The present invention is implemented using the following hardware and software.

[0122] Hardware

[0123] Server: Responsible for the central processing of the program. This is where data is stored, analyzed, and artificial intelligence models are trained and executed.

[0124] Terminal: The device operated by the user (smartphone, tablet, etc.) on which the application is installed.

[0125] User device: Serves as an interface with the user and is used to provide coordination suggestions and give feedback.

[0126] software

[0127] Weather API: Obtain weather information using the OpenWeather API, etc.

[0128] Artificial intelligence model: Generate coordinates using TensorFlow or PyTorch.

[0129] Database: Use a database system such as MySQL to store data.

[0130] Communication method: Sending and receiving data via REST API, notification and feedback processing using LINE API.

[0131] Specific examples

[0132] Specific examples are shown below.

[0133] Obtaining weather information

[0134] The server triggers a scheduled task every morning at 6:00, which retrieves the weather information for that day (e.g., temperature 15°C, humidity 70%, chance of precipitation 40%) from the OpenWeather API. This information is stored in a database in JSON format.

[0135] Obtaining user clothing data

[0136] A user registers a new shirt using a smartphone application. The user takes a photo of the shirt and enters the type (shirt), color (blue), and size (M). The device sends this data to the server via a REST API, and the server stores it in a database.

[0137] Coordinate generation

[0138] The server acquires the user's clothing data and weather information and inputs it into an artificial intelligence model using TensorFlow. For example, on a day when the temperature is 15 degrees, a coordination of "blue jacket, white shirt, black jeans" is generated. The results are saved as images and text.

[0139] notification

[0140] The generated outfit is sent to the user's device via the LINE API and displayed with the message, "Today's weather is 15 degrees Celsius and 70% humidity. We recommend the following outfit."

[0141] Processing Feedback

[0142] The user sends feedback via LINE, either "OK" or "NG." The device then sends this feedback to the server, which stores it in a database. This feedback is then reflected in the next proposal.

[0143] Identifying unused clothing

[0144] The server periodically analyzes the user's usage history and identifies clothing that has not been worn for a long time (e.g., a red dress). Based on this information, it creates a list of unused clothing and suggests items for sale to the user via LINE.

[0145] Listing proposal

[0146] When the user accepts the listing proposal, the server automatically processes the listing using the Yahoo! Flea Market API.

[0147] New clothing proposals

[0148] The server selects new clothing items (e.g., a yellow cardigan) based on weather information, fashion trends, and the contents of the user's closet, and suggests them via LINE.

[0149] Prompt Sentence Examples

[0150] "This system calls the OpenWeather API every morning at 6am to get the weather information for the day. Explain how it then matches this with the user's clothing data and uses TensorFlow to generate the optimal outfit."

[0151] In this way, the system saves users the trouble of choosing their daily clothes and efficiently supports closet management.

[0152] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0153] Step 1: Get weather information

[0154] The server triggers a scheduled task every morning at 6:00 AM. It calls a specified weather API (e.g., OpenWeather API) to "get weather information."

[0155] Input: Time (6 o'clock)

[0156] Output: Weather information for the day (Temperature 15°C, Humidity 70%, Chance of precipitation 40%)

[0157] Specific operation: The server issues an API request, analyzes the received JSON-formatted weather data, and stores the necessary information in a database.

[0158] Step 2: Obtaining the user's clothing data

[0159] When a user purchases new clothing, they use a smartphone application to take a photo of the clothing and enter details such as type (shirt), color (blue), and size (M).

[0160] Input: Clothing photos and details entered by the user

[0161] Output: Clothing data stored in a database

[0162] Specific operation: The device compresses the form input data and photo and sends them to the server via REST API. The server stores the received data in a database.

[0163] Step 3: Generate coordinates

[0164] The server receives the user's clothing data and weather information and inputs it into an AI model (e.g., TensorFlow), which then generates the optimal clothing combination.

[0165] Input: User clothing data stored in the database, weather information for the day

[0166] Output: Outfit suggestions (e.g. blue jacket, white shirt, black jeans)

[0167] What it does: The server runs a machine learning algorithm to generate outfits that take into account the user's preferences and past feedback. The results are stored in JSON format.

[0168] Step 4: Notification

[0169] The server notifies the user device of the generated coordination results as images and text via the LINE API.

[0170] Input: Coordination suggestions

[0171] Output: Coordination suggestions sent as LINE messages

[0172] Specific operation: The server sends the image URL and message to the LINE API, and the coordination is notified to the user's LINE account.

[0173] Step 5: Processing feedback

[0174] Users can provide feedback on the suggested outfits via LINE messages, either "OK" or "NG."

[0175] Input: User feedback (OK or NG)

[0176] Output: Feedback information stored in a database

[0177] Specific operation: The terminal sends a feedback message to the server, which stores the information in a database and uses it to adjust the parameters of the artificial intelligence model.

[0178] Step 6: Identify unused clothing

[0179] The server analyzes the user's usage history and identifies clothing that has not been used for a long time.

[0180] Input: User's clothing usage history

[0181] Output: List of unused clothing items

[0182] Specific behavior: The server periodically searches the database and lists any clothing that has not been used for more than a certain period of time (e.g., six months).

[0183] Step 7: Listing Proposal

[0184] The server suggests to users via LINE that they put up for sale unused clothing.

[0185] Input: Unused clothing list

[0186] Output: Listing suggestion message

[0187] Specific operation: The server uses the LINE API to send a message saying, "This dress doesn't seem to be worn much. Would you like to list it for sale?"

[0188] Step 8: New clothing suggestions

[0189] The server selects new clothing items based on weather information, fashion trends, and the contents of the user's closet.

[0190] Input: Weather information, trends, closet contents

[0191] Output: New clothing suggestions

[0192] Specific operation: The server analyzes the data based on the above information, selects new clothing items suitable for the user (e.g., a yellow cardigan), and suggests them via the LINE API.

[0193] Through the above processing steps, this system can save the user the trouble of choosing clothes on a daily basis and efficiently support closet management.

[0194] (Application example 1)

[0195] 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."

[0196] Previously, there were systems that suggested clothing coordination based on weather information and the user's clothing data. However, most of these systems required the user to manually input data, and only a limited number of systems utilized smart devices to provide real-time suggestions in a virtual space. Furthermore, the systems for effectively collecting user feedback and reflecting it in future suggestions were inadequate. Furthermore, efficient methods for managing closets, suggesting the sale of unused clothing, and suggesting new clothing were needed. Therefore, a comprehensive system that could significantly improve user convenience was needed.

[0197] 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.

[0198] In this invention, the server includes means for acquiring weather information, means for acquiring user clothing data, means for generating clothing combination suggestions using an AI model based on the acquired weather information and the user clothing data, means for notifying the user device of the suggestions, means for receiving feedback from the user, means for adjusting the AI ​​model based on the feedback, means for identifying unused clothing data and notifying the user of suggestions for clothing to be sold, means for suggesting new clothing, and means for the user to wear a smart device to check suggested outfits in a virtual space and provide feedback. This allows the user to receive outfit suggestions in a virtual space in real time, achieving efficient closet management and outfit suggestions.

[0199] "Weather information" is data about the weather conditions in a specific area, including temperature, humidity, probability of precipitation, and the like.

[0200] "User clothing data" is data including the type, color, size, and other related information of clothing owned by a user.

[0201] "Generation means" refers to a means for generating clothing combinations using an artificial intelligence model based on weather information and user clothing data.

[0202] "User Device" refers to electronic devices used by a User, such as computers, smartphones, tablets, and smart devices.

[0203] The "notification means" is a means for transmitting the generated coordination proposal to the user device.

[0204] "Feedback means" refers to a means for collecting evaluations and opinions from users and receiving that data.

[0205] The "adjustment means" is a means for adjusting the parameters of the artificial intelligence model based on feedback from the user.

[0206] "Unused clothing data" refers to information about clothing that a user has not worn within a specific period of time.

[0207] A "suggestion to sell" is a suggestion to sell unused clothing to other users.

[0208] "New clothing suggestions" refers to suggesting new clothing to the user based on the contents of the user's current closet and trend information.

[0209] "Smart devices" refers to interactive electronic devices such as internet-enabled glasses and head-mounted displays.

[0210] A "virtual space" is a three-dimensional virtual environment constructed using virtual reality technology, in which users can interact.

[0211] A "generative AI model" refers to a model that uses artificial intelligence technology to generate or suggest specific objects or situations.

[0212] A "prompt sentence" is a sentence that gives instructions to an artificial intelligence model and is an input sentence to perform a specific task.

[0213] To implement the present invention, a system is provided that uses the following hardware and software.

[0214] Hardware

[0215] Server: A high-performance server for acquiring weather information, managing the database, and generating and adjusting AI models.

[0216] User device: A device operated by a user, such as a smartphone, tablet, computer, smart glasses, or head-mounted display (e.g., Oculus Rift).

[0217] software

[0218] Weather API: API for obtaining weather information such as WeatherAPI.

[0219] LINE Messaging API: An API for notifying users of suggested outfits and collecting feedback.

[0220] Generative AI model: An artificial intelligence model built using a programming language such as Python.

[0221] Machine learning algorithms: Algorithms that use user feedback information to train and adjust models.

[0222] Data processing and calculation

[0223] The server calls the weather API every morning at 6am to obtain the day's weather information (e.g., temperature, humidity, and chance of precipitation) and stores it in a database. When users register for the first time or purchase new clothes, they register their clothing data through their smart devices. The server uses this information to generate optimal outfits using a generative AI model and notifies the user of the generated outfits using LINE's API. The user checks the suggested outfits on LINE and provides feedback. This feedback information is sent to the system, and the server uses it to adjust the artificial intelligence model.

[0224] The system also has a means of identifying unused clothing data and notifying users of suggestions for listing items. These suggestions are made via LINE, and if the user accepts, the listing process is automatically carried out using platforms such as Yahoo! Flea Market. New clothing suggestions are based on weather information, fashion trends, and the contents of the user's closet.

[0225] Specific examples

[0226] For example, when a user wakes up in the morning, launches the Virtual Closet Coordinator, and puts on the smart glasses, a message appears in the VR space saying, "Today's weather is 15 degrees Celsius and 70% humidity. We recommend the following outfit," along with a blue jacket, white shirt, and black jeans that can be virtually tried on. After virtually trying on the clothes, the user can give feedback of "OK," and this information will be reflected in the next outfit suggestions.

[0227] Prompt Sentence Examples

[0228] Enter the following information into the AI ​​model to generate the optimal outfit.

[0229] Weather information: Temperature is 15 degrees and humidity is 70%.

[0230] User clothing data: "Blue jacket, white shirt, black jeans."

[0231] As described above, this system reduces the effort required for users to choose their daily clothes and provides efficient support for closet management.

[0232] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0233] Step 1:

[0234] The server calls the weather API every morning at 6:00 to retrieve the weather information for that day. The retrieved weather information includes temperature, humidity, and probability of precipitation. This data is stored in a database and used for subsequent processing.

[0235] Input: Weather API call

[0236] Output: Weather information data (temperature, humidity, precipitation probability)

[0237] Step 2:

[0238] When a user first registers or purchases new clothes, they register their clothing data in the application via their smart device. They take a photo of the clothing and enter details such as type, color, and size. The entered information is sent from the device to the server and stored in a database.

[0239] Input: User's clothing data (photo, type, color, size)

[0240] Output: Updated clothing database

[0241] Step 3:

[0242] The server receives weather information and the user's clothing data and uses a generative AI model to generate optimal outfits. The generative AI model takes into account weather conditions and the user's past feedback information to suggest outfits.

[0243] Input: Weather information data, clothing data

[0244] Output: Coordination suggestions

[0245] Step 4:

[0246] The server generates an image and description of the coordinated outfit and sends it to the user's LINE account using the LINE API, allowing the user to receive the suggested coordinated outfit.

[0247] Input: Coordination suggestions

[0248] Output: LINE message (coordinate image and description)

[0249] Step 5:

[0250] The user checks the proposed outfits on LINE and sends feedback such as "OK" or "NG" via LINE message, which records the user's evaluation.

[0251] Input: Coordination suggestions, user feedback

[0252] Output: Feedback message

[0253] Step 6:

[0254] The device sends the feedback it receives to the server, which stores it in a database and uses it to adjust the parameters of the generative AI model to improve the accuracy of its next suggestions.

[0255] Input: User feedback

[0256] Output: An updated generative AI model

[0257] Step 7:

[0258] The server analyzes the user's usage history and identifies clothes that have not been used for a long time. Based on this data, it creates a list of unused clothes and notifies the user via LINE of suggestions to sell them.

[0259] Input: Clothing usage history

[0260] Output: Listing suggestion message

[0261] Step 8:

[0262] If the user accepts the listing proposal via LINE, the listing process is completed with one click. The server automatically completes the listing process using the Yahoo! Flea Market API.

[0263] Input: Accept the offer

[0264] Output: Listing procedure completed

[0265] Step 9:

[0266] The server selects new clothing items based on weather information, fashion trends, and the contents of the user's closet, and then suggests the selected new clothing items to the user via LINE.

[0267] Input: Weather information, trends, closet contents

[0268] Output: New clothing suggestion message

[0269] 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.

[0270] To implement this invention, a system using weather information, user clothing data, an AI model, a generation means, a notification means, a feedback, an adjustment means, unused clothing data, listing suggestions, new clothing suggestions, and an emotion recognition engine is required. This system suggests appropriate outfits to the user, streamlines closet management, and improves user convenience by suggesting new clothing, while also taking into account the user's emotional state.

[0271] Program processing explanation

[0272] The system's program mainly consists of the following steps: obtaining weather information, obtaining the user's clothing data, generating outfits, notifications, processing feedback, adjusting the AI ​​model, identifying unused clothing, suggesting items for sale, suggesting new clothing, and recognizing emotions.

[0273] Obtaining weather information

[0274] Server: Calls the weather API every morning at 6am to obtain the day's weather information (e.g. temperature, humidity, chance of precipitation). This information is stored in a database and used to generate outfits.

[0275] Obtaining user clothing data

[0276] Users: When registering for the first time and when purchasing new clothes, they register their clothing through the application, taking a photo of the clothing and entering details such as type, color, and size.

[0277] Terminal: Sends the entered information to the server, which stores it in a database.

[0278] Coordinate generation

[0279] Server: Based on the user's clothing data and weather information, an artificial intelligence model is used to generate the optimal outfit. At this stage, the machine learning algorithm takes into account the user's preferences and previous feedback.

[0280] notification

[0281] Server: Generates an image and description of the coordinated outfit, and sends it to the user's LINE account using the LINE API.

[0282] User: Check out the suggested outfits on LINE to help you choose your daily outfits.

[0283] Processing Feedback

[0284] User: Sends feedback on the proposed outfit, such as "OK" or "NG," via LINE message and grants permission to recognize facial expressions.

[0285] Device: Transfers the user's feedback message to the server, and at the same time activates the camera to capture facial expressions and send them to the emotion recognition engine.

[0286] Server: Stores the received feedback and emotion recognition data in a database and adjusts the parameters of the AI ​​model to improve the accuracy of the next outfit suggestion.

[0287] Identifying unused clothing

[0288] Server: Periodically analyzes the user's closet data and usage history to identify clothes that have not been worn for a long time. Based on this information, it creates a list of unused clothes.

[0289] Listing proposal

[0290] Server: Notifies users through LINE of suggestions to sell unused clothing. The message explains the reason for the recommendation and the steps to sell the clothing.

[0291] User: After reviewing the listing proposal, if they agree to the listing, they click the listing button on LINE, which automatically starts the listing process on Yahoo! Flea Market.

[0292] Terminal: Sends user clicks to the server.

[0293] Server: Based on the received listing request, the Yahoo! Flea Market API is called and the listing process is automatically carried out. A listing page is created based on the registered information.

[0294] New clothing proposals

[0295] Server: Analyzes weather information, fashion trends, and the contents of the user's closet to select appropriate new clothing items. Creates messages to suggest this information to the user.

[0296] Server: Sends new clothing suggestion messages to users via LINE. The messages include images, descriptions, and purchase links for the suggested new clothing. This allows users to easily purchase new clothes.

[0297] emotion recognition

[0298] User: Review the suggested outfit and allow the emotion recognition engine to analyze your facial expressions via the camera.

[0299] Device: Captures a picture of the user's facial expressions and sends them to an emotion recognition engine.

[0300] Server: The emotion recognition engine analyzes the user's facial expression data and recognizes the user's emotional state (e.g., satisfaction, confusion, disgust, etc.). Based on this emotional data, the AI ​​model will take the user's emotions into consideration when proposing the next outfit.

[0301] Specific examples

[0302] For example, when a user checks LINE in the morning, they receive a message saying, "Today's weather is 15 degrees Celsius and 70% humidity. We recommend the following outfit," along with an image of a suggested outfit: "Blue jacket, white shirt, black jeans." The user confirms the suggestion and sends feedback by saying "OK," along with facial expression data via the camera. This data is stored on the server and reflected in the next suggestion.

[0303] Furthermore, the system identifies a red dress that the user has hardly worn, and sends a message on LINE saying, "It looks like you haven't worn this dress much. Would you like to list it for sale?" If the user agrees to the listing, it will be listed on Yahoo! Flea Market with one click.

[0304] Additionally, based on the user's style and recent trends, a new "yellow cardigan" will be suggested via LINE, and a message will be sent asking, "What do you think of this item?"

[0305] In this way, the system reduces the effort required for users to choose their daily clothes and efficiently supports closet management. In addition, by utilizing emotion recognition, the system can provide more precise suggestions that take into account the user's emotions.

[0306] The processing flow will be explained below.

[0307] Step 1:

[0308] User: When registering for the first time, users enter their basic information (e.g., name, gender, height, weight, preferred style) into the application. At the same time, they register information about the clothing they own (e.g., type, color, size, material) along with a photo.

[0309] Terminal: Sends the entered information to the server.

[0310] Step 2:

[0311] Server: The received user's basic information and clothing data are stored in a database, and the characteristics of each piece of clothing are analyzed and classified using an AI-based image recognition algorithm.

[0312] Step 3:

[0313] Server: Calls the weather API every morning at 6am to obtain the day's weather information (e.g. temperature, humidity, chance of precipitation). This information is stored in a database and used to generate outfits.

[0314] Step 4:

[0315] Server: At a specified time (e.g., 7:00 a.m. every morning), weather data for the day is extracted based on each user's registered location information, and input into the AI ​​model along with the user's basic information and clothing data.

[0316] Step 5:

[0317] Server: The AI ​​model generates optimal outfits based on input weather data and the user's clothing data. During this process, machine learning algorithms take into account the user's past feedback and preferences.

[0318] Step 6:

[0319] Server: Creates an image and description of the generated outfit, and sends it to the user's LINE account using the LINE API.

[0320] Step 7:

[0321] User: Check the suggested outfits on LINE and send feedback by pressing the "OK" button if satisfied with the selection, or the "NG" button if not.

[0322] Step 8:

[0323] Device: Transfers the feedback message sent by the user to the server, and at the same time activates the camera to capture facial expressions and send them to the emotion recognition engine.

[0324] Step 9:

[0325] Server: Stores the received feedback and emotion recognition data in a database and adjusts the parameters of the AI ​​model to improve the accuracy of the next outfit suggestion.

[0326] Step 10:

[0327] Server: Periodically analyzes the user's closet data and usage history to identify clothes that have not been worn for a long time. Based on this information, a list of unused clothes is created.

[0328] Step 11:

[0329] Server: Notifies users through LINE of suggestions to sell unused clothing. The message explains the reason for the recommendation and the steps to sell the clothing.

[0330] Step 12:

[0331] User: After reviewing the listing proposal, if they agree to the listing, they click the listing button on LINE, which automatically starts the listing process on Yahoo! Flea Market.

[0332] Step 13:

[0333] Terminal: Sends user clicks to the server.

[0334] Step 14:

[0335] Server: Based on the received listing request, the Yahoo! Flea Market API is called and the listing process is automatically carried out. A listing page is created based on the registered information.

[0336] Step 15:

[0337] Server: Analyzes weather information, fashion trends, and the contents of the user's closet to select appropriate new clothing items. Creates messages to suggest this information to the user.

[0338] Step 16:

[0339] Server: Sends new clothing suggestion messages to users via LINE. The messages include images, descriptions, and purchase links for the suggested new clothing. This allows users to easily purchase new clothes.

[0340] Step 17:

[0341] User: Review the suggested outfit and allow the emotion recognition engine to analyze your facial expressions via the camera.

[0342] Step 18:

[0343] Device: Captures a picture of the user's facial expressions and sends them to an emotion recognition engine.

[0344] Step 19:

[0345] Server: The emotion recognition engine analyzes the user's facial expression data and recognizes the user's emotional state (e.g., satisfaction, confusion, disgust, etc.). Based on this emotional data, the AI ​​model will take the user's emotions into consideration when proposing the next outfit.

[0346] Specific examples

[0347] For example, when a user checks LINE in the morning, they receive a message saying, "Today's weather is 15 degrees Celsius and 70% humidity. We recommend the following outfit," along with an image of a suggested outfit: "Blue jacket, white shirt, black jeans." The user confirms the suggestion and sends feedback by saying "OK," along with facial expression data via the camera. This data is stored on the server and reflected in the next suggestion.

[0348] Furthermore, the system identifies a red dress that the user has hardly worn, and sends a message on LINE saying, "It looks like you haven't worn this dress much. Would you like to list it for sale?" If the user agrees to the listing, it will be listed on Yahoo! Flea Market with one click.

[0349] Additionally, based on the user's style and recent trends, a new "yellow cardigan" will be suggested via LINE, and a message will be sent asking, "What do you think of this item?"

[0350] In this way, the system reduces the effort required for users to choose their daily clothes and efficiently supports closet management. In addition, by utilizing emotion recognition, the system can provide more precise suggestions that take into account the user's emotions.

[0351] Example 2

[0352] 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."

[0353] Conventional outfit suggestion systems make suggestions based on weather information and the user's clothing data, but they do not consider the user's emotional state or suggest clothing that has not been worn for a long time. Furthermore, the AI ​​model is not adequately adjusted to effectively reflect user feedback, resulting in a problem of reduced suggestion accuracy. Furthermore, there is a need for a system that can make more accurate outfit suggestions by using user feedback and emotional state.

[0354] 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.

[0355] In this invention, the server includes means for acquiring weather information, means for acquiring user clothing data, means for generating clothing combination suggestions using an AI model based on the acquired weather information and the user clothing data, means for notifying the user device of the suggestions, means for receiving feedback from the user, means for adjusting the AI ​​model based on the feedback and the user's emotional state, means for analyzing facial expressions to recognize the user's emotional state, means for identifying unused clothing data and notifying the user of a suggestion for selling, and means for suggesting new clothing. This enables precise coordination suggestions that take the user's emotional state into consideration and also promotes the effective use of unused clothing.

[0356] "Weather information" refers to data about daily weather conditions, such as weather, temperature, humidity, and chance of precipitation.

[0357] "Clothing data" is information about clothing owned by a user, including the type, color, size, and other characteristics of the clothing.

[0358] An "artificial intelligence model" is a program based on machine learning algorithms that analyzes data and suggests optimal clothing combinations.

[0359] The "generation means" is a means for generating clothing combinations based on weather information and user clothing data using an artificial intelligence model.

[0360] The "notification means" is a means for notifying the user device of the generated clothing combinations and listing suggestions.

[0361] "Feedback" refers to information on the user's evaluation and reaction to the proposed clothing combinations.

[0362] The "adjustment means" is a means for changing the parameters of the artificial intelligence model based on feedback from the user and their emotional state, thereby improving the accuracy of the suggestions.

[0363] "Emotional state" refers to an emotional state such as satisfaction, confusion, or disgust that is recognized by analyzing the user's facial expression.

[0364] A "suggestion to sell" is a suggestion made to a user to encourage them to sell unused clothing.

[0365] "New clothing suggestions" are suggestions that introduce new clothing to the user based on the contents of the user's closet, weather information, and fashion information.

[0366] To implement this invention, a system using weather information, user clothing data, an AI model, a generation means, a notification means, a feedback, an adjustment means, unused clothing data, listing suggestions, new clothing suggestions, and an emotion recognition engine is required. This system suggests appropriate outfits to the user, streamlines closet management, and improves user convenience by suggesting new clothing, while also taking into account the user's emotional state.

[0367] The specific hardware and software for this system include a server, terminal, user device, weather API, LINE API, emotion recognition engine (e.g., Face API), and generative AI model (e.g., TensorFlow or PyTorch).

[0368] The server calls the weather API every morning at 6:00 to obtain the day's weather information (e.g., temperature, humidity, and chance of precipitation). This information is stored in the weather table of the database and used to generate outfits. Users also register their clothing through a smartphone app. They take photos of the clothing and enter detailed information such as type, color, and size. The device sends the entered information to the server in real time, and the server stores it in the clothing table of the database.

[0369] The server uses a generative AI model (for example, a model built with TensorFlow or PyTorch) to generate the optimal outfit based on the user's clothing data and the weather information for the day. The generated outfit is saved in the coordination_suggestions table in the database. This generated outfit is then generated as an image and description, and notified to the user's LINE account using the LINE API. The user can then check the presented outfit on LINE.

[0370] The user provides feedback on the proposed outfit. They reply with "OK" or "NG" via LINE message and give permission to capture their facial expression with the camera. The device then activates the camera, captures the user's facial expression, and sends the data in real time to the server. The feedback content is also sent. The server stores the received feedback and emotion recognition data in a database and adjusts the parameters of the artificial intelligence model based on the feedback and emotion recognition data. This improves the accuracy of the next outfit suggestion.

[0371] The server also periodically analyzes the user's closet data and usage history to identify clothing that has not been worn for a long time. It suggests selling unused clothing, and the user is notified via LINE. If the user accepts the listing, the listing process begins with one click. Once the server receives the user's acceptance, it calls the Yahoo! Flea Market API to automatically complete the listing process and create a listing page.

[0372] The server then analyzes weather information, fashion trends, and the contents of the user's closet to select appropriate new clothing. Based on this information, a suggestion message is created and sent to the user via LINE. The user receives the new clothing suggestion via LINE and can view an image, description, and purchase link of the suggested new clothing.

[0373] For example, when a user checks LINE in the morning, they receive a message saying, "Today's weather is 15 degrees Celsius and 70% humidity. We recommend the following outfit," along with an image of a suggested outfit: "Blue jacket, white shirt, black jeans." The user confirms the suggestion and sends feedback by saying "OK," along with facial expression data via the camera. This data is stored on the server and reflected in the next suggestion.

[0374] Furthermore, the system identifies a red dress that the user has rarely worn, and sends a LINE message saying, "It seems like you haven't worn this dress much. Would you like to list it for sale?" If the user accepts the listing, it will be listed on Yahoo! Flea Market with one click. Furthermore, based on the user's style and recent trends, the system also suggests a new "yellow cardigan" via LINE, sending a message saying, "What do you think of this item?"

[0375] An example prompt is:

[0376] "Please suggest an appropriate outfit based on the current weather and my clothing data. Also, please tell me how the AI ​​model used to make the suggestions is adjusted."

[0377] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0378] Step 1: Get weather information

[0379] Server: Calls the weather API every morning at 6am to obtain the day's weather information (e.g. temperature, humidity, probability of precipitation). The input is the response data from the weather API, which the server analyzes to extract the necessary information and saves in the weather table of the database. Specifically, it uses the API key to send an HTTP request and receives weather data in JSON format. After analysis, the temperature and humidity data is saved in the appropriate fields.

[0380] Step 2: Obtaining the user's clothing data

[0381] Users: When registering for the first time or when purchasing new clothes, they register their clothing items through a smartphone app. They input a photo of the clothing and detailed information such as type, color, and size.

[0382] Device: The entered information is sent in real time to the server, which then stores it in the clothing table in the database. Specifically, the user takes a photo of the clothing item in the app and enters the information in the text box. The device then sends this data to the server using an HTTP POST request.

[0383] Step 3: Generate coordinates

[0384] Server: Based on the user's clothing data and the weather information for the day, a generative AI model (for example, a model built with TensorFlow or PyTorch) is used to generate the optimal outfit. The input is the user's clothing data and weather information, and based on this, a machine learning algorithm processes and calculates the data to obtain the output. Specifically, it also takes into account previous user feedback and the preference patterns of other users. The results are saved in the coordination_suggestions table in the database.

[0385] Step 4: Notification

[0386] Server: Generates the generated outfit as an image and description, and uses this to notify the user's LINE account using the LINE API. The input is the outfit creation data, and the output is a message sent to the user's LINE account. Specifically, the server combines the image and text using a template message and sends an HTTP request to the LINE API.

[0387] Step 5: Processing feedback

[0388] User: Checks the proposed outfit on LINE and sends feedback of "OK" or "NG." The user also gives permission to capture their facial expression with the camera. The input is the user's feedback message and an image of their facial expression.

[0389] Device: Activates the camera, captures the user's facial expressions, and sends the data to the server in real time. It also sends feedback content in LINE messages. The output is the feedback data and an image of the facial expression. Specifically, it activates the camera API, obtains image data, and sends it to the server via an HTTP POST request.

[0390] Step 6: Tuning the AI ​​model

[0391] Server: Adjusts the parameters of the AI ​​model based on the received feedback and emotion recognition data. The input is the feedback data and emotion recognition data, and the output is the adjusted model parameters. Specifically, it updates the model weights using an optimization algorithm (e.g., gradient descent). This improves the accuracy of the next outfit suggestion.

[0392] Step 7: Identify unused clothing

[0393] Server: Periodically analyzes the user's closet data and usage history to identify clothes that have not been used for a long time. The input is closet data and usage history data, and the output is a list of unused clothes. Specifically, it uses a database query to extract items that have not been used for a certain period of time (e.g., six months).

[0394] Step 8: Listing Proposal

[0395] Server: Notifies the user via LINE of a suggestion to sell unused clothing. The input is the unused clothing data, and the output is a suggestion message. Specifically, a template message is used to describe the reason for recommending the item for sale and the listing procedure, and the notification is sent using the LINE API.

[0396] User: Checks the listing proposal and clicks the listing button on LINE if they wish to accept the listing. The input is the user's click, and the output is the listing acceptance data.

[0397] Terminal: The user's click operation is sent to the server. Specifically, the HTTP POST request is sent to the server along with the consent data.

[0398] Server: Based on the received listing request, the server calls the Yahoo! Flea Market API and automatically processes the listing. The input is the listing acceptance data, and the output is the created listing page. Specifically, the server calls the API, sends the necessary data, and saves the response.

[0399] Step 9: New clothing suggestions

[0400] Server: Analyzes the contents of the closet, weather information, and fashion information to select appropriate new clothing. The input is this data, and the output is a message suggesting new clothing. Specifically, it uses a data analysis algorithm to select the most suitable clothing item and sends the suggested message to the user using the LINE API.

[0401] User: Receives information about a new clothing item via LINE and clicks the purchase link to consider purchasing it. The input is the suggestion message, and the output is the click data of the purchase link.

[0402] Step 10: Emotion Recognition

[0403] User: Checks the proposed outfit and uses the camera to allow the emotion recognition engine to analyze the facial expressions. The input is the user's facial expression data, and the output is the emotional state data.

[0404] Device: Captures facial expressions and sends the data to the emotion recognition engine in real time. Specifically, it uses the camera API to obtain facial expression data and sends it via an HTTP POST request.

[0405] Server: The emotion recognition engine analyzes facial expression data and recognizes the user's emotional state. The output is emotional state data as the analysis result, which is used to improve the accuracy of the next outfit suggestion.

[0406] The above is the specific flow and operation of the program processing of this system.

[0407] (Application example 2)

[0408] 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."

[0409] Conventional closet management systems and outfit suggestion systems have limitations in improving user satisfaction because they do not fully consider the user's emotional state or in-store experience. Furthermore, it is necessary to provide more precise outfit suggestions by appropriately reflecting user feedback, but there has been no effective system for doing so.

[0410] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0411] In this invention, the server includes means for acquiring weather information, means for acquiring user clothing data, means for generating clothing combination suggestions using an AI model based on the acquired weather information and the user clothing data, means for notifying the user device of the suggestions, means for receiving feedback from the user, means for adjusting the AI ​​model based on the feedback, means for identifying unused clothing data and notifying the user of listing suggestions, means for suggesting new clothing, means for recognizing the user's emotional state, and means for the user device to be installed in a device installed in a physical store, means for recognizing the user's facial expression data, and means for adjusting the suggestions based on the acquired customer facial expression data. This enables more precise and personalized coordination suggestions that take the user's emotional state into consideration, improving the user experience in the physical store and enabling more efficient closet management.

[0412] "Weather information" refers to the temperature, humidity, chance of precipitation, and other weather-related data for that day.

[0413] "User clothing data" refers to detailed information about the type, color, size, and frequency of use of clothing owned by the user.

[0414] The "artificial intelligence model" is a machine learning algorithm that suggests optimal clothing combinations based on the user's clothing data and weather information.

[0415] A "generator" is a processing unit for generating suggested coordinates using an artificial intelligence model.

[0416] The "means for notifying" is a communication means for transmitting the generated coordination proposal to the user device.

[0417] The "means for receiving feedback" is a function for receiving opinions and evaluations of suggestions from users.

[0418] A "means for adjusting" is a process for optimizing an artificial intelligence model based on received feedback.

[0419] "Unused clothing data" is information about clothing that has not been used for a long period of time.

[0420] "Suggestion for sale" is a function that presents unused clothing to the user and suggests selling it on the online market.

[0421] The "emotional state" is a psychological state obtained by analyzing the facial expression data of the user.

[0422] "User Device" is a digital terminal that a user uses to receive suggested coordinates and provide feedback.

[0423] "Facial expression data" is image information of the user's face acquired using a camera, and is used for emotion recognition.

[0424] "In-store devices" are devices used to enhance the in-store experience, such as smart mirrors and tablets in fitting rooms.

[0425] System program generation

[0426] The system for implementing this invention mainly includes a means for acquiring weather information, a means for acquiring user clothing data, a generating means, a notifying means, a means for receiving feedback, an adjusting means, a means for identifying unused clothing data, a means for notifying of listing suggestions, a means for suggesting new clothing, a means for recognizing the emotional state of the user, a means for the user device to be installed in a device installed in a physical store, a means for recognizing facial expression data, and a means for adjusting suggestions.

[0427] Program processing explanation

[0428] 1. Obtaining weather information:

[0429] The server calls the weather API every morning at 6:00 to obtain the day's weather information (e.g., temperature, humidity, and probability of precipitation). The API used is provided by a general weather data provider. The obtained data is stored in a database and used when generating proposals.

[0430] 2. Get user clothing data:

[0431] Users register their clothing through the application when they first register or purchase new clothes. They take a photo of the clothing and enter its type, color, size, and other details. The device (such as a smartphone or tablet) then sends the entered data to the server and stores it in a database.

[0432] 3. Generation means:

[0433] The server generates optimal outfits based on the user's clothing data and weather information using an artificial intelligence model that includes machine learning algorithms that learn by taking into account the user's past feedback and emotional state.

[0434] 4. Means of notification:

[0435] The server generates an image and description of the coordinated outfit and notifies the user of the image and description on their device (e.g., a smartphone or tablet). The notification method can be, for example, the LINE API.

[0436] 5. How to receive feedback:

[0437] The user provides feedback on the proposed outfit, either "OK" or "NG." This feedback is sent to the server via the device. In addition, the user's facial expression is captured by a camera and sent to an emotion recognition engine (e.g., EmotionRecognizer).

[0438] 6. Adjustment methods:

[0439] Based on the received feedback and emotion recognition data, the server can adjust its artificial intelligence model to improve the accuracy of its next outfit suggestions.

[0440] Hardware and software used

[0441] Hardware: Smartphones, tablets, smart mirrors in brick-and-mortar stores

[0442] Software: Weather API, EmotionRecognizer, database management system, LINE API

[0443] Specific examples

[0444] When a user stands in front of a smart mirror in a physical store in the morning, a message appears saying, "Today's weather is 15 degrees Celsius and 70% humidity. We recommend the following outfit." Along with an image suggesting an outfit, the mirror suggests "a blue jacket, a white shirt, and black jeans."

[0445] The user reviews the suggestion and provides feedback, either "OK" or "NG," along with sending facial expression data via the camera. This data is stored on the server and reflected in the next suggestion.

[0446] Furthermore, the system identifies a red dress that the user has barely worn and displays a message saying, "It looks like you haven't worn this dress much. Would you like to list it for sale?" If the user agrees to the listing, it will be listed on an online marketplace with one click.

[0447] The user will also be notified of a new "yellow cardigan" suggestion based on their style and current trends, and will receive a message asking, "What do you think of this item?"

[0448] Example prompts for generative AI models

[0449] "Please suggest the best outfit based on the following information: user's clothing data, weather information, fashion information, and user's emotional state."

[0450] This system reduces the effort required for users to choose their daily outfits and efficiently supports closet management. Furthermore, by utilizing emotion recognition, it can improve user satisfaction.

[0451] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0452] Step 1:

[0453] The server calls the weather API every morning at 6:00 to obtain the weather information for that day. Specifically, it obtains data such as temperature, humidity, and probability of precipitation, which are then stored in a database. The input is data from the weather API, and the output is the weather information stored in the database.

[0454] Step 2:

[0455] Users register their clothing through the application when they first register or when they purchase new clothes. They take a photo of the clothing and enter detailed information such as type, color, size, and frequency of use. The device sends the entered data to the server and stores it in a database. The input is the clothing data entered by the user, and the output is the clothing information stored in the database.

[0456] Step 3:

[0457] The server uses an artificial intelligence model to generate optimal outfits based on the user's clothing data and weather information. The method used here is a machine learning algorithm. The input is clothing data stored in a database and weather information, and the output is the generated outfit.

[0458] Step 4:

[0459] The server generates an image and description of the coordinated outfit and notifies the user's device of this. The notification method uses LINE's API. The input is the coordinated outfit, and the output is a notification of the coordinated outfit sent to the user's device.

[0460] Step 5:

[0461] The user provides feedback on the proposed outfit, either "OK" or "NG." The feedback is sent to the server via the device. In addition, the user's facial expression is captured by a camera and sent to an emotion recognition engine. The input is the user's feedback and facial expression data, and the output is the feedback and emotion data stored on the server.

[0462] Step 6:

[0463] The server adjusts the AI ​​model based on the received feedback and emotion recognition data to improve the accuracy of the next outfit suggestion. Here, the machine learning algorithm learns from the feedback and emotion data and updates the model. The input is the feedback and emotion recognition data, and the output is the updated AI model.

[0464] Step 7:

[0465] The server periodically analyzes the user's closet data and usage history to identify clothes that have not been worn for a long time. Based on this information, it creates a list of unused clothes. The input is the user's closet data and usage history, and the output is a list of unused clothes.

[0466] Step 8:

[0467] The server notifies the user of suggestions for selling unused clothing. The recommendation, the reason for the recommendation, and the listing procedure are notified to the user via the LINE API. The input is a list of unused clothing, and the output is the suggestion sent to the user's device.

[0468] Step 9:

[0469] When the user agrees to the listing, they click the listing button on LINE. The device sends the user's click to the server, which calls the Yahoo! Flea Market API and automatically completes the listing process. The input is the user's approval to list the item, and the output is the listing page created on Yahoo! Flea Market.

[0470] Step 10:

[0471] The server analyzes weather information, fashion trends, and the contents of the user's closet to select appropriate new clothing items. The server notifies the user of new clothing suggestions via LINE. The input is weather information, fashion trends, and closet contents, and the output is new clothing suggestions sent to the user's device.

[0472] Step 11:

[0473] The user confirms the proposed outfit and allows the emotion recognition engine to analyze their facial expressions through the camera. The device captures the user's facial expression data and sends it to the emotion recognition engine. The input is the facial expression data, and the output is the emotional state analyzed by the emotion recognition engine.

[0474] 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.

[0475] 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.

[0476] 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.

[0477] [Second embodiment]

[0478] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0479] 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.

[0480] 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).

[0481] 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.

[0482] 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.

[0483] 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).

[0484] 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.

[0485] 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.

[0486] 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.

[0487] 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.

[0488] 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.

[0489] 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."

[0490] To implement this invention, a system using weather information, user clothing data, an AI model, a generation means, a notification means, feedback, an adjustment means, unused clothing data, listing suggestions, and a user device is required. This system aims to improve user convenience by suggesting appropriate outfits to users, streamlining closet management, and even suggesting new clothing.

[0491] Program processing explanation

[0492] The system's program mainly consists of the following steps: obtaining weather information, obtaining the user's clothing data, generating outfits, notifications, processing feedback, adjusting the AI ​​model, identifying unused clothing, suggesting items for sale, and suggesting new clothing.

[0493] Obtaining weather information

[0494] Server: Calls the weather API every morning at 6am to obtain the day's weather information (e.g. temperature, humidity, chance of precipitation). This information is stored in a database and used to generate outfits.

[0495] Obtaining user clothing data

[0496] Users: When registering for the first time and when purchasing new clothes, they register their clothing through the application, taking a photo of the clothing and entering details such as type, color, and size.

[0497] Terminal: Sends the entered information to the server, which stores it in a database.

[0498] Coordinate generation

[0499] Server: Based on the user's clothing data and weather information, an artificial intelligence model is used to generate the optimal outfit. At this stage, the machine learning algorithm takes into account the user's preferences and previous feedback.

[0500] notification

[0501] Server: Generates an image and description of the coordinated outfit, and sends it to the user's LINE account using the LINE API.

[0502] User: Receive suggested outfits via LINE to help with daily outfit selection.

[0503] Processing Feedback

[0504] User: Sends feedback on the proposed outfit, either "OK" or "NG," via LINE message.

[0505] Terminal: Sends a feedback message to the server.

[0506] Server: Stores the received feedback in a database and adjusts the parameters of the AI ​​model to improve the accuracy of the next suggestion.

[0507] Identifying unused clothing

[0508] Server: Analyzes the user's usage history and identifies clothes that have not been used for a long time. Based on this information, a list of unused clothes is created.

[0509] Listing proposal

[0510] Server: Proposes to users via LINE that they should sell unused clothing.

[0511] Users: If they accept the listing proposal, the listing process is completed with one click.

[0512] Server: Sends listing information to the Yahoo! Flea Market API and automatically processes the listing.

[0513] New clothing proposals

[0514] Server: Selects new clothing items based on weather information, fashion trends, and the contents of the user's closet.

[0515] Server: Providing information about selected new clothing items to users via LINE.

[0516] Specific examples

[0517] Here's a specific example. For example, when a user wakes up in the morning and checks LINE, they receive a message saying, "Today's weather is 15 degrees Celsius and 70% humidity. We recommend the following outfit," along with an image of an outfit suggestion: "Blue jacket, white shirt, black jeans." The user checks the suggestion and sends feedback saying "OK." This feedback information is sent to the server and reflected in the next suggestion.

[0518] Furthermore, the system identifies a red dress that the user has hardly worn, and sends a message on LINE saying, "It looks like you haven't worn this dress much. Would you like to list it for sale?" If the user agrees to the listing, it will be listed on Yahoo! Flea Market with one click.

[0519] Additionally, based on the user's style and recent trends, a new "yellow cardigan" will be suggested via LINE, and a message will be sent asking, "What do you think of this item?"

[0520] In this way, the system saves users the trouble of choosing their daily clothes and also efficiently supports closet management.

[0521] The processing flow will be explained below.

[0522] Step 1:

[0523] User: When registering for the first time, users enter their basic information (e.g., name, gender, height, weight, preferred style) into the application. At the same time, they also enter information about the clothing they own (e.g., type, color, size, material) along with a photo.

[0524] Step 2:

[0525] Terminal: The basic information and clothing data entered by the user is sent to the server via the Internet.

[0526] Step 3:

[0527] Server: The received user's basic information and clothing data are stored in a database, and the characteristics of each piece of clothing are analyzed and classified using an AI-based image recognition algorithm.

[0528] Step 4:

[0529] Server: Calls the weather API every morning at 6am to get the weather information for that day (e.g. temperature, humidity, chance of precipitation) for a specific region. Stores this information in a database.

[0530] Step 5:

[0531] Server: At a specified time (e.g., 7:00 a.m. every morning), weather data for the day is extracted based on each user's registered location information, and input into the AI ​​model along with the user's basic information and clothing data.

[0532] Step 6:

[0533] Server: The AI ​​model generates optimal outfits based on input weather data and the user's clothing data. During this process, machine learning algorithms take into account the user's past feedback and preferences.

[0534] Step 7:

[0535] Server: Creates an image and description of the generated outfit, and sends it to the user's LINE account using the LINE API.

[0536] Step 8:

[0537] User: Check the suggested outfits on LINE and send feedback by pressing the "OK" button if satisfied with the selection, or the "NG" button if not.

[0538] Step 9:

[0539] Terminal: Forwards the feedback messages sent by the user to the server.

[0540] Step 10:

[0541] Server: Stores the received feedback in a database and adjusts the parameters of the AI ​​model to improve the accuracy of the next outfit suggestion.

[0542] Step 11:

[0543] Server: Periodically analyzes the user's closet data and usage history to identify clothes that have not been worn for a long time. Based on this information, it creates a list of unused clothes.

[0544] Step 12:

[0545] Server: Sends suggestions to users via LINE about clothes that have not been used for a long time. The message explains why the item should be listed and provides instructions on how to list the item.

[0546] Step 13:

[0547] User: After reviewing the listing proposal, if they agree to the listing, they click the listing button on LINE, which automatically starts the listing process on Yahoo! Flea Market.

[0548] Step 14:

[0549] Terminal: Sends user clicks to the server.

[0550] Step 15:

[0551] Server: Based on the received listing request, the Yahoo! Flea Market API is called and the listing process is automatically carried out. A listing page is created based on the registered information.

[0552] Step 16:

[0553] Server: Analyzes weather information, fashion trends, and the contents of the user's closet to select appropriate new clothing items. Creates messages to suggest this information to the user.

[0554] Step 17:

[0555] Server: Sends new clothing suggestion messages to users via LINE. The messages include images, descriptions, and purchase links for the suggested new clothing. This allows users to easily purchase new clothes.

[0556] This allows the system to support users in choosing their daily outfits and provide efficient closet management, improving the accuracy of suggestions based on feedback and encouraging users to purchase new clothes or organize unused clothing.

[0557] Example 1

[0558] 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."

[0559] Conventional closet management systems have issues with insufficient clothing suggestions and closet management for users, and have low efficiency in suggesting daily outfits, identifying unused clothing, and suggesting items for sale. In particular, there is a need for systems that can generate appropriate outfits that reflect weather information and user preferences, improve the accuracy of AI models using user feedback, and suggest new clothing.

[0560] 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.

[0561] In this invention, the server includes means for acquiring weather information, means for acquiring user clothing data, means for generating clothing combination suggestions using an AI model based on the acquired weather information and the user clothing data, means for notifying the user device of the suggestions, means for receiving feedback from the user, means for adjusting the AI ​​model based on the feedback, means for identifying unused clothing data and notifying the user of suggestions for selling, means for suggesting new clothing, schedule management means for determining when to acquire weather information, means for controlling notifications based on the weather information and the state of the user device, and means for supporting the new registration of clothing purchased by the user based on the above means. This allows for efficient and accurate clothing suggestions to be made to the user, streamlining closet management, and enabling suggestions for selling unused clothing and new clothing to be made.

[0562] "Means of obtaining weather information" refers to the function of obtaining weather data such as temperature, humidity, and probability of precipitation at specified times using a weather API, etc.

[0563] "Means for obtaining user clothing data" refers to the function that allows the user to input photos and detailed information about clothing through the application, and then send it to the server and store it in a database.

[0564] "Generation method using artificial intelligence model" refers to a function that uses machine learning algorithms to suggest optimal clothing combinations based on the user's clothing data and weather information.

[0565] The "means for notifying the user device of the proposal" refers to a function for generating an image and description of the clothing combination and transmitting them to the user device using a communication means.

[0566] "Means for receiving feedback from users" refers to a function that allows users to send feedback such as "OK" or "NG" on proposed costumes.

[0567] "Means for adjusting the AI ​​model" refers to a function that adjusts the parameters of the AI ​​model based on feedback from users to improve the accuracy of future suggestions.

[0568] "Means for identifying unused clothing data and notifying users of listing suggestions" refers to a function that identifies clothing that has not been used for a long period of time from a database and makes suggestions to users based on that information.

[0569] "Means for suggesting new clothing" refers to a function that selects and suggests new clothing suitable for the user based on weather information, trend information, and the contents of the user's closet.

[0570] "Schedule management means for determining the timing of obtaining weather information" refers to a function that sets a regular schedule and manages the timing of obtaining weather information from the API at that time.

[0571] "Means for controlling notifications based on weather information and the status of the user device" refers to a function that determines weather information and the usage status of the user device, and notifies coordination suggestions at the optimal time.

[0572] "Means to support users in registering new clothing purchases" refers to a function that allows users to easily input and register information about newly purchased clothing through the application.

[0573] To implement this invention, a system using weather information, user clothing data, an AI model, a generation means, a notification means, a feedback means, an adjustment means, unused clothing data, listing suggestions, new clothing suggestions, and a user device is required. This system aims to improve user convenience by suggesting appropriate outfits to users, streamlining closet management, and suggesting new clothing.

[0574] The present invention is implemented using the following hardware and software.

[0575] Hardware

[0576] Server: Responsible for the central processing of the program. This is where data is stored, analyzed, and artificial intelligence models are trained and executed.

[0577] Terminal: The device operated by the user (smartphone, tablet, etc.) on which the application is installed.

[0578] User device: Serves as an interface with the user and is used to provide coordination suggestions and give feedback.

[0579] software

[0580] Weather API: Obtain weather information using the OpenWeather API, etc.

[0581] Artificial intelligence model: Generate coordinates using TensorFlow or PyTorch.

[0582] Database: Use a database system such as MySQL to store data.

[0583] Communication method: Sending and receiving data via REST API, notification and feedback processing using LINE API.

[0584] Specific examples

[0585] Specific examples are shown below.

[0586] Obtaining weather information

[0587] The server triggers a scheduled task every morning at 6:00, which retrieves the weather information for that day (e.g., temperature 15°C, humidity 70%, chance of precipitation 40%) from the OpenWeather API. This information is stored in a database in JSON format.

[0588] Obtaining user clothing data

[0589] A user registers a new shirt using a smartphone application. The user takes a photo of the shirt and enters the type (shirt), color (blue), and size (M). The device sends this data to the server via a REST API, and the server stores it in a database.

[0590] Coordinate generation

[0591] The server acquires the user's clothing data and weather information and inputs it into an artificial intelligence model using TensorFlow. For example, on a day when the temperature is 15 degrees, a coordination of "blue jacket, white shirt, black jeans" is generated. The results are saved as images and text.

[0592] notification

[0593] The generated outfit is sent to the user's device via the LINE API and displayed with the message, "Today's weather is 15 degrees Celsius and 70% humidity. We recommend the following outfit."

[0594] Processing Feedback

[0595] The user sends feedback via LINE, either "OK" or "NG." The device then sends this feedback to the server, which stores it in a database. This feedback is then reflected in the next proposal.

[0596] Identifying unused clothing

[0597] The server periodically analyzes the user's usage history and identifies clothing that has not been worn for a long time (e.g., a red dress). Based on this information, it creates a list of unused clothing and suggests items for sale to the user via LINE.

[0598] Listing proposal

[0599] When the user accepts the listing proposal, the server automatically processes the listing using the Yahoo! Flea Market API.

[0600] New clothing proposals

[0601] The server selects new clothing items (e.g., a yellow cardigan) based on weather information, fashion trends, and the contents of the user's closet, and suggests them via LINE.

[0602] Prompt Sentence Examples

[0603] "This system calls the OpenWeather API every morning at 6am to get the weather information for the day. Explain how it then matches this with the user's clothing data and uses TensorFlow to generate the optimal outfit."

[0604] In this way, the system saves users the trouble of choosing their daily clothes and efficiently supports closet management.

[0605] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0606] Step 1: Get weather information

[0607] The server triggers a scheduled task every morning at 6:00 AM. It calls a specified weather API (e.g., OpenWeather API) to "get weather information."

[0608] Input: Time (6 o'clock)

[0609] Output: Weather information for the day (Temperature 15°C, Humidity 70%, Chance of precipitation 40%)

[0610] Specific operation: The server issues an API request, analyzes the received JSON-formatted weather data, and stores the necessary information in a database.

[0611] Step 2: Obtaining the user's clothing data

[0612] When a user purchases new clothing, they use a smartphone application to take a photo of the clothing and enter details such as type (shirt), color (blue), and size (M).

[0613] Input: Clothing photos and details entered by the user

[0614] Output: Clothing data stored in a database

[0615] Specific operation: The device compresses the form input data and photo and sends them to the server via REST API. The server stores the received data in a database.

[0616] Step 3: Generate coordinates

[0617] The server receives the user's clothing data and weather information and inputs it into an AI model (e.g., TensorFlow), which then generates the optimal clothing combination.

[0618] Input: User clothing data stored in the database, weather information for the day

[0619] Output: Outfit suggestions (e.g. blue jacket, white shirt, black jeans)

[0620] What it does: The server runs a machine learning algorithm to generate outfits that take into account the user's preferences and past feedback. The results are stored in JSON format.

[0621] Step 4: Notification

[0622] The server notifies the user device of the generated coordination results as images and text via the LINE API.

[0623] Input: Coordination suggestions

[0624] Output: Coordination suggestions sent as LINE messages

[0625] Specific operation: The server sends the image URL and message to the LINE API, and the coordination is notified to the user's LINE account.

[0626] Step 5: Processing feedback

[0627] Users can provide feedback on the suggested outfits via LINE messages, either "OK" or "NG."

[0628] Input: User feedback (OK or NG)

[0629] Output: Feedback information stored in a database

[0630] Specific operation: The terminal sends a feedback message to the server, which stores the information in a database and uses it to adjust the parameters of the artificial intelligence model.

[0631] Step 6: Identify unused clothing

[0632] The server analyzes the user's usage history and identifies clothing that has not been used for a long time.

[0633] Input: User's clothing usage history

[0634] Output: List of unused clothing items

[0635] Specific behavior: The server periodically searches the database and lists any clothing that has not been used for more than a certain period of time (e.g., six months).

[0636] Step 7: Listing Proposal

[0637] The server suggests to users via LINE that they put up for sale unused clothing.

[0638] Input: Unused clothing list

[0639] Output: Listing suggestion message

[0640] Specific operation: The server uses the LINE API to send a message saying, "This dress doesn't seem to be worn much. Would you like to list it for sale?"

[0641] Step 8: New clothing suggestions

[0642] The server selects new clothing items based on weather information, fashion trends, and the contents of the user's closet.

[0643] Input: Weather information, trends, closet contents

[0644] Output: New clothing suggestions

[0645] Specific operation: The server analyzes the data based on the above information, selects new clothing items suitable for the user (e.g., a yellow cardigan), and suggests them via the LINE API.

[0646] Through the above processing steps, this system can save the user the trouble of choosing clothes on a daily basis and efficiently support closet management.

[0647] (Application example 1)

[0648] 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."

[0649] Previously, there were systems that suggested clothing coordination based on weather information and the user's clothing data. However, most of these systems required the user to manually input data, and only a limited number of systems utilized smart devices to provide real-time suggestions in a virtual space. Furthermore, the systems for effectively collecting user feedback and reflecting it in future suggestions were inadequate. Furthermore, efficient methods for managing closets, suggesting the sale of unused clothing, and suggesting new clothing were needed. Therefore, a comprehensive system that could significantly improve user convenience was needed.

[0650] 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.

[0651] In this invention, the server includes means for acquiring weather information, means for acquiring user clothing data, means for generating clothing combination suggestions using an AI model based on the acquired weather information and the user clothing data, means for notifying the user device of the suggestions, means for receiving feedback from the user, means for adjusting the AI ​​model based on the feedback, means for identifying unused clothing data and notifying the user of suggestions for clothing to be sold, means for suggesting new clothing, and means for the user to wear a smart device to check suggested outfits in a virtual space and provide feedback. This allows the user to receive outfit suggestions in a virtual space in real time, achieving efficient closet management and outfit suggestions.

[0652] "Weather information" is data about the weather conditions in a specific area, including temperature, humidity, probability of precipitation, and the like.

[0653] "User clothing data" is data including the type, color, size, and other related information of clothing owned by a user.

[0654] "Generation means" refers to a means for generating clothing combinations using an artificial intelligence model based on weather information and user clothing data.

[0655] "User Device" refers to electronic devices used by a User, such as computers, smartphones, tablets, and smart devices.

[0656] The "notification means" is a means for transmitting the generated coordination proposal to the user device.

[0657] "Feedback means" refers to a means for collecting evaluations and opinions from users and receiving that data.

[0658] The "adjustment means" is a means for adjusting the parameters of the artificial intelligence model based on feedback from the user.

[0659] "Unused clothing data" refers to information about clothing that a user has not worn within a specific period of time.

[0660] A "suggestion to sell" is a suggestion to sell unused clothing to other users.

[0661] "New clothing suggestions" refers to suggesting new clothing to the user based on the contents of the user's current closet and trend information.

[0662] "Smart devices" refers to interactive electronic devices such as internet-enabled glasses and head-mounted displays.

[0663] A "virtual space" is a three-dimensional virtual environment constructed using virtual reality technology, in which users can interact.

[0664] A "generative AI model" refers to a model that uses artificial intelligence technology to generate or suggest specific objects or situations.

[0665] A "prompt sentence" is a sentence that gives instructions to an artificial intelligence model and is an input sentence to perform a specific task.

[0666] To implement the present invention, a system is provided that uses the following hardware and software.

[0667] Hardware

[0668] Server: A high-performance server for acquiring weather information, managing the database, and generating and adjusting AI models.

[0669] User device: A device operated by a user, such as a smartphone, tablet, computer, smart glasses, or head-mounted display (e.g., Oculus Rift).

[0670] software

[0671] Weather API: API for obtaining weather information such as WeatherAPI.

[0672] LINE Messaging API: An API for notifying users of suggested outfits and collecting feedback.

[0673] Generative AI model: An artificial intelligence model built using a programming language such as Python.

[0674] Machine learning algorithms: Algorithms that use user feedback information to train and adjust models.

[0675] Data processing and calculation

[0676] The server calls the weather API every morning at 6am to obtain the day's weather information (e.g., temperature, humidity, and chance of precipitation) and stores it in a database. When users register for the first time or purchase new clothes, they register their clothing data through their smart devices. The server uses this information to generate optimal outfits using a generative AI model and notifies the user of the generated outfits using LINE's API. The user checks the suggested outfits on LINE and provides feedback. This feedback information is sent to the system, and the server uses it to adjust the artificial intelligence model.

[0677] The system also has a means of identifying unused clothing data and notifying users of suggestions for listing items. These suggestions are made via LINE, and if the user accepts, the listing process is automatically carried out using platforms such as Yahoo! Flea Market. New clothing suggestions are based on weather information, fashion trends, and the contents of the user's closet.

[0678] Specific examples

[0679] For example, when a user wakes up in the morning, launches the Virtual Closet Coordinator, and puts on the smart glasses, a message appears in the VR space saying, "Today's weather is 15 degrees Celsius and 70% humidity. We recommend the following outfit," along with a blue jacket, white shirt, and black jeans that can be virtually tried on. After virtually trying on the clothes, the user can give feedback of "OK," and this information will be reflected in the next outfit suggestions.

[0680] Prompt Sentence Examples

[0681] Enter the following information into the AI ​​model to generate the optimal outfit.

[0682] Weather information: Temperature is 15 degrees and humidity is 70%.

[0683] User clothing data: "Blue jacket, white shirt, black jeans."

[0684] As described above, this system reduces the effort required for users to choose their daily clothes and provides efficient support for closet management.

[0685] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0686] Step 1:

[0687] The server calls the weather API every morning at 6:00 to retrieve the weather information for that day. The retrieved weather information includes temperature, humidity, and probability of precipitation. This data is stored in a database and used for subsequent processing.

[0688] Input: Weather API call

[0689] Output: Weather information data (temperature, humidity, precipitation probability)

[0690] Step 2:

[0691] When a user first registers or purchases new clothes, they register their clothing data in the application via their smart device. They take a photo of the clothing and enter details such as type, color, and size. The entered information is sent from the device to the server and stored in a database.

[0692] Input: User's clothing data (photo, type, color, size)

[0693] Output: Updated clothing database

[0694] Step 3:

[0695] The server receives weather information and the user's clothing data and uses a generative AI model to generate optimal outfits. The generative AI model takes into account weather conditions and the user's past feedback information to suggest outfits.

[0696] Input: Weather information data, clothing data

[0697] Output: Coordination suggestions

[0698] Step 4:

[0699] The server generates an image and description of the coordinated outfit and sends it to the user's LINE account using the LINE API, allowing the user to receive the suggested coordinated outfit.

[0700] Input: Coordination suggestions

[0701] Output: LINE message (coordinate image and description)

[0702] Step 5:

[0703] The user checks the proposed outfits on LINE and sends feedback such as "OK" or "NG" via LINE message, which records the user's evaluation.

[0704] Input: Coordination suggestions, user feedback

[0705] Output: Feedback message

[0706] Step 6:

[0707] The device sends the feedback it receives to the server, which stores it in a database and uses it to adjust the parameters of the generative AI model to improve the accuracy of its next suggestions.

[0708] Input: User feedback

[0709] Output: An updated generative AI model

[0710] Step 7:

[0711] The server analyzes the user's usage history and identifies clothes that have not been used for a long time. Based on this data, it creates a list of unused clothes and notifies the user via LINE of suggestions to sell them.

[0712] Input: Clothing usage history

[0713] Output: Listing suggestion message

[0714] Step 8:

[0715] If the user accepts the listing proposal via LINE, the listing process is completed with one click. The server automatically completes the listing process using the Yahoo! Flea Market API.

[0716] Input: Accept the offer

[0717] Output: Listing procedure completed

[0718] Step 9:

[0719] The server selects new clothing items based on weather information, fashion trends, and the contents of the user's closet, and then suggests the selected new clothing items to the user via LINE.

[0720] Input: Weather information, trends, closet contents

[0721] Output: New clothing suggestion message

[0722] 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.

[0723] To implement this invention, a system using weather information, user clothing data, an AI model, a generation means, a notification means, a feedback, an adjustment means, unused clothing data, listing suggestions, new clothing suggestions, and an emotion recognition engine is required. This system suggests appropriate outfits to the user, streamlines closet management, and improves user convenience by suggesting new clothing, while also taking into account the user's emotional state.

[0724] Program processing explanation

[0725] The system's program mainly consists of the following steps: obtaining weather information, obtaining the user's clothing data, generating outfits, notifications, processing feedback, adjusting the AI ​​model, identifying unused clothing, suggesting items for sale, suggesting new clothing, and recognizing emotions.

[0726] Obtaining weather information

[0727] Server: Calls the weather API every morning at 6am to obtain the day's weather information (e.g. temperature, humidity, chance of precipitation). This information is stored in a database and used to generate outfits.

[0728] Obtaining user clothing data

[0729] Users: When registering for the first time and when purchasing new clothes, they register their clothing through the application, taking a photo of the clothing and entering details such as type, color, and size.

[0730] Terminal: Sends the entered information to the server, which stores it in a database.

[0731] Coordinate generation

[0732] Server: Based on the user's clothing data and weather information, an artificial intelligence model is used to generate the optimal outfit. At this stage, the machine learning algorithm takes into account the user's preferences and previous feedback.

[0733] notification

[0734] Server: Generates an image and description of the coordinated outfit, and sends it to the user's LINE account using the LINE API.

[0735] User: Check out the suggested outfits on LINE to help you choose your daily outfits.

[0736] Processing Feedback

[0737] User: Sends feedback on the proposed outfit, such as "OK" or "NG," via LINE message and grants permission to recognize facial expressions.

[0738] Device: Transfers the user's feedback message to the server, and at the same time activates the camera to capture facial expressions and send them to the emotion recognition engine.

[0739] Server: Stores the received feedback and emotion recognition data in a database and adjusts the parameters of the AI ​​model to improve the accuracy of the next outfit suggestion.

[0740] Identifying unused clothing

[0741] Server: Periodically analyzes the user's closet data and usage history to identify clothes that have not been worn for a long time. Based on this information, it creates a list of unused clothes.

[0742] Listing proposal

[0743] Server: Notifies users through LINE of suggestions to sell unused clothing. The message explains the reason for the recommendation and the steps to sell the clothing.

[0744] User: After reviewing the listing proposal, if they agree to the listing, they click the listing button on LINE, which automatically starts the listing process on Yahoo! Flea Market.

[0745] Terminal: Sends user clicks to the server.

[0746] Server: Based on the received listing request, the Yahoo! Flea Market API is called and the listing process is automatically carried out. A listing page is created based on the registered information.

[0747] New clothing proposals

[0748] Server: Analyzes weather information, fashion trends, and the contents of the user's closet to select appropriate new clothing items. Creates messages to suggest this information to the user.

[0749] Server: Sends new clothing suggestion messages to users via LINE. The messages include images, descriptions, and purchase links for the suggested new clothing. This allows users to easily purchase new clothes.

[0750] emotion recognition

[0751] User: Review the suggested outfit and allow the emotion recognition engine to analyze your facial expressions via the camera.

[0752] Device: Captures a picture of the user's facial expressions and sends them to an emotion recognition engine.

[0753] Server: The emotion recognition engine analyzes the user's facial expression data and recognizes the user's emotional state (e.g., satisfaction, confusion, disgust, etc.). Based on this emotional data, the AI ​​model will take the user's emotions into consideration when proposing the next outfit.

[0754] Specific examples

[0755] For example, when a user checks LINE in the morning, they receive a message saying, "Today's weather is 15 degrees Celsius and 70% humidity. We recommend the following outfit," along with an image of a suggested outfit: "Blue jacket, white shirt, black jeans." The user confirms the suggestion and sends feedback by saying "OK," along with facial expression data via the camera. This data is stored on the server and reflected in the next suggestion.

[0756] Furthermore, the system identifies a red dress that the user has hardly worn, and sends a message on LINE saying, "It looks like you haven't worn this dress much. Would you like to list it for sale?" If the user agrees to the listing, it will be listed on Yahoo! Flea Market with one click.

[0757] Additionally, based on the user's style and recent trends, a new "yellow cardigan" will be suggested via LINE, and a message will be sent asking, "What do you think of this item?"

[0758] In this way, the system reduces the effort required for users to choose their daily clothes and efficiently supports closet management. In addition, by utilizing emotion recognition, the system can provide more precise suggestions that take into account the user's emotions.

[0759] The processing flow will be explained below.

[0760] Step 1:

[0761] User: When registering for the first time, users enter their basic information (e.g., name, gender, height, weight, preferred style) into the application. At the same time, they register information about the clothing they own (e.g., type, color, size, material) along with a photo.

[0762] Terminal: Sends the entered information to the server.

[0763] Step 2:

[0764] Server: The received user's basic information and clothing data are stored in a database, and the characteristics of each piece of clothing are analyzed and classified using an AI-based image recognition algorithm.

[0765] Step 3:

[0766] Server: Calls the weather API every morning at 6am to obtain the day's weather information (e.g. temperature, humidity, chance of precipitation). This information is stored in a database and used to generate outfits.

[0767] Step 4:

[0768] Server: At a specified time (e.g., 7:00 a.m. every morning), weather data for the day is extracted based on each user's registered location information, and input into the AI ​​model along with the user's basic information and clothing data.

[0769] Step 5:

[0770] Server: The AI ​​model generates optimal outfits based on input weather data and the user's clothing data. During this process, machine learning algorithms take into account the user's past feedback and preferences.

[0771] Step 6:

[0772] Server: Creates an image and description of the generated outfit, and sends it to the user's LINE account using the LINE API.

[0773] Step 7:

[0774] User: Check the suggested outfits on LINE and send feedback by pressing the "OK" button if satisfied with the selection, or the "NG" button if not.

[0775] Step 8:

[0776] Device: Transfers the feedback message sent by the user to the server, and at the same time activates the camera to capture facial expressions and send them to the emotion recognition engine.

[0777] Step 9:

[0778] Server: Stores the received feedback and emotion recognition data in a database and adjusts the parameters of the AI ​​model to improve the accuracy of the next outfit suggestion.

[0779] Step 10:

[0780] Server: Periodically analyzes the user's closet data and usage history to identify clothes that have not been worn for a long time. Based on this information, a list of unused clothes is created.

[0781] Step 11:

[0782] Server: Notifies users through LINE of suggestions to sell unused clothing. The message explains the reason for the recommendation and the steps to sell the clothing.

[0783] Step 12:

[0784] User: After reviewing the listing proposal, if they agree to the listing, they click the listing button on LINE, which automatically starts the listing process on Yahoo! Flea Market.

[0785] Step 13:

[0786] Terminal: Sends user clicks to the server.

[0787] Step 14:

[0788] Server: Based on the received listing request, the Yahoo! Flea Market API is called and the listing process is automatically carried out. A listing page is created based on the registered information.

[0789] Step 15:

[0790] Server: Analyzes weather information, fashion trends, and the contents of the user's closet to select appropriate new clothing items. Creates messages to suggest this information to the user.

[0791] Step 16:

[0792] Server: Sends new clothing suggestion messages to users via LINE. The messages include images, descriptions, and purchase links for the suggested new clothing. This allows users to easily purchase new clothes.

[0793] Step 17:

[0794] User: Review the suggested outfit and allow the emotion recognition engine to analyze your facial expressions via the camera.

[0795] Step 18:

[0796] Device: Captures a picture of the user's facial expressions and sends them to an emotion recognition engine.

[0797] Step 19:

[0798] Server: The emotion recognition engine analyzes the user's facial expression data and recognizes the user's emotional state (e.g., satisfaction, confusion, disgust, etc.). Based on this emotional data, the AI ​​model will take the user's emotions into consideration when proposing the next outfit.

[0799] Specific examples

[0800] For example, when a user checks LINE in the morning, they receive a message saying, "Today's weather is 15 degrees Celsius and 70% humidity. We recommend the following outfit," along with an image of a suggested outfit: "Blue jacket, white shirt, black jeans." The user confirms the suggestion and sends feedback by saying "OK," along with facial expression data via the camera. This data is stored on the server and reflected in the next suggestion.

[0801] Furthermore, the system identifies a red dress that the user has hardly worn, and sends a message on LINE saying, "It looks like you haven't worn this dress much. Would you like to list it for sale?" If the user agrees to the listing, it will be listed on Yahoo! Flea Market with one click.

[0802] Additionally, based on the user's style and recent trends, a new "yellow cardigan" will be suggested via LINE, and a message will be sent asking, "What do you think of this item?"

[0803] In this way, the system reduces the effort required for users to choose their daily clothes and efficiently supports closet management. In addition, by utilizing emotion recognition, the system can provide more precise suggestions that take into account the user's emotions.

[0804] Example 2

[0805] 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."

[0806] Conventional outfit suggestion systems make suggestions based on weather information and the user's clothing data, but they do not consider the user's emotional state or suggest clothing that has not been worn for a long time. Furthermore, the AI ​​model is not adequately adjusted to effectively reflect user feedback, resulting in a problem of reduced suggestion accuracy. Furthermore, there is a need for a system that can make more accurate outfit suggestions by using user feedback and emotional state.

[0807] 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.

[0808] In this invention, the server includes means for acquiring weather information, means for acquiring user clothing data, means for generating clothing combination suggestions using an AI model based on the acquired weather information and the user clothing data, means for notifying the user device of the suggestions, means for receiving feedback from the user, means for adjusting the AI ​​model based on the feedback and the user's emotional state, means for analyzing facial expressions to recognize the user's emotional state, means for identifying unused clothing data and notifying the user of a suggestion for selling, and means for suggesting new clothing. This enables precise coordination suggestions that take the user's emotional state into consideration and also promotes the effective use of unused clothing.

[0809] "Weather information" refers to data about daily weather conditions, such as weather, temperature, humidity, and chance of precipitation.

[0810] "Clothing data" is information about clothing owned by a user, including the type, color, size, and other characteristics of the clothing.

[0811] An "artificial intelligence model" is a program based on machine learning algorithms that analyzes data and suggests optimal clothing combinations.

[0812] The "generation means" is a means for generating clothing combinations based on weather information and user clothing data using an artificial intelligence model.

[0813] The "notification means" is a means for notifying the user device of the generated clothing combinations and listing suggestions.

[0814] "Feedback" refers to information on the user's evaluation and reaction to the proposed clothing combinations.

[0815] The "adjustment means" is a means for changing the parameters of the artificial intelligence model based on feedback from the user and their emotional state, thereby improving the accuracy of the suggestions.

[0816] "Emotional state" refers to an emotional state such as satisfaction, confusion, or disgust that is recognized by analyzing the user's facial expression.

[0817] A "suggestion to sell" is a suggestion made to a user to encourage them to sell unused clothing.

[0818] "New clothing suggestions" are suggestions that introduce new clothing to the user based on the contents of the user's closet, weather information, and fashion information.

[0819] To implement this invention, a system using weather information, user clothing data, an AI model, a generation means, a notification means, a feedback, an adjustment means, unused clothing data, listing suggestions, new clothing suggestions, and an emotion recognition engine is required. This system suggests appropriate outfits to the user, streamlines closet management, and improves user convenience by suggesting new clothing, while also taking into account the user's emotional state.

[0820] The specific hardware and software for this system include a server, terminal, user device, weather API, LINE API, emotion recognition engine (e.g., Face API), and generative AI model (e.g., TensorFlow or PyTorch).

[0821] The server calls the weather API every morning at 6:00 to obtain the day's weather information (e.g., temperature, humidity, and chance of precipitation). This information is stored in the weather table of the database and used to generate outfits. Users also register their clothing through a smartphone app. They take photos of the clothing and enter detailed information such as type, color, and size. The device sends the entered information to the server in real time, and the server stores it in the clothing table of the database.

[0822] The server uses a generative AI model (for example, a model built with TensorFlow or PyTorch) to generate the optimal outfit based on the user's clothing data and the weather information for the day. The generated outfit is saved in the coordination_suggestions table in the database. This generated outfit is then generated as an image and description, and notified to the user's LINE account using the LINE API. The user can then check the presented outfit on LINE.

[0823] The user provides feedback on the proposed outfit. They reply with "OK" or "NG" via LINE message and give permission to capture their facial expression with the camera. The device then activates the camera, captures the user's facial expression, and sends the data in real time to the server. The feedback content is also sent. The server stores the received feedback and emotion recognition data in a database and adjusts the parameters of the artificial intelligence model based on the feedback and emotion recognition data. This improves the accuracy of the next outfit suggestion.

[0824] The server also periodically analyzes the user's closet data and usage history to identify clothing that has not been worn for a long time. It suggests selling unused clothing, and the user is notified via LINE. If the user accepts the listing, the listing process begins with one click. Once the server receives the user's acceptance, it calls the Yahoo! Flea Market API to automatically complete the listing process and create a listing page.

[0825] The server then analyzes weather information, fashion trends, and the contents of the user's closet to select appropriate new clothing. Based on this information, a suggestion message is created and sent to the user via LINE. The user receives the new clothing suggestion via LINE and can view an image, description, and purchase link of the suggested new clothing.

[0826] For example, when a user checks LINE in the morning, they receive a message saying, "Today's weather is 15 degrees Celsius and 70% humidity. We recommend the following outfit," along with an image of a suggested outfit: "Blue jacket, white shirt, black jeans." The user confirms the suggestion and sends feedback by saying "OK," along with facial expression data via the camera. This data is stored on the server and reflected in the next suggestion.

[0827] Furthermore, the system identifies a red dress that the user has rarely worn, and sends a LINE message saying, "It seems like you haven't worn this dress much. Would you like to list it for sale?" If the user accepts the listing, it will be listed on Yahoo! Flea Market with one click. Furthermore, based on the user's style and recent trends, the system also suggests a new "yellow cardigan" via LINE, sending a message saying, "What do you think of this item?"

[0828] An example prompt is:

[0829] "Please suggest an appropriate outfit based on the current weather and my clothing data. Also, please tell me how the AI ​​model used to make the suggestions is adjusted."

[0830] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0831] Step 1: Get weather information

[0832] Server: Calls the weather API every morning at 6am to obtain the day's weather information (e.g. temperature, humidity, probability of precipitation). The input is the response data from the weather API, which the server analyzes to extract the necessary information and saves in the weather table of the database. Specifically, it uses the API key to send an HTTP request and receives weather data in JSON format. After analysis, the temperature and humidity data is saved in the appropriate fields.

[0833] Step 2: Obtaining the user's clothing data

[0834] Users: When registering for the first time or when purchasing new clothes, they register their clothing items through a smartphone app. They input a photo of the clothing and detailed information such as type, color, and size.

[0835] Device: The entered information is sent in real time to the server, which then stores it in the clothing table in the database. Specifically, the user takes a photo of the clothing item in the app and enters the information in the text box. The device then sends this data to the server using an HTTP POST request.

[0836] Step 3: Generate coordinates

[0837] Server: Based on the user's clothing data and the weather information for the day, a generative AI model (for example, a model built with TensorFlow or PyTorch) is used to generate the optimal outfit. The input is the user's clothing data and weather information, and based on this, a machine learning algorithm processes and calculates the data to obtain the output. Specifically, it also takes into account previous user feedback and the preference patterns of other users. The results are saved in the coordination_suggestions table in the database.

[0838] Step 4: Notification

[0839] Server: Generates the generated outfit as an image and description, and uses this to notify the user's LINE account using the LINE API. The input is the outfit creation data, and the output is a message sent to the user's LINE account. Specifically, the server combines the image and text using a template message and sends an HTTP request to the LINE API.

[0840] Step 5: Processing feedback

[0841] User: Checks the proposed outfit on LINE and sends feedback of "OK" or "NG." The user also gives permission to capture their facial expression with the camera. The input is the user's feedback message and an image of their facial expression.

[0842] Device: Activates the camera, captures the user's facial expressions, and sends the data to the server in real time. It also sends feedback content in LINE messages. The output is the feedback data and an image of the facial expression. Specifically, it activates the camera API, obtains image data, and sends it to the server via an HTTP POST request.

[0843] Step 6: Tuning the AI ​​model

[0844] Server: Adjusts the parameters of the AI ​​model based on the received feedback and emotion recognition data. The input is the feedback data and emotion recognition data, and the output is the adjusted model parameters. Specifically, it updates the model weights using an optimization algorithm (e.g., gradient descent). This improves the accuracy of the next outfit suggestion.

[0845] Step 7: Identify unused clothing

[0846] Server: Periodically analyzes the user's closet data and usage history to identify clothes that have not been used for a long time. The input is closet data and usage history data, and the output is a list of unused clothes. Specifically, it uses a database query to extract items that have not been used for a certain period of time (e.g., six months).

[0847] Step 8: Listing Proposal

[0848] Server: Notifies the user via LINE of a suggestion to sell unused clothing. The input is the unused clothing data, and the output is a suggestion message. Specifically, a template message is used to describe the reason for recommending the item for sale and the listing procedure, and the notification is sent using the LINE API.

[0849] User: Checks the listing proposal and clicks the listing button on LINE if they wish to accept the listing. The input is the user's click, and the output is the listing acceptance data.

[0850] Terminal: The user's click operation is sent to the server. Specifically, the HTTP POST request is sent to the server along with the consent data.

[0851] Server: Based on the received listing request, the server calls the Yahoo! Flea Market API and automatically processes the listing. The input is the listing acceptance data, and the output is the created listing page. Specifically, the server calls the API, sends the necessary data, and saves the response.

[0852] Step 9: New clothing suggestions

[0853] Server: Analyzes the contents of the closet, weather information, and fashion information to select appropriate new clothing. The input is this data, and the output is a message suggesting new clothing. Specifically, it uses a data analysis algorithm to select the most suitable clothing item and sends the suggested message to the user using the LINE API.

[0854] User: Receives information about a new clothing item via LINE and clicks the purchase link to consider purchasing it. The input is the suggestion message, and the output is the click data of the purchase link.

[0855] Step 10: Emotion Recognition

[0856] User: Checks the proposed outfit and uses the camera to allow the emotion recognition engine to analyze the facial expressions. The input is the user's facial expression data, and the output is the emotional state data.

[0857] Device: Captures facial expressions and sends the data to the emotion recognition engine in real time. Specifically, it uses the camera API to obtain facial expression data and sends it via an HTTP POST request.

[0858] Server: The emotion recognition engine analyzes facial expression data and recognizes the user's emotional state. The output is emotional state data as the analysis result, which is used to improve the accuracy of the next outfit suggestion.

[0859] The above is the specific flow and operation of the program processing of this system.

[0860] (Application example 2)

[0861] 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."

[0862] Conventional closet management systems and outfit suggestion systems have limitations in improving user satisfaction because they do not fully consider the user's emotional state or in-store experience. Furthermore, it is necessary to provide more precise outfit suggestions by appropriately reflecting user feedback, but there has been no effective system for doing so.

[0863] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0864] In this invention, the server includes means for acquiring weather information, means for acquiring user clothing data, means for generating clothing combination suggestions using an AI model based on the acquired weather information and the user clothing data, means for notifying the user device of the suggestions, means for receiving feedback from the user, means for adjusting the AI ​​model based on the feedback, means for identifying unused clothing data and notifying the user of listing suggestions, means for suggesting new clothing, means for recognizing the user's emotional state, and means for the user device to be installed in a device installed in a physical store, means for recognizing the user's facial expression data, and means for adjusting the suggestions based on the acquired customer facial expression data. This enables more precise and personalized coordination suggestions that take the user's emotional state into consideration, improving the user experience in the physical store and enabling more efficient closet management.

[0865] "Weather information" refers to the temperature, humidity, chance of precipitation, and other weather-related data for that day.

[0866] "User clothing data" refers to detailed information about the type, color, size, and frequency of use of clothing owned by the user.

[0867] The "artificial intelligence model" is a machine learning algorithm that suggests optimal clothing combinations based on the user's clothing data and weather information.

[0868] A "generator" is a processing unit for generating suggested coordinates using an artificial intelligence model.

[0869] The "means for notifying" is a communication means for transmitting the generated coordination proposal to the user device.

[0870] The "means for receiving feedback" is a function for receiving opinions and evaluations of suggestions from users.

[0871] A "means for adjusting" is a process for optimizing an artificial intelligence model based on received feedback.

[0872] "Unused clothing data" is information about clothing that has not been used for a long period of time.

[0873] "Suggestion for sale" is a function that presents unused clothing to the user and suggests selling it on the online market.

[0874] The "emotional state" is a psychological state obtained by analyzing the facial expression data of the user.

[0875] "User Device" is a digital terminal that a user uses to receive suggested coordinates and provide feedback.

[0876] "Facial expression data" is image information of the user's face acquired using a camera, and is used for emotion recognition.

[0877] "In-store devices" are devices used to enhance the in-store experience, such as smart mirrors and tablets in fitting rooms.

[0878] System program generation

[0879] The system for implementing this invention mainly includes a means for acquiring weather information, a means for acquiring user clothing data, a generating means, a notifying means, a means for receiving feedback, an adjusting means, a means for identifying unused clothing data, a means for notifying of listing suggestions, a means for suggesting new clothing, a means for recognizing the emotional state of the user, a means for the user device to be installed in a device installed in a physical store, a means for recognizing facial expression data, and a means for adjusting suggestions.

[0880] Program processing explanation

[0881] 1. Obtaining weather information:

[0882] The server calls the weather API every morning at 6:00 to obtain the day's weather information (e.g., temperature, humidity, and probability of precipitation). The API used is provided by a general weather data provider. The obtained data is stored in a database and used when generating proposals.

[0883] 2. Get user clothing data:

[0884] Users register their clothing through the application when they first register or purchase new clothes. They take a photo of the clothing and enter its type, color, size, and other details. The device (such as a smartphone or tablet) then sends the entered data to the server and stores it in a database.

[0885] 3. Generation means:

[0886] The server generates optimal outfits based on the user's clothing data and weather information using an artificial intelligence model that includes machine learning algorithms that learn by taking into account the user's past feedback and emotional state.

[0887] 4. Means of notification:

[0888] The server generates an image and description of the coordinated outfit and notifies the user of the image and description on their device (e.g., a smartphone or tablet). The notification method can be, for example, the LINE API.

[0889] 5. How to receive feedback:

[0890] The user provides feedback on the proposed outfit, either "OK" or "NG." This feedback is sent to the server via the device. In addition, the user's facial expression is captured by a camera and sent to an emotion recognition engine (e.g., EmotionRecognizer).

[0891] 6. Adjustment methods:

[0892] Based on the received feedback and emotion recognition data, the server can adjust its artificial intelligence model to improve the accuracy of its next outfit suggestions.

[0893] Hardware and software used

[0894] Hardware: Smartphones, tablets, smart mirrors in brick-and-mortar stores

[0895] Software: Weather API, EmotionRecognizer, database management system, LINE API

[0896] Specific examples

[0897] When a user stands in front of a smart mirror in a physical store in the morning, a message appears saying, "Today's weather is 15 degrees Celsius and 70% humidity. We recommend the following outfit." Along with an image suggesting an outfit, the mirror suggests "a blue jacket, a white shirt, and black jeans."

[0898] The user reviews the suggestion and provides feedback, either "OK" or "NG," along with sending facial expression data via the camera. This data is stored on the server and reflected in the next suggestion.

[0899] Furthermore, the system identifies a red dress that the user has barely worn and displays a message saying, "It looks like you haven't worn this dress much. Would you like to list it for sale?" If the user agrees to the listing, it will be listed on an online marketplace with one click.

[0900] The user will also be notified of a new "yellow cardigan" suggestion based on their style and current trends, and will receive a message asking, "What do you think of this item?"

[0901] Example prompts for generative AI models

[0902] "Please suggest the best outfit based on the following information: user's clothing data, weather information, fashion information, and user's emotional state."

[0903] This system reduces the effort required for users to choose their daily outfits and efficiently supports closet management. Furthermore, by utilizing emotion recognition, it can improve user satisfaction.

[0904] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0905] Step 1:

[0906] The server calls the weather API every morning at 6:00 to obtain the weather information for that day. Specifically, it obtains data such as temperature, humidity, and probability of precipitation, which are then stored in a database. The input is data from the weather API, and the output is the weather information stored in the database.

[0907] Step 2:

[0908] Users register their clothing through the application when they first register or when they purchase new clothes. They take a photo of the clothing and enter detailed information such as type, color, size, and frequency of use. The device sends the entered data to the server and stores it in a database. The input is the clothing data entered by the user, and the output is the clothing information stored in the database.

[0909] Step 3:

[0910] The server uses an artificial intelligence model to generate optimal outfits based on the user's clothing data and weather information. The method used here is a machine learning algorithm. The input is clothing data stored in a database and weather information, and the output is the generated outfit.

[0911] Step 4:

[0912] The server generates an image and description of the coordinated outfit and notifies the user's device of this. The notification method uses LINE's API. The input is the coordinated outfit, and the output is a notification of the coordinated outfit sent to the user's device.

[0913] Step 5:

[0914] The user provides feedback on the proposed outfit, either "OK" or "NG." The feedback is sent to the server via the device. In addition, the user's facial expression is captured by a camera and sent to an emotion recognition engine. The input is the user's feedback and facial expression data, and the output is the feedback and emotion data stored on the server.

[0915] Step 6:

[0916] The server adjusts the AI ​​model based on the received feedback and emotion recognition data to improve the accuracy of the next outfit suggestion. Here, the machine learning algorithm learns from the feedback and emotion data and updates the model. The input is the feedback and emotion recognition data, and the output is the updated AI model.

[0917] Step 7:

[0918] The server periodically analyzes the user's closet data and usage history to identify clothes that have not been worn for a long time. Based on this information, it creates a list of unused clothes. The input is the user's closet data and usage history, and the output is a list of unused clothes.

[0919] Step 8:

[0920] The server notifies the user of suggestions for selling unused clothing. The recommendation, the reason for the recommendation, and the listing procedure are notified to the user via the LINE API. The input is a list of unused clothing, and the output is the suggestion sent to the user's device.

[0921] Step 9:

[0922] When the user agrees to the listing, they click the listing button on LINE. The device sends the user's click to the server, which calls the Yahoo! Flea Market API and automatically completes the listing process. The input is the user's approval to list the item, and the output is the listing page created on Yahoo! Flea Market.

[0923] Step 10:

[0924] The server analyzes weather information, fashion trends, and the contents of the user's closet to select appropriate new clothing items. The server notifies the user of new clothing suggestions via LINE. The input is weather information, fashion trends, and closet contents, and the output is new clothing suggestions sent to the user's device.

[0925] Step 11:

[0926] The user confirms the proposed outfit and allows the emotion recognition engine to analyze their facial expressions through the camera. The device captures the user's facial expression data and sends it to the emotion recognition engine. The input is the facial expression data, and the output is the emotional state analyzed by the emotion recognition engine.

[0927] 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.

[0928] 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.

[0929] 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.

[0930] [Third embodiment]

[0931] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0932] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0933] 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).

[0934] 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.

[0935] 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.

[0936] 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).

[0937] 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.

[0938] 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.

[0939] 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.

[0940] 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.

[0941] 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.

[0942] 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."

[0943] To implement this invention, a system using weather information, user clothing data, an AI model, a generation means, a notification means, feedback, an adjustment means, unused clothing data, listing suggestions, and a user device is required. This system aims to improve user convenience by suggesting appropriate outfits to users, streamlining closet management, and even suggesting new clothing.

[0944] Program processing explanation

[0945] The system's program mainly consists of the following steps: obtaining weather information, obtaining the user's clothing data, generating outfits, notifications, processing feedback, adjusting the AI ​​model, identifying unused clothing, suggesting items for sale, and suggesting new clothing.

[0946] Obtaining weather information

[0947] Server: Calls the weather API every morning at 6am to obtain the day's weather information (e.g. temperature, humidity, chance of precipitation). This information is stored in a database and used to generate outfits.

[0948] Obtaining user clothing data

[0949] Users: When registering for the first time and when purchasing new clothes, they register their clothing through the application, taking a photo of the clothing and entering details such as type, color, and size.

[0950] Terminal: Sends the entered information to the server, which stores it in a database.

[0951] Coordinate generation

[0952] Server: Based on the user's clothing data and weather information, an artificial intelligence model is used to generate the optimal outfit. At this stage, the machine learning algorithm takes into account the user's preferences and previous feedback.

[0953] notification

[0954] Server: Generates an image and description of the coordinated outfit, and sends it to the user's LINE account using the LINE API.

[0955] User: Receive suggested outfits via LINE to help with daily outfit selection.

[0956] Processing Feedback

[0957] User: Sends feedback on the proposed outfit, either "OK" or "NG," via LINE message.

[0958] Terminal: Sends a feedback message to the server.

[0959] Server: Stores the received feedback in a database and adjusts the parameters of the AI ​​model to improve the accuracy of the next suggestion.

[0960] Identifying unused clothing

[0961] Server: Analyzes the user's usage history and identifies clothes that have not been used for a long time. Based on this information, a list of unused clothes is created.

[0962] Listing proposal

[0963] Server: Proposes to users via LINE that they should sell unused clothing.

[0964] Users: If they accept the listing proposal, the listing process is completed with one click.

[0965] Server: Sends listing information to the Yahoo! Flea Market API and automatically processes the listing.

[0966] New clothing proposals

[0967] Server: Selects new clothing items based on weather information, fashion trends, and the contents of the user's closet.

[0968] Server: Providing information about selected new clothing items to users via LINE.

[0969] Specific examples

[0970] Here's a specific example. For example, when a user wakes up in the morning and checks LINE, they receive a message saying, "Today's weather is 15 degrees Celsius and 70% humidity. We recommend the following outfit," along with an image of an outfit suggestion: "Blue jacket, white shirt, black jeans." The user checks the suggestion and sends feedback saying "OK." This feedback information is sent to the server and reflected in the next suggestion.

[0971] Furthermore, the system identifies a red dress that the user has hardly worn, and sends a message on LINE saying, "It looks like you haven't worn this dress much. Would you like to list it for sale?" If the user agrees to the listing, it will be listed on Yahoo! Flea Market with one click.

[0972] Additionally, based on the user's style and recent trends, a new "yellow cardigan" will be suggested via LINE, and a message will be sent asking, "What do you think of this item?"

[0973] In this way, the system saves users the trouble of choosing their daily clothes and also efficiently supports closet management.

[0974] The processing flow will be explained below.

[0975] Step 1:

[0976] User: When registering for the first time, users enter their basic information (e.g., name, gender, height, weight, preferred style) into the application. At the same time, they also enter information about the clothing they own (e.g., type, color, size, material) along with a photo.

[0977] Step 2:

[0978] Terminal: The basic information and clothing data entered by the user is sent to the server via the Internet.

[0979] Step 3:

[0980] Server: The received user's basic information and clothing data are stored in a database, and the characteristics of each piece of clothing are analyzed and classified using an AI-based image recognition algorithm.

[0981] Step 4:

[0982] Server: Calls the weather API every morning at 6am to get the weather information for that day (e.g. temperature, humidity, chance of precipitation) for a specific region. Stores this information in a database.

[0983] Step 5:

[0984] Server: At a specified time (e.g., 7:00 a.m. every morning), weather data for the day is extracted based on each user's registered location information, and input into the AI ​​model along with the user's basic information and clothing data.

[0985] Step 6:

[0986] Server: The AI ​​model generates optimal outfits based on input weather data and the user's clothing data. During this process, machine learning algorithms take into account the user's past feedback and preferences.

[0987] Step 7:

[0988] Server: Creates an image and description of the generated outfit, and sends it to the user's LINE account using the LINE API.

[0989] Step 8:

[0990] User: Check the suggested outfits on LINE and send feedback by pressing the "OK" button if satisfied with the selection, or the "NG" button if not.

[0991] Step 9:

[0992] Terminal: Forwards the feedback messages sent by the user to the server.

[0993] Step 10:

[0994] Server: Stores the received feedback in a database and adjusts the parameters of the AI ​​model to improve the accuracy of the next outfit suggestion.

[0995] Step 11:

[0996] Server: Periodically analyzes the user's closet data and usage history to identify clothes that have not been worn for a long time. Based on this information, it creates a list of unused clothes.

[0997] Step 12:

[0998] Server: Sends suggestions to users via LINE about clothes that have not been used for a long time. The message explains why the item should be listed and provides instructions on how to list the item.

[0999] Step 13:

[1000] User: After reviewing the listing proposal, if they agree to the listing, they click the listing button on LINE, which automatically starts the listing process on Yahoo! Flea Market.

[1001] Step 14:

[1002] Terminal: Sends user clicks to the server.

[1003] Step 15:

[1004] Server: Based on the received listing request, the Yahoo! Flea Market API is called and the listing process is automatically carried out. A listing page is created based on the registered information.

[1005] Step 16:

[1006] Server: Analyzes weather information, fashion trends, and the contents of the user's closet to select appropriate new clothing items. Creates messages to suggest this information to the user.

[1007] Step 17:

[1008] Server: Sends new clothing suggestion messages to users via LINE. The messages include images, descriptions, and purchase links for the suggested new clothing. This allows users to easily purchase new clothes.

[1009] This allows the system to support users in choosing their daily outfits and provide efficient closet management, improving the accuracy of suggestions based on feedback and encouraging users to purchase new clothes or organize unused clothing.

[1010] Example 1

[1011] 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."

[1012] Conventional closet management systems have issues with insufficient clothing suggestions and closet management for users, and have low efficiency in suggesting daily outfits, identifying unused clothing, and suggesting items for sale. In particular, there is a need for systems that can generate appropriate outfits that reflect weather information and user preferences, improve the accuracy of AI models using user feedback, and suggest new clothing.

[1013] 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.

[1014] In this invention, the server includes means for acquiring weather information, means for acquiring user clothing data, means for generating clothing combination suggestions using an AI model based on the acquired weather information and the user clothing data, means for notifying the user device of the suggestions, means for receiving feedback from the user, means for adjusting the AI ​​model based on the feedback, means for identifying unused clothing data and notifying the user of suggestions for selling, means for suggesting new clothing, schedule management means for determining when to acquire weather information, means for controlling notifications based on the weather information and the state of the user device, and means for supporting the new registration of clothing purchased by the user based on the above means. This allows for efficient and accurate clothing suggestions to be made to the user, streamlining closet management, and enabling suggestions for selling unused clothing and new clothing to be made.

[1015] "Means of obtaining weather information" refers to the function of obtaining weather data such as temperature, humidity, and probability of precipitation at specified times using a weather API, etc.

[1016] "Means for obtaining user clothing data" refers to the function that allows the user to input photos and detailed information about clothing through the application, and then send it to the server and store it in a database.

[1017] "Generation method using artificial intelligence model" refers to a function that uses machine learning algorithms to suggest optimal clothing combinations based on the user's clothing data and weather information.

[1018] The "means for notifying the user device of the proposal" refers to a function for generating an image and description of the clothing combination and transmitting them to the user device using a communication means.

[1019] "Means for receiving feedback from users" refers to a function that allows users to send feedback such as "OK" or "NG" on proposed costumes.

[1020] "Means for adjusting the AI ​​model" refers to a function that adjusts the parameters of the AI ​​model based on feedback from users to improve the accuracy of future suggestions.

[1021] "Means for identifying unused clothing data and notifying users of listing suggestions" refers to a function that identifies clothing that has not been used for a long period of time from a database and makes suggestions to users based on that information.

[1022] "Means for suggesting new clothing" refers to a function that selects and suggests new clothing suitable for the user based on weather information, trend information, and the contents of the user's closet.

[1023] "Schedule management means for determining the timing of obtaining weather information" refers to a function that sets a regular schedule and manages the timing of obtaining weather information from the API at that time.

[1024] "Means for controlling notifications based on weather information and the status of the user device" refers to a function that determines weather information and the usage status of the user device, and notifies coordination suggestions at the optimal time.

[1025] "Means to support users in registering new clothing purchases" refers to a function that allows users to easily input and register information about newly purchased clothing through the application.

[1026] To implement this invention, a system using weather information, user clothing data, an AI model, a generation means, a notification means, a feedback means, an adjustment means, unused clothing data, listing suggestions, new clothing suggestions, and a user device is required. This system aims to improve user convenience by suggesting appropriate outfits to users, streamlining closet management, and suggesting new clothing.

[1027] The present invention is implemented using the following hardware and software.

[1028] Hardware

[1029] Server: Responsible for the central processing of the program. This is where data is stored, analyzed, and artificial intelligence models are trained and executed.

[1030] Terminal: The device operated by the user (smartphone, tablet, etc.) on which the application is installed.

[1031] User device: Serves as an interface with the user and is used to provide coordination suggestions and give feedback.

[1032] software

[1033] Weather API: Obtain weather information using the OpenWeather API, etc.

[1034] Artificial intelligence model: Generate coordinates using TensorFlow or PyTorch.

[1035] Database: Use a database system such as MySQL to store data.

[1036] Communication method: Sending and receiving data via REST API, notification and feedback processing using LINE API.

[1037] Specific examples

[1038] Specific examples are shown below.

[1039] Obtaining weather information

[1040] The server triggers a scheduled task every morning at 6:00, which retrieves the weather information for that day (e.g., temperature 15°C, humidity 70%, chance of precipitation 40%) from the OpenWeather API. This information is stored in a database in JSON format.

[1041] Obtaining user clothing data

[1042] A user registers a new shirt using a smartphone application. The user takes a photo of the shirt and enters the type (shirt), color (blue), and size (M). The device sends this data to the server via a REST API, and the server stores it in a database.

[1043] Coordinate generation

[1044] The server acquires the user's clothing data and weather information and inputs it into an artificial intelligence model using TensorFlow. For example, on a day when the temperature is 15 degrees, a coordination of "blue jacket, white shirt, black jeans" is generated. The results are saved as images and text.

[1045] notification

[1046] The generated outfit is sent to the user's device via the LINE API and displayed with the message, "Today's weather is 15 degrees Celsius and 70% humidity. We recommend the following outfit."

[1047] Processing Feedback

[1048] The user sends feedback via LINE, either "OK" or "NG." The device then sends this feedback to the server, which stores it in a database. This feedback is then reflected in the next proposal.

[1049] Identifying unused clothing

[1050] The server periodically analyzes the user's usage history and identifies clothing that has not been worn for a long time (e.g., a red dress). Based on this information, it creates a list of unused clothing and suggests items for sale to the user via LINE.

[1051] Listing proposal

[1052] When the user accepts the listing proposal, the server automatically processes the listing using the Yahoo! Flea Market API.

[1053] New clothing proposals

[1054] The server selects new clothing items (e.g., a yellow cardigan) based on weather information, fashion trends, and the contents of the user's closet, and suggests them via LINE.

[1055] Prompt Sentence Examples

[1056] "This system calls the OpenWeather API every morning at 6am to get the weather information for the day. Explain how it then matches this with the user's clothing data and uses TensorFlow to generate the optimal outfit."

[1057] In this way, the system saves users the trouble of choosing their daily clothes and efficiently supports closet management.

[1058] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1059] Step 1: Get weather information

[1060] The server triggers a scheduled task every morning at 6:00 AM. It calls a specified weather API (e.g., OpenWeather API) to "get weather information."

[1061] Input: Time (6 o'clock)

[1062] Output: Weather information for the day (Temperature 15°C, Humidity 70%, Chance of precipitation 40%)

[1063] Specific operation: The server issues an API request, analyzes the received JSON-formatted weather data, and stores the necessary information in a database.

[1064] Step 2: Obtaining the user's clothing data

[1065] When a user purchases new clothing, they use a smartphone application to take a photo of the clothing and enter details such as type (shirt), color (blue), and size (M).

[1066] Input: Clothing photos and details entered by the user

[1067] Output: Clothing data stored in a database

[1068] Specific operation: The device compresses the form input data and photo and sends them to the server via REST API. The server stores the received data in a database.

[1069] Step 3: Generate coordinates

[1070] The server receives the user's clothing data and weather information and inputs it into an AI model (e.g., TensorFlow), which then generates the optimal clothing combination.

[1071] Input: User clothing data stored in the database, weather information for the day

[1072] Output: Outfit suggestions (e.g. blue jacket, white shirt, black jeans)

[1073] What it does: The server runs a machine learning algorithm to generate outfits that take into account the user's preferences and past feedback. The results are stored in JSON format.

[1074] Step 4: Notification

[1075] The server notifies the user device of the generated coordination results as images and text via the LINE API.

[1076] Input: Coordination suggestions

[1077] Output: Coordination suggestions sent as LINE messages

[1078] Specific operation: The server sends the image URL and message to the LINE API, and the coordination is notified to the user's LINE account.

[1079] Step 5: Processing feedback

[1080] Users can provide feedback on the suggested outfits via LINE messages, either "OK" or "NG."

[1081] Input: User feedback (OK or NG)

[1082] Output: Feedback information stored in a database

[1083] Specific operation: The terminal sends a feedback message to the server, which stores the information in a database and uses it to adjust the parameters of the artificial intelligence model.

[1084] Step 6: Identify unused clothing

[1085] The server analyzes the user's usage history and identifies clothing that has not been used for a long time.

[1086] Input: User's clothing usage history

[1087] Output: List of unused clothing items

[1088] Specific behavior: The server periodically searches the database and lists any clothing that has not been used for more than a certain period of time (e.g., six months).

[1089] Step 7: Listing Proposal

[1090] The server suggests to users via LINE that they put up for sale unused clothing.

[1091] Input: Unused clothing list

[1092] Output: Listing suggestion message

[1093] Specific operation: The server uses the LINE API to send a message saying, "This dress doesn't seem to be worn much. Would you like to list it for sale?"

[1094] Step 8: New clothing suggestions

[1095] The server selects new clothing items based on weather information, fashion trends, and the contents of the user's closet.

[1096] Input: Weather information, trends, closet contents

[1097] Output: New clothing suggestions

[1098] Specific operation: The server analyzes the data based on the above information, selects new clothing items suitable for the user (e.g., a yellow cardigan), and suggests them via the LINE API.

[1099] Through the above processing steps, this system can save the user the trouble of choosing clothes on a daily basis and efficiently support closet management.

[1100] (Application example 1)

[1101] 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."

[1102] Previously, there were systems that suggested clothing coordination based on weather information and the user's clothing data. However, most of these systems required the user to manually input data, and only a limited number of systems utilized smart devices to provide real-time suggestions in a virtual space. Furthermore, the systems for effectively collecting user feedback and reflecting it in future suggestions were inadequate. Furthermore, efficient methods for managing closets, suggesting the sale of unused clothing, and suggesting new clothing were needed. Therefore, a comprehensive system that could significantly improve user convenience was needed.

[1103] 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.

[1104] In this invention, the server includes means for acquiring weather information, means for acquiring user clothing data, means for generating clothing combination suggestions using an AI model based on the acquired weather information and the user clothing data, means for notifying the user device of the suggestions, means for receiving feedback from the user, means for adjusting the AI ​​model based on the feedback, means for identifying unused clothing data and notifying the user of suggestions for clothing to be sold, means for suggesting new clothing, and means for the user to wear a smart device to check suggested outfits in a virtual space and provide feedback. This allows the user to receive outfit suggestions in a virtual space in real time, achieving efficient closet management and outfit suggestions.

[1105] "Weather information" is data about the weather conditions in a specific area, including temperature, humidity, probability of precipitation, and the like.

[1106] "User clothing data" is data including the type, color, size, and other related information of clothing owned by a user.

[1107] "Generation means" refers to a means for generating clothing combinations using an artificial intelligence model based on weather information and user clothing data.

[1108] "User Device" refers to electronic devices used by a User, such as computers, smartphones, tablets, and smart devices.

[1109] The "notification means" is a means for transmitting the generated coordination proposal to the user device.

[1110] "Feedback means" refers to a means for collecting evaluations and opinions from users and receiving that data.

[1111] The "adjustment means" is a means for adjusting the parameters of the artificial intelligence model based on feedback from the user.

[1112] "Unused clothing data" refers to information about clothing that a user has not worn within a specific period of time.

[1113] A "suggestion to sell" is a suggestion to sell unused clothing to other users.

[1114] "New clothing suggestions" refers to suggesting new clothing to the user based on the contents of the user's current closet and trend information.

[1115] "Smart devices" refers to interactive electronic devices such as internet-enabled glasses and head-mounted displays.

[1116] A "virtual space" is a three-dimensional virtual environment constructed using virtual reality technology, in which users can interact.

[1117] A "generative AI model" refers to a model that uses artificial intelligence technology to generate or suggest specific objects or situations.

[1118] A "prompt sentence" is a sentence that gives instructions to an artificial intelligence model and is an input sentence to perform a specific task.

[1119] To implement the present invention, a system is provided that uses the following hardware and software.

[1120] Hardware

[1121] Server: A high-performance server for acquiring weather information, managing the database, and generating and adjusting AI models.

[1122] User device: A device operated by a user, such as a smartphone, tablet, computer, smart glasses, or head-mounted display (e.g., Oculus Rift).

[1123] software

[1124] Weather API: API for obtaining weather information such as WeatherAPI.

[1125] LINE Messaging API: An API for notifying users of suggested outfits and collecting feedback.

[1126] Generative AI model: An artificial intelligence model built using a programming language such as Python.

[1127] Machine learning algorithms: Algorithms that use user feedback information to train and adjust models.

[1128] Data processing and calculation

[1129] The server calls the weather API every morning at 6am to obtain the day's weather information (e.g., temperature, humidity, and chance of precipitation) and stores it in a database. When users register for the first time or purchase new clothes, they register their clothing data through their smart devices. The server uses this information to generate optimal outfits using a generative AI model and notifies the user of the generated outfits using LINE's API. The user checks the suggested outfits on LINE and provides feedback. This feedback information is sent to the system, and the server uses it to adjust the artificial intelligence model.

[1130] The system also has a means of identifying unused clothing data and notifying users of suggestions for listing items. These suggestions are made via LINE, and if the user accepts, the listing process is automatically carried out using platforms such as Yahoo! Flea Market. New clothing suggestions are based on weather information, fashion trends, and the contents of the user's closet.

[1131] Specific examples

[1132] For example, when a user wakes up in the morning, launches the Virtual Closet Coordinator, and puts on the smart glasses, a message appears in the VR space saying, "Today's weather is 15 degrees Celsius and 70% humidity. We recommend the following outfit," along with a blue jacket, white shirt, and black jeans that can be virtually tried on. After virtually trying on the clothes, the user can give feedback of "OK," and this information will be reflected in the next outfit suggestions.

[1133] Prompt Sentence Examples

[1134] Enter the following information into the AI ​​model to generate the optimal outfit.

[1135] Weather information: Temperature is 15 degrees and humidity is 70%.

[1136] User clothing data: "Blue jacket, white shirt, black jeans."

[1137] As described above, this system reduces the effort required for users to choose their daily clothes and provides efficient support for closet management.

[1138] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1139] Step 1:

[1140] The server calls the weather API every morning at 6:00 to retrieve the weather information for that day. The retrieved weather information includes temperature, humidity, and probability of precipitation. This data is stored in a database and used for subsequent processing.

[1141] Input: Weather API call

[1142] Output: Weather information data (temperature, humidity, precipitation probability)

[1143] Step 2:

[1144] When a user first registers or purchases new clothes, they register their clothing data in the application via their smart device. They take a photo of the clothing and enter details such as type, color, and size. The entered information is sent from the device to the server and stored in a database.

[1145] Input: User's clothing data (photo, type, color, size)

[1146] Output: Updated clothing database

[1147] Step 3:

[1148] The server receives weather information and the user's clothing data and uses a generative AI model to generate optimal outfits. The generative AI model takes into account weather conditions and the user's past feedback information to suggest outfits.

[1149] Input: Weather information data, clothing data

[1150] Output: Coordination suggestions

[1151] Step 4:

[1152] The server generates an image and description of the coordinated outfit and sends it to the user's LINE account using the LINE API, allowing the user to receive the suggested coordinated outfit.

[1153] Input: Coordination suggestions

[1154] Output: LINE message (coordinate image and description)

[1155] Step 5:

[1156] The user checks the proposed outfits on LINE and sends feedback such as "OK" or "NG" via LINE message, which records the user's evaluation.

[1157] Input: Coordination suggestions, user feedback

[1158] Output: Feedback message

[1159] Step 6:

[1160] The device sends the feedback it receives to the server, which stores it in a database and uses it to adjust the parameters of the generative AI model to improve the accuracy of its next suggestions.

[1161] Input: User feedback

[1162] Output: An updated generative AI model

[1163] Step 7:

[1164] The server analyzes the user's usage history and identifies clothes that have not been used for a long time. Based on this data, it creates a list of unused clothes and notifies the user via LINE of suggestions to sell them.

[1165] Input: Clothing usage history

[1166] Output: Listing suggestion message

[1167] Step 8:

[1168] If the user accepts the listing proposal via LINE, the listing process is completed with one click. The server automatically completes the listing process using the Yahoo! Flea Market API.

[1169] Input: Accept the offer

[1170] Output: Listing procedure completed

[1171] Step 9:

[1172] The server selects new clothing items based on weather information, fashion trends, and the contents of the user's closet, and then suggests the selected new clothing items to the user via LINE.

[1173] Input: Weather information, trends, closet contents

[1174] Output: New clothing suggestion message

[1175] 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.

[1176] To implement this invention, a system using weather information, user clothing data, an AI model, a generation means, a notification means, a feedback, an adjustment means, unused clothing data, listing suggestions, new clothing suggestions, and an emotion recognition engine is required. This system suggests appropriate outfits to the user, streamlines closet management, and improves user convenience by suggesting new clothing, while also taking into account the user's emotional state.

[1177] Program processing explanation

[1178] The system's program mainly consists of the following steps: obtaining weather information, obtaining the user's clothing data, generating outfits, notifications, processing feedback, adjusting the AI ​​model, identifying unused clothing, suggesting items for sale, suggesting new clothing, and recognizing emotions.

[1179] Obtaining weather information

[1180] Server: Calls the weather API every morning at 6am to obtain the day's weather information (e.g. temperature, humidity, chance of precipitation). This information is stored in a database and used to generate outfits.

[1181] Obtaining user clothing data

[1182] Users: When registering for the first time and when purchasing new clothes, they register their clothing through the application, taking a photo of the clothing and entering details such as type, color, and size.

[1183] Terminal: Sends the entered information to the server, which stores it in a database.

[1184] Coordinate generation

[1185] Server: Based on the user's clothing data and weather information, an artificial intelligence model is used to generate the optimal outfit. At this stage, the machine learning algorithm takes into account the user's preferences and previous feedback.

[1186] notification

[1187] Server: Generates an image and description of the coordinated outfit, and sends it to the user's LINE account using the LINE API.

[1188] User: Check out the suggested outfits on LINE to help you choose your daily outfits.

[1189] Processing Feedback

[1190] User: Sends feedback on the proposed outfit, such as "OK" or "NG," via LINE message and grants permission to recognize facial expressions.

[1191] Device: Transfers the user's feedback message to the server, and at the same time activates the camera to capture facial expressions and send them to the emotion recognition engine.

[1192] Server: Stores the received feedback and emotion recognition data in a database and adjusts the parameters of the AI ​​model to improve the accuracy of the next outfit suggestion.

[1193] Identifying unused clothing

[1194] Server: Periodically analyzes the user's closet data and usage history to identify clothes that have not been worn for a long time. Based on this information, it creates a list of unused clothes.

[1195] Listing proposal

[1196] Server: Notifies users through LINE of suggestions to sell unused clothing. The message explains the reason for the recommendation and the steps to sell the clothing.

[1197] User: After reviewing the listing proposal, if they agree to the listing, they click the listing button on LINE, which automatically starts the listing process on Yahoo! Flea Market.

[1198] Terminal: Sends user clicks to the server.

[1199] Server: Based on the received listing request, the Yahoo! Flea Market API is called and the listing process is automatically carried out. A listing page is created based on the registered information.

[1200] New clothing proposals

[1201] Server: Analyzes weather information, fashion trends, and the contents of the user's closet to select appropriate new clothing items. Creates messages to suggest this information to the user.

[1202] Server: Sends new clothing suggestion messages to users via LINE. The messages include images, descriptions, and purchase links for the suggested new clothing. This allows users to easily purchase new clothes.

[1203] emotion recognition

[1204] User: Review the suggested outfit and allow the emotion recognition engine to analyze your facial expressions via the camera.

[1205] Device: Captures a picture of the user's facial expressions and sends them to an emotion recognition engine.

[1206] Server: The emotion recognition engine analyzes the user's facial expression data and recognizes the user's emotional state (e.g., satisfaction, confusion, disgust, etc.). Based on this emotional data, the AI ​​model will take the user's emotions into consideration when proposing the next outfit.

[1207] Specific examples

[1208] For example, when a user checks LINE in the morning, they receive a message saying, "Today's weather is 15 degrees Celsius and 70% humidity. We recommend the following outfit," along with an image of a suggested outfit: "Blue jacket, white shirt, black jeans." The user confirms the suggestion and sends feedback by saying "OK," along with facial expression data via the camera. This data is stored on the server and reflected in the next suggestion.

[1209] Furthermore, the system identifies a red dress that the user has hardly worn, and sends a message on LINE saying, "It looks like you haven't worn this dress much. Would you like to list it for sale?" If the user agrees to the listing, it will be listed on Yahoo! Flea Market with one click.

[1210] Additionally, based on the user's style and recent trends, a new "yellow cardigan" will be suggested via LINE, and a message will be sent asking, "What do you think of this item?"

[1211] In this way, the system reduces the effort required for users to choose their daily clothes and efficiently supports closet management. In addition, by utilizing emotion recognition, the system can provide more precise suggestions that take into account the user's emotions.

[1212] The processing flow will be explained below.

[1213] Step 1:

[1214] User: When registering for the first time, users enter their basic information (e.g., name, gender, height, weight, preferred style) into the application. At the same time, they register information about the clothing they own (e.g., type, color, size, material) along with a photo.

[1215] Terminal: Sends the entered information to the server.

[1216] Step 2:

[1217] Server: The received user's basic information and clothing data are stored in a database, and the characteristics of each piece of clothing are analyzed and classified using an AI-based image recognition algorithm.

[1218] Step 3:

[1219] Server: Calls the weather API every morning at 6am to obtain the day's weather information (e.g. temperature, humidity, chance of precipitation). This information is stored in a database and used to generate outfits.

[1220] Step 4:

[1221] Server: At a specified time (e.g., 7:00 a.m. every morning), weather data for the day is extracted based on each user's registered location information, and input into the AI ​​model along with the user's basic information and clothing data.

[1222] Step 5:

[1223] Server: The AI ​​model generates optimal outfits based on input weather data and the user's clothing data. During this process, machine learning algorithms take into account the user's past feedback and preferences.

[1224] Step 6:

[1225] Server: Creates an image and description of the generated outfit, and sends it to the user's LINE account using the LINE API.

[1226] Step 7:

[1227] User: Check the suggested outfits on LINE and send feedback by pressing the "OK" button if satisfied with the selection, or the "NG" button if not.

[1228] Step 8:

[1229] Device: Transfers the feedback message sent by the user to the server, and at the same time activates the camera to capture facial expressions and send them to the emotion recognition engine.

[1230] Step 9:

[1231] Server: Stores the received feedback and emotion recognition data in a database and adjusts the parameters of the AI ​​model to improve the accuracy of the next outfit suggestion.

[1232] Step 10:

[1233] Server: Periodically analyzes the user's closet data and usage history to identify clothes that have not been worn for a long time. Based on this information, a list of unused clothes is created.

[1234] Step 11:

[1235] Server: Notifies users through LINE of suggestions to sell unused clothing. The message explains the reason for the recommendation and the steps to sell the clothing.

[1236] Step 12:

[1237] User: After reviewing the listing proposal, if they agree to the listing, they click the listing button on LINE, which automatically starts the listing process on Yahoo! Flea Market.

[1238] Step 13:

[1239] Terminal: Sends user clicks to the server.

[1240] Step 14:

[1241] Server: Based on the received listing request, the Yahoo! Flea Market API is called and the listing process is automatically carried out. A listing page is created based on the registered information.

[1242] Step 15:

[1243] Server: Analyzes weather information, fashion trends, and the contents of the user's closet to select appropriate new clothing items. Creates messages to suggest this information to the user.

[1244] Step 16:

[1245] Server: Sends new clothing suggestion messages to users via LINE. The messages include images, descriptions, and purchase links for the suggested new clothing. This allows users to easily purchase new clothes.

[1246] Step 17:

[1247] User: Review the suggested outfit and allow the emotion recognition engine to analyze your facial expressions via the camera.

[1248] Step 18:

[1249] Device: Captures a picture of the user's facial expressions and sends them to an emotion recognition engine.

[1250] Step 19:

[1251] Server: The emotion recognition engine analyzes the user's facial expression data and recognizes the user's emotional state (e.g., satisfaction, confusion, disgust, etc.). Based on this emotional data, the AI ​​model will take the user's emotions into consideration when proposing the next outfit.

[1252] Specific examples

[1253] For example, when a user checks LINE in the morning, they receive a message saying, "Today's weather is 15 degrees Celsius and 70% humidity. We recommend the following outfit," along with an image of a suggested outfit: "Blue jacket, white shirt, black jeans." The user confirms the suggestion and sends feedback by saying "OK," along with facial expression data via the camera. This data is stored on the server and reflected in the next suggestion.

[1254] Furthermore, the system identifies a red dress that the user has hardly worn, and sends a message on LINE saying, "It looks like you haven't worn this dress much. Would you like to list it for sale?" If the user agrees to the listing, it will be listed on Yahoo! Flea Market with one click.

[1255] Additionally, based on the user's style and recent trends, a new "yellow cardigan" will be suggested via LINE, and a message will be sent asking, "What do you think of this item?"

[1256] In this way, the system reduces the effort required for users to choose their daily clothes and efficiently supports closet management. In addition, by utilizing emotion recognition, the system can provide more precise suggestions that take into account the user's emotions.

[1257] Example 2

[1258] 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."

[1259] Conventional outfit suggestion systems make suggestions based on weather information and the user's clothing data, but they do not consider the user's emotional state or suggest clothing that has not been worn for a long time. Furthermore, the AI ​​model is not adequately adjusted to effectively reflect user feedback, resulting in a problem of reduced suggestion accuracy. Furthermore, there is a need for a system that can make more accurate outfit suggestions by using user feedback and emotional state.

[1260] 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.

[1261] In this invention, the server includes means for acquiring weather information, means for acquiring user clothing data, means for generating clothing combination suggestions using an AI model based on the acquired weather information and the user clothing data, means for notifying the user device of the suggestions, means for receiving feedback from the user, means for adjusting the AI ​​model based on the feedback and the user's emotional state, means for analyzing facial expressions to recognize the user's emotional state, means for identifying unused clothing data and notifying the user of a suggestion for selling, and means for suggesting new clothing. This enables precise coordination suggestions that take the user's emotional state into consideration and also promotes the effective use of unused clothing.

[1262] "Weather information" refers to data about daily weather conditions, such as weather, temperature, humidity, and chance of precipitation.

[1263] "Clothing data" is information about clothing owned by a user, including the type, color, size, and other characteristics of the clothing.

[1264] An "artificial intelligence model" is a program based on machine learning algorithms that analyzes data and suggests optimal clothing combinations.

[1265] The "generation means" is a means for generating clothing combinations based on weather information and user clothing data using an artificial intelligence model.

[1266] The "notification means" is a means for notifying the user device of the generated clothing combinations and listing suggestions.

[1267] "Feedback" refers to information on the user's evaluation and reaction to the proposed clothing combinations.

[1268] The "adjustment means" is a means for changing the parameters of the artificial intelligence model based on feedback from the user and their emotional state, thereby improving the accuracy of the suggestions.

[1269] "Emotional state" refers to an emotional state such as satisfaction, confusion, or disgust that is recognized by analyzing the user's facial expression.

[1270] A "suggestion to sell" is a suggestion made to a user to encourage them to sell unused clothing.

[1271] "New clothing suggestions" are suggestions that introduce new clothing to the user based on the contents of the user's closet, weather information, and fashion information.

[1272] To implement this invention, a system using weather information, user clothing data, an AI model, a generation means, a notification means, a feedback, an adjustment means, unused clothing data, listing suggestions, new clothing suggestions, and an emotion recognition engine is required. This system suggests appropriate outfits to the user, streamlines closet management, and improves user convenience by suggesting new clothing, while also taking into account the user's emotional state.

[1273] The specific hardware and software for this system include a server, terminal, user device, weather API, LINE API, emotion recognition engine (e.g., Face API), and generative AI model (e.g., TensorFlow or PyTorch).

[1274] The server calls the weather API every morning at 6:00 to obtain the day's weather information (e.g., temperature, humidity, and chance of precipitation). This information is stored in the weather table of the database and used to generate outfits. Users also register their clothing through a smartphone app. They take photos of the clothing and enter detailed information such as type, color, and size. The device sends the entered information to the server in real time, and the server stores it in the clothing table of the database.

[1275] The server uses a generative AI model (for example, a model built with TensorFlow or PyTorch) to generate the optimal outfit based on the user's clothing data and the weather information for the day. The generated outfit is saved in the coordination_suggestions table in the database. This generated outfit is then generated as an image and description, and notified to the user's LINE account using the LINE API. The user can then check the presented outfit on LINE.

[1276] The user provides feedback on the proposed outfit. They reply with "OK" or "NG" via LINE message and give permission to capture their facial expression with the camera. The device then activates the camera, captures the user's facial expression, and sends the data in real time to the server. The feedback content is also sent. The server stores the received feedback and emotion recognition data in a database and adjusts the parameters of the artificial intelligence model based on the feedback and emotion recognition data. This improves the accuracy of the next outfit suggestion.

[1277] The server also periodically analyzes the user's closet data and usage history to identify clothing that has not been worn for a long time. It suggests selling unused clothing, and the user is notified via LINE. If the user accepts the listing, the listing process begins with one click. Once the server receives the user's acceptance, it calls the Yahoo! Flea Market API to automatically complete the listing process and create a listing page.

[1278] The server then analyzes weather information, fashion trends, and the contents of the user's closet to select appropriate new clothing. Based on this information, a suggestion message is created and sent to the user via LINE. The user receives the new clothing suggestion via LINE and can view an image, description, and purchase link of the suggested new clothing.

[1279] For example, when a user checks LINE in the morning, they receive a message saying, "Today's weather is 15 degrees Celsius and 70% humidity. We recommend the following outfit," along with an image of a suggested outfit: "Blue jacket, white shirt, black jeans." The user confirms the suggestion and sends feedback by saying "OK," along with facial expression data via the camera. This data is stored on the server and reflected in the next suggestion.

[1280] Furthermore, the system identifies a red dress that the user has rarely worn, and sends a LINE message saying, "It seems like you haven't worn this dress much. Would you like to list it for sale?" If the user accepts the listing, it will be listed on Yahoo! Flea Market with one click. Furthermore, based on the user's style and recent trends, the system also suggests a new "yellow cardigan" via LINE, sending a message saying, "What do you think of this item?"

[1281] An example prompt is:

[1282] "Please suggest an appropriate outfit based on the current weather and my clothing data. Also, please tell me how the AI ​​model used to make the suggestions is adjusted."

[1283] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1284] Step 1: Get weather information

[1285] Server: Calls the weather API every morning at 6am to obtain the day's weather information (e.g. temperature, humidity, probability of precipitation). The input is the response data from the weather API, which the server analyzes to extract the necessary information and saves in the weather table of the database. Specifically, it uses the API key to send an HTTP request and receives weather data in JSON format. After analysis, the temperature and humidity data is saved in the appropriate fields.

[1286] Step 2: Obtaining the user's clothing data

[1287] Users: When registering for the first time or when purchasing new clothes, they register their clothing items through a smartphone app. They input a photo of the clothing and detailed information such as type, color, and size.

[1288] Device: The entered information is sent in real time to the server, which then stores it in the clothing table in the database. Specifically, the user takes a photo of the clothing item in the app and enters the information in the text box. The device then sends this data to the server using an HTTP POST request.

[1289] Step 3: Generate coordinates

[1290] Server: Based on the user's clothing data and the weather information for the day, a generative AI model (for example, a model built with TensorFlow or PyTorch) is used to generate the optimal outfit. The input is the user's clothing data and weather information, and based on this, a machine learning algorithm processes and calculates the data to obtain the output. Specifically, it also takes into account previous user feedback and the preference patterns of other users. The results are saved in the coordination_suggestions table in the database.

[1291] Step 4: Notification

[1292] Server: Generates the generated outfit as an image and description, and uses this to notify the user's LINE account using the LINE API. The input is the outfit creation data, and the output is a message sent to the user's LINE account. Specifically, the server combines the image and text using a template message and sends an HTTP request to the LINE API.

[1293] Step 5: Processing feedback

[1294] User: Checks the proposed outfit on LINE and sends feedback of "OK" or "NG." The user also gives permission to capture their facial expression with the camera. The input is the user's feedback message and an image of their facial expression.

[1295] Device: Activates the camera, captures the user's facial expressions, and sends the data to the server in real time. It also sends feedback content in LINE messages. The output is the feedback data and an image of the facial expression. Specifically, it activates the camera API, obtains image data, and sends it to the server via an HTTP POST request.

[1296] Step 6: Tuning the AI ​​model

[1297] Server: Adjusts the parameters of the AI ​​model based on the received feedback and emotion recognition data. The input is the feedback data and emotion recognition data, and the output is the adjusted model parameters. Specifically, it updates the model weights using an optimization algorithm (e.g., gradient descent). This improves the accuracy of the next outfit suggestion.

[1298] Step 7: Identify unused clothing

[1299] Server: Periodically analyzes the user's closet data and usage history to identify clothes that have not been used for a long time. The input is closet data and usage history data, and the output is a list of unused clothes. Specifically, it uses a database query to extract items that have not been used for a certain period of time (e.g., six months).

[1300] Step 8: Listing Proposal

[1301] Server: Notifies the user via LINE of a suggestion to sell unused clothing. The input is the unused clothing data, and the output is a suggestion message. Specifically, a template message is used to describe the reason for recommending the item for sale and the listing procedure, and the notification is sent using the LINE API.

[1302] User: Checks the listing proposal and clicks the listing button on LINE if they wish to accept the listing. The input is the user's click, and the output is the listing acceptance data.

[1303] Terminal: The user's click operation is sent to the server. Specifically, the HTTP POST request is sent to the server along with the consent data.

[1304] Server: Based on the received listing request, the server calls the Yahoo! Flea Market API and automatically processes the listing. The input is the listing acceptance data, and the output is the created listing page. Specifically, the server calls the API, sends the necessary data, and saves the response.

[1305] Step 9: New clothing suggestions

[1306] Server: Analyzes the contents of the closet, weather information, and fashion information to select appropriate new clothing. The input is this data, and the output is a message suggesting new clothing. Specifically, it uses a data analysis algorithm to select the most suitable clothing item and sends the suggested message to the user using the LINE API.

[1307] User: Receives information about a new clothing item via LINE and clicks the purchase link to consider purchasing it. The input is the suggestion message, and the output is the click data of the purchase link.

[1308] Step 10: Emotion Recognition

[1309] User: Checks the proposed outfit and uses the camera to allow the emotion recognition engine to analyze the facial expressions. The input is the user's facial expression data, and the output is the emotional state data.

[1310] Device: Captures facial expressions and sends the data to the emotion recognition engine in real time. Specifically, it uses the camera API to obtain facial expression data and sends it via an HTTP POST request.

[1311] Server: The emotion recognition engine analyzes facial expression data and recognizes the user's emotional state. The output is emotional state data as the analysis result, which is used to improve the accuracy of the next outfit suggestion.

[1312] The above is the specific flow and operation of the program processing of this system.

[1313] (Application example 2)

[1314] 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."

[1315] Conventional closet management systems and outfit suggestion systems have limitations in improving user satisfaction because they do not fully consider the user's emotional state or in-store experience. Furthermore, it is necessary to provide more precise outfit suggestions by appropriately reflecting user feedback, but there has been no effective system for doing so.

[1316] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1317] In this invention, the server includes means for acquiring weather information, means for acquiring user clothing data, means for generating clothing combination suggestions using an AI model based on the acquired weather information and the user clothing data, means for notifying the user device of the suggestions, means for receiving feedback from the user, means for adjusting the AI ​​model based on the feedback, means for identifying unused clothing data and notifying the user of listing suggestions, means for suggesting new clothing, means for recognizing the user's emotional state, and means for the user device to be installed in a device installed in a physical store, means for recognizing the user's facial expression data, and means for adjusting the suggestions based on the acquired customer facial expression data. This enables more precise and personalized coordination suggestions that take the user's emotional state into consideration, improving the user experience in the physical store and enabling more efficient closet management.

[1318] "Weather information" refers to the temperature, humidity, chance of precipitation, and other weather-related data for that day.

[1319] "User clothing data" refers to detailed information about the type, color, size, and frequency of use of clothing owned by the user.

[1320] The "artificial intelligence model" is a machine learning algorithm that suggests optimal clothing combinations based on the user's clothing data and weather information.

[1321] A "generator" is a processing unit for generating suggested coordinates using an artificial intelligence model.

[1322] The "means for notifying" is a communication means for transmitting the generated coordination proposal to the user device.

[1323] The "means for receiving feedback" is a function for receiving opinions and evaluations of suggestions from users.

[1324] A "means for adjusting" is a process for optimizing an artificial intelligence model based on received feedback.

[1325] "Unused clothing data" is information about clothing that has not been used for a long period of time.

[1326] "Suggestion for sale" is a function that presents unused clothing to the user and suggests selling it on the online market.

[1327] The "emotional state" is a psychological state obtained by analyzing the facial expression data of the user.

[1328] "User Device" is a digital terminal that a user uses to receive suggested coordinates and provide feedback.

[1329] "Facial expression data" is image information of the user's face acquired using a camera, and is used for emotion recognition.

[1330] "In-store devices" are devices used to enhance the in-store experience, such as smart mirrors and tablets in fitting rooms.

[1331] System program generation

[1332] The system for implementing this invention mainly includes a means for acquiring weather information, a means for acquiring user clothing data, a generating means, a notifying means, a means for receiving feedback, an adjusting means, a means for identifying unused clothing data, a means for notifying of listing suggestions, a means for suggesting new clothing, a means for recognizing the emotional state of the user, a means for the user device to be installed in a device installed in a physical store, a means for recognizing facial expression data, and a means for adjusting suggestions.

[1333] Program processing explanation

[1334] 1. Obtaining weather information:

[1335] The server calls the weather API every morning at 6:00 to obtain the day's weather information (e.g., temperature, humidity, and probability of precipitation). The API used is provided by a general weather data provider. The obtained data is stored in a database and used when generating proposals.

[1336] 2. Get user clothing data:

[1337] Users register their clothing through the application when they first register or purchase new clothes. They take a photo of the clothing and enter its type, color, size, and other details. The device (such as a smartphone or tablet) then sends the entered data to the server and stores it in a database.

[1338] 3. Generation means:

[1339] The server generates optimal outfits based on the user's clothing data and weather information using an artificial intelligence model that includes machine learning algorithms that learn by taking into account the user's past feedback and emotional state.

[1340] 4. Means of notification:

[1341] The server generates an image and description of the coordinated outfit and notifies the user of the image and description on their device (e.g., a smartphone or tablet). The notification method can be, for example, the LINE API.

[1342] 5. How to receive feedback:

[1343] The user provides feedback on the proposed outfit, either "OK" or "NG." This feedback is sent to the server via the device. In addition, the user's facial expression is captured by a camera and sent to an emotion recognition engine (e.g., EmotionRecognizer).

[1344] 6. Adjustment methods:

[1345] Based on the received feedback and emotion recognition data, the server can adjust its artificial intelligence model to improve the accuracy of its next outfit suggestions.

[1346] Hardware and software used

[1347] Hardware: Smartphones, tablets, smart mirrors in brick-and-mortar stores

[1348] Software: Weather API, EmotionRecognizer, database management system, LINE API

[1349] Specific examples

[1350] When a user stands in front of a smart mirror in a physical store in the morning, a message appears saying, "Today's weather is 15 degrees Celsius and 70% humidity. We recommend the following outfit." Along with an image suggesting an outfit, the mirror suggests "a blue jacket, a white shirt, and black jeans."

[1351] The user reviews the suggestion and provides feedback, either "OK" or "NG," along with sending facial expression data via the camera. This data is stored on the server and reflected in the next suggestion.

[1352] Furthermore, the system identifies a red dress that the user has barely worn and displays a message saying, "It looks like you haven't worn this dress much. Would you like to list it for sale?" If the user agrees to the listing, it will be listed on an online marketplace with one click.

[1353] The user will also be notified of a new "yellow cardigan" suggestion based on their style and current trends, and will receive a message asking, "What do you think of this item?"

[1354] Example prompts for generative AI models

[1355] "Please suggest the best outfit based on the following information: user's clothing data, weather information, fashion information, and user's emotional state."

[1356] This system reduces the effort required for users to choose their daily outfits and efficiently supports closet management. Furthermore, by utilizing emotion recognition, it can improve user satisfaction.

[1357] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1358] Step 1:

[1359] The server calls the weather API every morning at 6:00 to obtain the weather information for that day. Specifically, it obtains data such as temperature, humidity, and probability of precipitation, which are then stored in a database. The input is data from the weather API, and the output is the weather information stored in the database.

[1360] Step 2:

[1361] Users register their clothing through the application when they first register or when they purchase new clothes. They take a photo of the clothing and enter detailed information such as type, color, size, and frequency of use. The device sends the entered data to the server and stores it in a database. The input is the clothing data entered by the user, and the output is the clothing information stored in the database.

[1362] Step 3:

[1363] The server uses an artificial intelligence model to generate optimal outfits based on the user's clothing data and weather information. The method used here is a machine learning algorithm. The input is clothing data stored in a database and weather information, and the output is the generated outfit.

[1364] Step 4:

[1365] The server generates an image and description of the coordinated outfit and notifies the user's device of this. The notification method uses LINE's API. The input is the coordinated outfit, and the output is a notification of the coordinated outfit sent to the user's device.

[1366] Step 5:

[1367] The user provides feedback on the proposed outfit, either "OK" or "NG." The feedback is sent to the server via the device. In addition, the user's facial expression is captured by a camera and sent to an emotion recognition engine. The input is the user's feedback and facial expression data, and the output is the feedback and emotion data stored on the server.

[1368] Step 6:

[1369] The server adjusts the AI ​​model based on the received feedback and emotion recognition data to improve the accuracy of the next outfit suggestion. Here, the machine learning algorithm learns from the feedback and emotion data and updates the model. The input is the feedback and emotion recognition data, and the output is the updated AI model.

[1370] Step 7:

[1371] The server periodically analyzes the user's closet data and usage history to identify clothes that have not been worn for a long time. Based on this information, it creates a list of unused clothes. The input is the user's closet data and usage history, and the output is a list of unused clothes.

[1372] Step 8:

[1373] The server notifies the user of suggestions for selling unused clothing. The recommendation, the reason for the recommendation, and the listing procedure are notified to the user via the LINE API. The input is a list of unused clothing, and the output is the suggestion sent to the user's device.

[1374] Step 9:

[1375] When the user agrees to the listing, they click the listing button on LINE. The device sends the user's click to the server, which calls the Yahoo! Flea Market API and automatically completes the listing process. The input is the user's approval to list the item, and the output is the listing page created on Yahoo! Flea Market.

[1376] Step 10:

[1377] The server analyzes weather information, fashion trends, and the contents of the user's closet to select appropriate new clothing items. The server notifies the user of new clothing suggestions via LINE. The input is weather information, fashion trends, and closet contents, and the output is new clothing suggestions sent to the user's device.

[1378] Step 11:

[1379] The user confirms the proposed outfit and allows the emotion recognition engine to analyze their facial expressions through the camera. The device captures the user's facial expression data and sends it to the emotion recognition engine. The input is the facial expression data, and the output is the emotional state analyzed by the emotion recognition engine.

[1380] 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.

[1381] 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.

[1382] 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.

[1383] [Fourth embodiment]

[1384] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1385] 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.

[1386] 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).

[1387] 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.

[1388] 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.

[1389] 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).

[1390] 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.

[1391] 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.

[1392] 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.

[1393] 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.

[1394] 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.

[1395] 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.

[1396] 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."

[1397] To implement this invention, a system using weather information, user clothing data, an AI model, a generation means, a notification means, feedback, an adjustment means, unused clothing data, listing suggestions, and a user device is required. This system aims to improve user convenience by suggesting appropriate outfits to users, streamlining closet management, and even suggesting new clothing.

[1398] Program processing explanation

[1399] The system's program mainly consists of the following steps: obtaining weather information, obtaining the user's clothing data, generating outfits, notifications, processing feedback, adjusting the AI ​​model, identifying unused clothing, suggesting items for sale, and suggesting new clothing.

[1400] Obtaining weather information

[1401] Server: Calls the weather API every morning at 6am to obtain the day's weather information (e.g. temperature, humidity, chance of precipitation). This information is stored in a database and used to generate outfits.

[1402] Obtaining user clothing data

[1403] Users: When registering for the first time and when purchasing new clothes, they register their clothing through the application, taking a photo of the clothing and entering details such as type, color, and size.

[1404] Terminal: Sends the entered information to the server, which stores it in a database.

[1405] Coordinate generation

[1406] Server: Based on the user's clothing data and weather information, an artificial intelligence model is used to generate the optimal outfit. At this stage, the machine learning algorithm takes into account the user's preferences and previous feedback.

[1407] notification

[1408] Server: Generates an image and description of the coordinated outfit, and sends it to the user's LINE account using the LINE API.

[1409] User: Receive suggested outfits via LINE to help with daily outfit selection.

[1410] Processing Feedback

[1411] User: Sends feedback on the proposed outfit, either "OK" or "NG," via LINE message.

[1412] Terminal: Sends a feedback message to the server.

[1413] Server: Stores the received feedback in a database and adjusts the parameters of the AI ​​model to improve the accuracy of the next suggestion.

[1414] Identifying unused clothing

[1415] Server: Analyzes the user's usage history and identifies clothes that have not been used for a long time. Based on this information, a list of unused clothes is created.

[1416] Listing proposal

[1417] Server: Proposes to users via LINE that they should sell unused clothing.

[1418] Users: If they accept the listing proposal, the listing process is completed with one click.

[1419] Server: Sends listing information to the Yahoo! Flea Market API and automatically processes the listing.

[1420] New clothing proposals

[1421] Server: Selects new clothing items based on weather information, fashion trends, and the contents of the user's closet.

[1422] Server: Providing information about selected new clothing items to users via LINE.

[1423] Specific examples

[1424] Here's a specific example. For example, when a user wakes up in the morning and checks LINE, they receive a message saying, "Today's weather is 15 degrees Celsius and 70% humidity. We recommend the following outfit," along with an image of an outfit suggestion: "Blue jacket, white shirt, black jeans." The user checks the suggestion and sends feedback saying "OK." This feedback information is sent to the server and reflected in the next suggestion.

[1425] Furthermore, the system identifies a red dress that the user has hardly worn, and sends a message on LINE saying, "It looks like you haven't worn this dress much. Would you like to list it for sale?" If the user agrees to the listing, it will be listed on Yahoo! Flea Market with one click.

[1426] Additionally, based on the user's style and recent trends, a new "yellow cardigan" will be suggested via LINE, and a message will be sent asking, "What do you think of this item?"

[1427] In this way, the system saves users the trouble of choosing their daily clothes and also efficiently supports closet management.

[1428] The processing flow will be explained below.

[1429] Step 1:

[1430] User: When registering for the first time, users enter their basic information (e.g., name, gender, height, weight, preferred style) into the application. At the same time, they also enter information about the clothing they own (e.g., type, color, size, material) along with a photo.

[1431] Step 2:

[1432] Terminal: The basic information and clothing data entered by the user is sent to the server via the Internet.

[1433] Step 3:

[1434] Server: The received user's basic information and clothing data are stored in a database, and the characteristics of each piece of clothing are analyzed and classified using an AI-based image recognition algorithm.

[1435] Step 4:

[1436] Server: Calls the weather API every morning at 6am to get the weather information for that day (e.g. temperature, humidity, chance of precipitation) for a specific region. Stores this information in a database.

[1437] Step 5:

[1438] Server: At a specified time (e.g., 7:00 a.m. every morning), weather data for the day is extracted based on each user's registered location information, and input into the AI ​​model along with the user's basic information and clothing data.

[1439] Step 6:

[1440] Server: The AI ​​model generates optimal outfits based on input weather data and the user's clothing data. During this process, machine learning algorithms take into account the user's past feedback and preferences.

[1441] Step 7:

[1442] Server: Creates an image and description of the generated outfit, and sends it to the user's LINE account using the LINE API.

[1443] Step 8:

[1444] User: Check the suggested outfits on LINE and send feedback by pressing the "OK" button if satisfied with the selection, or the "NG" button if not.

[1445] Step 9:

[1446] Terminal: Forwards the feedback messages sent by the user to the server.

[1447] Step 10:

[1448] Server: Stores the received feedback in a database and adjusts the parameters of the AI ​​model to improve the accuracy of the next outfit suggestion.

[1449] Step 11:

[1450] Server: Periodically analyzes the user's closet data and usage history to identify clothes that have not been worn for a long time. Based on this information, it creates a list of unused clothes.

[1451] Step 12:

[1452] Server: Sends suggestions to users via LINE about clothes that have not been used for a long time. The message explains why the item should be listed and provides instructions on how to list the item.

[1453] Step 13:

[1454] User: After reviewing the listing proposal, if they agree to the listing, they click the listing button on LINE, which automatically starts the listing process on Yahoo! Flea Market.

[1455] Step 14:

[1456] Terminal: Sends user clicks to the server.

[1457] Step 15:

[1458] Server: Based on the received listing request, the Yahoo! Flea Market API is called and the listing process is automatically carried out. A listing page is created based on the registered information.

[1459] Step 16:

[1460] Server: Analyzes weather information, fashion trends, and the contents of the user's closet to select appropriate new clothing items. Creates messages to suggest this information to the user.

[1461] Step 17:

[1462] Server: Sends new clothing suggestion messages to users via LINE. The messages include images, descriptions, and purchase links for the suggested new clothing. This allows users to easily purchase new clothes.

[1463] This allows the system to support users in choosing their daily outfits and provide efficient closet management, improving the accuracy of suggestions based on feedback and encouraging users to purchase new clothes or organize unused clothing.

[1464] Example 1

[1465] 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."

[1466] Conventional closet management systems have issues with insufficient clothing suggestions and closet management for users, and have low efficiency in suggesting daily outfits, identifying unused clothing, and suggesting items for sale. In particular, there is a need for systems that can generate appropriate outfits that reflect weather information and user preferences, improve the accuracy of AI models using user feedback, and suggest new clothing.

[1467] 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.

[1468] In this invention, the server includes means for acquiring weather information, means for acquiring user clothing data, means for generating clothing combination suggestions using an AI model based on the acquired weather information and the user clothing data, means for notifying the user device of the suggestions, means for receiving feedback from the user, means for adjusting the AI ​​model based on the feedback, means for identifying unused clothing data and notifying the user of suggestions for selling, means for suggesting new clothing, schedule management means for determining when to acquire weather information, means for controlling notifications based on the weather information and the state of the user device, and means for supporting the new registration of clothing purchased by the user based on the above means. This allows for efficient and accurate clothing suggestions to be made to the user, streamlining closet management, and enabling suggestions for selling unused clothing and new clothing to be made.

[1469] "Means of obtaining weather information" refers to the function of obtaining weather data such as temperature, humidity, and probability of precipitation at specified times using a weather API, etc.

[1470] "Means for obtaining user clothing data" refers to the function that allows the user to input photos and detailed information about clothing through the application, and then send it to the server and store it in a database.

[1471] "Generation method using artificial intelligence model" refers to a function that uses machine learning algorithms to suggest optimal clothing combinations based on the user's clothing data and weather information.

[1472] The "means for notifying the user device of the proposal" refers to a function for generating an image and description of the clothing combination and transmitting them to the user device using a communication means.

[1473] "Means for receiving feedback from users" refers to a function that allows users to send feedback such as "OK" or "NG" on proposed costumes.

[1474] "Means for adjusting the AI ​​model" refers to a function that adjusts the parameters of the AI ​​model based on feedback from users to improve the accuracy of future suggestions.

[1475] "Means for identifying unused clothing data and notifying users of listing suggestions" refers to a function that identifies clothing that has not been used for a long period of time from a database and makes suggestions to users based on that information.

[1476] "Means for suggesting new clothing" refers to a function that selects and suggests new clothing suitable for the user based on weather information, trend information, and the contents of the user's closet.

[1477] "Schedule management means for determining the timing of obtaining weather information" refers to a function that sets a regular schedule and manages the timing of obtaining weather information from the API at that time.

[1478] "Means for controlling notifications based on weather information and the status of the user device" refers to a function that determines weather information and the usage status of the user device, and notifies coordination suggestions at the optimal time.

[1479] "Means to support users in registering new clothing purchases" refers to a function that allows users to easily input and register information about newly purchased clothing through the application.

[1480] To implement this invention, a system using weather information, user clothing data, an AI model, a generation means, a notification means, a feedback means, an adjustment means, unused clothing data, listing suggestions, new clothing suggestions, and a user device is required. This system aims to improve user convenience by suggesting appropriate outfits to users, streamlining closet management, and suggesting new clothing.

[1481] The present invention is implemented using the following hardware and software.

[1482] Hardware

[1483] Server: Responsible for the central processing of the program. This is where data is stored, analyzed, and artificial intelligence models are trained and executed.

[1484] Terminal: The device operated by the user (smartphone, tablet, etc.) on which the application is installed.

[1485] User device: Serves as an interface with the user and is used to provide coordination suggestions and give feedback.

[1486] software

[1487] Weather API: Obtain weather information using the OpenWeather API, etc.

[1488] Artificial intelligence model: Generate coordinates using TensorFlow or PyTorch.

[1489] Database: Use a database system such as MySQL to store data.

[1490] Communication method: Sending and receiving data via REST API, notification and feedback processing using LINE API.

[1491] Specific examples

[1492] Specific examples are shown below.

[1493] Obtaining weather information

[1494] The server triggers a scheduled task every morning at 6:00, which retrieves the weather information for that day (e.g., temperature 15°C, humidity 70%, chance of precipitation 40%) from the OpenWeather API. This information is stored in a database in JSON format.

[1495] Obtaining user clothing data

[1496] A user registers a new shirt using a smartphone application. The user takes a photo of the shirt and enters the type (shirt), color (blue), and size (M). The device sends this data to the server via a REST API, and the server stores it in a database.

[1497] Coordinate generation

[1498] The server acquires the user's clothing data and weather information and inputs it into an artificial intelligence model using TensorFlow. For example, on a day when the temperature is 15 degrees, a coordination of "blue jacket, white shirt, black jeans" is generated. The results are saved as images and text.

[1499] notification

[1500] The generated outfit is sent to the user's device via the LINE API and displayed with the message, "Today's weather is 15 degrees Celsius and 70% humidity. We recommend the following outfit."

[1501] Processing Feedback

[1502] The user sends feedback via LINE, either "OK" or "NG." The device then sends this feedback to the server, which stores it in a database. This feedback is then reflected in the next proposal.

[1503] Identifying unused clothing

[1504] The server periodically analyzes the user's usage history and identifies clothing that has not been worn for a long time (e.g., a red dress). Based on this information, it creates a list of unused clothing and suggests items for sale to the user via LINE.

[1505] Listing proposal

[1506] When the user accepts the listing proposal, the server automatically processes the listing using the Yahoo! Flea Market API.

[1507] New clothing proposals

[1508] The server selects new clothing items (e.g., a yellow cardigan) based on weather information, fashion trends, and the contents of the user's closet, and suggests them via LINE.

[1509] Prompt Sentence Examples

[1510] "This system calls the OpenWeather API every morning at 6am to get the weather information for the day. Explain how it then matches this with the user's clothing data and uses TensorFlow to generate the optimal outfit."

[1511] In this way, the system saves users the trouble of choosing their daily clothes and efficiently supports closet management.

[1512] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1513] Step 1: Get weather information

[1514] The server triggers a scheduled task every morning at 6:00 AM. It calls a specified weather API (e.g., OpenWeather API) to "get weather information."

[1515] Input: Time (6 o'clock)

[1516] Output: Weather information for the day (Temperature 15°C, Humidity 70%, Chance of precipitation 40%)

[1517] Specific operation: The server issues an API request, analyzes the received JSON-formatted weather data, and stores the necessary information in a database.

[1518] Step 2: Obtaining the user's clothing data

[1519] When a user purchases new clothing, they use a smartphone application to take a photo of the clothing and enter details such as type (shirt), color (blue), and size (M).

[1520] Input: Clothing photos and details entered by the user

[1521] Output: Clothing data stored in a database

[1522] Specific operation: The device compresses the form input data and photo and sends them to the server via REST API. The server stores the received data in a database.

[1523] Step 3: Generate coordinates

[1524] The server receives the user's clothing data and weather information and inputs it into an AI model (e.g., TensorFlow), which then generates the optimal clothing combination.

[1525] Input: User clothing data stored in the database, weather information for the day

[1526] Output: Outfit suggestions (e.g. blue jacket, white shirt, black jeans)

[1527] What it does: The server runs a machine learning algorithm to generate outfits that take into account the user's preferences and past feedback. The results are stored in JSON format.

[1528] Step 4: Notification

[1529] The server notifies the user device of the generated coordination results as images and text via the LINE API.

[1530] Input: Coordination suggestions

[1531] Output: Coordination suggestions sent as LINE messages

[1532] Specific operation: The server sends the image URL and message to the LINE API, and the coordination is notified to the user's LINE account.

[1533] Step 5: Processing feedback

[1534] Users can provide feedback on the suggested outfits via LINE messages, either "OK" or "NG."

[1535] Input: User feedback (OK or NG)

[1536] Output: Feedback information stored in a database

[1537] Specific operation: The terminal sends a feedback message to the server, which stores the information in a database and uses it to adjust the parameters of the artificial intelligence model.

[1538] Step 6: Identify unused clothing

[1539] The server analyzes the user's usage history and identifies clothing that has not been used for a long time.

[1540] Input: User's clothing usage history

[1541] Output: List of unused clothing items

[1542] Specific behavior: The server periodically searches the database and lists any clothing that has not been used for more than a certain period of time (e.g., six months).

[1543] Step 7: Listing Proposal

[1544] The server suggests to users via LINE that they put up for sale unused clothing.

[1545] Input: Unused clothing list

[1546] Output: Listing suggestion message

[1547] Specific operation: The server uses the LINE API to send a message saying, "This dress doesn't seem to be worn much. Would you like to list it for sale?"

[1548] Step 8: New clothing suggestions

[1549] The server selects new clothing items based on weather information, fashion trends, and the contents of the user's closet.

[1550] Input: Weather information, trends, closet contents

[1551] Output: New clothing suggestions

[1552] Specific operation: The server analyzes the data based on the above information, selects new clothing items suitable for the user (e.g., a yellow cardigan), and suggests them via the LINE API.

[1553] Through the above processing steps, this system can save the user the trouble of choosing clothes on a daily basis and efficiently support closet management.

[1554] (Application example 1)

[1555] 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."

[1556] Previously, there were systems that suggested clothing coordination based on weather information and the user's clothing data. However, most of these systems required the user to manually input data, and only a limited number of systems utilized smart devices to provide real-time suggestions in a virtual space. Furthermore, the systems for effectively collecting user feedback and reflecting it in future suggestions were inadequate. Furthermore, efficient methods for managing closets, suggesting the sale of unused clothing, and suggesting new clothing were needed. Therefore, a comprehensive system that could significantly improve user convenience was needed.

[1557] 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.

[1558] In this invention, the server includes means for acquiring weather information, means for acquiring user clothing data, means for generating clothing combination suggestions using an AI model based on the acquired weather information and the user clothing data, means for notifying the user device of the suggestions, means for receiving feedback from the user, means for adjusting the AI ​​model based on the feedback, means for identifying unused clothing data and notifying the user of suggestions for clothing to be sold, means for suggesting new clothing, and means for the user to wear a smart device to check suggested outfits in a virtual space and provide feedback. This allows the user to receive outfit suggestions in a virtual space in real time, achieving efficient closet management and outfit suggestions.

[1559] "Weather information" is data about the weather conditions in a specific area, including temperature, humidity, probability of precipitation, and the like.

[1560] "User clothing data" is data including the type, color, size, and other related information of clothing owned by a user.

[1561] "Generation means" refers to a means for generating clothing combinations using an artificial intelligence model based on weather information and user clothing data.

[1562] "User Device" refers to electronic devices used by a User, such as computers, smartphones, tablets, and smart devices.

[1563] The "notification means" is a means for transmitting the generated coordination proposal to the user device.

[1564] "Feedback means" refers to a means for collecting evaluations and opinions from users and receiving that data.

[1565] The "adjustment means" is a means for adjusting the parameters of the artificial intelligence model based on feedback from the user.

[1566] "Unused clothing data" refers to information about clothing that a user has not worn within a specific period of time.

[1567] A "suggestion to sell" is a suggestion to sell unused clothing to other users.

[1568] "New clothing suggestions" refers to suggesting new clothing to the user based on the contents of the user's current closet and trend information.

[1569] "Smart devices" refers to interactive electronic devices such as internet-enabled glasses and head-mounted displays.

[1570] A "virtual space" is a three-dimensional virtual environment constructed using virtual reality technology, in which users can interact.

[1571] A "generative AI model" refers to a model that uses artificial intelligence technology to generate or suggest specific objects or situations.

[1572] A "prompt sentence" is a sentence that gives instructions to an artificial intelligence model and is an input sentence to perform a specific task.

[1573] To implement the present invention, a system is provided that uses the following hardware and software.

[1574] Hardware

[1575] Server: A high-performance server for acquiring weather information, managing the database, and generating and adjusting AI models.

[1576] User device: A device operated by a user, such as a smartphone, tablet, computer, smart glasses, or head-mounted display (e.g., Oculus Rift).

[1577] software

[1578] Weather API: API for obtaining weather information such as WeatherAPI.

[1579] LINE Messaging API: An API for notifying users of suggested outfits and collecting feedback.

[1580] Generative AI model: An artificial intelligence model built using a programming language such as Python.

[1581] Machine learning algorithms: Algorithms that use user feedback information to train and adjust models.

[1582] Data processing and calculation

[1583] The server calls the weather API every morning at 6am to obtain the day's weather information (e.g., temperature, humidity, and chance of precipitation) and stores it in a database. When users register for the first time or purchase new clothes, they register their clothing data through their smart devices. The server uses this information to generate optimal outfits using a generative AI model and notifies the user of the generated outfits using LINE's API. The user checks the suggested outfits on LINE and provides feedback. This feedback information is sent to the system, and the server uses it to adjust the artificial intelligence model.

[1584] The system also has a means of identifying unused clothing data and notifying users of suggestions for listing items. These suggestions are made via LINE, and if the user accepts, the listing process is automatically carried out using platforms such as Yahoo! Flea Market. New clothing suggestions are based on weather information, fashion trends, and the contents of the user's closet.

[1585] Specific examples

[1586] For example, when a user wakes up in the morning, launches the Virtual Closet Coordinator, and puts on the smart glasses, a message appears in the VR space saying, "Today's weather is 15 degrees Celsius and 70% humidity. We recommend the following outfit," along with a blue jacket, white shirt, and black jeans that can be virtually tried on. After virtually trying on the clothes, the user can give feedback of "OK," and this information will be reflected in the next outfit suggestions.

[1587] Prompt Sentence Examples

[1588] Enter the following information into the AI ​​model to generate the optimal outfit.

[1589] Weather information: Temperature is 15 degrees and humidity is 70%.

[1590] User clothing data: "Blue jacket, white shirt, black jeans."

[1591] As described above, this system reduces the effort required for users to choose their daily clothes and provides efficient support for closet management.

[1592] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1593] Step 1:

[1594] The server calls the weather API every morning at 6:00 to retrieve the weather information for that day. The retrieved weather information includes temperature, humidity, and probability of precipitation. This data is stored in a database and used for subsequent processing.

[1595] Input: Weather API call

[1596] Output: Weather information data (temperature, humidity, precipitation probability)

[1597] Step 2:

[1598] When a user first registers or purchases new clothes, they register their clothing data in the application via their smart device. They take a photo of the clothing and enter details such as type, color, and size. The entered information is sent from the device to the server and stored in a database.

[1599] Input: User's clothing data (photo, type, color, size)

[1600] Output: Updated clothing database

[1601] Step 3:

[1602] The server receives weather information and the user's clothing data and uses a generative AI model to generate optimal outfits. The generative AI model takes into account weather conditions and the user's past feedback information to suggest outfits.

[1603] Input: Weather information data, clothing data

[1604] Output: Coordination suggestions

[1605] Step 4:

[1606] The server generates an image and description of the coordinated outfit and sends it to the user's LINE account using the LINE API, allowing the user to receive the suggested coordinated outfit.

[1607] Input: Coordination suggestions

[1608] Output: LINE message (coordinate image and description)

[1609] Step 5:

[1610] The user checks the proposed outfits on LINE and sends feedback such as "OK" or "NG" via LINE message, which records the user's evaluation.

[1611] Input: Coordination suggestions, user feedback

[1612] Output: Feedback message

[1613] Step 6:

[1614] The device sends the feedback it receives to the server, which stores it in a database and uses it to adjust the parameters of the generative AI model to improve the accuracy of its next suggestions.

[1615] Input: User feedback

[1616] Output: An updated generative AI model

[1617] Step 7:

[1618] The server analyzes the user's usage history and identifies clothes that have not been used for a long time. Based on this data, it creates a list of unused clothes and notifies the user via LINE of suggestions to sell them.

[1619] Input: Clothing usage history

[1620] Output: Listing suggestion message

[1621] Step 8:

[1622] If the user accepts the listing proposal via LINE, the listing process is completed with one click. The server automatically completes the listing process using the Yahoo! Flea Market API.

[1623] Input: Accept the offer

[1624] Output: Listing procedure completed

[1625] Step 9:

[1626] The server selects new clothing items based on weather information, fashion trends, and the contents of the user's closet, and then suggests the selected new clothing items to the user via LINE.

[1627] Input: Weather information, trends, closet contents

[1628] Output: New clothing suggestion message

[1629] 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.

[1630] To implement this invention, a system using weather information, user clothing data, an AI model, a generation means, a notification means, a feedback, an adjustment means, unused clothing data, listing suggestions, new clothing suggestions, and an emotion recognition engine is required. This system suggests appropriate outfits to the user, streamlines closet management, and improves user convenience by suggesting new clothing, while also taking into account the user's emotional state.

[1631] Program processing explanation

[1632] The system's program mainly consists of the following steps: obtaining weather information, obtaining the user's clothing data, generating outfits, notifications, processing feedback, adjusting the AI ​​model, identifying unused clothing, suggesting items for sale, suggesting new clothing, and recognizing emotions.

[1633] Obtaining weather information

[1634] Server: Calls the weather API every morning at 6am to obtain the day's weather information (e.g. temperature, humidity, chance of precipitation). This information is stored in a database and used to generate outfits.

[1635] Obtaining user clothing data

[1636] Users: When registering for the first time and when purchasing new clothes, they register their clothing through the application, taking a photo of the clothing and entering details such as type, color, and size.

[1637] Terminal: Sends the entered information to the server, which stores it in a database.

[1638] Coordinate generation

[1639] Server: Based on the user's clothing data and weather information, an artificial intelligence model is used to generate the optimal outfit. At this stage, the machine learning algorithm takes into account the user's preferences and previous feedback.

[1640] notification

[1641] Server: Generates an image and description of the coordinated outfit, and sends it to the user's LINE account using the LINE API.

[1642] User: Check out the suggested outfits on LINE to help you choose your daily outfits.

[1643] Processing Feedback

[1644] User: Sends feedback on the proposed outfit, such as "OK" or "NG," via LINE message and grants permission to recognize facial expressions.

[1645] Device: Transfers the user's feedback message to the server, and at the same time activates the camera to capture facial expressions and send them to the emotion recognition engine.

[1646] Server: Stores the received feedback and emotion recognition data in a database and adjusts the parameters of the AI ​​model to improve the accuracy of the next outfit suggestion.

[1647] Identifying unused clothing

[1648] Server: Periodically analyzes the user's closet data and usage history to identify clothes that have not been worn for a long time. Based on this information, it creates a list of unused clothes.

[1649] Listing proposal

[1650] Server: Notifies users through LINE of suggestions to sell unused clothing. The message explains the reason for the recommendation and the steps to sell the clothing.

[1651] User: After reviewing the listing proposal, if they agree to the listing, they click the listing button on LINE, which automatically starts the listing process on Yahoo! Flea Market.

[1652] Terminal: Sends user clicks to the server.

[1653] Server: Based on the received listing request, the Yahoo! Flea Market API is called and the listing process is automatically carried out. A listing page is created based on the registered information.

[1654] New clothing proposals

[1655] Server: Analyzes weather information, fashion trends, and the contents of the user's closet to select appropriate new clothing items. Creates messages to suggest this information to the user.

[1656] Server: Sends new clothing suggestion messages to users via LINE. The messages include images, descriptions, and purchase links for the suggested new clothing. This allows users to easily purchase new clothes.

[1657] emotion recognition

[1658] User: Review the suggested outfit and allow the emotion recognition engine to analyze your facial expressions via the camera.

[1659] Device: Captures a picture of the user's facial expressions and sends them to an emotion recognition engine.

[1660] Server: The emotion recognition engine analyzes the user's facial expression data and recognizes the user's emotional state (e.g., satisfaction, confusion, disgust, etc.). Based on this emotional data, the AI ​​model will take the user's emotions into consideration when proposing the next outfit.

[1661] Specific examples

[1662] For example, when a user checks LINE in the morning, they receive a message saying, "Today's weather is 15 degrees Celsius and 70% humidity. We recommend the following outfit," along with an image of a suggested outfit: "Blue jacket, white shirt, black jeans." The user confirms the suggestion and sends feedback by saying "OK," along with facial expression data via the camera. This data is stored on the server and reflected in the next suggestion.

[1663] Furthermore, the system identifies a red dress that the user has hardly worn, and sends a message on LINE saying, "It looks like you haven't worn this dress much. Would you like to list it for sale?" If the user agrees to the listing, it will be listed on Yahoo! Flea Market with one click.

[1664] Additionally, based on the user's style and recent trends, a new "yellow cardigan" will be suggested via LINE, and a message will be sent asking, "What do you think of this item?"

[1665] In this way, the system reduces the effort required for users to choose their daily clothes and efficiently supports closet management. In addition, by utilizing emotion recognition, the system can provide more precise suggestions that take into account the user's emotions.

[1666] The processing flow will be explained below.

[1667] Step 1:

[1668] User: When registering for the first time, users enter their basic information (e.g., name, gender, height, weight, preferred style) into the application. At the same time, they register information about the clothing they own (e.g., type, color, size, material) along with a photo.

[1669] Terminal: Sends the entered information to the server.

[1670] Step 2:

[1671] Server: The received user's basic information and clothing data are stored in a database, and the characteristics of each piece of clothing are analyzed and classified using an AI-based image recognition algorithm.

[1672] Step 3:

[1673] Server: Calls the weather API every morning at 6am to obtain the day's weather information (e.g. temperature, humidity, chance of precipitation). This information is stored in a database and used to generate outfits.

[1674] Step 4:

[1675] Server: At a specified time (e.g., 7:00 a.m. every morning), weather data for the day is extracted based on each user's registered location information, and input into the AI ​​model along with the user's basic information and clothing data.

[1676] Step 5:

[1677] Server: The AI ​​model generates optimal outfits based on input weather data and the user's clothing data. During this process, machine learning algorithms take into account the user's past feedback and preferences.

[1678] Step 6:

[1679] Server: Creates an image and description of the generated outfit, and sends it to the user's LINE account using the LINE API.

[1680] Step 7:

[1681] User: Check the suggested outfits on LINE and send feedback by pressing the "OK" button if satisfied with the selection, or the "NG" button if not.

[1682] Step 8:

[1683] Device: Transfers the feedback message sent by the user to the server, and at the same time activates the camera to capture facial expressions and send them to the emotion recognition engine.

[1684] Step 9:

[1685] Server: Stores the received feedback and emotion recognition data in a database and adjusts the parameters of the AI ​​model to improve the accuracy of the next outfit suggestion.

[1686] Step 10:

[1687] Server: Periodically analyzes the user's closet data and usage history to identify clothes that have not been worn for a long time. Based on this information, a list of unused clothes is created.

[1688] Step 11:

[1689] Server: Notifies users through LINE of suggestions to sell unused clothing. The message explains the reason for the recommendation and the steps to sell the clothing.

[1690] Step 12:

[1691] User: After reviewing the listing proposal, if they agree to the listing, they click the listing button on LINE, which automatically starts the listing process on Yahoo! Flea Market.

[1692] Step 13:

[1693] Terminal: Sends user clicks to the server.

[1694] Step 14:

[1695] Server: Based on the received listing request, the Yahoo! Flea Market API is called and the listing process is automatically carried out. A listing page is created based on the registered information.

[1696] Step 15:

[1697] Server: Analyzes weather information, fashion trends, and the contents of the user's closet to select appropriate new clothing items. Creates messages to suggest this information to the user.

[1698] Step 16:

[1699] Server: Sends new clothing suggestion messages to users via LINE. The messages include images, descriptions, and purchase links for the suggested new clothing. This allows users to easily purchase new clothes.

[1700] Step 17:

[1701] User: Review the suggested outfit and allow the emotion recognition engine to analyze your facial expressions via the camera.

[1702] Step 18:

[1703] Device: Captures a picture of the user's facial expressions and sends them to an emotion recognition engine.

[1704] Step 19:

[1705] Server: The emotion recognition engine analyzes the user's facial expression data and recognizes the user's emotional state (e.g., satisfaction, confusion, disgust, etc.). Based on this emotional data, the AI ​​model will take the user's emotions into consideration when proposing the next outfit.

[1706] Specific examples

[1707] For example, when a user checks LINE in the morning, they receive a message saying, "Today's weather is 15 degrees Celsius and 70% humidity. We recommend the following outfit," along with an image of a suggested outfit: "Blue jacket, white shirt, black jeans." The user confirms the suggestion and sends feedback by saying "OK," along with facial expression data via the camera. This data is stored on the server and reflected in the next suggestion.

[1708] Furthermore, the system identifies a red dress that the user has hardly worn, and sends a message on LINE saying, "It looks like you haven't worn this dress much. Would you like to list it for sale?" If the user agrees to the listing, it will be listed on Yahoo! Flea Market with one click.

[1709] Additionally, based on the user's style and recent trends, a new "yellow cardigan" will be suggested via LINE, and a message will be sent asking, "What do you think of this item?"

[1710] In this way, the system reduces the effort required for users to choose their daily clothes and efficiently supports closet management. In addition, by utilizing emotion recognition, the system can provide more precise suggestions that take into account the user's emotions.

[1711] Example 2

[1712] 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."

[1713] Conventional outfit suggestion systems make suggestions based on weather information and the user's clothing data, but they do not consider the user's emotional state or suggest clothing that has not been worn for a long time. Furthermore, the AI ​​model is not adequately adjusted to effectively reflect user feedback, resulting in a problem of reduced suggestion accuracy. Furthermore, there is a need for a system that can make more accurate outfit suggestions by using user feedback and emotional state.

[1714] 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.

[1715] In this invention, the server includes means for acquiring weather information, means for acquiring user clothing data, means for generating clothing combination suggestions using an AI model based on the acquired weather information and the user clothing data, means for notifying the user device of the suggestions, means for receiving feedback from the user, means for adjusting the AI ​​model based on the feedback and the user's emotional state, means for analyzing facial expressions to recognize the user's emotional state, means for identifying unused clothing data and notifying the user of a suggestion for selling, and means for suggesting new clothing. This enables precise coordination suggestions that take the user's emotional state into consideration and also promotes the effective use of unused clothing.

[1716] "Weather information" refers to data about daily weather conditions, such as weather, temperature, humidity, and chance of precipitation.

[1717] "Clothing data" is information about clothing owned by a user, including the type, color, size, and other characteristics of the clothing.

[1718] An "artificial intelligence model" is a program based on machine learning algorithms that analyzes data and suggests optimal clothing combinations.

[1719] The "generation means" is a means for generating clothing combinations based on weather information and user clothing data using an artificial intelligence model.

[1720] The "notification means" is a means for notifying the user device of the generated clothing combinations and listing suggestions.

[1721] "Feedback" refers to information on the user's evaluation and reaction to the proposed clothing combinations.

[1722] The "adjustment means" is a means for changing the parameters of the artificial intelligence model based on feedback from the user and their emotional state, thereby improving the accuracy of the suggestions.

[1723] "Emotional state" refers to an emotional state such as satisfaction, confusion, or disgust that is recognized by analyzing the user's facial expression.

[1724] A "suggestion to sell" is a suggestion made to a user to encourage them to sell unused clothing.

[1725] "New clothing suggestions" are suggestions that introduce new clothing to the user based on the contents of the user's closet, weather information, and fashion information.

[1726] To implement this invention, a system using weather information, user clothing data, an AI model, a generation means, a notification means, a feedback, an adjustment means, unused clothing data, listing suggestions, new clothing suggestions, and an emotion recognition engine is required. This system suggests appropriate outfits to the user, streamlines closet management, and improves user convenience by suggesting new clothing, while also taking into account the user's emotional state.

[1727] The specific hardware and software for this system include a server, terminal, user device, weather API, LINE API, emotion recognition engine (e.g., Face API), and generative AI model (e.g., TensorFlow or PyTorch).

[1728] The server calls the weather API every morning at 6:00 to obtain the day's weather information (e.g., temperature, humidity, and chance of precipitation). This information is stored in the weather table of the database and used to generate outfits. Users also register their clothing through a smartphone app. They take photos of the clothing and enter detailed information such as type, color, and size. The device sends the entered information to the server in real time, and the server stores it in the clothing table of the database.

[1729] The server uses a generative AI model (for example, a model built with TensorFlow or PyTorch) to generate the optimal outfit based on the user's clothing data and the weather information for the day. The generated outfit is saved in the coordination_suggestions table in the database. This generated outfit is then generated as an image and description, and notified to the user's LINE account using the LINE API. The user can then check the presented outfit on LINE.

[1730] The user provides feedback on the proposed outfit. They reply with "OK" or "NG" via LINE message and give permission to capture their facial expression with the camera. The device then activates the camera, captures the user's facial expression, and sends the data in real time to the server. The feedback content is also sent. The server stores the received feedback and emotion recognition data in a database and adjusts the parameters of the artificial intelligence model based on the feedback and emotion recognition data. This improves the accuracy of the next outfit suggestion.

[1731] The server also periodically analyzes the user's closet data and usage history to identify clothing that has not been worn for a long time. It suggests selling unused clothing, and the user is notified via LINE. If the user accepts the listing, the listing process begins with one click. Once the server receives the user's acceptance, it calls the Yahoo! Flea Market API to automatically complete the listing process and create a listing page.

[1732] The server then analyzes weather information, fashion trends, and the contents of the user's closet to select appropriate new clothing. Based on this information, a suggestion message is created and sent to the user via LINE. The user receives the new clothing suggestion via LINE and can view an image, description, and purchase link of the suggested new clothing.

[1733] For example, when a user checks LINE in the morning, they receive a message saying, "Today's weather is 15 degrees Celsius and 70% humidity. We recommend the following outfit," along with an image of a suggested outfit: "Blue jacket, white shirt, black jeans." The user confirms the suggestion and sends feedback by saying "OK," along with facial expression data via the camera. This data is stored on the server and reflected in the next suggestion.

[1734] Furthermore, the system identifies a red dress that the user has rarely worn, and sends a LINE message saying, "It seems like you haven't worn this dress much. Would you like to list it for sale?" If the user accepts the listing, it will be listed on Yahoo! Flea Market with one click. Furthermore, based on the user's style and recent trends, the system also suggests a new "yellow cardigan" via LINE, sending a message saying, "What do you think of this item?"

[1735] An example prompt is:

[1736] "Please suggest an appropriate outfit based on the current weather and my clothing data. Also, please tell me how the AI ​​model used to make the suggestions is adjusted."

[1737] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1738] Step 1: Get weather information

[1739] Server: Calls the weather API every morning at 6am to obtain the day's weather information (e.g. temperature, humidity, probability of precipitation). The input is the response data from the weather API, which the server analyzes to extract the necessary information and saves in the weather table of the database. Specifically, it uses the API key to send an HTTP request and receives weather data in JSON format. After analysis, the temperature and humidity data is saved in the appropriate fields.

[1740] Step 2: Obtaining the user's clothing data

[1741] Users: When registering for the first time or when purchasing new clothes, they register their clothing items through a smartphone app. They input a photo of the clothing and detailed information such as type, color, and size.

[1742] Device: The entered information is sent in real time to the server, which then stores it in the clothing table in the database. Specifically, the user takes a photo of the clothing item in the app and enters the information in the text box. The device then sends this data to the server using an HTTP POST request.

[1743] Step 3: Generate coordinates

[1744] Server: Based on the user's clothing data and the weather information for the day, a generative AI model (for example, a model built with TensorFlow or PyTorch) is used to generate the optimal outfit. The input is the user's clothing data and weather information, and based on this, a machine learning algorithm processes and calculates the data to obtain the output. Specifically, it also takes into account previous user feedback and the preference patterns of other users. The results are saved in the coordination_suggestions table in the database.

[1745] Step 4: Notification

[1746] Server: Generates the generated outfit as an image and description, and uses this to notify the user's LINE account using the LINE API. The input is the outfit creation data, and the output is a message sent to the user's LINE account. Specifically, the server combines the image and text using a template message and sends an HTTP request to the LINE API.

[1747] Step 5: Processing feedback

[1748] User: Checks the proposed outfit on LINE and sends feedback of "OK" or "NG." The user also gives permission to capture their facial expression with the camera. The input is the user's feedback message and an image of their facial expression.

[1749] Device: Activates the camera, captures the user's facial expressions, and sends the data to the server in real time. It also sends feedback content in LINE messages. The output is the feedback data and an image of the facial expression. Specifically, it activates the camera API, obtains image data, and sends it to the server via an HTTP POST request.

[1750] Step 6: Tuning the AI ​​model

[1751] Server: Adjusts the parameters of the AI ​​model based on the received feedback and emotion recognition data. The input is the feedback data and emotion recognition data, and the output is the adjusted model parameters. Specifically, it updates the model weights using an optimization algorithm (e.g., gradient descent). This improves the accuracy of the next outfit suggestion.

[1752] Step 7: Identify unused clothing

[1753] Server: Periodically analyzes the user's closet data and usage history to identify clothes that have not been used for a long time. The input is closet data and usage history data, and the output is a list of unused clothes. Specifically, it uses a database query to extract items that have not been used for a certain period of time (e.g., six months).

[1754] Step 8: Listing Proposal

[1755] Server: Notifies the user via LINE of a suggestion to sell unused clothing. The input is the unused clothing data, and the output is a suggestion message. Specifically, a template message is used to describe the reason for recommending the item for sale and the listing procedure, and the notification is sent using the LINE API.

[1756] User: Checks the listing proposal and clicks the listing button on LINE if they wish to accept the listing. The input is the user's click, and the output is the listing acceptance data.

[1757] Terminal: The user's click operation is sent to the server. Specifically, the HTTP POST request is sent to the server along with the consent data.

[1758] Server: Based on the received listing request, the server calls the Yahoo! Flea Market API and automatically processes the listing. The input is the listing acceptance data, and the output is the created listing page. Specifically, the server calls the API, sends the necessary data, and saves the response.

[1759] Step 9: New clothing suggestions

[1760] Server: Analyzes the contents of the closet, weather information, and fashion information to select appropriate new clothing. The input is this data, and the output is a message suggesting new clothing. Specifically, it uses a data analysis algorithm to select the most suitable clothing item and sends the suggested message to the user using the LINE API.

[1761] User: Receives information about a new clothing item via LINE and clicks the purchase link to consider purchasing it. The input is the suggestion message, and the output is the click data of the purchase link.

[1762] Step 10: Emotion Recognition

[1763] User: Checks the proposed outfit and uses the camera to allow the emotion recognition engine to analyze the facial expressions. The input is the user's facial expression data, and the output is the emotional state data.

[1764] Device: Captures facial expressions and sends the data to the emotion recognition engine in real time. Specifically, it uses the camera API to obtain facial expression data and sends it via an HTTP POST request.

[1765] Server: The emotion recognition engine analyzes facial expression data and recognizes the user's emotional state. The output is emotional state data as the analysis result, which is used to improve the accuracy of the next outfit suggestion.

[1766] The above is the specific flow and operation of the program processing of this system.

[1767] (Application example 2)

[1768] 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."

[1769] Conventional closet management systems and outfit suggestion systems have limitations in improving user satisfaction because they do not fully consider the user's emotional state or in-store experience. Furthermore, it is necessary to provide more precise outfit suggestions by appropriately reflecting user feedback, but there has been no effective system for doing so.

[1770] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1771] In this invention, the server includes means for acquiring weather information, means for acquiring user clothing data, means for generating clothing combination suggestions using an AI model based on the acquired weather information and the user clothing data, means for notifying the user device of the suggestions, means for receiving feedback from the user, means for adjusting the AI ​​model based on the feedback, means for identifying unused clothing data and notifying the user of listing suggestions, means for suggesting new clothing, means for recognizing the user's emotional state, and means for the user device to be installed in a device installed in a physical store, means for recognizing the user's facial expression data, and means for adjusting the suggestions based on the acquired customer facial expression data. This enables more precise and personalized coordination suggestions that take the user's emotional state into consideration, improving the user experience in the physical store and enabling more efficient closet management.

[1772] "Weather information" refers to the temperature, humidity, chance of precipitation, and other weather-related data for that day.

[1773] "User clothing data" refers to detailed information about the type, color, size, and frequency of use of clothing owned by the user.

[1774] The "artificial intelligence model" is a machine learning algorithm that suggests optimal clothing combinations based on the user's clothing data ...

Claims

1. a means for obtaining weather information; A means for acquiring user clothing data; A generating means using an artificial intelligence model to suggest clothing combinations based on the acquired weather information and clothing data of the user; means for notifying a user device of the proposal; a means for receiving feedback from users; means for adjusting the artificial intelligence model based on the feedback; A means for identifying unused clothing data and notifying the user of a proposal to sell the clothing; A means of proposing new clothing, A system including:

2. The system of claim 1 , wherein the artificial intelligence model comprises a machine learning algorithm that learns using weather information and user feedback information.

3. The system of claim 1 , wherein the user device comprises communication means for receiving suggested clothing combinations and listing suggestions and transmitting user feedback and listing acceptances.

Images