System

Abstract

A system is provided.SOLUTION: A system comprising: means for inputting information relating to a fashion style and a lifestyle by a user; means including a generation-related AI model for learning trend information and a coordination theory; means for proposing optimal coordination based on the information of the user; means for specifying an item insufficient for the proposed coordination and proposing purchase of the item; and means for displaying the proposed information to the user.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] In modern life, there is a demand for systems that can quickly and efficiently suggest optimal outfits tailored to individual fashion styles and lifestyles. However, conventional methods require users to collect information and think about outfits themselves, which takes time and effort, and sometimes does not provide the optimal suggestions that suit their style. Furthermore, with fashion trends changing so quickly, it is difficult to incorporate the latest styles. Furthermore, when users are lacking a particular item, the system often does not provide appropriate purchasing suggestions to supplement that item, which can be a hassle for users. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides a system including the following means: By providing a means for users to input information about their fashion style and lifestyle, information from users can be collected efficiently. In addition, by using a means equipped with a generative AI model that learns trend information and coordination theory, it is possible to always propose coordinations based on the latest fashion trends. Furthermore, by providing a means for proposing optimal coordinations based on user information, the system meets the individual needs of each user. By providing a means for identifying items that are missing from the proposed coordination and suggesting the purchase of those items, it supports the rapid purchase of missing items and reduces the user's effort. Furthermore, by including a means for displaying the proposed information to the user, all suggestions can be conveyed to the user intuitively and visually.

[0006] The "user information input means" is a means for providing an interface for the user to input information about fashion style and lifestyle.

[0007] A "generative AI model" is a machine learning model used to learn trend information and coordination theory, and has the ability to generate optimal coordination and suggestions based on user information.

[0008] The "optimal coordination suggestion method" is a method for suggesting optimal fashion coordination using a generative AI model based on user information.

[0009] The "purchase suggestion means" is a means for identifying an item that is missing from the suggested coordination and suggesting to the user to purchase that item.

[0010] The "display means" is a means for visually displaying information such as suggested outfits and candidate items for purchase to the user. [Brief explanation of the drawings]

[0011] [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

[0012] 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.

[0013] First, the terms used in the following description will be explained.

[0014] 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).

[0015] 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.

[0016] 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.

[0017] 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.

[0018] 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."

[0019] [First embodiment]

[0020] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0021] 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.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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."

[0032] The present invention relates to an AI assistant system that provides optimal coordination and purchase suggestions to suit a user's fashion style and lifestyle. This system includes a user information input means, a generative AI model, optimal coordination suggestion means, purchase suggestion means, and display means.

[0033] Program processing overview

[0034] 1. Enter user information

[0035] - Users access a dedicated application or web interface and enter information about their fashion style and lifestyle, including their age, gender, favorite colors, body type, favorite places, and social media accounts.

[0036] - The device checks this information and then sends it to the server.

[0037] - The server stores the received information in a database.

[0038] 2. Study of trend and coordination theory

[0039] - The server collects the latest fashion articles, social media posts, and information on new brand products from the Internet.

[0040] - The server analyzes this data using text processing and image recognition technology, and trains a generative AI model to learn trend information and coordination theory.

[0041] 3. Coordination suggestions

[0042] - The user performs an operation to request outfit suggestions (for example, enter a command such as "Tell me today's recommended outfits").

[0043] - The device sends this request to the server.

[0044] - The server searches the database for user information and generates optimal outfit suggestions using a generative AI model.

[0045] - The server sends the generated coordination plan to the terminal.

[0046] - The terminal displays the suggested coordination to the user.

[0047] 4. Purchase Proposal

[0048] - The server retrieves the user's closet information (data on the clothes and accessories they own) from the database.

[0049] - The server uses a generative AI model to identify missing items in the proposed outfit.

[0050] - The server searches the API of the partner online shop or brand to find the item.

[0051] - The server sends information about the items to be purchased to the device.

[0052] - The device displays suggested purchase items and links to them to the user.

[0053] 5. Interface Operation

[0054] - The user operates the device to confirm each suggestion.

[0055] - When users click on an outfit or purchase item that interests them, detailed information will be displayed.

[0056] - Users can click on the purchase link and be taken to the online store or brand site to complete the purchase.

[0057] Specific examples

[0058] For example, let's say a female user in her 30s works in an office during the week and enjoys the outdoors on weekends, preferring a casual lifestyle. The user logs in to a dedicated application and enters her information. The server stores that information in a database and uses a generative AI model to suggest the user's optimal outfit. For example, it might suggest a "navy blazer, white blouse, jeans, and sneakers." Furthermore, it might identify that the user is short on navy blazers based on their closet information and suggest purchasing them. By finding a navy blazer at a partner online shop and providing the user with a purchase link, the user can easily purchase the missing item.

[0059] This system allows users to significantly reduce the time and effort spent on everyday fashion coordination and enjoy stylish outfits based on the latest trends.

[0060] The processing flow will be explained below.

[0061] Step 1:

[0062] Users access a dedicated application or web interface and enter information about their fashion style and lifestyle, such as age, gender, favorite colors, body type, and favorite places.

[0063] Step 2:

[0064] The terminal checks the entered information for formatting errors and, once the check is complete, sends the information to the server.

[0065] Step 3:

[0066] The server stores the received information in a database, which is managed individually for each user.

[0067] Step 4:

[0068] The server periodically collects the latest fashion articles, social media posts, and information on new brand releases from the internet, which is used to obtain trend information and update coordination theory.

[0069] Step 5:

[0070] The server analyzes the collected data using text processing and image recognition technology, and the analysis results are used as input data for the generative AI model.

[0071] Step 6:

[0072] The server trains the generative AI model by feeding it trend information and coordination theory. This process is carried out periodically to ensure that the model is constantly learning new information.

[0073] Step 7:

[0074] The user inputs a command such as "Tell me today's recommended outfits." After input, the request is sent from the device to the server.

[0075] Step 8:

[0076] The server searches the database for user information and uses a generative AI model to generate optimal outfit suggestions based on the user's preferences and lifestyle.

[0077] Step 9:

[0078] The server transmits the generated coordinate plan to the terminal, where the transmitted data is converted into a format for visual display.

[0079] Step 10:

[0080] The device will display the suggested outfits to the user, who can review them and, if they like them, request more information.

[0081] Step 11:

[0082] The server retrieves the user's closet information (data on the clothes and accessories they own) from a database and uses this information to identify any missing items for the proposed outfit.

[0083] Step 12:

[0084] The server searches the APIs of partner online shops or brands to find the identified missing items. It also collects information on potential items.

[0085] Step 13:

[0086] The server sends information about the items to be purchased to the device, including a purchase link and detailed product information.

[0087] Step 14:

[0088] The device displays the suggested purchase items and their associated purchase links to the user, who can then review the displayed content and click the purchase link if necessary.

[0089] Step 15:

[0090] The user clicks on the purchase link, which takes them to the online shop or brand site, allowing them to seamlessly purchase the suggested item.

[0091] In this way, the system can provide optimal coordination and purchase suggestions based on the user's fashion style and lifestyle.

[0092] Example 1

[0093] 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."

[0094] Conventional fashion coordination and purchase suggestion systems require users to collect and analyze vast amounts of information themselves, which requires a great deal of time and effort to efficiently enjoy stylish coordination.In addition, the technology to effectively manage and suggest items that users already own and items they need to purchase is insufficient.

[0095] 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.

[0096] In this invention, the server includes a means for a user to input information about their fashion style and lifestyle, a means having a generative AI model that learns trend information and coordination theory, a means for proposing optimal coordination based on the user information, a means for identifying items missing from the proposed coordination and proposing the purchase of those items, a means for displaying the proposed information to the user, and a means for the user to complete an online purchase via the suggested purchase link, thereby enabling the user to enjoy stylish coordination based on the latest trends without any hassle.

[0097] "User information" refers to data related to a user's fashion style and lifestyle, such as their age, gender, favorite colors, body type, favorite places, and social media accounts.

[0098] A "generative AI model" is an artificial intelligence model that analyzes and learns from fashion articles, social media posts, and new brand information collected from the internet, and generates trend information and coordination theories.

[0099] "Coordination suggestions" refer to suggestions for combining fashion items and styles created by a generative AI model based on user information.

[0100] "Purchase suggestion" refers to identifying items the user is missing from the generated outfit and providing links or information to purchase those items.

[0101] "Database" refers to the system that stores and manages user information, closet information, and collected fashion-related data.

[0102] "Closet information" refers to data about the clothes and accessories a user already owns.

[0103] "Trend information" refers to information about currently popular fashion styles and items.

[0104] "Method of completing an online purchase" refers to the user's actions to purchase an item from an online store or brand site via a suggested link.

[0105] "Learning with generative AI models" refers to the process of analyzing collected fashion-related data to understand and update trends and coordination theories.

[0106] This invention relates to an AI assistant system that provides optimal coordination and purchase suggestions to suit a user's fashion style and lifestyle. The system includes a user information input means, a generating AI model, optimal coordination suggestion means, purchase suggestion means, and display means.

[0107] First, the user accesses a dedicated application or web interface and enters their information, including age, gender, favorite colors, body type, favorite places, social media accounts, etc. The device verifies the information and sends it to the server, which then stores it in a database.

[0108] The server uses a scheduler to periodically collect the latest fashion articles, social media posts, and information on new brand releases from the Internet. Specific scraping tools (e.g., Beautiful Soup, Scrapy) are used to collect the data. After collection, the server analyzes the data using text processing (e.g., NLTK, spaCy) and image recognition techniques (e.g., OpenCV, TensorFlow).

[0109] The server then uses a generative AI model (e.g., GPT-3, BERT) to learn the newly acquired trend information and coordination theory. Training takes several hours to several days using a large amount of fashion-related data.

[0110] When a user makes a request on their device, such as "Tell me what outfits you recommend for today," the device sends this request to the server. The server searches the user's information from a database and generates optimal outfit suggestions using a generative AI model. For example, the prompt could be, "Please suggest a casual outfit. The user is in their 30s, works in an office during the week, enjoys the outdoors on weekends, and their favorite color is navy." The generated outfit suggestions are sent to the device and displayed to the user.

[0111] The server then retrieves the user's closet information (data on the clothes and accessories they own) from a database. It then uses a generative AI model to identify items missing from the suggested outfit. The server searches the APIs of affiliated online shops or brands to find the relevant items. It then sends the information about the items to be purchased to the device, which then displays the suggested items and a link to purchase them.

[0112] Users can use their devices to check each suggestion, and by clicking on an outfit or item they are interested in, detailed information will be displayed, and by clicking on the purchase link they will be taken to the online shop or brand site to complete the purchase.

[0113] This system allows users to significantly reduce the time and effort required for everyday fashion coordination and enjoy stylish outfits based on the latest trends.

[0114] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0115] Step 1: Enter user information

[0116] Users access a dedicated application or web interface and enter information about their fashion style and lifestyle, such as age, gender, favorite colors, body type, favorite places, and social media accounts. For example, they might enter "30 years old, female, navy, slim build, prefers office and outdoor activities."

[0117] Input: Information entered by the user.

[0118] The terminal checks the entered information to see if there are any errors. Specifically, it performs real-time validation and displays an error message.

[0119] Output: Successfully validated data.

[0120] The terminal transmits data that has passed validation to the server.

[0121] Step 2: Save user information

[0122] Input: Information about the user's fashion style and lifestyle is sent to the server.

[0123] The server stores the received information in a database by executing an INSERT statement in the SQL database, storing data in fields such as "User ID," "Age," "Gender," "Favorite Color," "Body Type," and "Frequently Visited Places."

[0124] Output: Saved user information.

[0125] Step 3: Learn trend and coordination theory

[0126] Input: Fashion articles, social media posts, and new brand information retrieved by the server from the Internet.

[0127] The server uses a scheduler to periodically collect the latest fashion articles, social media posts, information on new brand products, etc. Specifically, it uses Beautiful Soup and Scrapy to collect data.

[0128] Output: Collected fashion related data.

[0129] The server analyzes the data using text processing (NLTK, spaCy) and image recognition (OpenCV, TensorFlow). Specifically, it categorizes articles by topic and extracts features of fashion items from image data.

[0130] Output: analyzed trend information and coordination theory.

[0131] The server uses a generative AI model (such as GPT-3 or BERT) to learn the newly collected trend information. Specifically, fashion-related data is input into the AI ​​model and trained.

[0132] Output: A trained generative AI model.

[0133] Step 4: Coordination suggestions

[0134] Input: A user request such as "Tell me what outfits I recommend for today."

[0135] The user requests outfit suggestions by voice or text input to the application.

[0136] The device sends a request to the server, specifically by using an API call to send the request data.

[0137] Output: The request data sent to the server.

[0138] The server searches for user information from a database and inputs it into the generative AI model using appropriate prompts (e.g., "Please suggest a casual outfit. Age: 30s, works in an office during the week, enjoys the outdoors on weekends, and favorite color is navy blue.").

[0139] The generative AI model generates optimal coordination ideas.

[0140] Output: The generated coordinate plan.

[0141] The server transmits the generated coordination plan to the terminal.

[0142] The device displays the suggested coordination to the user visually using GUI components (e.g., card view, list view) within the application.

[0143] Output: Coordination ideas displayed.

[0144] Step 5: Purchase proposal

[0145] Input: User's closet information is stored in a database.

[0146] The server retrieves the user's closet information from the database.

[0147] Output: Retrieved closet information.

[0148] The server uses a generative AI model to identify missing items in the proposed outfit by comparing the closet information with the proposed outfit and listing the missing items.

[0149] Output: A list of identified missing items.

[0150] The server searches the APIs of partner online stores or brands to find the relevant items, sending API requests to get product prices and availability information.

[0151] Output: Information about the item you are considering purchasing.

[0152] The server transmits information about the items to be purchased to the terminal.

[0153] The device displays suggested purchase items and their purchase links to the user. Specifically, it creates a list that displays product images, prices, purchase links, etc.

[0154] Output: Displayed suggested items and a link to purchase.

[0155] Step 6: Interface Operation

[0156] Input: Suggested outfit ideas and purchase item information.

[0157] The user can check each suggestion by operating the device, specifically by scrolling through the item list and outfit ideas.

[0158] Output: The user's selected outfits and items.

[0159] When a user clicks on an outfit or purchase item that interests them, detailed information is displayed. Specifically, a click event is triggered and the details page is displayed.

[0160] The user clicks on the purchase link, goes to the online store or brand site, and completes the purchase. Specifically, the user opens an external or in-app browser and completes the purchase.

[0161] Output: Purchase completion information.

[0162] Through the above processing steps, the user can efficiently create fashionable outfits based on the latest trends and purchase the necessary items.

[0163] (Application example 1)

[0164] 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."

[0165] Conventional fashion assistant systems only suggest outfits based on information entered by the user, making it difficult to use in physical stores or to suggest outfits in real time. In addition, the information required for users to actually try on and select clothes had to be manually searched and checked, limiting the accuracy and convenience of the suggestions.

[0166] 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.

[0167] In this invention, the server includes a means for a user to input information about their fashion style and lifestyle, a means having a generative AI model that learns trend information and coordination theory, a means for recognizing the user's appearance through smart glasses and scanning items in the store, a means for proposing optimal coordination based on the user information, a means for identifying items missing from the proposed coordination and suggesting the purchase of those items, and a means for displaying the proposed information to the user. This allows users to receive coordination suggestions in real time in a physical store, making it easier to try on and purchase items in the store.

[0168] "User" refers to an individual who inputs information about their fashion style and lifestyle and receives coordination suggestions from the system.

[0169] "Information about fashion style and lifestyle" is data about style preferences and lifestyle habits based on the user's preferences and daily activities.

[0170] "Trend information and coordination theory" refers to knowledge and rules regarding the latest fashion trends and clothing combinations.

[0171] A "generative AI model" is an artificial intelligence algorithm that generates optimal outfits based on user information and trend information.

[0172] "Smart glasses" refers to a wearable device in the form of glasses that incorporates a computer and display.

[0173] "Means for recognizing the user's appearance and scanning items in the store" refers to devices or programs that use smart glasses or cameras to identify the user's appearance and location and identify items placed in the store.

[0174] "Means for suggesting optimal outfits" refers to a function that suggests clothing combinations suitable for a user based on the user's information and trend information.

[0175] "Means for identifying missing items and suggesting the purchase of those items" refers to a device or program that has the function of determining whether the user has missing items necessary for the suggested outfit and recommending their purchase.

[0176] "Means for displaying information to a user" refers to a device or program that visually presents the generated coordination and purchase suggestions to a user.

[0177] The term "system" refers to a structure including a series of devices, programs, and networks that integrate and operate the above-mentioned means.

[0178] The present invention provides a fashion assistant system that utilizes smart glasses. This system allows users to input information about their fashion style and lifestyle, and based on that information, the system will provide optimal coordination and purchase suggestions.

[0179] The system's hardware consists of smart glasses, a smartphone, and a cloud server. The smart glasses are equipped with a camera and display that recognize the user's appearance and scan items in the store. A dedicated application is installed on the smartphone, which inputs and displays user information. The cloud server hosts a generative AI model and uses trend information and user information to generate outfit suggestions.

[0180] The program processing is explained in natural language below.

[0181] First, the user puts on the smart glasses and enters a brick-and-mortar fashion store. The smart glasses use a camera to recognize the user's appearance and send information such as fashion style, lifestyle, and preferences previously entered into the application to a cloud server. The cloud server uses the acquired information to generate an optimal outfit using a generative AI model that has learned the user's lifestyle and trend information. The generated outfit is presented to the user in real time through the smart glasses' AR display.

[0182] The cloud server then identifies any missing items from the suggested outfit. It retrieves the user's closet information from a database and detects the missing items. The cloud server then searches for potential purchases of the items via the API of affiliated online shops and displays the information on the smart glasses' display.

[0183] This system allows users to receive coordination suggestions in real time in physical stores, and allows them to check the suggested items on the spot, try them on, and make purchases smoothly.

[0184] As a concrete example, consider a female user in her 30s who prefers a casual style for enjoying the outdoors on her days off. When this user enters a store, the smart glasses recognize her appearance and send information to the cloud server. The generative AI model suggests outfits such as a casual jacket, a white T-shirt, jeans, and sneakers, and displays them through the smart glasses. If it is determined based on the user's closet information that she is short of a jacket, the cloud server searches for the appropriate jacket in an online shop and displays a link to purchase it.

[0185] An example of a prompt sentence is as follows:

[0186] User Information:

[0187] Age: 30

[0188] Gender: Female

[0189] Favorite style: Casual

[0190] Lifestyle: Outdoors on holidays

[0191] Store item data:

[0192] white T-shirt

[0193] casual jacket

[0194] jeans

[0195] Prompt for AI:

[0196] Please suggest the perfect casual style for this user."

[0197] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0198] Step 1:

[0199] A user puts on smart glasses and enters a physical store. The smart glasses recognize the user's appearance using a built-in camera. The smart glasses recognize the user's appearance and acquire information about the user's attributes (age, gender, fashion style, etc.). This information is then sent to a cloud server.

[0200] Step 2:

[0201] The server stores the received user information in a database. This is where information about the user's fashion style and lifestyle is updated. The server collects the latest fashion articles, social media posts, and information on new brand products. Based on this, it trains a generative AI model to learn trend information and coordination theory. The input is user information and collected data, and the output is an updated generative AI model.

[0202] Step 3:

[0203] The user requests outfit suggestions through the smart glasses (for example, by entering a command such as "Tell me today's recommended outfits"). The smart glasses recognize this operation and send a request to the cloud server. The input is the user's command, and the output is a request sent to the server.

[0204] Step 4:

[0205] The server retrieves user information from the database and generates optimal outfit suggestions using the most recently trained generative AI model. The generated outfit suggestions are then sent to the smart glasses. The input is the user information retrieved from the database and the generative AI model, and the output is the generated outfit suggestions.

[0206] Step 5:

[0207] The smart glasses display the generated outfit suggestions in the user's field of view using an AR display. The user can then check the suggested outfits. The input is the generated outfit suggestions, and the output is a visual presentation to the user. Specifically, the smart glasses display overlays the suggested items.

[0208] Step 6:

[0209] The server retrieves the user's closet information from a database and uses a generative AI model to identify items that are necessary for the suggested outfit but are not present in the user's closet. It then searches the APIs of affiliated online shops to find the relevant items. The input is the closet information retrieved by the server, and the output is information about items that are candidates for purchase.

[0210] Step 7:

[0211] The server sends information about potential purchase items to the smart glasses, which then display the items and their associated purchase links in the user's field of view using AR. The user can check detailed information about the items they are interested in and click the purchase link to access the online shop. The input is the information about the items they are interested in, and the output is a visual presentation and link provided to the user.

[0212] 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.

[0213] The present invention relates to an AI assistant system that makes optimal coordination suggestions and purchase suggestions tailored to a user's fashion style and lifestyle, and in particular, makes even more personalized suggestions by combining it with an emotion engine that recognizes the user's emotions. This system includes a user information input means, a generative AI model, an optimal coordination suggestion means, a purchase suggestion means, a display means, and an emotion engine.

[0214] Program processing overview

[0215] 1. Enter user information

[0216] Users access a dedicated application or web interface and enter information about their fashion style and lifestyle, such as age, gender, favorite colors, body type, and favorite places. Users can also link their frequently used social media accounts.

[0217] The device checks this information to make sure there are no errors, and then sends the information to the server.

[0218] The server stores the received information in a database.

[0219] 2. Study of trend and coordination theory

[0220] The server collects the latest fashion articles, social media posts, and information on new brand releases from the Internet.

[0221] The server analyzes the collected data using text processing and image recognition technology, and trains a generative AI model that learns trend information and coordination theory.

[0222] 3. Emotion recognition

[0223] Users input brief feedback about their daily emotions and current mood via an application or web interface.

[0224] The device monitors changes in emotions and sends the information to a server.

[0225] The server uses an emotion engine to analyze emotions from user input and interaction patterns, and the analysis results are fed back to the generative AI model.

[0226] 4. Coordination suggestions

[0227] The user enters a command such as "Tell me today's recommended outfit." The request is sent from the device to the server.

[0228] The server searches a database for user information and emotional data, and uses a generative AI model to generate optimal outfit suggestions based on the user's preferences, lifestyle, and emotional state.

[0229] The server transmits the generated coordination plan to the terminal.

[0230] The terminal displays the suggested coordination to the user.

[0231] 5. Purchase Proposal

[0232] The server retrieves the user's closet information (data on the clothes and accessories they own) from a database and identifies items that are missing from the suggested outfit.

[0233] The server searches the API of partner online stores or brands to find the identified missing items.

[0234] The server transmits information about the items to be purchased to the terminal.

[0235] The terminal displays suggested purchase items and links to them to the user.

[0236] 6. Interface Operation

[0237] The user operates the terminal to confirm each suggestion.

[0238] When a user clicks on an outfit or purchase item that interests them, detailed information will be displayed.

[0239] Users can click on the purchase link to be taken to an online store or brand site, where they can seamlessly purchase the suggested item.

[0240] Specific examples

[0241] For example, consider a female user in her 30s who works in an office during the week and enjoys the outdoors on weekends, and who prefers a casual lifestyle. The user logs into a dedicated application and enters her personal information and emotional state. The server stores this information in a database and uses a generative AI model to suggest the user's optimal outfit. For example, it might suggest a "navy blazer, white blouse, jeans, and sneakers." It might also identify that the user is short of a navy blazer based on their closet information and suggest purchasing one. It can then find a navy blazer at a partner online shop and provide the user with a link to purchase it. An emotional engine can be incorporated into this process to make appropriate suggestions based on the user's current emotional state. For example, if the user is feeling stressed, it could suggest a relaxing style.

[0242] This system allows users to significantly reduce the time and effort spent on everyday fashion coordination and enjoy stylish outfits based on the latest trends.In addition, by utilizing an emotion engine, users can receive more personalized suggestions based on their emotional state.

[0243] The processing flow will be explained below.

[0244] Step 1:

[0245] Users access a dedicated application or web interface and enter information about their fashion style and lifestyle, such as age, gender, favorite colors, body type, and favorite places. Users can also link their frequently used social media accounts.

[0246] Step 2:

[0247] The terminal checks the entered information for formatting errors and, once the check is complete, sends the information to the server.

[0248] Step 3:

[0249] The server stores the received information in a database, which is managed individually for each user.

[0250] Step 4:

[0251] The server regularly collects the latest fashion articles, social media posts, and information on new brand products from the Internet.

[0252] Step 5:

[0253] The server analyzes the collected data using text processing and image recognition technology, and the analysis results are used as input data for the generative AI model.

[0254] Step 6:

[0255] The server trains the generative AI model by feeding it trend information and coordination theory. This process runs periodically to ensure the model is constantly learning new information.

[0256] Step 7:

[0257] Users input brief feedback about their daily emotions and current mood via an application or web interface.

[0258] Step 8:

[0259] The device monitors changes in emotions and transmits the emotional data entered by the user to the server.

[0260] Step 9:

[0261] The server uses an emotion engine to analyze emotions from user input and interaction patterns, and the analysis results are fed back to the generative AI model.

[0262] Step 10:

[0263] The user inputs a command such as "Tell me today's recommended outfits." After input, the request is sent from the device to the server.

[0264] Step 11:

[0265] The server searches a database for user information and emotional data, and uses a generative AI model to generate optimal outfit suggestions based on the user's preferences, lifestyle, and emotional state.

[0266] Step 12:

[0267] The server transmits the generated coordinate plan to the terminal, where the transmitted data is converted into a format for visual display.

[0268] Step 13:

[0269] The device will display the suggested outfits to the user, who can review them and, if they like them, request more information.

[0270] Step 14:

[0271] The server retrieves the user's closet information (data on the clothes and accessories they own) from a database and uses this information to identify any missing items for the proposed outfit.

[0272] Step 15:

[0273] The server searches the APIs of partner online shops or brands to find the identified missing items and collects information on potential purchase items.

[0274] Step 16:

[0275] The server sends information about the items to be purchased to the device, including a purchase link and detailed product information.

[0276] Step 17:

[0277] The device displays the suggested purchase items and their associated purchase links to the user, who can then review the displayed content and click the purchase link if necessary.

[0278] Step 18:

[0279] The user clicks on the purchase link, which takes them to the online shop or brand site, allowing them to seamlessly purchase the suggested item.

[0280] In this way, the system can provide optimal coordination and purchase suggestions based on the user's fashion style, lifestyle, and emotional state.

[0281] Example 2

[0282] 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."

[0283] Conventional fashion advice systems only suggest outfits based on a user's basic fashion information and lifestyle, making it difficult to provide personalized suggestions that take into account the user's emotional state. Furthermore, they have problems in that they are unable to efficiently identify missing items in the suggested outfits or make purchasing suggestions based on those items. This often means that users have to spend time and effort trying out the suggested outfits.

[0284] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for the user to input information about fashion style and lifestyle, a means for recognizing the user's emotions and identifying the emotional state by analyzing the data, a means having a generative AI model that learns trend information and coordination theory, a means for proposing an optimal coordination based on the user's information and emotional state, a means for identifying items that are missing from the proposed coordination and suggesting the purchase of those items, and a means for displaying the proposed information to the user. This enables personalized coordination suggestions that take the user's emotional state into consideration and efficient item purchase suggestions.

[0285] The "user information input means" is a means by which a user provides information about fashion style and lifestyle to the system.

[0286] An "emotion recognition means" is a means for detecting a user's emotions and identifying their emotional state by analyzing the data.

[0287] A "generative AI model" is an artificial intelligence model that learns trend information and coordination theory and suggests coordination based on user information.

[0288] The "coordination suggestion means" is a means for advising the user on the most appropriate coordination based on the information input by the user and the user's emotional state.

[0289] The "purchase suggestion means" is a means for identifying an item that is missing from the suggested coordination and recommending the purchase of that item.

[0290] "Display means" refers to the means by which the system notifies the user of suggested outfits and purchase information.

[0291] A "database" is a system for managing and storing a variety of data, such as information entered by users, emotional data, or trend information.

[0292] "Trend information" refers to information that shows the latest trends in the fashion industry, such as the latest fashion articles, social media posts, and information on new brand products.

[0293] "Closet information" is data about the clothes and accessories a user owns.

[0294] The present invention relates to an AI assistant system that makes optimal coordination suggestions and purchase suggestions tailored to a user's fashion style and lifestyle. This system includes a user information input means, an emotion recognition means, a generative AI model, a coordination suggestion means, a purchase suggestion means, and a display means.

[0295] The user information input means allows a user to use a dedicated application or web interface to enter information related to their fashion style and lifestyle, such as their age, gender, favorite colors, body type, and favorite places. For example, information such as "30s, female, prefers casual style, works in an office on weekdays, enjoys outdoor activities on weekends" might be entered.

[0296] Emotion recognition is a means of detecting a user's emotions and identifying their emotional state by analyzing the data. The user inputs simple feedback about their daily emotions and current mood through an application or web interface. For example, they can provide feedback such as "I'm feeling a little stressed today."

[0297] The generative AI model is an artificial intelligence model that learns trend information and coordination theory and suggests outfits based on user information. The server collects the latest fashion articles, social media posts, and information on new brand products from the internet, and analyzes them using text processing and image recognition technology to train the generative AI model.

[0298] The outfit suggestion method is a means of advising the optimal outfit based on the user's input information and emotional state. When a user inputs a request such as "Tell me today's recommended outfit," the server uses a generative AI model to generate the optimal outfit suggestion. For example, a suggestion might be "a navy blazer, a white blouse, jeans, and sneakers."

[0299] The purchase suggestion means identifies items missing from the suggested outfit and recommends the purchase of those items. The server retrieves the user's closet information from the database and identifies the missing items. For example, it determines that a "navy blazer" is missing, searches for the corresponding item from affiliated online shops, and provides a link to purchase it.

[0300] The display means is a means by which the system notifies the user of suggested outfits and purchase information. The generated outfit ideas and purchase links are sent to the terminal and displayed to the user.

[0301] Specific examples

[0302] For example, let's say a female user in her 30s works in an office during the week and enjoys the outdoors on weekends, preferring a casual lifestyle. The user logs into a dedicated application and enters her personal information and emotional state. For example, she might enter, "I want to relax today." The server stores this information in a database and uses a generative AI model to suggest the perfect outfit for the user. For example, it might suggest "a navy blazer, a white blouse, jeans, and sneakers." Furthermore, based on the user's closet information, it might identify that the user is short of a navy blazer and suggest purchasing it. It then finds a suitable navy blazer at a partner online shop and provides the user with a purchase link. This allows the user to quickly obtain the items needed for their outfit.

[0303] Prompt Sentence Examples

[0304] "Please suggest a casual style outfit for a woman in her 30s who works in an office during the week and enjoys the outdoors on weekends."

[0305] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0306] Step 1: Enter your user information

[0307] Users access a dedicated application or web interface and enter information about their fashion style and lifestyle, such as their age, gender, favorite colors, body type, and favorite places. For example, they might enter information such as "30s, female, prefers casual style, works in an office during the week, and enjoys the outdoors on weekends."

[0308] Input: User's basic information (age, gender, favorite color, body type, lifestyle, etc.)

[0309] Output: Checking input data on the terminal and sending it to the server

[0310] Step 2: Verify and save user information

[0311] The terminal checks the entered data for any errors or omissions, and once the check is complete, sends the data to the server.

[0312] The server stores the received user information in a database, which is linked to each user's unique ID.

[0313] Input: User information sent from the device

[0314] Output: User information stored in the database

[0315] Step 3: Learn trend and coordination theory

[0316] The server crawls and collects fashion-related articles, social media posts, and information on new brand releases from the internet. Specifically, it automatically retrieves new collections and posts from popular Instagrammers.

[0317] The server analyzes the collected data using text processing technology (Natural Language Processing) and image recognition technology, for example, by analyzing the color, shape, and style of the captured image.

[0318] The server uses the analysis results to train the generative AI model, which builds a model based on the latest trend information and coordination theory.

[0319] Input: Collected trend information and image data

[0320] Output: A trained generative AI model

[0321] Step 4: Input and analyze emotion data

[0322] Through the application or web interface, users input brief feedback about their daily emotions and current mood, for example, "I feel like relaxing today."

[0323] The device receives the feedback and sends it to the server.

[0324] The server uses an emotion engine to analyze the user's emotional state, and the analysis results are fed back to the generative AI model.

[0325] Input: User's emotional feedback

[0326] Output: Parsed user emotional state data

[0327] Step 5: Generate outfit suggestions

[0328] When a user inputs a request such as "Tell me today's recommended outfit," the request is sent to the server via the terminal.

[0329] The server searches the database for user information and emotional data, and then uses a generative AI model to generate optimal outfit suggestions, such as a navy blazer, a white blouse, jeans, and sneakers.

[0330] The generated outfit suggestions are based on the user's preferences, lifestyle, and emotional state.

[0331] Input: User information, emotion data, request

[0332] Output: Generated optimal coordination plan

[0333] Step 6: Send and view your outfit ideas

[0334] The server transmits the generated coordination plan to the terminal.

[0335] The terminal displays the suggested coordination to the user.

[0336] Input: Generated coordination plan

[0337] Output: Coordination ideas displayed on the user's screen

[0338] Step 7: Generate a purchase offer

[0339] The server retrieves the user's closet information from a database and identifies any missing items from the proposed outfit, such as a navy blazer.

[0340] The server searches the API of partner online stores or brands to find the missing items, for example, searching for a navy blazer from a partner store.

[0341] The server transmits information about the items to be purchased to the terminal.

[0342] Input: Suggested outfit ideas, closet information

[0343] Output: Item information and purchase link

[0344] Step 8: View purchase offers

[0345] The terminal displays suggested purchase items and links to them to the user.

[0346] Users can click on the purchase link to be taken to an online shop or brand site, allowing them to seamlessly purchase the suggested item.

[0347] Input: Item information and link for potential purchases

[0348] Output: Purchase offer and link displayed to the user

[0349] This allows users to receive personalized outfit suggestions and smoothly purchase any items they are missing.

[0350] (Application example 2)

[0351] 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."

[0352] While conventional fashion assistant systems could provide suggestions based on a user's fashion style and lifestyle, they struggled to reflect the user's emotional state or real-time product information in physical stores. As a result, suggestions often did not reflect the user's current mood or the actual inventory status in the store, resulting in an unsatisfactory experience. Furthermore, they provided insufficient support for users to purchase specific coordinating items on the spot.

[0353] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for the user to input information about their fashion style and lifestyle, a means equipped with a generative AI model that learns trend information and coordination theory, a means for proposing optimal outfits based on the user's information and item information in the physical store, a means for identifying items missing from the proposed outfit and suggesting the purchase of those items, a means for displaying the proposed information to the user, and a means for recognizing the user's emotions and changing the proposed outfits in response to those emotions. This enables personalized fashion suggestions that reflect the user's current emotional state and real-time product information in the physical store. It also enhances on-the-spot purchasing support for the suggested items.

[0354] "User" refers to a person who uses a system or service.

[0355] "Fashion style" refers to the combination and design trends of clothing and accessories preferred by individual users.

[0356] "Lifestyle" is a concept that comprehensively expresses a user's daily life patterns, activities, hobbies, and preferences.

[0357] A "generative AI model" is an artificial intelligence model that uses techniques such as machine learning and deep learning to generate appropriate output based on input data.

[0358] "Trend information" refers to information about current trends and fashions in the market and society.

[0359] "Coordination theory" refers to a theoretical framework for suggesting and selecting optimal clothing by combining elements such as color, design, and material.

[0360] "In-store item information" refers to information about products that are actually sold in physical stores.

[0361] The "emotion engine" is a system that recognizes and analyzes emotions from the user's facial expressions and input data.

[0362] "Suggestion" refers to recommendations for coordination or purchases made to users.

[0363] "Real time" refers to a state or action that is reflected immediately at that point in time.

[0364] "Personalized" refers to a state that is optimized to suit the characteristics and circumstances of each individual user.

[0365] The system for realizing this invention allows users to input information about their fashion style and lifestyle, analyzes the user's emotional state using an emotion engine, and integrates this with real-time product information from physical stores to suggest optimal outfits. The system performs processing in the following steps:

[0366] Users use devices such as smartphones or head-mounted displays to input information such as age, gender, favorite colors, body type, and frequently visited places. Users also provide the system with their current mood through simple input or facial expression analysis using a camera. This information is then sent from the device to a server for data processing.

[0367] The server integrates the collected user information with information on items in physical stores and uses a generative AI model to learn the latest trends and coordination theories. The generative AI model uses advanced machine learning algorithms (e.g., GPT-3 and DALL-E) to generate optimal coordination for each user. It also uses emotion engines such as OpenAI's emotion analysis API to analyze user emotion data.

[0368] The server generates personalized outfit suggestions based on user information and product trend and inventory data from physical stores. The suggested outfits reflect the user's preferences, lifestyle, and current emotional state. The suggested outfits are displayed to the user via their device.

[0369] As a specific example, consider a female user in her 30s who works in an office during the week, enjoys outdoor activities on the weekends, and prefers casual fashion. The user logs into the application and enters her personal information and current emotional state (e.g., "I want to relax"). The server stores this information in a database and uses a generative AI model to suggest outfits such as a navy blazer, a white blouse, jeans, and sneakers.

[0370] Furthermore, the server uses the user's closet information and the store's inventory information to identify any missing items in the suggested outfit (in this case, a navy blazer) and provides the user with a link to purchase the item. This process is carried out in real time, allowing the user to instantly receive outfit suggestions via their smartphone or head-mounted display in the store and purchase the necessary items on the spot.

[0371] This system allows users to always enjoy stylish outfits that reflect the latest trends, and offers suggestions based on the user's emotional state, providing a more comfortable and satisfying shopping experience.

[0372] Prompt Sentence Examples

[0373] Age: 30

[0374] Gender: Female

[0375] Favorite color: Blue

[0376] Body shape: normal

[0377] Favorite place: Office

[0378] Current mood: Relaxing

[0379] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0380] Step 1:

[0381] The user inputs information about their fashion style and lifestyle. Using a smartphone or head-mounted display, the user inputs information such as age, gender, favorite colors, body type, and favorite places. This input data is acquired by the device, and after checking the input information and confirming any errors, it is sent to the server. Input: Age, gender, favorite colors, body type, favorite places. Output: User information data.

[0382] Step 2:

[0383] The server stores the received user information in a database. The stored data is used as the basis for future coordination suggestions and sentiment analysis. Input: User information data. Output: User information stored in the database.

[0384] Step 3:

[0385] The terminal collects item information (tag information and image data) from within the physical store and sends it to the server. Using a smartphone or head-mounted display, product information is obtained using RFID tags and image recognition technology within the store. Input: Item information within the store (tag information, image data). Output: Collected item information data.

[0386] Step 4:

[0387] The user inputs their current emotional information. The user can analyze their emotions by entering simple feedback into the application or by reading their facial expressions using the camera function. This data is acquired by the device and sent to the server. Input: Emotional information (e.g., "I want to relax"). Output: Emotional data.

[0388] Step 5:

[0389] The server integrates user information, emotional data, and item information from physical stores, and uses a generative AI model to generate optimal outfit suggestions. Trend information and outfit theory are also taken into consideration. The generated outfit suggestions are based on the user's preferences, lifestyle, and emotional state. Input: User information data, emotional data, item information data. Output: Optimal outfit suggestions.

[0390] Step 6:

[0391] The server sends the generated outfit suggestions to the device. The user can then check the outfit suggestions on their smartphone or head-mounted display. Input: Outfit suggestions. Output: Outfit suggestions displayed on the user device.

[0392] Step 7:

[0393] The server retrieves the user's closet information from the database and identifies items that are missing from the suggested outfit. The identified missing items are provided as purchase links by referencing inventory information from affiliated online shops or physical stores. Input: User's closet information, suggested outfit. Output: Purchase link information for missing items.

[0394] Step 8:

[0395] The user operates the device to check the suggested outfits and purchase links. By clicking the purchase link for the missing item on the device, the user is redirected to the relevant page of a partner online shop or physical store, where the purchase can be made. Input: Purchase link information. Output: Transition to the purchase page of the online shop or physical store.

[0396] This processing flow enables real-time fashion coordination suggestions, personalized suggestions based on the user's emotional state, and even immediate support for purchasing missing items.

[0397] 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.

[0398] 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.

[0399] 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.

[0400] [Second embodiment]

[0401] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0402] 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.

[0403] 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).

[0404] 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.

[0405] 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.

[0406] 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).

[0407] 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.

[0408] 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.

[0409] 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.

[0410] 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.

[0411] 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.

[0412] 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."

[0413] The present invention relates to an AI assistant system that provides optimal coordination and purchase suggestions to suit a user's fashion style and lifestyle. This system includes a user information input means, a generative AI model, optimal coordination suggestion means, purchase suggestion means, and display means.

[0414] Program processing overview

[0415] 1. Enter user information

[0416] - Users access a dedicated application or web interface and enter information about their fashion style and lifestyle, including their age, gender, favorite colors, body type, favorite places, and social media accounts.

[0417] - The device checks this information and then sends it to the server.

[0418] - The server stores the received information in a database.

[0419] 2. Study of trend and coordination theory

[0420] - The server collects the latest fashion articles, social media posts, and information on new brand products from the Internet.

[0421] - The server analyzes this data using text processing and image recognition technology, and trains a generative AI model to learn trend information and coordination theory.

[0422] 3. Coordination suggestions

[0423] - The user performs an operation to request outfit suggestions (for example, enter a command such as "Tell me today's recommended outfits").

[0424] - The device sends this request to the server.

[0425] - The server searches the database for user information and generates optimal outfit suggestions using a generative AI model.

[0426] - The server sends the generated coordination plan to the terminal.

[0427] - The terminal displays the suggested coordination to the user.

[0428] 4. Purchase Proposal

[0429] - The server retrieves the user's closet information (data on the clothes and accessories they own) from the database.

[0430] - The server uses a generative AI model to identify missing items in the proposed outfit.

[0431] - The server searches the API of the partner online shop or brand to find the item.

[0432] - The server sends information about the items to be purchased to the device.

[0433] - The device displays suggested purchase items and links to them to the user.

[0434] 5. Interface Operation

[0435] - The user operates the device to confirm each suggestion.

[0436] - When users click on an outfit or purchase item that interests them, detailed information will be displayed.

[0437] - Users can click on the purchase link and be taken to the online store or brand site to complete the purchase.

[0438] Specific examples

[0439] For example, let's say a female user in her 30s works in an office during the week and enjoys the outdoors on weekends, preferring a casual lifestyle. The user logs in to a dedicated application and enters her information. The server stores that information in a database and uses a generative AI model to suggest the user's optimal outfit. For example, it might suggest a "navy blazer, white blouse, jeans, and sneakers." Furthermore, it might identify that the user is short on navy blazers based on their closet information and suggest purchasing them. By finding a navy blazer at a partner online shop and providing the user with a purchase link, the user can easily purchase the missing item.

[0440] This system allows users to significantly reduce the time and effort spent on everyday fashion coordination and enjoy stylish outfits based on the latest trends.

[0441] The processing flow will be explained below.

[0442] Step 1:

[0443] Users access a dedicated application or web interface and enter information about their fashion style and lifestyle, such as age, gender, favorite colors, body type, and favorite places.

[0444] Step 2:

[0445] The terminal checks the entered information for formatting errors and, once the check is complete, sends the information to the server.

[0446] Step 3:

[0447] The server stores the received information in a database, which is managed individually for each user.

[0448] Step 4:

[0449] The server periodically collects the latest fashion articles, social media posts, and information on new brand releases from the internet, which is used to obtain trend information and update coordination theory.

[0450] Step 5:

[0451] The server analyzes the collected data using text processing and image recognition technology, and the analysis results are used as input data for the generative AI model.

[0452] Step 6:

[0453] The server trains the generative AI model by feeding it trend information and coordination theory. This process is carried out periodically to ensure that the model is constantly learning new information.

[0454] Step 7:

[0455] The user inputs a command such as "Tell me today's recommended outfits." After input, the request is sent from the device to the server.

[0456] Step 8:

[0457] The server searches the database for user information and uses a generative AI model to generate optimal outfit suggestions based on the user's preferences and lifestyle.

[0458] Step 9:

[0459] The server transmits the generated coordinate plan to the terminal, where the transmitted data is converted into a format for visual display.

[0460] Step 10:

[0461] The device will display the suggested outfits to the user, who can review them and, if they like them, request more information.

[0462] Step 11:

[0463] The server retrieves the user's closet information (data on the clothes and accessories they own) from a database and uses this information to identify any missing items for the proposed outfit.

[0464] Step 12:

[0465] The server searches the APIs of partner online shops or brands to find the identified missing items. It also collects information on potential items.

[0466] Step 13:

[0467] The server sends information about the items to be purchased to the device, including a purchase link and detailed product information.

[0468] Step 14:

[0469] The device displays the suggested purchase items and their associated purchase links to the user, who can then review the displayed content and click the purchase link if necessary.

[0470] Step 15:

[0471] The user clicks on the purchase link, which takes them to the online shop or brand site, allowing them to seamlessly purchase the suggested item.

[0472] In this way, the system can provide optimal coordination and purchase suggestions based on the user's fashion style and lifestyle.

[0473] Example 1

[0474] 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."

[0475] Conventional fashion coordination and purchase suggestion systems require users to collect and analyze vast amounts of information themselves, which requires a great deal of time and effort to efficiently enjoy stylish coordination.In addition, the technology to effectively manage and suggest items that users already own and items they need to purchase is insufficient.

[0476] 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.

[0477] In this invention, the server includes a means for a user to input information about their fashion style and lifestyle, a means having a generative AI model that learns trend information and coordination theory, a means for proposing optimal coordination based on the user information, a means for identifying items missing from the proposed coordination and proposing the purchase of those items, a means for displaying the proposed information to the user, and a means for the user to complete an online purchase via the suggested purchase link, thereby enabling the user to enjoy stylish coordination based on the latest trends without any hassle.

[0478] "User information" refers to data related to a user's fashion style and lifestyle, such as their age, gender, favorite colors, body type, favorite places, and social media accounts.

[0479] A "generative AI model" is an artificial intelligence model that analyzes and learns from fashion articles, social media posts, and new brand information collected from the internet, and generates trend information and coordination theories.

[0480] "Coordination suggestions" refer to suggestions for combining fashion items and styles created by a generative AI model based on user information.

[0481] "Purchase suggestion" refers to identifying items the user is missing from the generated outfit and providing links or information to purchase those items.

[0482] "Database" refers to the system that stores and manages user information, closet information, and collected fashion-related data.

[0483] "Closet information" refers to data about the clothes and accessories a user already owns.

[0484] "Trend information" refers to information about currently popular fashion styles and items.

[0485] "Method of completing an online purchase" refers to the user's actions to purchase an item from an online store or brand site via a suggested link.

[0486] "Learning with generative AI models" refers to the process of analyzing collected fashion-related data to understand and update trends and coordination theories.

[0487] This invention relates to an AI assistant system that provides optimal coordination and purchase suggestions to suit a user's fashion style and lifestyle. The system includes a user information input means, a generating AI model, optimal coordination suggestion means, purchase suggestion means, and display means.

[0488] First, the user accesses a dedicated application or web interface and enters their information, including age, gender, favorite colors, body type, favorite places, social media accounts, etc. The device verifies the information and sends it to the server, which then stores it in a database.

[0489] The server uses a scheduler to periodically collect the latest fashion articles, social media posts, and information on new brand releases from the Internet. Specific scraping tools (e.g., Beautiful Soup, Scrapy) are used to collect the data. After collection, the server analyzes the data using text processing (e.g., NLTK, spaCy) and image recognition techniques (e.g., OpenCV, TensorFlow).

[0490] The server then uses a generative AI model (e.g., GPT-3, BERT) to learn the newly acquired trend information and coordination theory. Training takes several hours to several days using a large amount of fashion-related data.

[0491] When a user makes a request on their device, such as "Tell me what outfits you recommend for today," the device sends this request to the server. The server searches the user's information from a database and generates optimal outfit suggestions using a generative AI model. For example, the prompt could be, "Please suggest a casual outfit. The user is in their 30s, works in an office during the week, enjoys the outdoors on weekends, and their favorite color is navy." The generated outfit suggestions are sent to the device and displayed to the user.

[0492] The server then retrieves the user's closet information (data on the clothes and accessories they own) from a database. It then uses a generative AI model to identify items missing from the suggested outfit. The server searches the APIs of affiliated online shops or brands to find the relevant items. It then sends the information about the items to be purchased to the device, which then displays the suggested items and a link to purchase them.

[0493] Users can use their devices to check each suggestion, and by clicking on an outfit or item they are interested in, detailed information will be displayed, and by clicking on the purchase link they will be taken to the online shop or brand site to complete the purchase.

[0494] This system allows users to significantly reduce the time and effort required for everyday fashion coordination and enjoy stylish outfits based on the latest trends.

[0495] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0496] Step 1: Enter user information

[0497] Users access a dedicated application or web interface and enter information about their fashion style and lifestyle, such as age, gender, favorite colors, body type, favorite places, and social media accounts. For example, they might enter "30 years old, female, navy, slim build, prefers office and outdoor activities."

[0498] Input: Information entered by the user.

[0499] The terminal checks the entered information to see if there are any errors. Specifically, it performs real-time validation and displays an error message.

[0500] Output: Successfully validated data.

[0501] The terminal transmits data that has passed validation to the server.

[0502] Step 2: Save user information

[0503] Input: Information about the user's fashion style and lifestyle is sent to the server.

[0504] The server stores the received information in a database by executing an INSERT statement in the SQL database, storing data in fields such as "User ID," "Age," "Gender," "Favorite Color," "Body Type," and "Frequently Visited Places."

[0505] Output: Saved user information.

[0506] Step 3: Learn trend and coordination theory

[0507] Input: Fashion articles, social media posts, and new brand information retrieved by the server from the Internet.

[0508] The server uses a scheduler to periodically collect the latest fashion articles, social media posts, information on new brand products, etc. Specifically, it uses Beautiful Soup and Scrapy to collect data.

[0509] Output: Collected fashion related data.

[0510] The server analyzes the data using text processing (NLTK, spaCy) and image recognition (OpenCV, TensorFlow). Specifically, it categorizes articles by topic and extracts features of fashion items from image data.

[0511] Output: analyzed trend information and coordination theory.

[0512] The server uses a generative AI model (such as GPT-3 or BERT) to learn the newly collected trend information. Specifically, fashion-related data is input into the AI ​​model and trained.

[0513] Output: A trained generative AI model.

[0514] Step 4: Coordination suggestions

[0515] Input: A user request such as "Tell me what outfits I recommend for today."

[0516] The user requests outfit suggestions by voice or text input to the application.

[0517] The device sends a request to the server, specifically by using an API call to send the request data.

[0518] Output: The request data sent to the server.

[0519] The server searches for user information from a database and inputs it into the generative AI model using appropriate prompts (e.g., "Please suggest a casual outfit. Age: 30s, works in an office during the week, enjoys the outdoors on weekends, and favorite color is navy blue.").

[0520] The generative AI model generates optimal coordination ideas.

[0521] Output: The generated coordinate plan.

[0522] The server transmits the generated coordination plan to the terminal.

[0523] The device displays the suggested coordination to the user visually using GUI components (e.g., card view, list view) within the application.

[0524] Output: Coordination ideas displayed.

[0525] Step 5: Purchase proposal

[0526] Input: User's closet information is stored in a database.

[0527] The server retrieves the user's closet information from the database.

[0528] Output: Retrieved closet information.

[0529] The server uses a generative AI model to identify missing items in the proposed outfit by comparing the closet information with the proposed outfit and listing the missing items.

[0530] Output: A list of identified missing items.

[0531] The server searches the APIs of partner online stores or brands to find the relevant items, sending API requests to get product prices and availability information.

[0532] Output: Information about the item you are considering purchasing.

[0533] The server transmits information about the items to be purchased to the terminal.

[0534] The device displays suggested purchase items and their purchase links to the user. Specifically, it creates a list that displays product images, prices, purchase links, etc.

[0535] Output: Displayed suggested items and a link to purchase.

[0536] Step 6: Interface Operation

[0537] Input: Suggested outfit ideas and purchase item information.

[0538] The user can check each suggestion by operating the device, specifically by scrolling through the item list and outfit ideas.

[0539] Output: The user's selected outfits and items.

[0540] When a user clicks on an outfit or purchase item that interests them, detailed information is displayed. Specifically, a click event is triggered and the details page is displayed.

[0541] The user clicks on the purchase link, goes to the online store or brand site, and completes the purchase. Specifically, the user opens an external or in-app browser and completes the purchase.

[0542] Output: Purchase completion information.

[0543] Through the above processing steps, the user can efficiently create fashionable outfits based on the latest trends and purchase the necessary items.

[0544] (Application example 1)

[0545] 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."

[0546] Conventional fashion assistant systems only suggest outfits based on information entered by the user, making it difficult to use in physical stores or to suggest outfits in real time. In addition, the information required for users to actually try on and select clothes had to be manually searched and checked, limiting the accuracy and convenience of the suggestions.

[0547] 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.

[0548] In this invention, the server includes a means for a user to input information about their fashion style and lifestyle, a means having a generative AI model that learns trend information and coordination theory, a means for recognizing the user's appearance through smart glasses and scanning items in the store, a means for proposing optimal coordination based on the user information, a means for identifying items missing from the proposed coordination and suggesting the purchase of those items, and a means for displaying the proposed information to the user. This allows users to receive coordination suggestions in real time in a physical store, making it easier to try on and purchase items in the store.

[0549] "User" refers to an individual who inputs information about their fashion style and lifestyle and receives coordination suggestions from the system.

[0550] "Information about fashion style and lifestyle" is data about style preferences and lifestyle habits based on the user's preferences and daily activities.

[0551] "Trend information and coordination theory" refers to knowledge and rules regarding the latest fashion trends and clothing combinations.

[0552] A "generative AI model" is an artificial intelligence algorithm that generates optimal outfits based on user information and trend information.

[0553] "Smart glasses" refers to a wearable device in the form of glasses that incorporates a computer and display.

[0554] "Means for recognizing the user's appearance and scanning items in the store" refers to devices or programs that use smart glasses or cameras to identify the user's appearance and location and identify items placed in the store.

[0555] "Means for suggesting optimal outfits" refers to a function that suggests clothing combinations suitable for a user based on the user's information and trend information.

[0556] "Means for identifying missing items and suggesting the purchase of those items" refers to a device or program that has the function of determining whether the user has missing items necessary for the suggested outfit and recommending their purchase.

[0557] "Means for displaying information to a user" refers to a device or program that visually presents the generated coordination and purchase suggestions to a user.

[0558] The term "system" refers to a structure including a series of devices, programs, and networks that integrate and operate the above-mentioned means.

[0559] The present invention provides a fashion assistant system that utilizes smart glasses. This system allows users to input information about their fashion style and lifestyle, and based on that information, the system will provide optimal coordination and purchase suggestions.

[0560] The system's hardware consists of smart glasses, a smartphone, and a cloud server. The smart glasses are equipped with a camera and display that recognize the user's appearance and scan items in the store. A dedicated application is installed on the smartphone, which inputs and displays user information. The cloud server hosts a generative AI model and uses trend information and user information to generate outfit suggestions.

[0561] The program processing is explained in natural language below.

[0562] First, the user puts on the smart glasses and enters a brick-and-mortar fashion store. The smart glasses use a camera to recognize the user's appearance and send information such as fashion style, lifestyle, and preferences previously entered into the application to a cloud server. The cloud server uses the acquired information to generate an optimal outfit using a generative AI model that has learned the user's lifestyle and trend information. The generated outfit is presented to the user in real time through the smart glasses' AR display.

[0563] The cloud server then identifies any missing items from the suggested outfit. It retrieves the user's closet information from a database and detects the missing items. The cloud server then searches for potential purchases of the items via the API of affiliated online shops and displays the information on the smart glasses' display.

[0564] This system allows users to receive coordination suggestions in real time in physical stores, and allows them to check the suggested items on the spot, try them on, and make purchases smoothly.

[0565] As a concrete example, consider a female user in her 30s who prefers a casual style for enjoying the outdoors on her days off. When this user enters a store, the smart glasses recognize her appearance and send information to the cloud server. The generative AI model suggests outfits such as a casual jacket, a white T-shirt, jeans, and sneakers, and displays them through the smart glasses. If it is determined based on the user's closet information that she is short of a jacket, the cloud server searches for the appropriate jacket in an online shop and displays a link to purchase it.

[0566] An example of a prompt sentence is as follows:

[0567] User Information:

[0568] Age: 30

[0569] Gender: Female

[0570] Favorite style: Casual

[0571] Lifestyle: Outdoors on holidays

[0572] Store item data:

[0573] white T-shirt

[0574] casual jacket

[0575] jeans

[0576] Prompt for AI:

[0577] Please suggest the perfect casual style for this user."

[0578] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0579] Step 1:

[0580] A user puts on smart glasses and enters a physical store. The smart glasses recognize the user's appearance using a built-in camera. The smart glasses recognize the user's appearance and acquire information about the user's attributes (age, gender, fashion style, etc.). This information is then sent to a cloud server.

[0581] Step 2:

[0582] The server stores the received user information in a database. This is where information about the user's fashion style and lifestyle is updated. The server collects the latest fashion articles, social media posts, and information on new brand products. Based on this, it trains a generative AI model to learn trend information and coordination theory. The input is user information and collected data, and the output is an updated generative AI model.

[0583] Step 3:

[0584] The user requests outfit suggestions through the smart glasses (for example, by entering a command such as "Tell me today's recommended outfits"). The smart glasses recognize this operation and send a request to the cloud server. The input is the user's command, and the output is a request sent to the server.

[0585] Step 4:

[0586] The server retrieves user information from the database and generates optimal outfit suggestions using the most recently trained generative AI model. The generated outfit suggestions are then sent to the smart glasses. The input is the user information retrieved from the database and the generative AI model, and the output is the generated outfit suggestions.

[0587] Step 5:

[0588] The smart glasses display the generated outfit suggestions in the user's field of view using an AR display. The user can then check the suggested outfits. The input is the generated outfit suggestions, and the output is a visual presentation to the user. Specifically, the smart glasses display overlays the suggested items.

[0589] Step 6:

[0590] The server retrieves the user's closet information from a database and uses a generative AI model to identify items that are necessary for the suggested outfit but are not present in the user's closet. It then searches the APIs of affiliated online shops to find the relevant items. The input is the closet information retrieved by the server, and the output is information about items that are candidates for purchase.

[0591] Step 7:

[0592] The server sends information about potential purchase items to the smart glasses, which then display the items and their associated purchase links in the user's field of view using AR. The user can check detailed information about the items they are interested in and click the purchase link to access the online shop. The input is the information about the items they are interested in, and the output is a visual presentation and link provided to the user.

[0593] 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.

[0594] The present invention relates to an AI assistant system that makes optimal coordination suggestions and purchase suggestions tailored to a user's fashion style and lifestyle, and in particular, makes even more personalized suggestions by combining it with an emotion engine that recognizes the user's emotions. This system includes a user information input means, a generative AI model, an optimal coordination suggestion means, a purchase suggestion means, a display means, and an emotion engine.

[0595] Program processing overview

[0596] 1. Enter user information

[0597] Users access a dedicated application or web interface and enter information about their fashion style and lifestyle, such as age, gender, favorite colors, body type, and favorite places. Users can also link their frequently used social media accounts.

[0598] The device checks this information to make sure there are no errors, and then sends the information to the server.

[0599] The server stores the received information in a database.

[0600] 2. Study of trend and coordination theory

[0601] The server collects the latest fashion articles, social media posts, and information on new brand releases from the Internet.

[0602] The server analyzes the collected data using text processing and image recognition technology, and trains a generative AI model that learns trend information and coordination theory.

[0603] 3. Emotion recognition

[0604] Users input brief feedback about their daily emotions and current mood via an application or web interface.

[0605] The device monitors changes in emotions and sends the information to a server.

[0606] The server uses an emotion engine to analyze emotions from user input and interaction patterns, and the analysis results are fed back to the generative AI model.

[0607] 4. Coordination suggestions

[0608] The user enters a command such as "Tell me today's recommended outfit." The request is sent from the device to the server.

[0609] The server searches a database for user information and emotional data, and uses a generative AI model to generate optimal outfit suggestions based on the user's preferences, lifestyle, and emotional state.

[0610] The server transmits the generated coordination plan to the terminal.

[0611] The terminal displays the suggested coordination to the user.

[0612] 5. Purchase Proposal

[0613] The server retrieves the user's closet information (data on the clothes and accessories they own) from a database and identifies items that are missing from the suggested outfit.

[0614] The server searches the API of partner online stores or brands to find the identified missing items.

[0615] The server transmits information about the items to be purchased to the terminal.

[0616] The terminal displays suggested purchase items and links to them to the user.

[0617] 6. Interface Operation

[0618] The user operates the terminal to confirm each suggestion.

[0619] When a user clicks on an outfit or purchase item that interests them, detailed information will be displayed.

[0620] Users can click on the purchase link to be taken to an online store or brand site, where they can seamlessly purchase the suggested item.

[0621] Specific examples

[0622] For example, consider a female user in her 30s who works in an office during the week and enjoys the outdoors on weekends, and who prefers a casual lifestyle. The user logs into a dedicated application and enters her personal information and emotional state. The server stores this information in a database and uses a generative AI model to suggest the user's optimal outfit. For example, it might suggest a "navy blazer, white blouse, jeans, and sneakers." It might also identify that the user is short of a navy blazer based on their closet information and suggest purchasing one. It can then find a navy blazer at a partner online shop and provide the user with a link to purchase it. An emotional engine can be incorporated into this process to make appropriate suggestions based on the user's current emotional state. For example, if the user is feeling stressed, it could suggest a relaxing style.

[0623] This system allows users to significantly reduce the time and effort spent on everyday fashion coordination and enjoy stylish outfits based on the latest trends.In addition, by utilizing an emotion engine, users can receive more personalized suggestions based on their emotional state.

[0624] The processing flow will be explained below.

[0625] Step 1:

[0626] Users access a dedicated application or web interface and enter information about their fashion style and lifestyle, such as age, gender, favorite colors, body type, and favorite places. Users can also link their frequently used social media accounts.

[0627] Step 2:

[0628] The terminal checks the entered information for formatting errors and, once the check is complete, sends the information to the server.

[0629] Step 3:

[0630] The server stores the received information in a database, which is managed individually for each user.

[0631] Step 4:

[0632] The server regularly collects the latest fashion articles, social media posts, and information on new brand products from the Internet.

[0633] Step 5:

[0634] The server analyzes the collected data using text processing and image recognition technology, and the analysis results are used as input data for the generative AI model.

[0635] Step 6:

[0636] The server trains the generative AI model by feeding it trend information and coordination theory. This process runs periodically to ensure the model is constantly learning new information.

[0637] Step 7:

[0638] Users input brief feedback about their daily emotions and current mood via an application or web interface.

[0639] Step 8:

[0640] The device monitors changes in emotions and transmits the emotional data entered by the user to the server.

[0641] Step 9:

[0642] The server uses an emotion engine to analyze emotions from user input and interaction patterns, and the analysis results are fed back to the generative AI model.

[0643] Step 10:

[0644] The user inputs a command such as "Tell me today's recommended outfits." After input, the request is sent from the device to the server.

[0645] Step 11:

[0646] The server searches a database for user information and emotional data, and uses a generative AI model to generate optimal outfit suggestions based on the user's preferences, lifestyle, and emotional state.

[0647] Step 12:

[0648] The server transmits the generated coordinate plan to the terminal, where the transmitted data is converted into a format for visual display.

[0649] Step 13:

[0650] The device will display the suggested outfits to the user, who can review them and, if they like them, request more information.

[0651] Step 14:

[0652] The server retrieves the user's closet information (data on the clothes and accessories they own) from a database and uses this information to identify any missing items for the proposed outfit.

[0653] Step 15:

[0654] The server searches the APIs of partner online shops or brands to find the identified missing items and collects information on potential purchase items.

[0655] Step 16:

[0656] The server sends information about the items to be purchased to the device, including a purchase link and detailed product information.

[0657] Step 17:

[0658] The device displays the suggested purchase items and their associated purchase links to the user, who can then review the displayed content and click the purchase link if necessary.

[0659] Step 18:

[0660] The user clicks on the purchase link, which takes them to the online shop or brand site, allowing them to seamlessly purchase the suggested item.

[0661] In this way, the system can provide optimal coordination and purchase suggestions based on the user's fashion style, lifestyle, and emotional state.

[0662] Example 2

[0663] 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."

[0664] Conventional fashion advice systems only suggest outfits based on a user's basic fashion information and lifestyle, making it difficult to provide personalized suggestions that take into account the user's emotional state. Furthermore, they have problems in that they are unable to efficiently identify missing items in the suggested outfits or make purchasing suggestions based on those items. This often means that users have to spend time and effort trying out the suggested outfits.

[0665] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for the user to input information about fashion style and lifestyle, a means for recognizing the user's emotions and identifying the emotional state by analyzing the data, a means having a generative AI model that learns trend information and coordination theory, a means for proposing an optimal coordination based on the user's information and emotional state, a means for identifying items that are missing from the proposed coordination and suggesting the purchase of those items, and a means for displaying the proposed information to the user. This enables personalized coordination suggestions that take the user's emotional state into consideration and efficient item purchase suggestions.

[0666] The "user information input means" is a means by which a user provides information about fashion style and lifestyle to the system.

[0667] An "emotion recognition means" is a means for detecting a user's emotions and identifying their emotional state by analyzing the data.

[0668] A "generative AI model" is an artificial intelligence model that learns trend information and coordination theory and suggests coordination based on user information.

[0669] The "coordination suggestion means" is a means for advising the user on the most appropriate coordination based on the information input by the user and the user's emotional state.

[0670] The "purchase suggestion means" is a means for identifying an item that is missing from the suggested coordination and recommending the purchase of that item.

[0671] "Display means" refers to the means by which the system notifies the user of suggested outfits and purchase information.

[0672] A "database" is a system for managing and storing a variety of data, such as information entered by users, emotional data, or trend information.

[0673] "Trend information" refers to information that shows the latest trends in the fashion industry, such as the latest fashion articles, social media posts, and information on new brand products.

[0674] "Closet information" is data about the clothes and accessories a user owns.

[0675] The present invention relates to an AI assistant system that makes optimal coordination suggestions and purchase suggestions tailored to a user's fashion style and lifestyle. This system includes a user information input means, an emotion recognition means, a generative AI model, a coordination suggestion means, a purchase suggestion means, and a display means.

[0676] The user information input means allows a user to use a dedicated application or web interface to enter information related to their fashion style and lifestyle, such as their age, gender, favorite colors, body type, and favorite places. For example, information such as "30s, female, prefers casual style, works in an office on weekdays, enjoys outdoor activities on weekends" might be entered.

[0677] Emotion recognition is a means of detecting a user's emotions and identifying their emotional state by analyzing the data. The user inputs simple feedback about their daily emotions and current mood through an application or web interface. For example, they can provide feedback such as "I'm feeling a little stressed today."

[0678] The generative AI model is an artificial intelligence model that learns trend information and coordination theory and suggests outfits based on user information. The server collects the latest fashion articles, social media posts, and information on new brand products from the internet, and analyzes them using text processing and image recognition technology to train the generative AI model.

[0679] The outfit suggestion method is a means of advising the optimal outfit based on the user's input information and emotional state. When a user inputs a request such as "Tell me today's recommended outfit," the server uses a generative AI model to generate the optimal outfit suggestion. For example, a suggestion might be "a navy blazer, a white blouse, jeans, and sneakers."

[0680] The purchase suggestion means identifies items missing from the suggested outfit and recommends the purchase of those items. The server retrieves the user's closet information from the database and identifies the missing items. For example, it determines that a "navy blazer" is missing, searches for the corresponding item from affiliated online shops, and provides a link to purchase it.

[0681] The display means is a means by which the system notifies the user of suggested outfits and purchase information. The generated outfit ideas and purchase links are sent to the terminal and displayed to the user.

[0682] Specific examples

[0683] For example, let's say a female user in her 30s works in an office during the week and enjoys the outdoors on weekends, preferring a casual lifestyle. The user logs into a dedicated application and enters her personal information and emotional state. For example, she might enter, "I want to relax today." The server stores this information in a database and uses a generative AI model to suggest the perfect outfit for the user. For example, it might suggest "a navy blazer, a white blouse, jeans, and sneakers." Furthermore, based on the user's closet information, it might identify that the user is short of a navy blazer and suggest purchasing it. It then finds a suitable navy blazer at a partner online shop and provides the user with a purchase link. This allows the user to quickly obtain the items needed for their outfit.

[0684] Prompt Sentence Examples

[0685] "Please suggest a casual style outfit for a woman in her 30s who works in an office during the week and enjoys the outdoors on weekends."

[0686] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0687] Step 1: Enter your user information

[0688] Users access a dedicated application or web interface and enter information about their fashion style and lifestyle, such as their age, gender, favorite colors, body type, and favorite places. For example, they might enter information such as "30s, female, prefers casual style, works in an office during the week, and enjoys the outdoors on weekends."

[0689] Input: User's basic information (age, gender, favorite color, body type, lifestyle, etc.)

[0690] Output: Checking input data on the terminal and sending it to the server

[0691] Step 2: Verify and save user information

[0692] The terminal checks the entered data for any errors or omissions, and once the check is complete, sends the data to the server.

[0693] The server stores the received user information in a database, which is linked to each user's unique ID.

[0694] Input: User information sent from the device

[0695] Output: User information stored in the database

[0696] Step 3: Learn trend and coordination theory

[0697] The server crawls and collects fashion-related articles, social media posts, and information on new brand releases from the internet. Specifically, it automatically retrieves new collections and posts from popular Instagrammers.

[0698] The server analyzes the collected data using text processing technology (Natural Language Processing) and image recognition technology, for example, by analyzing the color, shape, and style of the captured image.

[0699] The server uses the analysis results to train the generative AI model, which builds a model based on the latest trend information and coordination theory.

[0700] Input: Collected trend information and image data

[0701] Output: A trained generative AI model

[0702] Step 4: Input and analyze emotion data

[0703] Through the application or web interface, users input brief feedback about their daily emotions and current mood, for example, "I feel like relaxing today."

[0704] The device receives the feedback and sends it to the server.

[0705] The server uses an emotion engine to analyze the user's emotional state, and the analysis results are fed back to the generative AI model.

[0706] Input: User's emotional feedback

[0707] Output: Parsed user emotional state data

[0708] Step 5: Generate outfit suggestions

[0709] When a user inputs a request such as "Tell me today's recommended outfit," the request is sent to the server via the terminal.

[0710] The server searches the database for user information and emotional data, and then uses a generative AI model to generate optimal outfit suggestions, such as a navy blazer, a white blouse, jeans, and sneakers.

[0711] The generated outfit suggestions are based on the user's preferences, lifestyle, and emotional state.

[0712] Input: User information, emotion data, request

[0713] Output: Generated optimal coordination plan

[0714] Step 6: Send and view your outfit ideas

[0715] The server transmits the generated coordination plan to the terminal.

[0716] The terminal displays the suggested coordination to the user.

[0717] Input: Generated coordination plan

[0718] Output: Coordination ideas displayed on the user's screen

[0719] Step 7: Generate a purchase offer

[0720] The server retrieves the user's closet information from a database and identifies any missing items from the proposed outfit, such as a navy blazer.

[0721] The server searches the API of partner online stores or brands to find the missing items, for example, searching for a navy blazer from a partner store.

[0722] The server transmits information about the items to be purchased to the terminal.

[0723] Input: Suggested outfit ideas, closet information

[0724] Output: Item information and purchase link

[0725] Step 8: View purchase offers

[0726] The terminal displays suggested purchase items and links to them to the user.

[0727] Users can click on the purchase link to be taken to an online shop or brand site, allowing them to seamlessly purchase the suggested item.

[0728] Input: Item information and link for potential purchases

[0729] Output: Purchase offer and link displayed to the user

[0730] This allows users to receive personalized outfit suggestions and smoothly purchase any items they are missing.

[0731] (Application example 2)

[0732] 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."

[0733] While conventional fashion assistant systems could provide suggestions based on a user's fashion style and lifestyle, they struggled to reflect the user's emotional state or real-time product information in physical stores. As a result, suggestions often did not reflect the user's current mood or the actual inventory status in the store, resulting in an unsatisfactory experience. Furthermore, they provided insufficient support for users to purchase specific coordinating items on the spot.

[0734] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for the user to input information about their fashion style and lifestyle, a means equipped with a generative AI model that learns trend information and coordination theory, a means for proposing optimal outfits based on the user's information and item information in the physical store, a means for identifying items missing from the proposed outfit and suggesting the purchase of those items, a means for displaying the proposed information to the user, and a means for recognizing the user's emotions and changing the proposed outfits in response to those emotions. This enables personalized fashion suggestions that reflect the user's current emotional state and real-time product information in the physical store. It also enhances on-the-spot purchasing support for the suggested items.

[0735] "User" refers to a person who uses a system or service.

[0736] "Fashion style" refers to the combination and design trends of clothing and accessories preferred by individual users.

[0737] "Lifestyle" is a concept that comprehensively expresses a user's daily life patterns, activities, hobbies, and preferences.

[0738] A "generative AI model" is an artificial intelligence model that uses techniques such as machine learning and deep learning to generate appropriate output based on input data.

[0739] "Trend information" refers to information about current trends and fashions in the market and society.

[0740] "Coordination theory" refers to a theoretical framework for suggesting and selecting optimal clothing by combining elements such as color, design, and material.

[0741] "In-store item information" refers to information about products that are actually sold in physical stores.

[0742] The "emotion engine" is a system that recognizes and analyzes emotions from the user's facial expressions and input data.

[0743] "Suggestion" refers to recommendations for coordination or purchases made to users.

[0744] "Real time" refers to a state or action that is reflected immediately at that point in time.

[0745] "Personalized" refers to a state that is optimized to suit the characteristics and circumstances of each individual user.

[0746] The system for realizing this invention allows users to input information about their fashion style and lifestyle, analyzes the user's emotional state using an emotion engine, and integrates this with real-time product information from physical stores to suggest optimal outfits. The system performs processing in the following steps:

[0747] Users use devices such as smartphones or head-mounted displays to input information such as age, gender, favorite colors, body type, and frequently visited places. Users also provide the system with their current mood through simple input or facial expression analysis using a camera. This information is then sent from the device to a server for data processing.

[0748] The server integrates the collected user information with information on items in physical stores and uses a generative AI model to learn the latest trends and coordination theories. The generative AI model uses advanced machine learning algorithms (e.g., GPT-3 and DALL-E) to generate optimal coordination for each user. It also uses emotion engines such as OpenAI's emotion analysis API to analyze user emotion data.

[0749] The server generates personalized outfit suggestions based on user information and product trend and inventory data from physical stores. The suggested outfits reflect the user's preferences, lifestyle, and current emotional state. The suggested outfits are displayed to the user via their device.

[0750] As a specific example, consider a female user in her 30s who works in an office during the week, enjoys outdoor activities on the weekends, and prefers casual fashion. The user logs into the application and enters her personal information and current emotional state (e.g., "I want to relax"). The server stores this information in a database and uses a generative AI model to suggest outfits such as a navy blazer, a white blouse, jeans, and sneakers.

[0751] Furthermore, the server uses the user's closet information and the store's inventory information to identify any missing items in the suggested outfit (in this case, a navy blazer) and provides the user with a link to purchase the item. This process is carried out in real time, allowing the user to instantly receive outfit suggestions via their smartphone or head-mounted display in the store and purchase the necessary items on the spot.

[0752] This system allows users to always enjoy stylish outfits that reflect the latest trends, and offers suggestions based on the user's emotional state, providing a more comfortable and satisfying shopping experience.

[0753] Prompt Sentence Examples

[0754] Age: 30

[0755] Gender: Female

[0756] Favorite color: Blue

[0757] Body shape: normal

[0758] Favorite place: Office

[0759] Current mood: Relaxing

[0760] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0761] Step 1:

[0762] The user inputs information about their fashion style and lifestyle. Using a smartphone or head-mounted display, the user inputs information such as age, gender, favorite colors, body type, and favorite places. This input data is acquired by the device, and after checking the input information and confirming any errors, it is sent to the server. Input: Age, gender, favorite colors, body type, favorite places. Output: User information data.

[0763] Step 2:

[0764] The server stores the received user information in a database. The stored data is used as the basis for future coordination suggestions and sentiment analysis. Input: User information data. Output: User information stored in the database.

[0765] Step 3:

[0766] The terminal collects item information (tag information and image data) from within the physical store and sends it to the server. Using a smartphone or head-mounted display, product information is obtained using RFID tags and image recognition technology within the store. Input: Item information within the store (tag information, image data). Output: Collected item information data.

[0767] Step 4:

[0768] The user inputs their current emotional information. The user can analyze their emotions by entering simple feedback into the application or by reading their facial expressions using the camera function. This data is acquired by the device and sent to the server. Input: Emotional information (e.g., "I want to relax"). Output: Emotional data.

[0769] Step 5:

[0770] The server integrates user information, emotional data, and item information from physical stores, and uses a generative AI model to generate optimal outfit suggestions. Trend information and outfit theory are also taken into consideration. The generated outfit suggestions are based on the user's preferences, lifestyle, and emotional state. Input: User information data, emotional data, item information data. Output: Optimal outfit suggestions.

[0771] Step 6:

[0772] The server sends the generated outfit suggestions to the device. The user can then check the outfit suggestions on their smartphone or head-mounted display. Input: Outfit suggestions. Output: Outfit suggestions displayed on the user device.

[0773] Step 7:

[0774] The server retrieves the user's closet information from the database and identifies items that are missing from the suggested outfit. The identified missing items are provided as purchase links by referencing inventory information from affiliated online shops or physical stores. Input: User's closet information, suggested outfit. Output: Purchase link information for missing items.

[0775] Step 8:

[0776] The user operates the device to check the suggested outfits and purchase links. By clicking the purchase link for the missing item on the device, the user is redirected to the relevant page of a partner online shop or physical store, where the purchase can be made. Input: Purchase link information. Output: Transition to the purchase page of the online shop or physical store.

[0777] This processing flow enables real-time fashion coordination suggestions, personalized suggestions based on the user's emotional state, and even immediate support for purchasing missing items.

[0778] 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.

[0779] 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.

[0780] 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.

[0781] [Third embodiment]

[0782] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0783] 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.

[0784] 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).

[0785] 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.

[0786] 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.

[0787] 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).

[0788] 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.

[0789] 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.

[0790] 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.

[0791] 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.

[0792] 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.

[0793] 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."

[0794] The present invention relates to an AI assistant system that provides optimal coordination and purchase suggestions to suit a user's fashion style and lifestyle. This system includes a user information input means, a generative AI model, optimal coordination suggestion means, purchase suggestion means, and display means.

[0795] Program processing overview

[0796] 1. Enter user information

[0797] - Users access a dedicated application or web interface and enter information about their fashion style and lifestyle, including their age, gender, favorite colors, body type, favorite places, and social media accounts.

[0798] - The device checks this information and then sends it to the server.

[0799] - The server stores the received information in a database.

[0800] 2. Study of trend and coordination theory

[0801] - The server collects the latest fashion articles, social media posts, and information on new brand products from the Internet.

[0802] - The server analyzes this data using text processing and image recognition technology, and trains a generative AI model to learn trend information and coordination theory.

[0803] 3. Coordination suggestions

[0804] - The user performs an operation to request outfit suggestions (for example, enter a command such as "Tell me today's recommended outfits").

[0805] - The device sends this request to the server.

[0806] - The server searches the database for user information and generates optimal outfit suggestions using a generative AI model.

[0807] - The server sends the generated coordination plan to the terminal.

[0808] - The terminal displays the suggested coordination to the user.

[0809] 4. Purchase Proposal

[0810] - The server retrieves the user's closet information (data on the clothes and accessories they own) from the database.

[0811] - The server uses a generative AI model to identify missing items in the proposed outfit.

[0812] - The server searches the API of the partner online shop or brand to find the item.

[0813] - The server sends information about the items to be purchased to the device.

[0814] - The device displays suggested purchase items and links to them to the user.

[0815] 5. Interface Operation

[0816] - The user operates the device to confirm each suggestion.

[0817] - When users click on an outfit or purchase item that interests them, detailed information will be displayed.

[0818] - Users can click on the purchase link and be taken to the online store or brand site to complete the purchase.

[0819] Specific examples

[0820] For example, let's say a female user in her 30s works in an office during the week and enjoys the outdoors on weekends, preferring a casual lifestyle. The user logs in to a dedicated application and enters her information. The server stores that information in a database and uses a generative AI model to suggest the user's optimal outfit. For example, it might suggest a "navy blazer, white blouse, jeans, and sneakers." Furthermore, it might identify that the user is short on navy blazers based on their closet information and suggest purchasing them. By finding a navy blazer at a partner online shop and providing the user with a purchase link, the user can easily purchase the missing item.

[0821] This system allows users to significantly reduce the time and effort spent on everyday fashion coordination and enjoy stylish outfits based on the latest trends.

[0822] The processing flow will be explained below.

[0823] Step 1:

[0824] Users access a dedicated application or web interface and enter information about their fashion style and lifestyle, such as age, gender, favorite colors, body type, and favorite places.

[0825] Step 2:

[0826] The terminal checks the entered information for formatting errors and, once the check is complete, sends the information to the server.

[0827] Step 3:

[0828] The server stores the received information in a database, which is managed individually for each user.

[0829] Step 4:

[0830] The server periodically collects the latest fashion articles, social media posts, and information on new brand releases from the internet, which is used to obtain trend information and update coordination theory.

[0831] Step 5:

[0832] The server analyzes the collected data using text processing and image recognition technology, and the analysis results are used as input data for the generative AI model.

[0833] Step 6:

[0834] The server trains the generative AI model by feeding it trend information and coordination theory. This process is carried out periodically to ensure that the model is constantly learning new information.

[0835] Step 7:

[0836] The user inputs a command such as "Tell me today's recommended outfits." After input, the request is sent from the device to the server.

[0837] Step 8:

[0838] The server searches the database for user information and uses a generative AI model to generate optimal outfit suggestions based on the user's preferences and lifestyle.

[0839] Step 9:

[0840] The server transmits the generated coordinate plan to the terminal, where the transmitted data is converted into a format for visual display.

[0841] Step 10:

[0842] The device will display the suggested outfits to the user, who can review them and, if they like them, request more information.

[0843] Step 11:

[0844] The server retrieves the user's closet information (data on the clothes and accessories they own) from a database and uses this information to identify any missing items for the proposed outfit.

[0845] Step 12:

[0846] The server searches the APIs of partner online shops or brands to find the identified missing items. It also collects information on potential items.

[0847] Step 13:

[0848] The server sends information about the items to be purchased to the device, including a purchase link and detailed product information.

[0849] Step 14:

[0850] The device displays the suggested purchase items and their associated purchase links to the user, who can then review the displayed content and click the purchase link if necessary.

[0851] Step 15:

[0852] The user clicks on the purchase link, which takes them to the online shop or brand site, allowing them to seamlessly purchase the suggested item.

[0853] In this way, the system can provide optimal coordination and purchase suggestions based on the user's fashion style and lifestyle.

[0854] Example 1

[0855] 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."

[0856] Conventional fashion coordination and purchase suggestion systems require users to collect and analyze vast amounts of information themselves, which requires a great deal of time and effort to efficiently enjoy stylish coordination.In addition, the technology to effectively manage and suggest items that users already own and items they need to purchase is insufficient.

[0857] 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.

[0858] In this invention, the server includes a means for a user to input information about their fashion style and lifestyle, a means having a generative AI model that learns trend information and coordination theory, a means for proposing optimal coordination based on the user information, a means for identifying items missing from the proposed coordination and proposing the purchase of those items, a means for displaying the proposed information to the user, and a means for the user to complete an online purchase via the suggested purchase link, thereby enabling the user to enjoy stylish coordination based on the latest trends without any hassle.

[0859] "User information" refers to data related to a user's fashion style and lifestyle, such as their age, gender, favorite colors, body type, favorite places, and social media accounts.

[0860] A "generative AI model" is an artificial intelligence model that analyzes and learns from fashion articles, social media posts, and new brand information collected from the internet, and generates trend information and coordination theories.

[0861] "Coordination suggestions" refer to suggestions for combining fashion items and styles created by a generative AI model based on user information.

[0862] "Purchase suggestion" refers to identifying items the user is missing from the generated outfit and providing links or information to purchase those items.

[0863] "Database" refers to the system that stores and manages user information, closet information, and collected fashion-related data.

[0864] "Closet information" refers to data about the clothes and accessories a user already owns.

[0865] "Trend information" refers to information about currently popular fashion styles and items.

[0866] "Method of completing an online purchase" refers to the user's actions to purchase an item from an online store or brand site via a suggested link.

[0867] "Learning with generative AI models" refers to the process of analyzing collected fashion-related data to understand and update trends and coordination theories.

[0868] This invention relates to an AI assistant system that provides optimal coordination and purchase suggestions to suit a user's fashion style and lifestyle. The system includes a user information input means, a generating AI model, optimal coordination suggestion means, purchase suggestion means, and display means.

[0869] First, the user accesses a dedicated application or web interface and enters their information, including age, gender, favorite colors, body type, favorite places, social media accounts, etc. The device verifies the information and sends it to the server, which then stores it in a database.

[0870] The server uses a scheduler to periodically collect the latest fashion articles, social media posts, and information on new brand releases from the Internet. Specific scraping tools (e.g., Beautiful Soup, Scrapy) are used to collect the data. After collection, the server analyzes the data using text processing (e.g., NLTK, spaCy) and image recognition techniques (e.g., OpenCV, TensorFlow).

[0871] The server then uses a generative AI model (e.g., GPT-3, BERT) to learn the newly acquired trend information and coordination theory. Training takes several hours to several days using a large amount of fashion-related data.

[0872] When a user makes a request on their device, such as "Tell me what outfits you recommend for today," the device sends this request to the server. The server searches the user's information from a database and generates optimal outfit suggestions using a generative AI model. For example, the prompt could be, "Please suggest a casual outfit. The user is in their 30s, works in an office during the week, enjoys the outdoors on weekends, and their favorite color is navy." The generated outfit suggestions are sent to the device and displayed to the user.

[0873] The server then retrieves the user's closet information (data on the clothes and accessories they own) from a database. It then uses a generative AI model to identify items missing from the suggested outfit. The server searches the APIs of affiliated online shops or brands to find the relevant items. It then sends the information about the items to be purchased to the device, which then displays the suggested items and a link to purchase them.

[0874] Users can use their devices to check each suggestion, and by clicking on an outfit or item they are interested in, detailed information will be displayed, and by clicking on the purchase link they will be taken to the online shop or brand site to complete the purchase.

[0875] This system allows users to significantly reduce the time and effort required for everyday fashion coordination and enjoy stylish outfits based on the latest trends.

[0876] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0877] Step 1: Enter user information

[0878] Users access a dedicated application or web interface and enter information about their fashion style and lifestyle, such as age, gender, favorite colors, body type, favorite places, and social media accounts. For example, they might enter "30 years old, female, navy, slim build, prefers office and outdoor activities."

[0879] Input: Information entered by the user.

[0880] The terminal checks the entered information to see if there are any errors. Specifically, it performs real-time validation and displays an error message.

[0881] Output: Successfully validated data.

[0882] The terminal transmits data that has passed validation to the server.

[0883] Step 2: Save user information

[0884] Input: Information about the user's fashion style and lifestyle is sent to the server.

[0885] The server stores the received information in a database by executing an INSERT statement in the SQL database, storing data in fields such as "User ID," "Age," "Gender," "Favorite Color," "Body Type," and "Frequently Visited Places."

[0886] Output: Saved user information.

[0887] Step 3: Learn trend and coordination theory

[0888] Input: Fashion articles, social media posts, and new brand information retrieved by the server from the Internet.

[0889] The server uses a scheduler to periodically collect the latest fashion articles, social media posts, information on new brand products, etc. Specifically, it uses Beautiful Soup and Scrapy to collect data.

[0890] Output: Collected fashion related data.

[0891] The server analyzes the data using text processing (NLTK, spaCy) and image recognition (OpenCV, TensorFlow). Specifically, it categorizes articles by topic and extracts features of fashion items from image data.

[0892] Output: analyzed trend information and coordination theory.

[0893] The server uses a generative AI model (such as GPT-3 or BERT) to learn the newly collected trend information. Specifically, fashion-related data is input into the AI ​​model and trained.

[0894] Output: A trained generative AI model.

[0895] Step 4: Coordination suggestions

[0896] Input: A user request such as "Tell me what outfits I recommend for today."

[0897] The user requests outfit suggestions by voice or text input to the application.

[0898] The device sends a request to the server, specifically by using an API call to send the request data.

[0899] Output: The request data sent to the server.

[0900] The server searches for user information from a database and inputs it into the generative AI model using appropriate prompts (e.g., "Please suggest a casual outfit. Age: 30s, works in an office during the week, enjoys the outdoors on weekends, and favorite color is navy blue.").

[0901] The generative AI model generates optimal coordination ideas.

[0902] Output: The generated coordinate plan.

[0903] The server transmits the generated coordination plan to the terminal.

[0904] The device displays the suggested coordination to the user visually using GUI components (e.g., card view, list view) within the application.

[0905] Output: Coordination ideas displayed.

[0906] Step 5: Purchase proposal

[0907] Input: User's closet information is stored in a database.

[0908] The server retrieves the user's closet information from the database.

[0909] Output: Retrieved closet information.

[0910] The server uses a generative AI model to identify missing items in the proposed outfit by comparing the closet information with the proposed outfit and listing the missing items.

[0911] Output: A list of identified missing items.

[0912] The server searches the APIs of partner online stores or brands to find the relevant items, sending API requests to get product prices and availability information.

[0913] Output: Information about the item you are considering purchasing.

[0914] The server transmits information about the items to be purchased to the terminal.

[0915] The device displays suggested purchase items and their purchase links to the user. Specifically, it creates a list that displays product images, prices, purchase links, etc.

[0916] Output: Displayed suggested items and a link to purchase.

[0917] Step 6: Interface Operation

[0918] Input: Suggested outfit ideas and purchase item information.

[0919] The user can check each suggestion by operating the device, specifically by scrolling through the item list and outfit ideas.

[0920] Output: The user's selected outfits and items.

[0921] When a user clicks on an outfit or purchase item that interests them, detailed information is displayed. Specifically, a click event is triggered and the details page is displayed.

[0922] The user clicks on the purchase link, goes to the online store or brand site, and completes the purchase. Specifically, the user opens an external or in-app browser and completes the purchase.

[0923] Output: Purchase completion information.

[0924] Through the above processing steps, the user can efficiently create fashionable outfits based on the latest trends and purchase the necessary items.

[0925] (Application example 1)

[0926] 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."

[0927] Conventional fashion assistant systems only suggest outfits based on information entered by the user, making it difficult to use in physical stores or to suggest outfits in real time. In addition, the information required for users to actually try on and select clothes had to be manually searched and checked, limiting the accuracy and convenience of the suggestions.

[0928] 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.

[0929] In this invention, the server includes a means for a user to input information about their fashion style and lifestyle, a means having a generative AI model that learns trend information and coordination theory, a means for recognizing the user's appearance through smart glasses and scanning items in the store, a means for proposing optimal coordination based on the user information, a means for identifying items missing from the proposed coordination and suggesting the purchase of those items, and a means for displaying the proposed information to the user. This allows users to receive coordination suggestions in real time in a physical store, making it easier to try on and purchase items in the store.

[0930] "User" refers to an individual who inputs information about their fashion style and lifestyle and receives coordination suggestions from the system.

[0931] "Information about fashion style and lifestyle" is data about style preferences and lifestyle habits based on the user's preferences and daily activities.

[0932] "Trend information and coordination theory" refers to knowledge and rules regarding the latest fashion trends and clothing combinations.

[0933] A "generative AI model" is an artificial intelligence algorithm that generates optimal outfits based on user information and trend information.

[0934] "Smart glasses" refers to a wearable device in the form of glasses that incorporates a computer and display.

[0935] "Means for recognizing the user's appearance and scanning items in the store" refers to devices or programs that use smart glasses or cameras to identify the user's appearance and location and identify items placed in the store.

[0936] "Means for suggesting optimal outfits" refers to a function that suggests clothing combinations suitable for a user based on the user's information and trend information.

[0937] "Means for identifying missing items and suggesting the purchase of those items" refers to a device or program that has the function of determining whether the user has missing items necessary for the suggested outfit and recommending their purchase.

[0938] "Means for displaying information to a user" refers to a device or program that visually presents the generated coordination and purchase suggestions to a user.

[0939] The term "system" refers to a structure including a series of devices, programs, and networks that integrate and operate the above-mentioned means.

[0940] The present invention provides a fashion assistant system that utilizes smart glasses. This system allows users to input information about their fashion style and lifestyle, and based on that information, the system will provide optimal coordination and purchase suggestions.

[0941] The system's hardware consists of smart glasses, a smartphone, and a cloud server. The smart glasses are equipped with a camera and display that recognize the user's appearance and scan items in the store. A dedicated application is installed on the smartphone, which inputs and displays user information. The cloud server hosts a generative AI model and uses trend information and user information to generate outfit suggestions.

[0942] The program processing is explained in natural language below.

[0943] First, the user puts on the smart glasses and enters a brick-and-mortar fashion store. The smart glasses use a camera to recognize the user's appearance and send information such as fashion style, lifestyle, and preferences previously entered into the application to a cloud server. The cloud server uses the acquired information to generate an optimal outfit using a generative AI model that has learned the user's lifestyle and trend information. The generated outfit is presented to the user in real time through the smart glasses' AR display.

[0944] The cloud server then identifies any missing items from the suggested outfit. It retrieves the user's closet information from a database and detects the missing items. The cloud server then searches for potential purchases of the items via the API of affiliated online shops and displays the information on the smart glasses' display.

[0945] This system allows users to receive coordination suggestions in real time in physical stores, and allows them to check the suggested items on the spot, try them on, and make purchases smoothly.

[0946] As a concrete example, consider a female user in her 30s who prefers a casual style for enjoying the outdoors on her days off. When this user enters a store, the smart glasses recognize her appearance and send information to the cloud server. The generative AI model suggests outfits such as a casual jacket, a white T-shirt, jeans, and sneakers, and displays them through the smart glasses. If it is determined based on the user's closet information that she is short of a jacket, the cloud server searches for the appropriate jacket in an online shop and displays a link to purchase it.

[0947] An example of a prompt sentence is as follows:

[0948] User Information:

[0949] Age: 30

[0950] Gender: Female

[0951] Favorite style: Casual

[0952] Lifestyle: Outdoors on holidays

[0953] Store item data:

[0954] white T-shirt

[0955] casual jacket

[0956] jeans

[0957] Prompt for AI:

[0958] Please suggest the perfect casual style for this user."

[0959] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0960] Step 1:

[0961] A user puts on smart glasses and enters a physical store. The smart glasses recognize the user's appearance using a built-in camera. The smart glasses recognize the user's appearance and acquire information about the user's attributes (age, gender, fashion style, etc.). This information is then sent to a cloud server.

[0962] Step 2:

[0963] The server stores the received user information in a database. This is where information about the user's fashion style and lifestyle is updated. The server collects the latest fashion articles, social media posts, and information on new brand products. Based on this, it trains a generative AI model to learn trend information and coordination theory. The input is user information and collected data, and the output is an updated generative AI model.

[0964] Step 3:

[0965] The user requests outfit suggestions through the smart glasses (for example, by entering a command such as "Tell me today's recommended outfits"). The smart glasses recognize this operation and send a request to the cloud server. The input is the user's command, and the output is a request sent to the server.

[0966] Step 4:

[0967] The server retrieves user information from the database and generates optimal outfit suggestions using the most recently trained generative AI model. The generated outfit suggestions are then sent to the smart glasses. The input is the user information retrieved from the database and the generative AI model, and the output is the generated outfit suggestions.

[0968] Step 5:

[0969] The smart glasses display the generated outfit suggestions in the user's field of view using an AR display. The user can then check the suggested outfits. The input is the generated outfit suggestions, and the output is a visual presentation to the user. Specifically, the smart glasses display overlays the suggested items.

[0970] Step 6:

[0971] The server retrieves the user's closet information from a database and uses a generative AI model to identify items that are necessary for the suggested outfit but are not present in the user's closet. It then searches the APIs of affiliated online shops to find the relevant items. The input is the closet information retrieved by the server, and the output is information about items that are candidates for purchase.

[0972] Step 7:

[0973] The server sends information about potential purchase items to the smart glasses, which then display the items and their associated purchase links in the user's field of view using AR. The user can check detailed information about the items they are interested in and click the purchase link to access the online shop. The input is the information about the items they are interested in, and the output is a visual presentation and link provided to the user.

[0974] 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.

[0975] The present invention relates to an AI assistant system that makes optimal coordination suggestions and purchase suggestions tailored to a user's fashion style and lifestyle, and in particular, makes even more personalized suggestions by combining it with an emotion engine that recognizes the user's emotions. This system includes a user information input means, a generative AI model, an optimal coordination suggestion means, a purchase suggestion means, a display means, and an emotion engine.

[0976] Program processing overview

[0977] 1. Enter user information

[0978] Users access a dedicated application or web interface and enter information about their fashion style and lifestyle, such as age, gender, favorite colors, body type, and favorite places. Users can also link their frequently used social media accounts.

[0979] The device checks this information to make sure there are no errors, and then sends the information to the server.

[0980] The server stores the received information in a database.

[0981] 2. Study of trend and coordination theory

[0982] The server collects the latest fashion articles, social media posts, and information on new brand releases from the Internet.

[0983] The server analyzes the collected data using text processing and image recognition technology, and trains a generative AI model that learns trend information and coordination theory.

[0984] 3. Emotion recognition

[0985] Users input brief feedback about their daily emotions and current mood via an application or web interface.

[0986] The device monitors changes in emotions and sends the information to a server.

[0987] The server uses an emotion engine to analyze emotions from user input and interaction patterns, and the analysis results are fed back to the generative AI model.

[0988] 4. Coordination suggestions

[0989] The user enters a command such as "Tell me today's recommended outfit." The request is sent from the device to the server.

[0990] The server searches a database for user information and emotional data, and uses a generative AI model to generate optimal outfit suggestions based on the user's preferences, lifestyle, and emotional state.

[0991] The server transmits the generated coordination plan to the terminal.

[0992] The terminal displays the suggested coordination to the user.

[0993] 5. Purchase Proposal

[0994] The server retrieves the user's closet information (data on the clothes and accessories they own) from a database and identifies items that are missing from the suggested outfit.

[0995] The server searches the API of partner online stores or brands to find the identified missing items.

[0996] The server transmits information about the items to be purchased to the terminal.

[0997] The terminal displays suggested purchase items and links to them to the user.

[0998] 6. Interface Operation

[0999] The user operates the terminal to confirm each suggestion.

[1000] When a user clicks on an outfit or purchase item that interests them, detailed information will be displayed.

[1001] Users can click on the purchase link to be taken to an online store or brand site, where they can seamlessly purchase the suggested item.

[1002] Specific examples

[1003] For example, consider a female user in her 30s who works in an office during the week and enjoys the outdoors on weekends, and who prefers a casual lifestyle. The user logs into a dedicated application and enters her personal information and emotional state. The server stores this information in a database and uses a generative AI model to suggest the user's optimal outfit. For example, it might suggest a "navy blazer, white blouse, jeans, and sneakers." It might also identify that the user is short of a navy blazer based on their closet information and suggest purchasing one. It can then find a navy blazer at a partner online shop and provide the user with a link to purchase it. An emotional engine can be incorporated into this process to make appropriate suggestions based on the user's current emotional state. For example, if the user is feeling stressed, it could suggest a relaxing style.

[1004] This system allows users to significantly reduce the time and effort spent on everyday fashion coordination and enjoy stylish outfits based on the latest trends.In addition, by utilizing an emotion engine, users can receive more personalized suggestions based on their emotional state.

[1005] The processing flow will be explained below.

[1006] Step 1:

[1007] Users access a dedicated application or web interface and enter information about their fashion style and lifestyle, such as age, gender, favorite colors, body type, and favorite places. Users can also link their frequently used social media accounts.

[1008] Step 2:

[1009] The terminal checks the entered information for formatting errors and, once the check is complete, sends the information to the server.

[1010] Step 3:

[1011] The server stores the received information in a database, which is managed individually for each user.

[1012] Step 4:

[1013] The server regularly collects the latest fashion articles, social media posts, and information on new brand products from the Internet.

[1014] Step 5:

[1015] The server analyzes the collected data using text processing and image recognition technology, and the analysis results are used as input data for the generative AI model.

[1016] Step 6:

[1017] The server trains the generative AI model by feeding it trend information and coordination theory. This process runs periodically to ensure the model is constantly learning new information.

[1018] Step 7:

[1019] Users input brief feedback about their daily emotions and current mood via an application or web interface.

[1020] Step 8:

[1021] The device monitors changes in emotions and transmits the emotional data entered by the user to the server.

[1022] Step 9:

[1023] The server uses an emotion engine to analyze emotions from user input and interaction patterns, and the analysis results are fed back to the generative AI model.

[1024] Step 10:

[1025] The user inputs a command such as "Tell me today's recommended outfits." After input, the request is sent from the device to the server.

[1026] Step 11:

[1027] The server searches a database for user information and emotional data, and uses a generative AI model to generate optimal outfit suggestions based on the user's preferences, lifestyle, and emotional state.

[1028] Step 12:

[1029] The server transmits the generated coordinate plan to the terminal, where the transmitted data is converted into a format for visual display.

[1030] Step 13:

[1031] The device will display the suggested outfits to the user, who can review them and, if they like them, request more information.

[1032] Step 14:

[1033] The server retrieves the user's closet information (data on the clothes and accessories they own) from a database and uses this information to identify any missing items for the proposed outfit.

[1034] Step 15:

[1035] The server searches the APIs of partner online shops or brands to find the identified missing items and collects information on potential purchase items.

[1036] Step 16:

[1037] The server sends information about the items to be purchased to the device, including a purchase link and detailed product information.

[1038] Step 17:

[1039] The device displays the suggested purchase items and their associated purchase links to the user, who can then review the displayed content and click the purchase link if necessary.

[1040] Step 18:

[1041] The user clicks on the purchase link, which takes them to the online shop or brand site, allowing them to seamlessly purchase the suggested item.

[1042] In this way, the system can provide optimal coordination and purchase suggestions based on the user's fashion style, lifestyle, and emotional state.

[1043] Example 2

[1044] 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."

[1045] Conventional fashion advice systems only suggest outfits based on a user's basic fashion information and lifestyle, making it difficult to provide personalized suggestions that take into account the user's emotional state. Furthermore, they have problems in that they are unable to efficiently identify missing items in the suggested outfits or make purchasing suggestions based on those items. This often means that users have to spend time and effort trying out the suggested outfits.

[1046] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for the user to input information about fashion style and lifestyle, a means for recognizing the user's emotions and identifying the emotional state by analyzing the data, a means having a generative AI model that learns trend information and coordination theory, a means for proposing an optimal coordination based on the user's information and emotional state, a means for identifying items that are missing from the proposed coordination and suggesting the purchase of those items, and a means for displaying the proposed information to the user. This enables personalized coordination suggestions that take the user's emotional state into consideration and efficient item purchase suggestions.

[1047] The "user information input means" is a means by which a user provides information about fashion style and lifestyle to the system.

[1048] An "emotion recognition means" is a means for detecting a user's emotions and identifying their emotional state by analyzing the data.

[1049] A "generative AI model" is an artificial intelligence model that learns trend information and coordination theory and suggests coordination based on user information.

[1050] The "coordination suggestion means" is a means for advising the user on the most appropriate coordination based on the information input by the user and the user's emotional state.

[1051] The "purchase suggestion means" is a means for identifying an item that is missing from the suggested coordination and recommending the purchase of that item.

[1052] "Display means" refers to the means by which the system notifies the user of suggested outfits and purchase information.

[1053] A "database" is a system for managing and storing a variety of data, such as information entered by users, emotional data, or trend information.

[1054] "Trend information" refers to information that shows the latest trends in the fashion industry, such as the latest fashion articles, social media posts, and information on new brand products.

[1055] "Closet information" is data about the clothes and accessories a user owns.

[1056] The present invention relates to an AI assistant system that makes optimal coordination suggestions and purchase suggestions tailored to a user's fashion style and lifestyle. This system includes a user information input means, an emotion recognition means, a generative AI model, a coordination suggestion means, a purchase suggestion means, and a display means.

[1057] The user information input means allows a user to use a dedicated application or web interface to enter information related to their fashion style and lifestyle, such as their age, gender, favorite colors, body type, and favorite places. For example, information such as "30s, female, prefers casual style, works in an office on weekdays, enjoys outdoor activities on weekends" might be entered.

[1058] Emotion recognition is a means of detecting a user's emotions and identifying their emotional state by analyzing the data. The user inputs simple feedback about their daily emotions and current mood through an application or web interface. For example, they can provide feedback such as "I'm feeling a little stressed today."

[1059] The generative AI model is an artificial intelligence model that learns trend information and coordination theory and suggests outfits based on user information. The server collects the latest fashion articles, social media posts, and information on new brand products from the internet, and analyzes them using text processing and image recognition technology to train the generative AI model.

[1060] The outfit suggestion method is a means of advising the optimal outfit based on the user's input information and emotional state. When a user inputs a request such as "Tell me today's recommended outfit," the server uses a generative AI model to generate the optimal outfit suggestion. For example, a suggestion might be "a navy blazer, a white blouse, jeans, and sneakers."

[1061] The purchase suggestion means identifies items missing from the suggested outfit and recommends the purchase of those items. The server retrieves the user's closet information from the database and identifies the missing items. For example, it determines that a "navy blazer" is missing, searches for the corresponding item from affiliated online shops, and provides a link to purchase it.

[1062] The display means is a means by which the system notifies the user of suggested outfits and purchase information. The generated outfit ideas and purchase links are sent to the terminal and displayed to the user.

[1063] Specific examples

[1064] For example, let's say a female user in her 30s works in an office during the week and enjoys the outdoors on weekends, preferring a casual lifestyle. The user logs into a dedicated application and enters her personal information and emotional state. For example, she might enter, "I want to relax today." The server stores this information in a database and uses a generative AI model to suggest the perfect outfit for the user. For example, it might suggest "a navy blazer, a white blouse, jeans, and sneakers." Furthermore, based on the user's closet information, it might identify that the user is short of a navy blazer and suggest purchasing it. It then finds a suitable navy blazer at a partner online shop and provides the user with a purchase link. This allows the user to quickly obtain the items needed for their outfit.

[1065] Prompt Sentence Examples

[1066] "Please suggest a casual style outfit for a woman in her 30s who works in an office during the week and enjoys the outdoors on weekends."

[1067] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1068] Step 1: Enter your user information

[1069] Users access a dedicated application or web interface and enter information about their fashion style and lifestyle, such as their age, gender, favorite colors, body type, and favorite places. For example, they might enter information such as "30s, female, prefers casual style, works in an office during the week, and enjoys the outdoors on weekends."

[1070] Input: User's basic information (age, gender, favorite color, body type, lifestyle, etc.)

[1071] Output: Checking input data on the terminal and sending it to the server

[1072] Step 2: Verify and save user information

[1073] The terminal checks the entered data for any errors or omissions, and once the check is complete, sends the data to the server.

[1074] The server stores the received user information in a database, which is linked to each user's unique ID.

[1075] Input: User information sent from the device

[1076] Output: User information stored in the database

[1077] Step 3: Learn trend and coordination theory

[1078] The server crawls and collects fashion-related articles, social media posts, and information on new brand releases from the internet. Specifically, it automatically retrieves new collections and posts from popular Instagrammers.

[1079] The server analyzes the collected data using text processing technology (Natural Language Processing) and image recognition technology, for example, by analyzing the color, shape, and style of the captured image.

[1080] The server uses the analysis results to train the generative AI model, which builds a model based on the latest trend information and coordination theory.

[1081] Input: Collected trend information and image data

[1082] Output: A trained generative AI model

[1083] Step 4: Input and analyze emotion data

[1084] Through the application or web interface, users input brief feedback about their daily emotions and current mood, for example, "I feel like relaxing today."

[1085] The device receives the feedback and sends it to the server.

[1086] The server uses an emotion engine to analyze the user's emotional state, and the analysis results are fed back to the generative AI model.

[1087] Input: User's emotional feedback

[1088] Output: Parsed user emotional state data

[1089] Step 5: Generate outfit suggestions

[1090] When a user inputs a request such as "Tell me today's recommended outfit," the request is sent to the server via the terminal.

[1091] The server searches the database for user information and emotional data, and then uses a generative AI model to generate optimal outfit suggestions, such as a navy blazer, a white blouse, jeans, and sneakers.

[1092] The generated outfit suggestions are based on the user's preferences, lifestyle, and emotional state.

[1093] Input: User information, emotion data, request

[1094] Output: Generated optimal coordination plan

[1095] Step 6: Send and view your outfit ideas

[1096] The server transmits the generated coordination plan to the terminal.

[1097] The terminal displays the suggested coordination to the user.

[1098] Input: Generated coordination plan

[1099] Output: Coordination ideas displayed on the user's screen

[1100] Step 7: Generate a purchase offer

[1101] The server retrieves the user's closet information from a database and identifies any missing items from the proposed outfit, such as a navy blazer.

[1102] The server searches the API of partner online stores or brands to find the missing items, for example, searching for a navy blazer from a partner store.

[1103] The server transmits information about the items to be purchased to the terminal.

[1104] Input: Suggested outfit ideas, closet information

[1105] Output: Item information and purchase link

[1106] Step 8: View purchase offers

[1107] The terminal displays suggested purchase items and links to them to the user.

[1108] Users can click on the purchase link to be taken to an online shop or brand site, allowing them to seamlessly purchase the suggested item.

[1109] Input: Item information and link for potential purchases

[1110] Output: Purchase offer and link displayed to the user

[1111] This allows users to receive personalized outfit suggestions and smoothly purchase any items they are missing.

[1112] (Application example 2)

[1113] 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."

[1114] While conventional fashion assistant systems could provide suggestions based on a user's fashion style and lifestyle, they struggled to reflect the user's emotional state or real-time product information in physical stores. As a result, suggestions often did not reflect the user's current mood or the actual inventory status in the store, resulting in an unsatisfactory experience. Furthermore, they provided insufficient support for users to purchase specific coordinating items on the spot.

[1115] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for the user to input information about their fashion style and lifestyle, a means equipped with a generative AI model that learns trend information and coordination theory, a means for proposing optimal outfits based on the user's information and item information in the physical store, a means for identifying items missing from the proposed outfit and suggesting the purchase of those items, a means for displaying the proposed information to the user, and a means for recognizing the user's emotions and changing the proposed outfits in response to those emotions. This enables personalized fashion suggestions that reflect the user's current emotional state and real-time product information in the physical store. It also enhances on-the-spot purchasing support for the suggested items.

[1116] "User" refers to a person who uses a system or service.

[1117] "Fashion style" refers to the combination and design trends of clothing and accessories preferred by individual users.

[1118] "Lifestyle" is a concept that comprehensively expresses a user's daily life patterns, activities, hobbies, and preferences.

[1119] A "generative AI model" is an artificial intelligence model that uses techniques such as machine learning and deep learning to generate appropriate output based on input data.

[1120] "Trend information" refers to information about current trends and fashions in the market and society.

[1121] "Coordination theory" refers to a theoretical framework for suggesting and selecting optimal clothing by combining elements such as color, design, and material.

[1122] "In-store item information" refers to information about products that are actually sold in physical stores.

[1123] The "emotion engine" is a system that recognizes and analyzes emotions from the user's facial expressions and input data.

[1124] "Suggestion" refers to recommendations for coordination or purchases made to users.

[1125] "Real time" refers to a state or action that is reflected immediately at that point in time.

[1126] "Personalized" refers to a state that is optimized to suit the characteristics and circumstances of each individual user.

[1127] The system for realizing this invention allows users to input information about their fashion style and lifestyle, analyzes the user's emotional state using an emotion engine, and integrates this with real-time product information from physical stores to suggest optimal outfits. The system performs processing in the following steps:

[1128] Users use devices such as smartphones or head-mounted displays to input information such as age, gender, favorite colors, body type, and frequently visited places. Users also provide the system with their current mood through simple input or facial expression analysis using a camera. This information is then sent from the device to a server for data processing.

[1129] The server integrates the collected user information with information on items in physical stores and uses a generative AI model to learn the latest trends and coordination theories. The generative AI model uses advanced machine learning algorithms (e.g., GPT-3 and DALL-E) to generate optimal coordination for each user. It also uses emotion engines such as OpenAI's emotion analysis API to analyze user emotion data.

[1130] The server generates personalized outfit suggestions based on user information and product trend and inventory data from physical stores. The suggested outfits reflect the user's preferences, lifestyle, and current emotional state. The suggested outfits are displayed to the user via their device.

[1131] As a specific example, consider a female user in her 30s who works in an office during the week, enjoys outdoor activities on the weekends, and prefers casual fashion. The user logs into the application and enters her personal information and current emotional state (e.g., "I want to relax"). The server stores this information in a database and uses a generative AI model to suggest outfits such as a navy blazer, a white blouse, jeans, and sneakers.

[1132] Furthermore, the server uses the user's closet information and the store's inventory information to identify any missing items in the suggested outfit (in this case, a navy blazer) and provides the user with a link to purchase the item. This process is carried out in real time, allowing the user to instantly receive outfit suggestions via their smartphone or head-mounted display in the store and purchase the necessary items on the spot.

[1133] This system allows users to always enjoy stylish outfits that reflect the latest trends, and offers suggestions based on the user's emotional state, providing a more comfortable and satisfying shopping experience.

[1134] Prompt Sentence Examples

[1135] Age: 30

[1136] Gender: Female

[1137] Favorite color: Blue

[1138] Body shape: normal

[1139] Favorite place: Office

[1140] Current mood: Relaxing

[1141] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1142] Step 1:

[1143] The user inputs information about their fashion style and lifestyle. Using a smartphone or head-mounted display, the user inputs information such as age, gender, favorite colors, body type, and favorite places. This input data is acquired by the device, and after checking the input information and confirming any errors, it is sent to the server. Input: Age, gender, favorite colors, body type, favorite places. Output: User information data.

[1144] Step 2:

[1145] The server stores the received user information in a database. The stored data is used as the basis for future coordination suggestions and sentiment analysis. Input: User information data. Output: User information stored in the database.

[1146] Step 3:

[1147] The terminal collects item information (tag information and image data) from within the physical store and sends it to the server. Using a smartphone or head-mounted display, product information is obtained using RFID tags and image recognition technology within the store. Input: Item information within the store (tag information, image data). Output: Collected item information data.

[1148] Step 4:

[1149] The user inputs their current emotional information. The user can analyze their emotions by entering simple feedback into the application or by reading their facial expressions using the camera function. This data is acquired by the device and sent to the server. Input: Emotional information (e.g., "I want to relax"). Output: Emotional data.

[1150] Step 5:

[1151] The server integrates user information, emotional data, and item information from physical stores, and uses a generative AI model to generate optimal outfit suggestions. Trend information and outfit theory are also taken into consideration. The generated outfit suggestions are based on the user's preferences, lifestyle, and emotional state. Input: User information data, emotional data, item information data. Output: Optimal outfit suggestions.

[1152] Step 6:

[1153] The server sends the generated outfit suggestions to the device. The user can then check the outfit suggestions on their smartphone or head-mounted display. Input: Outfit suggestions. Output: Outfit suggestions displayed on the user device.

[1154] Step 7:

[1155] The server retrieves the user's closet information from the database and identifies items that are missing from the suggested outfit. The identified missing items are provided as purchase links by referencing inventory information from affiliated online shops or physical stores. Input: User's closet information, suggested outfit. Output: Purchase link information for missing items.

[1156] Step 8:

[1157] The user operates the device to check the suggested outfits and purchase links. By clicking the purchase link for the missing item on the device, the user is redirected to the relevant page of a partner online shop or physical store, where the purchase can be made. Input: Purchase link information. Output: Transition to the purchase page of the online shop or physical store.

[1158] This processing flow enables real-time fashion coordination suggestions, personalized suggestions based on the user's emotional state, and even immediate support for purchasing missing items.

[1159] 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.

[1160] 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.

[1161] 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.

[1162] [Fourth embodiment]

[1163] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1164] 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.

[1165] 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).

[1166] 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.

[1167] 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.

[1168] 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).

[1169] 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.

[1170] 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.

[1171] 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.

[1172] 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.

[1173] 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.

[1174] 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.

[1175] 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."

[1176] The present invention relates to an AI assistant system that provides optimal coordination and purchase suggestions to suit a user's fashion style and lifestyle. This system includes a user information input means, a generative AI model, optimal coordination suggestion means, purchase suggestion means, and display means.

[1177] Program processing overview

[1178] 1. Enter user information

[1179] - Users access a dedicated application or web interface and enter information about their fashion style and lifestyle, including their age, gender, favorite colors, body type, favorite places, and social media accounts.

[1180] - The device checks this information and then sends it to the server.

[1181] - The server stores the received information in a database.

[1182] 2. Study of trend and coordination theory

[1183] - The server collects the latest fashion articles, social media posts, and information on new brand products from the Internet.

[1184] - The server analyzes this data using text processing and image recognition technology, and trains a generative AI model to learn trend information and coordination theory.

[1185] 3. Coordination suggestions

[1186] - The user performs an operation to request outfit suggestions (for example, enter a command such as "Tell me today's recommended outfits").

[1187] - The device sends this request to the server.

[1188] - The server searches the database for user information and generates optimal outfit suggestions using a generative AI model.

[1189] - The server sends the generated coordination plan to the terminal.

[1190] - The terminal displays the suggested coordination to the user.

[1191] 4. Purchase Proposal

[1192] - The server retrieves the user's closet information (data on the clothes and accessories they own) from the database.

[1193] - The server uses a generative AI model to identify missing items in the proposed outfit.

[1194] - The server searches the API of the partner online shop or brand to find the item.

[1195] - The server sends information about the items to be purchased to the device.

[1196] - The device displays suggested purchase items and links to them to the user.

[1197] 5. Interface Operation

[1198] - The user operates the device to confirm each suggestion.

[1199] - When users click on an outfit or purchase item that interests them, detailed information will be displayed.

[1200] - Users can click on the purchase link and be taken to the online store or brand site to complete the purchase.

[1201] Specific examples

[1202] For example, let's say a female user in her 30s works in an office during the week and enjoys the outdoors on weekends, preferring a casual lifestyle. The user logs in to a dedicated application and enters her information. The server stores that information in a database and uses a generative AI model to suggest the user's optimal outfit. For example, it might suggest a "navy blazer, white blouse, jeans, and sneakers." Furthermore, it might identify that the user is short on navy blazers based on their closet information and suggest purchasing them. By finding a navy blazer at a partner online shop and providing the user with a purchase link, the user can easily purchase the missing item.

[1203] This system allows users to significantly reduce the time and effort spent on everyday fashion coordination and enjoy stylish outfits based on the latest trends.

[1204] The processing flow will be explained below.

[1205] Step 1:

[1206] Users access a dedicated application or web interface and enter information about their fashion style and lifestyle, such as age, gender, favorite colors, body type, and favorite places.

[1207] Step 2:

[1208] The terminal checks the entered information for formatting errors and, once the check is complete, sends the information to the server.

[1209] Step 3:

[1210] The server stores the received information in a database, which is managed individually for each user.

[1211] Step 4:

[1212] The server periodically collects the latest fashion articles, social media posts, and information on new brand releases from the internet, which is used to obtain trend information and update coordination theory.

[1213] Step 5:

[1214] The server analyzes the collected data using text processing and image recognition technology, and the analysis results are used as input data for the generative AI model.

[1215] Step 6:

[1216] The server trains the generative AI model by feeding it trend information and coordination theory. This process is carried out periodically to ensure that the model is constantly learning new information.

[1217] Step 7:

[1218] The user inputs a command such as "Tell me today's recommended outfits." After input, the request is sent from the device to the server.

[1219] Step 8:

[1220] The server searches the database for user information and uses a generative AI model to generate optimal outfit suggestions based on the user's preferences and lifestyle.

[1221] Step 9:

[1222] The server transmits the generated coordinate plan to the terminal, where the transmitted data is converted into a format for visual display.

[1223] Step 10:

[1224] The device will display the suggested outfits to the user, who can review them and, if they like them, request more information.

[1225] Step 11:

[1226] The server retrieves the user's closet information (data on the clothes and accessories they own) from a database and uses this information to identify any missing items for the proposed outfit.

[1227] Step 12:

[1228] The server searches the APIs of partner online shops or brands to find the identified missing items. It also collects information on potential items.

[1229] Step 13:

[1230] The server sends information about the items to be purchased to the device, including a purchase link and detailed product information.

[1231] Step 14:

[1232] The device displays the suggested purchase items and their associated purchase links to the user, who can then review the displayed content and click the purchase link if necessary.

[1233] Step 15:

[1234] The user clicks on the purchase link, which takes them to the online shop or brand site, allowing them to seamlessly purchase the suggested item.

[1235] In this way, the system can provide optimal coordination and purchase suggestions based on the user's fashion style and lifestyle.

[1236] Example 1

[1237] 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."

[1238] Conventional fashion coordination and purchase suggestion systems require users to collect and analyze vast amounts of information themselves, which requires a great deal of time and effort to efficiently enjoy stylish coordination.In addition, the technology to effectively manage and suggest items that users already own and items they need to purchase is insufficient.

[1239] 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.

[1240] In this invention, the server includes a means for a user to input information about their fashion style and lifestyle, a means having a generative AI model that learns trend information and coordination theory, a means for proposing optimal coordination based on the user information, a means for identifying items missing from the proposed coordination and proposing the purchase of those items, a means for displaying the proposed information to the user, and a means for the user to complete an online purchase via the suggested purchase link, thereby enabling the user to enjoy stylish coordination based on the latest trends without any hassle.

[1241] "User information" refers to data related to a user's fashion style and lifestyle, such as their age, gender, favorite colors, body type, favorite places, and social media accounts.

[1242] A "generative AI model" is an artificial intelligence model that analyzes and learns from fashion articles, social media posts, and new brand information collected from the internet, and generates trend information and coordination theories.

[1243] "Coordination suggestions" refer to suggestions for combining fashion items and styles created by a generative AI model based on user information.

[1244] "Purchase suggestion" refers to identifying items the user is missing from the generated outfit and providing links or information to purchase those items.

[1245] "Database" refers to the system that stores and manages user information, closet information, and collected fashion-related data.

[1246] "Closet information" refers to data about the clothes and accessories a user already owns.

[1247] "Trend information" refers to information about currently popular fashion styles and items.

[1248] "Method of completing an online purchase" refers to the user's actions to purchase an item from an online store or brand site via a suggested link.

[1249] "Learning with generative AI models" refers to the process of analyzing collected fashion-related data to understand and update trends and coordination theories.

[1250] This invention relates to an AI assistant system that provides optimal coordination and purchase suggestions to suit a user's fashion style and lifestyle. The system includes a user information input means, a generating AI model, optimal coordination suggestion means, purchase suggestion means, and display means.

[1251] First, the user accesses a dedicated application or web interface and enters their information, including age, gender, favorite colors, body type, favorite places, social media accounts, etc. The device verifies the information and sends it to the server, which then stores it in a database.

[1252] The server uses a scheduler to periodically collect the latest fashion articles, social media posts, and information on new brand releases from the Internet. Specific scraping tools (e.g., Beautiful Soup, Scrapy) are used to collect the data. After collection, the server analyzes the data using text processing (e.g., NLTK, spaCy) and image recognition techniques (e.g., OpenCV, TensorFlow).

[1253] The server then uses a generative AI model (e.g., GPT-3, BERT) to learn the newly acquired trend information and coordination theory. Training takes several hours to several days using a large amount of fashion-related data.

[1254] When a user makes a request on their device, such as "Tell me what outfits you recommend for today," the device sends this request to the server. The server searches the user's information from a database and generates optimal outfit suggestions using a generative AI model. For example, the prompt could be, "Please suggest a casual outfit. The user is in their 30s, works in an office during the week, enjoys the outdoors on weekends, and their favorite color is navy." The generated outfit suggestions are sent to the device and displayed to the user.

[1255] The server then retrieves the user's closet information (data on the clothes and accessories they own) from a database. It then uses a generative AI model to identify items missing from the suggested outfit. The server searches the APIs of affiliated online shops or brands to find the relevant items. It then sends the information about the items to be purchased to the device, which then displays the suggested items and a link to purchase them.

[1256] Users can use their devices to check each suggestion, and by clicking on an outfit or item they are interested in, detailed information will be displayed, and by clicking on the purchase link they will be taken to the online shop or brand site to complete the purchase.

[1257] This system allows users to significantly reduce the time and effort required for everyday fashion coordination and enjoy stylish outfits based on the latest trends.

[1258] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1259] Step 1: Enter user information

[1260] Users access a dedicated application or web interface and enter information about their fashion style and lifestyle, such as age, gender, favorite colors, body type, favorite places, and social media accounts. For example, they might enter "30 years old, female, navy, slim build, prefers office and outdoor activities."

[1261] Input: Information entered by the user.

[1262] The terminal checks the entered information to see if there are any errors. Specifically, it performs real-time validation and displays an error message.

[1263] Output: Successfully validated data.

[1264] The terminal transmits data that has passed validation to the server.

[1265] Step 2: Save user information

[1266] Input: Information about the user's fashion style and lifestyle is sent to the server.

[1267] The server stores the received information in a database by executing an INSERT statement in the SQL database, storing data in fields such as "User ID," "Age," "Gender," "Favorite Color," "Body Type," and "Frequently Visited Places."

[1268] Output: Saved user information.

[1269] Step 3: Learn trend and coordination theory

[1270] Input: Fashion articles, social media posts, and new brand information retrieved by the server from the Internet.

[1271] The server uses a scheduler to periodically collect the latest fashion articles, social media posts, information on new brand products, etc. Specifically, it uses Beautiful Soup and Scrapy to collect data.

[1272] Output: Collected fashion related data.

[1273] The server analyzes the data using text processing (NLTK, spaCy) and image recognition (OpenCV, TensorFlow). Specifically, it categorizes articles by topic and extracts features of fashion items from image data.

[1274] Output: analyzed trend information and coordination theory.

[1275] The server uses a generative AI model (such as GPT-3 or BERT) to learn the newly collected trend information. Specifically, fashion-related data is input into the AI ​​model and trained.

[1276] Output: A trained generative AI model.

[1277] Step 4: Coordination suggestions

[1278] Input: A user request such as "Tell me what outfits I recommend for today."

[1279] The user requests outfit suggestions by voice or text input to the application.

[1280] The device sends a request to the server, specifically by using an API call to send the request data.

[1281] Output: The request data sent to the server.

[1282] The server searches for user information from a database and inputs it into the generative AI model using appropriate prompts (e.g., "Please suggest a casual outfit. Age: 30s, works in an office during the week, enjoys the outdoors on weekends, and favorite color is navy blue.").

[1283] The generative AI model generates optimal coordination ideas.

[1284] Output: The generated coordinate plan.

[1285] The server transmits the generated coordination plan to the terminal.

[1286] The device displays the suggested coordination to the user visually using GUI components (e.g., card view, list view) within the application.

[1287] Output: Coordination ideas displayed.

[1288] Step 5: Purchase proposal

[1289] Input: User's closet information is stored in a database.

[1290] The server retrieves the user's closet information from the database.

[1291] Output: Retrieved closet information.

[1292] The server uses a generative AI model to identify missing items in the proposed outfit by comparing the closet information with the proposed outfit and listing the missing items.

[1293] Output: A list of identified missing items.

[1294] The server searches the APIs of partner online stores or brands to find the relevant items, sending API requests to get product prices and availability information.

[1295] Output: Information about the item you are considering purchasing.

[1296] The server transmits information about the items to be purchased to the terminal.

[1297] The device displays suggested purchase items and their purchase links to the user. Specifically, it creates a list that displays product images, prices, purchase links, etc.

[1298] Output: Displayed suggested items and a link to purchase.

[1299] Step 6: Interface Operation

[1300] Input: Suggested outfit ideas and purchase item information.

[1301] The user can check each suggestion by operating the device, specifically by scrolling through the item list and outfit ideas.

[1302] Output: The user's selected outfits and items.

[1303] When a user clicks on an outfit or purchase item that interests them, detailed information is displayed. Specifically, a click event is triggered and the details page is displayed.

[1304] The user clicks on the purchase link, goes to the online store or brand site, and completes the purchase. Specifically, the user opens an external or in-app browser and completes the purchase.

[1305] Output: Purchase completion information.

[1306] Through the above processing steps, the user can efficiently create fashionable outfits based on the latest trends and purchase the necessary items.

[1307] (Application example 1)

[1308] 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."

[1309] Conventional fashion assistant systems only suggest outfits based on information entered by the user, making it difficult to use in physical stores or to suggest outfits in real time. In addition, the information required for users to actually try on and select clothes had to be manually searched and checked, limiting the accuracy and convenience of the suggestions.

[1310] 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.

[1311] In this invention, the server includes a means for a user to input information about their fashion style and lifestyle, a means having a generative AI model that learns trend information and coordination theory, a means for recognizing the user's appearance through smart glasses and scanning items in the store, a means for proposing optimal coordination based on the user information, a means for identifying items missing from the proposed coordination and suggesting the purchase of those items, and a means for displaying the proposed information to the user. This allows users to receive coordination suggestions in real time in a physical store, making it easier to try on and purchase items in the store.

[1312] "User" refers to an individual who inputs information about their fashion style and lifestyle and receives coordination suggestions from the system.

[1313] "Information about fashion style and lifestyle" is data about style preferences and lifestyle habits based on the user's preferences and daily activities.

[1314] "Trend information and coordination theory" refers to knowledge and rules regarding the latest fashion trends and clothing combinations.

[1315] A "generative AI model" is an artificial intelligence algorithm that generates optimal outfits based on user information and trend information.

[1316] "Smart glasses" refers to a wearable device in the form of glasses that incorporates a computer and display.

[1317] "Means for recognizing the user's appearance and scanning items in the store" refers to devices or programs that use smart glasses or cameras to identify the user's appearance and location and identify items placed in the store.

[1318] "Means for suggesting optimal outfits" refers to a function that suggests clothing combinations suitable for a user based on the user's information and trend information.

[1319] "Means for identifying missing items and suggesting the purchase of those items" refers to a device or program that has the function of determining whether the user has missing items necessary for the suggested outfit and recommending their purchase.

[1320] "Means for displaying information to a user" refers to a device or program that visually presents the generated coordination and purchase suggestions to a user.

[1321] The term "system" refers to a structure including a series of devices, programs, and networks that integrate and operate the above-mentioned means.

[1322] The present invention provides a fashion assistant system that utilizes smart glasses. This system allows users to input information about their fashion style and lifestyle, and based on that information, the system will provide optimal coordination and purchase suggestions.

[1323] The system's hardware consists of smart glasses, a smartphone, and a cloud server. The smart glasses are equipped with a camera and display that recognize the user's appearance and scan items in the store. A dedicated application is installed on the smartphone, which inputs and displays user information. The cloud server hosts a generative AI model and uses trend information and user information to generate outfit suggestions.

[1324] The program processing is explained in natural language below.

[1325] First, the user puts on the smart glasses and enters a brick-and-mortar fashion store. The smart glasses use a camera to recognize the user's appearance and send information such as fashion style, lifestyle, and preferences previously entered into the application to a cloud server. The cloud server uses the acquired information to generate an optimal outfit using a generative AI model that has learned the user's lifestyle and trend information. The generated outfit is presented to the user in real time through the smart glasses' AR display.

[1326] The cloud server then identifies any missing items from the suggested outfit. It retrieves the user's closet information from a database and detects the missing items. The cloud server then searches for potential purchases of the items via the API of affiliated online shops and displays the information on the smart glasses' display.

[1327] This system allows users to receive coordination suggestions in real time in physical stores, and allows them to check the suggested items on the spot, try them on, and make purchases smoothly.

[1328] As a concrete example, consider a female user in her 30s who prefers a casual style for enjoying the outdoors on her days off. When this user enters a store, the smart glasses recognize her appearance and send information to the cloud server. The generative AI model suggests outfits such as a casual jacket, a white T-shirt, jeans, and sneakers, and displays them through the smart glasses. If it is determined based on the user's closet information that she is short of a jacket, the cloud server searches for the appropriate jacket in an online shop and displays a link to purchase it.

[1329] An example of a prompt sentence is as follows:

[1330] User Information:

[1331] Age: 30

[1332] Gender: Female

[1333] Favorite style: Casual

[1334] Lifestyle: Outdoors on holidays

[1335] Store item data:

[1336] white T-shirt

[1337] casual jacket

[1338] jeans

[1339] Prompt for AI:

[1340] Please suggest the perfect casual style for this user."

[1341] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1342] Step 1:

[1343] A user puts on smart glasses and enters a physical store. The smart glasses recognize the user's appearance using a built-in camera. The smart glasses recognize the user's appearance and acquire information about the user's attributes (age, gender, fashion style, etc.). This information is then sent to a cloud server.

[1344] Step 2:

[1345] The server stores the received user information in a database. This is where information about the user's fashion style and lifestyle is updated. The server collects the latest fashion articles, social media posts, and information on new brand products. Based on this, it trains a generative AI model to learn trend information and coordination theory. The input is user information and collected data, and the output is an updated generative AI model.

[1346] Step 3:

[1347] The user requests outfit suggestions through the smart glasses (for example, by entering a command such as "Tell me today's recommended outfits"). The smart glasses recognize this operation and send a request to the cloud server. The input is the user's command, and the output is a request sent to the server.

[1348] Step 4:

[1349] The server retrieves user information from the database and generates optimal outfit suggestions using the most recently trained generative AI model. The generated outfit suggestions are then sent to the smart glasses. The input is the user information retrieved from the database and the generative AI model, and the output is the generated outfit suggestions.

[1350] Step 5:

[1351] The smart glasses display the generated outfit suggestions in the user's field of view using an AR display. The user can then check the suggested outfits. The input is the generated outfit suggestions, and the output is a visual presentation to the user. Specifically, the smart glasses display overlays the suggested items.

[1352] Step 6:

[1353] The server retrieves the user's closet information from a database and uses a generative AI model to identify items that are necessary for the suggested outfit but are not present in the user's closet. It then searches the APIs of affiliated online shops to find the relevant items. The input is the closet information retrieved by the server, and the output is information about items that are candidates for purchase.

[1354] Step 7:

[1355] The server sends information about potential purchase items to the smart glasses, which then display the items and their associated purchase links in the user's field of view using AR. The user can check detailed information about the items they are interested in and click the purchase link to access the online shop. The input is the information about the items they are interested in, and the output is a visual presentation and link provided to the user.

[1356] 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.

[1357] The present invention relates to an AI assistant system that makes optimal coordination suggestions and purchase suggestions tailored to a user's fashion style and lifestyle, and in particular, makes even more personalized suggestions by combining it with an emotion engine that recognizes the user's emotions. This system includes a user information input means, a generative AI model, an optimal coordination suggestion means, a purchase suggestion means, a display means, and an emotion engine.

[1358] Program processing overview

[1359] 1. Enter user information

[1360] Users access a dedicated application or web interface and enter information about their fashion style and lifestyle, such as age, gender, favorite colors, body type, and favorite places. Users can also link their frequently used social media accounts.

[1361] The device checks this information to make sure there are no errors, and then sends the information to the server.

[1362] The server stores the received information in a database.

[1363] 2. Study of trend and coordination theory

[1364] The server collects the latest fashion articles, social media posts, and information on new brand releases from the Internet.

[1365] The server analyzes the collected data using text processing and image recognition technology, and trains a generative AI model that learns trend information and coordination theory.

[1366] 3. Emotion recognition

[1367] Users input brief feedback about their daily emotions and current mood via an application or web interface.

[1368] The device monitors changes in emotions and sends the information to a server.

[1369] The server uses an emotion engine to analyze emotions from user input and interaction patterns, and the analysis results are fed back to the generative AI model.

[1370] 4. Coordination suggestions

[1371] The user enters a command such as "Tell me today's recommended outfit." The request is sent from the device to the server.

[1372] The server searches a database for user information and emotional data, and uses a generative AI model to generate optimal outfit suggestions based on the user's preferences, lifestyle, and emotional state.

[1373] The server transmits the generated coordination plan to the terminal.

[1374] The terminal displays the suggested coordination to the user.

[1375] 5. Purchase Proposal

[1376] The server retrieves the user's closet information (data on the clothes and accessories they own) from a database and identifies items that are missing from the suggested outfit.

[1377] The server searches the API of partner online stores or brands to find the identified missing items.

[1378] The server transmits information about the items to be purchased to the terminal.

[1379] The terminal displays suggested purchase items and links to them to the user.

[1380] 6. Interface Operation

[1381] The user operates the terminal to confirm each suggestion.

[1382] When a user clicks on an outfit or purchase item that interests them, detailed information will be displayed.

[1383] Users can click on the purchase link to be taken to an online store or brand site, where they can seamlessly purchase the suggested item.

[1384] Specific examples

[1385] For example, consider a female user in her 30s who works in an office during the week and enjoys the outdoors on weekends, and who prefers a casual lifestyle. The user logs into a dedicated application and enters her personal information and emotional state. The server stores this information in a database and uses a generative AI model to suggest the user's optimal outfit. For example, it might suggest a "navy blazer, white blouse, jeans, and sneakers." It might also identify that the user is short of a navy blazer based on their closet information and suggest purchasing one. It can then find a navy blazer at a partner online shop and provide the user with a link to purchase it. An emotional engine can be incorporated into this process to make appropriate suggestions based on the user's current emotional state. For example, if the user is feeling stressed, it could suggest a relaxing style.

[1386] This system allows users to significantly reduce the time and effort spent on everyday fashion coordination and enjoy stylish outfits based on the latest trends.In addition, by utilizing an emotion engine, users can receive more personalized suggestions based on their emotional state.

[1387] The processing flow will be explained below.

[1388] Step 1:

[1389] Users access a dedicated application or web interface and enter information about their fashion style and lifestyle, such as age, gender, favorite colors, body type, and favorite places. Users can also link their frequently used social media accounts.

[1390] Step 2:

[1391] The terminal checks the entered information for formatting errors and, once the check is complete, sends the information to the server.

[1392] Step 3:

[1393] The server stores the received information in a database, which is managed individually for each user.

[1394] Step 4:

[1395] The server regularly collects the latest fashion articles, social media posts, and information on new brand products from the Internet.

[1396] Step 5:

[1397] The server analyzes the collected data using text processing and image recognition technology, and the analysis results are used as input data for the generative AI model.

[1398] Step 6:

[1399] The server trains the generative AI model by feeding it trend information and coordination theory. This process runs periodically to ensure the model is constantly learning new information.

[1400] Step 7:

[1401] Users input brief feedback about their daily emotions and current mood via an application or web interface.

[1402] Step 8:

[1403] The device monitors changes in emotions and transmits the emotional data entered by the user to the server.

[1404] Step 9:

[1405] The server uses an emotion engine to analyze emotions from user input and interaction patterns, and the analysis results are fed back to the generative AI model.

[1406] Step 10:

[1407] The user inputs a command such as "Tell me today's recommended outfits." After input, the request is sent from the device to the server.

[1408] Step 11:

[1409] The server searches a database for user information and emotional data, and uses a generative AI model to generate optimal outfit suggestions based on the user's preferences, lifestyle, and emotional state.

[1410] Step 12:

[1411] The server transmits the generated coordinate plan to the terminal, where the transmitted data is converted into a format for visual display.

[1412] Step 13:

[1413] The device will display the suggested outfits to the user, who can review them and, if they like them, request more information.

[1414] Step 14:

[1415] The server retrieves the user's closet information (data on the clothes and accessories they own) from a database and uses this information to identify any missing items for the proposed outfit.

[1416] Step 15:

[1417] The server searches the APIs of partner online shops or brands to find the identified missing items and collects information on potential purchase items.

[1418] Step 16:

[1419] The server sends information about the items to be purchased to the device, including a purchase link and detailed product information.

[1420] Step 17:

[1421] The device displays the suggested purchase items and their associated purchase links to the user, who can then review the displayed content and click the purchase link if necessary.

[1422] Step 18:

[1423] The user clicks on the purchase link, which takes them to the online shop or brand site, allowing them to seamlessly purchase the suggested item.

[1424] In this way, the system can provide optimal coordination and purchase suggestions based on the user's fashion style, lifestyle, and emotional state.

[1425] Example 2

[1426] 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."

[1427] Conventional fashion advice systems only suggest outfits based on a user's basic fashion information and lifestyle, making it difficult to provide personalized suggestions that take into account the user's emotional state. Furthermore, they have problems in that they are unable to efficiently identify missing items in the suggested outfits or make purchasing suggestions based on those items. This often means that users have to spend time and effort trying out the suggested outfits.

[1428] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for the user to input information about fashion style and lifestyle, a means for recognizing the user's emotions and identifying the emotional state by analyzing the data, a means having a generative AI model that learns trend information and coordination theory, a means for proposing an optimal coordination based on the user's information and emotional state, a means for identifying items that are missing from the proposed coordination and suggesting the purchase of those items, and a means for displaying the proposed information to the user. This enables personalized coordination suggestions that take the user's emotional state into consideration and efficient item purchase suggestions.

[1429] The "user information input means" is a means by which a user provides information about fashion style and lifestyle to the system.

[1430] An "emotion recognition means" is a means for detecting a user's emotions and identifying their emotional state by analyzing the data.

[1431] A "generative AI model" is an artificial intelligence model that learns trend information and coordination theory and suggests coordination based on user information.

[1432] The "coordination suggestion means" is a means for advising the user on the most appropriate coordination based on the information input by the user and the user's emotional state.

[1433] The "purchase suggestion means" is a means for identifying an item that is missing from the suggested coordination and recommending the purchase of that item.

[1434] "Display means" refers to the means by which the system notifies the user of suggested outfits and purchase information.

[1435] A "database" is a system for managing and storing a variety of data, such as information entered by users, emotional data, or trend information.

[1436] "Trend information" refers to information that shows the latest trends in the fashion industry, such as the latest fashion articles, social media posts, and information on new brand products.

[1437] "Closet information" is data about the clothes and accessories a user owns.

[1438] The present invention relates to an AI assistant system that makes optimal coordination suggestions and purchase suggestions tailored to a user's fashion style and lifestyle. This system includes a user information input means, an emotion recognition means, a generative AI model, a coordination suggestion means, a purchase suggestion means, and a display means.

[1439] The user information input means allows a user to use a dedicated application or web interface to enter information related to their fashion style and lifestyle, such as their age, gender, favorite colors, body type, and favorite places. For example, information such as "30s, female, prefers casual style, works in an office on weekdays, enjoys outdoor activities on weekends" might be entered.

[1440] Emotion recognition is a means of detecting a user's emotions and identifying their emotional state by analyzing the data. The user inputs simple feedback about their daily emotions and current mood through an application or web interface. For example, they can provide feedback such as "I'm feeling a little stressed today."

[1441] The generative AI model is an artificial intelligence model that learns trend information and coordination theory and suggests outfits based on user information. The server collects the latest fashion articles, social media posts, and information on new brand products from the internet, and analyzes them using text processing and image recognition technology to train the generative AI model.

[1442] The outfit suggestion method is a means of advising the optimal outfit based on the user's input information and emotional state. When a user inputs a request such as "Tell me today's recommended outfit," the server uses a generative AI model to generate the optimal outfit suggestion. For example, a suggestion might be "a navy blazer, a white blouse, jeans, and sneakers."

[1443] The purchase suggestion means identifies items missing from the suggested outfit and recommends the purchase of those items. The server retrieves the user's closet information from the database and identifies the missing items. For example, it determines that a "navy blazer" is missing, searches for the corresponding item from affiliated online shops, and provides a link to purchase it.

[1444] The display means is a means by which the system notifies the user of suggested outfits and purchase information. The generated outfit ideas and purchase links are sent to the terminal and displayed to the user.

[1445] Specific examples

[1446] For example, let's say a female user in her 30s works in an office during the week and enjoys the outdoors on weekends, preferring a casual lifestyle. The user logs into a dedicated application and enters her personal information and emotional state. For example, she might enter, "I want to relax today." The server stores this information in a database and uses a generative AI model to suggest the perfect outfit for the user. For example, it might suggest "a navy blazer, a white blouse, jeans, and sneakers." Furthermore, based on the user's closet information, it might identify that the user is short of a navy blazer and suggest purchasing it. It then finds a suitable navy blazer at a partner online shop and provides the user with a purchase link. This allows the user to quickly obtain the items needed for their outfit.

[1447] Prompt Sentence Examples

[1448] "Please suggest a casual style outfit for a woman in her 30s who works in an office during the week and enjoys the outdoors on weekends."

[1449] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1450] Step 1: Enter your user information

[1451] Users access a dedicated application or web interface and enter information about their fashion style and lifestyle, such as their age, gender, favorite colors, body type, and favorite places. For example, they might enter information such as "30s, female, prefers casual style, works in an office during the week, and enjoys the outdoors on weekends."

[1452] Input: User's basic information (age, gender, favorite color, body type, lifestyle, etc.)

[1453] Output: Checking input data on the terminal and sending it to the server

[1454] Step 2: Verify and save user information

[1455] The terminal checks the entered data for any errors or omissions, and once the check is complete, sends the data to the server.

[1456] The server stores the received user information in a database, which is linked to each user's unique ID.

[1457] Input: User information sent from the device

[1458] Output: User information stored in the database

[1459] Step 3: Learn trend and coordination theory

[1460] The server crawls and collects fashion-related articles, social media posts, and information on new brand releases from the internet. Specifically, it automatically retrieves new collections and posts from popular Instagrammers.

[1461] The server analyzes the collected data using text processing technology (Natural Language Processing) and image recognition technology, for example, by analyzing the color, shape, and style of the captured image.

[1462] The server uses the analysis results to train the generative AI model, which builds a model based on the latest trend information and coordination theory.

[1463] Input: Collected trend information and image data

[1464] Output: A trained generative AI model

[1465] Step 4: Input and analyze emotion data

[1466] Through the application or web interface, users input brief feedback about their daily emotions and current mood, for example, "I feel like relaxing today."

[1467] The device receives the feedback and sends it to the server.

[1468] The server uses an emotion engine to analyze the user's emotional state, and the analysis results are fed back to the generative AI model.

[1469] Input: User's emotional feedback

[1470] Output: Parsed user emotional state data

[1471] Step 5: Generate outfit suggestions

[1472] When a user inputs a request such as "Tell me today's recommended outfit," the request is sent to the server via the terminal.

[1473] The server searches the database for user information and emotional data, and then uses a generative AI model to generate optimal outfit suggestions, such as a navy blazer, a white blouse, jeans, and sneakers.

[1474] The generated outfit suggestions are based on the user's preferences, lifestyle, and emotional state.

[1475] Input: User information, emotion data, request

[1476] Output: Generated optimal coordination plan

[1477] Step 6: Send and view your outfit ideas

[1478] The server transmits the generated coordination plan to the terminal.

[1479] The terminal displays the suggested coordination to the user.

[1480] Input: Generated coordination plan

[1481] Output: Coordination ideas displayed on the user's screen

[1482] Step 7: Generate a purchase offer

[1483] The server retrieves the user's closet information from a database and identifies any missing items from the proposed outfit, such as a navy blazer.

[1484] The server searches the API of partner online stores or brands to find the missing items, for example, searching for a navy blazer from a partner store.

[1485] The server transmits information about the items to be purchased to the terminal.

[1486] Input: Suggested outfit ideas, closet information

[1487] Output: Item information and purchase link

[1488] Step 8: View purchase offers

[1489] The terminal displays suggested purchase items and links to them to the user.

[1490] Users can click on the purchase link to be taken to an online shop or brand site, allowing them to seamlessly purchase the suggested item.

[1491] Input: Item information and link for potential purchases

[1492] Output: Purchase offer and link displayed to the user

[1493] This allows users to receive personalized outfit suggestions and smoothly purchase any items they are missing.

[1494] (Application example 2)

[1495] 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."

[1496] While conventional fashion assistant systems could provide suggestions based on a user's fashion style and lifestyle, they struggled to reflect the user's emotional state or real-time product information in physical stores. As a result, suggestions often did not reflect the user's current mood or the actual inventory status in the store, resulting in an unsatisfactory experience. Furthermore, they provided insufficient support for users to purchase specific coordinating items on the spot.

[1497] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for the user to input information about their fashion style and lifestyle, a means equipped with a generative AI model that learns trend information and coordination theory, a means for proposing optimal outfits based on the user's information and item information in the physical store, a means for identifying items missing from the proposed outfit and suggesting the purchase of those items, a means for displaying the proposed information to the user, and a means for recognizing the user's emotions and changing the proposed outfits in response to those emotions. This enables personalized fashion suggestions that reflect the user's current emotional state and real-time product information in the physical store. It also enhances on-the-spot purchasing support for the suggested items.

[1498] "User" refers to a person who uses a system or service.

[1499] "Fashion style" refers to the combination and design trends of clothing and accessories preferred by individual users.

[1500] "Lifestyle" is a concept that comprehensively expresses a user's daily life patterns, activities, hobbies, and preferences.

[1501] A "generative AI model" is an artificial intelligence model that uses techniques such as machine learning and deep learning to generate appropriate output based on input data.

[1502] "Trend information" refers to information about current trends and fashions in the market and society.

[1503] "Coordination theory" refers to a theoretical framework for suggesting and selecting optimal clothing by combining elements such as color, design, and material.

[1504] "In-store item information" refers to information about products that are actually sold in physical stores.

[1505] The "emotion engine" is a system that recognizes and analyzes emotions from the user's facial expressions and input data.

[1506] "Suggestion" refers to recommendations for coordination or purchases made to users.

[1507] "Real time" refers to a state or action that is reflected immediately at that point in time.

[1508] "Personalized" refers to a state that is optimized to suit the characteristics and circumstances of each individual user.

[1509] The system for realizing this invention allows users to input information about their fashion style and lifestyle, analyzes the user's emotional state using an emotion engine, and integrates this with real-time product information from physical stores to suggest optimal outfits. The system performs processing in the following steps:

[1510] Users use devices such as smartphones or head-mounted displays to input information such as age, gender, favorite colors, body type, and frequently visited places. Users also provide the system with their current mood through simple input or facial expression analysis using a camera. This information is then sent from the device to a server for data processing.

[1511] The server integrates the collected user information with information on items in physical stores and uses a generative AI model to learn the latest trends and coordination theories. The generative AI model uses advanced machine learning algorithms (e.g., GPT-3 and DALL-E) to generate optimal coordination for each user. It also uses emotion engines such as OpenAI's emotion analysis API to analyze user emotion data.

[1512] The server generates personalized outfit suggestions based on user information and product trend and inventory data from physical stores. The suggested outfits reflect the user's preferences, lifestyle, and current emotional state. The suggested outfits are displayed to the user via their device.

[1513] As a specific example, consider a female user in her 30s who works in an office during the week, enjoys outdoor activities on the weekends, and prefers casual fashion. The user logs into the application and enters her personal information and current emotional state (e.g., "I want to relax"). The server stores this information in a database and uses a generative AI model to suggest outfits such as a navy blazer, a white blouse, jeans, and sneakers.

[1514] Furthermore, the server uses the user's closet information and the store's inventory information to identify any missing items in the suggested outfit (in this case, a navy blazer) and provides the user with a link to purchase the item. This process is carried out in real time, allowing the user to instantly receive outfit suggestions via their smartphone or head-mounted display in the store and purchase the necessary items on the spot.

[1515] This system allows users to always enjoy stylish outfits that reflect the latest trends, and offers suggestions based on the user's emotional state, providing a more comfortable and satisfying shopping experience.

[1516] Prompt Sentence Examples

[1517] Age: 30

[1518] Gender: Female

[1519] Favorite color: Blue

[1520] Body shape: normal

[1521] Favorite place: Office

[1522] Current mood: Relaxing

[1523] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1524] Step 1:

[1525] The user inputs information about their fashion style and lifestyle. Using a smartphone or head-mounted display, the user inputs information such as age, gender, favorite colors, body type, and favorite places. This input data is acquired by the device, and after checking the input information and confirming any errors, it is sent to the server. Input: Age, gender, favorite colors, body type, favorite places. Output: User information data.

[1526] Step 2:

[1527] The server stores the received user information in a database. The stored data is used as the basis for future coordination suggestions and sentiment analysis. Input: User information data. Output: User information stored in the database.

[1528] Step 3:

[1529] The terminal collects item information (tag information and image data) from within the physical store and sends it to the server. Using a smartphone or head-mounted display, product information is obtained using RFID tags and image recognition technology within the store. Input: Item information within the store (tag information, image data). Output: Collected item information data.

[1530] Step 4:

[1531] The user inputs their current emotional information. The user can analyze their emotions by entering simple feedback into the application or by reading their facial expressions using the camera function. This data is acquired by the device and sent to the server. Input: Emotional information (e.g., "I want to relax"). Output: Emotional data.

[1532] Step 5:

[1533] The server integrates user information, emotional data, and item information from physical stores, and uses a generative AI model to generate optimal outfit suggestions. Trend information and outfit theory are also taken into consideration. The generated outfit suggestions are based on the user's preferences, lifestyle, and emotional state. Input: User information data, emotional data, item information data. Output: Optimal outfit suggestions.

[1534] Step 6:

[1535] The server sends the generated outfit suggestions to the device. The user can then check the outfit suggestions on their smartphone or head-mounted display. Input: Outfit suggestions. Output: Outfit suggestions displayed on the user device.

[1536] Step 7:

[1537] The server retrieves the user's closet information from the database and identifies items that are missing from the suggested outfit. The identified missing items are provided as purchase links by referencing inventory information from affiliated online shops or physical stores. Input: User's closet information, suggested outfit. Output: Purchase link information for missing items.

[1538] Step 8:

[1539] The user operates the device to check the suggested outfits and purchase links. By clicking the purchase link for the missing item on the device, the user is redirected to the relevant page of a partner online shop or physical store, where the purchase can be made. Input: Purchase link information. Output: Transition to the purchase page of the online shop or physical store.

[1540] This processing flow enables real-time fashion coordination suggestions, personalized suggestions based on the user's emotional state, and even immediate support for purchasing missing items.

[1541] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1542] 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.

[1543] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1544] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1545] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1546] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1547] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1548] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1549] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1550] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1551] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1552] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1553] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1554] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1555] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1556] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1557] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1558] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1559] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1560] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1561] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1562] The following is further disclosed regarding the above embodiment.

[1563] (Claim 1)

[1564] A means for users to input information about their fashion style and lifestyle;

[1565] A means equipped with a generative AI model that learns trend information and coordination theory,

[1566] A means to suggest the best outfit based on the user's information,

[1567] A means for identifying missing items for the proposed coordination and suggesting the purchase of the items;

[1568] a means for displaying the suggested information to the user;

[1569] A system including:

[1570] (Claim 2)

[1571] 10. The system of claim 1, wherein the information entered by the user is stored in a database.

[1572] (Claim 3)

[1573] 2. The system according to claim 1, further comprising means for acquiring closet information of a user, generating an optimal coordination, and making a purchase suggestion.

[1574] "Example 1"

[1575] (Claim 1)

[1576] A means for users to input information about their fashion style and lifestyle;

[1577] A means equipped with a generative AI model that learns trend information and coordination theory,

[1578] A means to suggest the best outfit based on the user's information,

[1579] A means for identifying missing items for the proposed coordination and suggesting the purchase of the items;

[1580] a means for displaying the suggested information to the user;

[1581] A means for the user to complete an online purchase via the suggested purchase link;

[1582] A system including:

[1583] (Claim 2)

[1584] 10. The system of claim 1, wherein the information entered by the user is stored in a database.

[1585] (Claim 3)

[1586] 2. The system according to claim 1, further comprising means for acquiring closet information of a user, generating an optimal coordination, and making a purchase suggestion.

[1587] "Application Example 1"

[1588] (Claim 1)

[1589] A means for users to input information about their fashion style and lifestyle;

[1590] A means equipped with a generative AI model that learns trend information and coordination theory,

[1591] A means of recognizing the user's appearance using smart glasses and scanning items in the store;

[1592] A means to suggest the best outfit based on the user's information,

[1593] A means for identifying missing items for the proposed coordination and suggesting the purchase of the items;

[1594] a means for displaying the suggested information to the user;

[1595] A system including:

[1596] (Claim 2)

[1597] 10. The system of claim 1, wherein the information entered by the user is stored in a database.

[1598] (Claim 3)

[1599] 2. The system according to claim 1, further comprising means for acquiring closet information of a user, generating an optimal coordination, and making a purchase suggestion.

[1600] "Example 2: Combining Emotion Engines"

[1601] (Claim 1)

[1602] A means for users to input information about their fashion style and lifestyle;

[1603] means for recognizing a user's emotions and analyzing the data to identify the user's emotional state;

[1604] A means equipped with a generative AI model that learns trend information and coordination theory,

[1605] A means for suggesting optimal outfits based on the user's information and emotional state;

[1606] A means for identifying missing items for the proposed coordination and suggesting the purchase of the items;

[1607] a means for displaying the suggested information to the user;

[1608] A system including:

[1609] (Claim 2)

[1610] 10. The system of claim 1, wherein the information and emotion data input by the user are stored in a database.

[1611] (Claim 3)

[1612] 2. The system according to claim 1, further comprising means for acquiring closet information of a user, generating an optimal coordination, and making a purchase suggestion.

[1613] "Application example 2 when combining emotion engines"

[1614] (Claim 1)

[1615] A means for users to input information about their fashion style and lifestyle;

[1616] A means equipped with a generative AI model that learns trend information and coordination theory,

[1617] A means to suggest optimal coordination based on user information and item information in physical stores,

[1618] A means for identifying missing items for the proposed coordination and suggesting the purchase of the items;

[1619] a means for displaying the suggested information to the user;

[1620] A means for recognizing a user's emotions and changing the outfit suggestions according to the emotions;

[1621] A system including:

[1622] (Claim 2)

[1623] 10. The system of claim 1, wherein the information entered by the user is stored in a database.

[1624] (Claim 3)

[1625] 2. The system according to claim 1, further comprising means for acquiring closet information of a user, generating an optimal coordination, and making a purchase suggestion. [Explanation of symbols]

[1626] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for users to input information about their fashion style and lifestyle; A means equipped with a generative AI model that learns trend information and coordination theory, A means to suggest the best outfit based on the user's information, A means for identifying missing items for the proposed coordination and suggesting the purchase of the items; a means for displaying the suggested information to the user; A system including:

2. 10. The system of claim 1, wherein the information entered by the user is stored in a database.

3. The system according to claim 1, further comprising means for acquiring closet information of a user, generating an optimal coordination, and making a purchase suggestion.

Images